diff --git a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q index 0ee49fc..4a9fd91 100644 --- a/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q +++ b/ql/src/test/queries/clientpositive/bucket_map_join_tez2.q @@ -37,9 +37,11 @@ analyze table tab_part compute statistics for columns; set hive.auto.convert.join.noconditionaltask.size=1500; set hive.convert.join.bucket.mapjoin.tez = false; +set hive.cbo.enable=false; explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value; set hive.convert.join.bucket.mapjoin.tez = true; explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part b on a.value = b.value; +reset hive.cbo.enable; CREATE TABLE tab1(key int, value string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; insert overwrite table tab1 diff --git a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out index 060039b..7e9f2ca 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_2.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_2.q.out @@ -129,7 +129,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -148,7 +148,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -253,7 +253,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -272,7 +272,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -301,7 +301,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -320,7 +320,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -349,7 +349,7 @@ data_type string min max num_nulls 20 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -368,7 +368,7 @@ data_type string min max num_nulls 10 -distinct_count 319 +distinct_count 316 avg_col_len 8.0 max_col_len 8 num_trues diff --git a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out index a2554f1..60ebd62 100644 --- a/ql/src/test/results/clientpositive/autoColumnStats_9.q.out +++ b/ql/src/test/results/clientpositive/autoColumnStats_9.q.out @@ -253,7 +253,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -272,7 +272,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.834630350194552 max_col_len 7 num_trues diff --git a/ql/src/test/results/clientpositive/bitvector.q.out b/ql/src/test/results/clientpositive/bitvector.q.out index 1e0284f..e310ebe 100644 --- a/ql/src/test/results/clientpositive/bitvector.q.out +++ b/ql/src/test/results/clientpositive/bitvector.q.out @@ -9,7 +9,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/compute_stats_date.q.out b/ql/src/test/results/clientpositive/compute_stats_date.q.out index 35c0f8d..58d2d70 100644 --- a/ql/src/test/results/clientpositive/compute_stats_date.q.out +++ b/ql/src/test/results/clientpositive/compute_stats_date.q.out @@ -43,7 +43,7 @@ POSTHOOK: query: select compute_stats(fl_date, 'hll') from tab_date POSTHOOK: type: QUERY POSTHOOK: Input: default@tab_date #### A masked pattern was here #### -{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":19,"ndvbitvector":HLL�ê����!���]����������������Y���T��P��R������W��� �ĈN������������} +{"columntype":"Date","min":"2000-11-20","max":"2010-10-29","countnulls":0,"numdistinctvalues":19,"ndvbitvector":HLL�Ǫ����!���]����������������Y���T���P��R������W��� �ĈN������������} PREHOOK: query: explain analyze table tab_date compute statistics for columns fl_date PREHOOK: type: ANALYZE_TABLE diff --git a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out index a900194..846b600 100644 --- a/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out +++ b/ql/src/test/results/clientpositive/confirm_initial_tbl_stats.q.out @@ -19,7 +19,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -105,7 +105,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -134,7 +134,7 @@ data_type string min max num_nulls 0 -distinct_count 430 +distinct_count 431 avg_col_len 6.802 max_col_len 7 num_trues @@ -163,7 +163,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -199,7 +199,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/cross_join_merge.q.out b/ql/src/test/results/clientpositive/cross_join_merge.q.out index 84d78f3..3389638 100644 --- a/ql/src/test/results/clientpositive/cross_join_merge.q.out +++ b/ql/src/test/results/clientpositive/cross_join_merge.q.out @@ -233,7 +233,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[11][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain select src1.key from src src1 join src src2 on 5 = src2.key join src src3 on src1.key=src3.key PREHOOK: type: QUERY @@ -250,7 +250,7 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: src3 + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) @@ -260,29 +260,34 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) TableScan - alias: src2 + alias: src3 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(key) = 5.0D) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 - 1 + 0 _col0 (type: string) + 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -295,45 +300,36 @@ STAGE PLANS: Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 125000 Data size: 2781000 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string) TableScan - alias: src1 + alias: src2 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(key) = 5.0D) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + sort order: + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col2 - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col2 (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 137500 Data size: 3059100 Basic stats: COMPLETE Column stats: NONE - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 0 + 1 + outputColumnNames: _col0 + Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 137500 Data size: 3059050 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/describe_table.q.out b/ql/src/test/results/clientpositive/describe_table.q.out index 2323685..1529557 100644 --- a/ql/src/test/results/clientpositive/describe_table.q.out +++ b/ql/src/test/results/clientpositive/describe_table.q.out @@ -206,7 +206,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -304,7 +304,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues diff --git a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out index 096f491..cdeae4e 100644 --- a/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out +++ b/ql/src/test/results/clientpositive/encrypted/encryption_move_tbl.q.out @@ -66,7 +66,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -85,7 +85,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -117,7 +117,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -136,7 +136,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues diff --git a/ql/src/test/results/clientpositive/hll.q.out b/ql/src/test/results/clientpositive/hll.q.out index 12f6a36..4b445ea 100644 --- a/ql/src/test/results/clientpositive/hll.q.out +++ b/ql/src/test/results/clientpositive/hll.q.out @@ -182,7 +182,7 @@ data_type int min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 303 avg_col_len max_col_len num_trues @@ -236,7 +236,7 @@ data_type double min 0.0 max 498.0 num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len max_col_len num_trues @@ -290,7 +290,7 @@ data_type decimal(10,0) min 0 max 498 num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len max_col_len num_trues diff --git a/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out b/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out index f03e64b..3922909 100644 --- a/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out +++ b/ql/src/test/results/clientpositive/llap/acid_no_buckets.q.out @@ -304,15 +304,15 @@ STAGE PLANS: Statistics: Num rows: 2015 Data size: 916825 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key) IN ('1001', '213', '43') (type: boolean) - Statistics: Num rows: 20 Data size: 9100 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8645 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -322,10 +322,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -804,16 +804,16 @@ STAGE PLANS: Statistics: Num rows: 2015 Data size: 916825 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key) IN ('1001', '213', '43') (type: boolean) - Statistics: Num rows: 20 Data size: 9100 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8645 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct), ds (type: string), hr (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -823,10 +823,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct), VALUE._col0 (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 8880 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 19 Data size: 8436 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out b/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out index f1ae2a5..6331bb5 100644 --- a/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out +++ b/ql/src/test/results/clientpositive/llap/autoColumnStats_2.q.out @@ -127,7 +127,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -146,7 +146,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -251,7 +251,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -270,7 +270,7 @@ data_type string min max num_nulls 0 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -299,7 +299,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -318,7 +318,7 @@ data_type string min max num_nulls 10 -distinct_count 309 +distinct_count 307 avg_col_len 6.812 max_col_len 7 num_trues @@ -347,7 +347,7 @@ data_type string min max num_nulls 20 -distinct_count 309 +distinct_count 316 avg_col_len 2.812 max_col_len 3 num_trues @@ -366,7 +366,7 @@ data_type string min max num_nulls 10 -distinct_count 319 +distinct_count 316 avg_col_len 8.0 max_col_len 8 num_trues diff --git a/ql/src/test/results/clientpositive/llap/auto_join1.q.out b/ql/src/test/results/clientpositive/llap/auto_join1.q.out index 41e56e1..4233eb2 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join1.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join1.q.out @@ -69,14 +69,14 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -85,7 +85,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/llap/auto_join21.q.out b/ql/src/test/results/clientpositive/llap/auto_join21.q.out index 64e6422..5889720 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join21.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join21.q.out @@ -75,25 +75,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join29.q.out b/ql/src/test/results/clientpositive/llap/auto_join29.q.out index c357c1f..3891ea0 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join29.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join29.q.out @@ -75,25 +75,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -693,25 +693,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 137 Data size: 73158 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1311,25 +1311,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 432 Data size: 230688 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1938,25 +1938,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 434 Data size: 231756 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 415 Data size: 221610 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2567,25 +2567,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2685,25 +2685,25 @@ STAGE PLANS: 1 key (type: string) 2 key (type: string) outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3263,15 +3263,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -3312,10 +3312,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 136 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3394,15 +3394,15 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -3427,10 +3427,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 431 Data size: 230154 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 414 Data size: 221076 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3511,15 +3511,15 @@ STAGE PLANS: input vertices: 1 Map 3 2 Map 4 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string) sort order: ++++++ - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -3560,10 +3560,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string), KEY.reducesinkkey3 (type: string), KEY.reducesinkkey4 (type: string), KEY.reducesinkkey5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 143 Data size: 76362 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 72090 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/auto_join30.q.out b/ql/src/test/results/clientpositive/llap/auto_join30.q.out index 19d6c55..1f95237 100644 --- a/ql/src/test/results/clientpositive/llap/auto_join30.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_join30.q.out @@ -67,7 +67,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -167,7 +167,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -300,7 +300,7 @@ STAGE PLANS: outputColumnNames: _col2, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -431,7 +431,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -605,7 +605,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -758,7 +758,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -911,7 +911,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash @@ -1064,7 +1064,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1251 Data size: 222678 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2,_col3)) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out index ec80797..80d2c37 100644 --- a/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out +++ b/ql/src/test/results/clientpositive/llap/auto_sortmerge_join_6.q.out @@ -84,23 +84,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -110,20 +100,14 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -143,6 +127,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -152,7 +155,23 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -162,7 +181,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -211,23 +230,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -237,20 +246,14 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -270,6 +273,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -279,7 +301,23 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -289,7 +327,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -338,23 +376,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -364,20 +392,14 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -397,6 +419,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -406,7 +447,23 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -416,7 +473,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -465,23 +522,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -491,20 +538,14 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 3236 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 809 Data size: 3236 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -524,6 +565,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -533,7 +593,23 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1305 Data size: 10440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -543,7 +619,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -636,7 +712,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1361 Data size: 10888 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -702,15 +778,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + alias: c + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -726,33 +802,33 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: TableScan - alias: c - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -762,9 +838,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -808,7 +884,7 @@ POSTHOOK: Input: default@tbl1 POSTHOOK: Input: default@tbl2 POSTHOOK: Input: default@tbl4 #### A masked pattern was here #### -2654 +90 PREHOOK: query: explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value PREHOOK: type: QUERY POSTHOOK: query: explain select count(*) FROM tbl1 a JOIN tbl2 b ON a.key = b.key join src c on c.value = a.value @@ -823,23 +899,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -849,20 +915,14 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -882,6 +942,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -891,7 +970,23 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -901,7 +996,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -950,23 +1045,13 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) + Reducer 3 <- Map 6 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Map Operator Tree: - TableScan alias: a Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator @@ -976,20 +1061,14 @@ STAGE PLANS: expressions: key (type: int) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Merge Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 3236 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) - sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 809 Data size: 3236 Basic stats: COMPLETE Column stats: COMPLETE - Execution mode: llap + Reduce Output Operator + key expressions: UDFToDouble(_col0) (type: double) + sort order: + + Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs Map 5 Map Operator Tree: TableScan @@ -1009,6 +1088,25 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs + Map 6 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1018,7 +1116,23 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0 + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 791 Data size: 3164 Basic stats: COMPLETE Column stats: COMPLETE + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1305 Data size: 10440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1028,7 +1142,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint) - Reducer 3 + Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator @@ -1121,7 +1235,7 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) 2 _col0 (type: int) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1361 Data size: 10888 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1187,15 +1301,15 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: b - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + alias: c + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: int) + expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Map Operator Tree: TableScan alias: a @@ -1211,33 +1325,33 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col1 - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col1 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 73619 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 3256 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: llap Map 5 Map Operator Tree: TableScan - alias: c - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + alias: b + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) + expressions: key (type: int) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -1247,9 +1361,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1293,4 +1407,4 @@ POSTHOOK: Input: default@tbl1 POSTHOOK: Input: default@tbl2 POSTHOOK: Input: default@tbl4 #### A masked pattern was here #### -2654 +90 diff --git a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out index 3a7d744..4925de5 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_groupby.q.out @@ -666,12 +666,12 @@ STAGE PLANS: keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -683,10 +683,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1051,12 +1051,12 @@ STAGE PLANS: keys: key (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: bigint) Execution mode: llap LLAP IO: no inputs @@ -1068,10 +1068,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out index 66b019b..2416384 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out @@ -235,25 +235,25 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -823,15 +823,15 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 3 @@ -840,10 +840,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string), KEY.reducesinkkey2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1436,7 +1436,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 207 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1565,7 +1565,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 4 - Statistics: Num rows: 207 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1696,7 +1696,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 708 Data size: 5664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 689 Data size: 5512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1731,16 +1731,16 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -1838,11 +1838,11 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1851,7 +1851,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 708 Data size: 5664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 689 Data size: 5512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2007,7 +2007,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 708 Data size: 5664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 689 Data size: 5512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2042,16 +2042,16 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -2149,11 +2149,11 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 414 Data size: 1656 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -2162,7 +2162,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 0 Map 1 - Statistics: Num rows: 708 Data size: 5664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 689 Data size: 5512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2566,11 +2566,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col1, _col2 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) @@ -2708,11 +2708,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Map 2 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: int), substr(_col2, 5) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) keys: _col0 (type: int) @@ -2866,14 +2866,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col1 (type: int) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2949,14 +2949,14 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Reducer 3 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3139,14 +3139,14 @@ STAGE PLANS: 1 _col0 (type: int) 2 _col0 (type: int) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3202,14 +3202,14 @@ STAGE PLANS: input vertices: 1 Map 2 2 Map 3 - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 655 Data size: 121830 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 646 Data size: 120156 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3304,12 +3304,12 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -3362,14 +3362,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3422,7 +3422,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 414 Data size: 39330 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 38760 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -3432,14 +3432,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Map 3 - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 654 Data size: 121644 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 645 Data size: 119970 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3586,14 +3586,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3675,14 +3675,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 207 Data size: 21321 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 204 Data size: 21012 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3799,14 +3799,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3882,14 +3882,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Reducer 2 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 261 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 258 Data size: 26574 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3987,10 +3987,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4071,10 +4071,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4178,14 +4178,14 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4258,14 +4258,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4364,7 +4364,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -4374,14 +4374,14 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 1 Map 4 - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4430,7 +4430,7 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -4440,14 +4440,14 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1385 Data size: 11080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1375 Data size: 11000 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4585,14 +4585,14 @@ STAGE PLANS: 0 _col0 (type: int), _col2 (type: string) 1 _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4689,14 +4689,14 @@ STAGE PLANS: 0 _col0 (type: int), _col2 (type: string) 1 _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col4 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 414 Data size: 77004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -4774,14 +4774,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5349,14 +5349,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -5970,14 +5970,14 @@ STAGE PLANS: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -6545,14 +6545,14 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 73284 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out index af37ef3..3db172c 100644 --- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out +++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez2.q.out @@ -189,29 +189,21 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: value (type: string) Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + value expressions: key (type: int) Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -222,15 +214,11 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -240,15 +228,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 key (type: int) + 1 key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int) Reducer 3 Execution mode: llap @@ -258,16 +246,16 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 1 value (type: string) + outputColumnNames: _col0, _col12 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col12 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -304,26 +292,22 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 key (type: int) + 1 key (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + input vertices: + 1 Map 3 + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col1 (type: string) + sort order: + + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 825 Data size: 78375 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: no inputs Map 3 @@ -334,15 +318,11 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -353,16 +333,12 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + value expressions: key (type: int) Execution mode: vectorized, llap LLAP IO: no inputs Reducer 2 @@ -373,16 +349,16 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 1 value (type: string) + outputColumnNames: _col0, _col12 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col12 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -496,14 +472,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -585,14 +561,14 @@ STAGE PLANS: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(_col0) (type: double) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 382 Data size: 71052 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -670,10 +646,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -724,10 +700,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -826,10 +802,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -880,10 +856,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -982,10 +958,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1055,10 +1031,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 267 Data size: 2136 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 272 Data size: 2176 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1565,7 +1541,7 @@ STAGE PLANS: keys: 0 _col0 (type: int), _col1 (type: string) 1 _col0 (type: int), _col1 (type: string) - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 1576 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1675,7 +1651,7 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: string) input vertices: 1 Map 4 - Statistics: Num rows: 195 Data size: 1560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 1576 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1893,8 +1869,8 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 3 (CUSTOM_EDGE) Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -1909,41 +1885,12 @@ STAGE PLANS: expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - input vertices: - 1 Map 3 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) - Execution mode: vectorized, llap - LLAP IO: no inputs - Map 3 - Map Operator Tree: - TableScan - alias: c - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Filter Operator - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -1966,6 +1913,25 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: no inputs + Map 5 + Map Operator Tree: + TableScan + alias: c + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 500 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: vectorized, llap + LLAP IO: no inputs Reducer 2 Execution mode: llap Reduce Operator Tree: @@ -1975,15 +1941,32 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + outputColumnNames: _col0, _col2 + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) + Reducer 3 + Execution mode: llap + Reduce Operator Tree: + Merge Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2010,7 +1993,7 @@ STAGE PLANS: #### A masked pattern was here #### Edges: Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE) - Reducer 3 <- Map 1 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) + Reducer 3 <- Map 5 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -2026,11 +2009,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) + Execution mode: vectorized, llap + LLAP IO: no inputs + Map 4 + Map Operator Tree: + TableScan + alias: b + Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 47500 Basic stats: COMPLETE Column stats: COMPLETE @@ -2046,7 +2036,7 @@ STAGE PLANS: value expressions: _col0 (type: int) Execution mode: vectorized, llap LLAP IO: no inputs - Map 4 + Map 5 Map Operator Tree: TableScan alias: c @@ -2072,16 +2062,16 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: int) + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 814 Data size: 6512 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col2 (type: int) Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2089,17 +2079,17 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 10472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1343 Data size: 10744 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/check_constraint.q.out b/ql/src/test/results/clientpositive/llap/check_constraint.q.out index 5b47bb3..9533a61 100644 --- a/ql/src/test/results/clientpositive/llap/check_constraint.q.out +++ b/ql/src/test/results/clientpositive/llap/check_constraint.q.out @@ -1536,11 +1536,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 268 Data size: 71020 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 69430 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), CAST( _col2 AS decimal(5,2)) (type: decimal(5,2)), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 268 Data size: 55476 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 262 Data size: 54234 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 2070 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out index e91b699..99f3c56 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer1.q.out @@ -72,7 +72,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -220,7 +220,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -360,7 +360,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 0 Map 1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -515,18 +515,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1634 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -536,11 +536,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) mode: hash @@ -668,18 +668,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 20 Data size: 1720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1634 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -689,11 +689,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 940 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 9 Data size: 846 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1) mode: hash @@ -810,7 +810,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -952,7 +952,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -1094,7 +1094,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1236,7 +1236,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1375,18 +1375,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 40 Data size: 7080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1396,10 +1396,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1506,18 +1506,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 40 Data size: 7080 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6903 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -1527,10 +1527,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3700 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3515 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1924,7 +1924,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2066,7 +2066,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2208,7 +2208,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2350,7 +2350,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 525 Data size: 3526 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 525 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2499,18 +2499,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2520,11 +2520,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -2648,18 +2648,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2669,11 +2669,11 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3660 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3477 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -2796,7 +2796,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -2944,7 +2944,7 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out index 0f839ea..8e17d95 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer2.q.out @@ -1804,16 +1804,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -1825,11 +1825,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) mode: hash @@ -1985,16 +1985,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -2006,11 +2006,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col1) (type: int), hash(_col2) (type: int), hash(_col3) (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 30 Data size: 8070 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 29 Data size: 7801 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2), sum(_col3) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out index 852f391..2e4010e 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer3.q.out @@ -101,16 +101,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -122,11 +122,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -161,7 +161,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -318,16 +318,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -339,11 +339,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -378,7 +378,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -482,11 +482,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -496,11 +496,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 1 Reducer 5 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col0) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -553,7 +553,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -746,16 +746,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -767,11 +767,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -806,7 +806,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -963,16 +963,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -984,11 +984,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -1023,7 +1023,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) @@ -1127,11 +1127,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 3 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1141,11 +1141,11 @@ STAGE PLANS: outputColumnNames: _col1, _col2, _col3 input vertices: 1 Reducer 5 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: hash(_col2) (type: int), hash(_col3) (type: int), hash(_col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7320 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7137 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), sum(_col1), sum(_col2) mode: hash @@ -1198,7 +1198,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3354 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col1 (type: string) diff --git a/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out index 499ef4b..9e424c2 100644 --- a/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out +++ b/ql/src/test/results/clientpositive/llap/correlationoptimizer6.q.out @@ -172,18 +172,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 8 Execution mode: vectorized, llap @@ -193,12 +193,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -416,18 +416,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 8 Execution mode: vectorized, llap @@ -437,12 +437,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -593,18 +593,18 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -650,7 +650,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -788,10 +788,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -929,10 +929,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 3620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3439 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1105,18 +1105,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -1126,12 +1126,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -1286,18 +1286,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -1307,12 +1307,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -1864,14 +1864,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1886,18 +1886,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -1907,12 +1907,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -2082,14 +2082,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string), _col3 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2104,18 +2104,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -2125,12 +2125,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Stage: Stage-0 @@ -2298,18 +2298,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2319,12 +2319,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -2338,14 +2338,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2516,18 +2516,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2537,12 +2537,12 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: llap @@ -2556,14 +2556,14 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7059 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3327,18 +3327,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 9 Execution mode: vectorized, llap @@ -3348,12 +3348,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint) Stage: Stage-0 @@ -3572,18 +3572,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 8 Execution mode: vectorized, llap @@ -3593,12 +3593,12 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint) Stage: Stage-0 @@ -3749,18 +3749,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -3806,7 +3806,7 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 73470 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/cross_join.q.out b/ql/src/test/results/clientpositive/llap/cross_join.q.out index e95407d..64f669b 100644 --- a/ql/src/test/results/clientpositive/llap/cross_join.q.out +++ b/ql/src/test/results/clientpositive/llap/cross_join.q.out @@ -200,10 +200,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -390,10 +390,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out index 72e34e4..a0789dd 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction.q.out @@ -452,12 +452,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Dynamic Partitioning Event Operator Target column: ds (string) Target Input: srcpart_small Partition key expr: ds - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Target Vertex: Map 4 Execution mode: vectorized, llap LLAP IO: all inputs @@ -723,7 +723,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 174000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -826,7 +826,7 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out index 618f018..2f64b90 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_reduction_sw.q.out @@ -231,7 +231,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -284,7 +284,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -369,7 +369,7 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE @@ -430,7 +430,7 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 552 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out index 2ed71f8..cd5c8e7 100644 --- a/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out +++ b/ql/src/test/results/clientpositive/llap/dynamic_semijoin_user_level.q.out @@ -256,8 +256,8 @@ Stage-0 predicate:key is not null TableScan [TS_0] (rows=2000 width=87) default@srcpart_date,srcpart_date,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - Dynamic Partitioning Event Operator [EVENT_21] (rows=309 width=87) - Group By Operator [GBY_20] (rows=309 width=87) + Dynamic Partitioning Event Operator [EVENT_21] (rows=316 width=87) + Group By Operator [GBY_20] (rows=316 width=87) Output:["_col0"],keys:_col0 Select Operator [SEL_19] (rows=2000 width=87) Output:["_col0"] @@ -434,11 +434,11 @@ Stage-0 <-Reducer 4 [BROADCAST_EDGE] llap BROADCAST [RS_44] Group By Operator [GBY_41] (rows=1 width=552) - Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=309)"] + Output:["_col0","_col1","_col2"],aggregations:["min(VALUE._col0)","max(VALUE._col1)","bloom_filter(VALUE._col2, expectedEntries=316)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_40] Group By Operator [GBY_39] (rows=1 width=552) - Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=309)"] + Output:["_col0","_col1","_col2"],aggregations:["min(_col0)","max(_col0)","bloom_filter(_col0, expectedEntries=316)"] Select Operator [SEL_38] (rows=2000 width=87) Output:["_col0"] Please refer to the previous Select Operator [SEL_2] diff --git a/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out b/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out index 8a6b70d..23c3807 100644 --- a/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainanalyze_2.q.out @@ -41,134 +41,129 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) +Map 12 <- Union 10 (CONTAINS) Map 13 <- Union 14 (CONTAINS) Map 16 <- Union 14 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 10 <- Map 9 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 11 <- Map 17 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 6 (CONTAINS) +Map 9 <- Union 10 (CONTAINS) +Reducer 11 <- Union 10 (SIMPLE_EDGE) Reducer 15 <- Union 14 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE) +Reducer 6 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 7 <- Reducer 15 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 llap + Reducer 5 llap File Output Operator [FS_56] - Group By Operator [GBY_54] (rows=32/15 width=177) + Group By Operator [GBY_54] (rows=48/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_53] PartitionCols:_col0, _col1 - Select Operator [SEL_49] (rows=67/61 width=177) + Select Operator [SEL_24] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_82] (rows=67/61 width=177) - Conds:RS_46._col2=RS_47._col0(Inner),Output:["_col1","_col2"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_47] - PartitionCols:_col0 - Select Operator [SEL_42] (rows=500/500 width=87) - Output:["_col0"] - Filter Operator [FIL_78] (rows=500/500 width=87) - predicate:key is not null - TableScan [TS_40] (rows=500/500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_46] + Merge Join Operator [MERGEJOIN_79] (rows=66/61 width=177) + Conds:RS_21._col2=RS_22._col1(Inner),Output:["_col1","_col4"] + <-Reducer 11 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 10 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_72] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Map 9 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_71] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_21] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_81] (rows=42/52 width=177) - Conds:RS_43._col1=RS_44._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_44] - PartitionCols:_col1 - Select Operator [SEL_14] (rows=25/25 width=175) + Merge Join Operator [MERGEJOIN_77] (rows=39/37 width=175) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_18] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=87) + Output:["_col0"] + Filter Operator [FIL_69] (rows=500/500 width=87) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=87) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_73] (rows=25/25 width=175) + Filter Operator [FIL_70] (rows=25/25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) + TableScan [TS_3] (rows=25/25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] llap - SHUFFLE [RS_43] - PartitionCols:_col1 - Select Operator [SEL_36] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_75] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_76] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + <-Reducer 7 [CONTAINS] llap Reduce Output Operator [RS_53] PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) + Select Operator [SEL_49] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_80] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col1","_col2"] - <-Map 12 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=87) - Output:["_col0"] - Filter Operator [FIL_74] (rows=500/500 width=87) - predicate:key is not null - TableScan [TS_15] (rows=500/500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_21] + Merge Join Operator [MERGEJOIN_80] (rows=66/61 width=177) + Conds:RS_46._col2=RS_47._col1(Inner),Output:["_col1","_col4"] + <-Reducer 15 [SIMPLE_EDGE] llap + SHUFFLE [RS_47] + PartitionCols:_col1 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_75] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_76] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 6 [SIMPLE_EDGE] llap + SHUFFLE [RS_46] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_79] (rows=42/52 width=177) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_71] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=175) - Output:["key","value"] - <-Map 8 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_72] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] + Merge Join Operator [MERGEJOIN_78] (rows=39/37 width=175) + Conds:RS_43._col0=RS_44._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_43] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] + <-Map 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_44] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] PREHOOK: query: SELECT x.key, y.value FROM src1 x JOIN src y ON (x.key = y.key) @@ -229,249 +224,234 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Union 2 (CONTAINS) -Map 17 <- Union 18 (CONTAINS) -Map 22 <- Union 18 (CONTAINS) -Map 23 <- Union 20 (CONTAINS) -Map 25 <- Union 26 (CONTAINS) -Map 32 <- Union 26 (CONTAINS) -Map 33 <- Union 28 (CONTAINS) -Map 34 <- Union 30 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 14 <- Map 11 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) -Reducer 15 <- Map 16 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) -Reducer 21 <- Union 20 (SIMPLE_EDGE) +Map 12 <- Union 13 (CONTAINS) +Map 15 <- Union 13 (CONTAINS) +Map 16 <- Union 17 (CONTAINS) +Map 21 <- Union 17 (CONTAINS) +Map 22 <- Union 19 (CONTAINS) +Map 23 <- Union 24 (CONTAINS) +Map 30 <- Union 24 (CONTAINS) +Map 31 <- Union 26 (CONTAINS) +Map 32 <- Union 28 (CONTAINS) +Reducer 10 <- Reducer 20 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 14 <- Union 13 (SIMPLE_EDGE) +Reducer 18 <- Union 17 (SIMPLE_EDGE), Union 19 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 20 <- Union 19 (SIMPLE_EDGE) +Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Union 28 (SIMPLE_EDGE), Union 30 (CONTAINS) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 31 <- Union 30 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 29 <- Union 28 (SIMPLE_EDGE) +Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 9 llap + Reducer 7 llap File Output Operator [FS_114] - Group By Operator [GBY_112] (rows=398/15 width=177) + Group By Operator [GBY_112] (rows=384/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] llap - Reduce Output Operator [RS_111] - PartitionCols:_col0, _col1 - Select Operator [SEL_107] (rows=199/61 width=177) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_162] (rows=199/61 width=177) - Conds:RS_104._col2=RS_105._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap - SHUFFLE [RS_105] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_145] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_15] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_104] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_161] (rows=123/52 width=86) - Conds:RS_101._col1=RS_102._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_102] - PartitionCols:_col1 - Select Operator [SEL_14] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_144] (rows=25/25 width=175) - predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) - default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 31 [SIMPLE_EDGE] llap - SHUFFLE [RS_101] - PartitionCols:_col1 - Select Operator [SEL_94] (rows=1525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_93] (rows=1525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 30 [SIMPLE_EDGE] - <-Map 34 [CONTAINS] llap - Reduce Output Operator [RS_92] - PartitionCols:_col1, _col0 - Select Operator [SEL_88] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_86] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 29 [CONTAINS] llap - Reduce Output Operator [RS_92] - PartitionCols:_col1, _col0 - Select Operator [SEL_85] (rows=1025/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_84] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 28 [SIMPLE_EDGE] - <-Map 33 [CONTAINS] llap - Reduce Output Operator [RS_83] - PartitionCols:_col1, _col0 - Select Operator [SEL_79] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_77] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 27 [CONTAINS] llap - Reduce Output Operator [RS_83] - PartitionCols:_col1, _col0 - Select Operator [SEL_76] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_75] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 26 [SIMPLE_EDGE] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_74] - PartitionCols:_col1, _col0 - Select Operator [SEL_67] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_65] (rows=25/25 width=175) - Output:["key","value"] - <-Map 32 [CONTAINS] llap - Reduce Output Operator [RS_74] - PartitionCols:_col1, _col0 - Select Operator [SEL_70] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_68] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 7 [CONTAINS] llap + <-Union 6 [SIMPLE_EDGE] + <-Reducer 5 [CONTAINS] llap Reduce Output Operator [RS_111] PartitionCols:_col0, _col1 - Group By Operator [GBY_63] (rows=199/15 width=177) + Group By Operator [GBY_63] (rows=196/15 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 10 [CONTAINS] llap Reduce Output Operator [RS_62] PartitionCols:_col0, _col1 - Select Operator [SEL_58] (rows=132/61 width=177) + Select Operator [SEL_58] (rows=130/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_160] (rows=132/61 width=177) - Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_155] (rows=130/61 width=177) + Conds:RS_55._col3=RS_56._col1(Inner),Output:["_col1","_col2"] + <-Reducer 20 [SIMPLE_EDGE] llap SHUFFLE [RS_56] - PartitionCols:_col0 - Select Operator [SEL_51] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_49] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap + PartitionCols:_col1 + Select Operator [SEL_51] (rows=1025/319 width=178) + Output:["_col1"] + Group By Operator [GBY_50] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 19 [SIMPLE_EDGE] + <-Map 22 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_45] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_43] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 18 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 17 [SIMPLE_EDGE] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_142] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 21 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_143] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 9 [SIMPLE_EDGE] llap SHUFFLE [RS_55] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_159] (rows=82/52 width=86) - Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_152] (rows=39/37 width=266) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_52] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_136] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 11 [SIMPLE_EDGE] llap SHUFFLE [RS_53] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 21 [SIMPLE_EDGE] llap - SHUFFLE [RS_52] - PartitionCols:_col1 - Select Operator [SEL_45] (rows=1025/319 width=178) - Output:["_col1"] - Group By Operator [GBY_44] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_39] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_37] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 19 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_36] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_146] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 22 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_147] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + PartitionCols:_col0 + Select Operator [SEL_5] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_137] (rows=25/25 width=175) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25/25 width=175) + default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_62] PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) + Select Operator [SEL_24] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_158] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_17] - <-Reducer 4 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_154] (rows=66/61 width=177) + Conds:RS_21._col3=RS_22._col1(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_157] (rows=42/52 width=86) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_151] (rows=39/37 width=266) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_18] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_2] <-Map 11 [SIMPLE_EDGE] llap SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_142] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=175) - Output:["key","value"] - <-Map 10 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_143] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Reducer 14 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 13 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_138] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Map 15 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_139] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 8 [CONTAINS] llap + Reduce Output Operator [RS_111] + PartitionCols:_col0, _col1 + Select Operator [SEL_107] (rows=193/61 width=177) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_156] (rows=193/61 width=177) + Conds:RS_104._col3=RS_105._col1(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_104] + PartitionCols:_col3 + Please refer to the previous Merge Join Operator [MERGEJOIN_151] + <-Reducer 29 [SIMPLE_EDGE] llap + SHUFFLE [RS_105] + PartitionCols:_col1 + Select Operator [SEL_100] (rows=1525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_99] (rows=1525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 28 [SIMPLE_EDGE] + <-Map 32 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_94] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_150] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_92] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 27 [CONTAINS] llap + Reduce Output Operator [RS_98] + PartitionCols:_col1, _col0 + Select Operator [SEL_91] (rows=1025/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_90] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 26 [SIMPLE_EDGE] + <-Map 31 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_85] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_83] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 25 [CONTAINS] llap + Reduce Output Operator [RS_89] + PartitionCols:_col1, _col0 + Select Operator [SEL_82] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_81] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 24 [SIMPLE_EDGE] + <-Map 23 [CONTAINS] llap + Reduce Output Operator [RS_80] + PartitionCols:_col1, _col0 + Select Operator [SEL_73] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_71] (rows=25/25 width=175) + Output:["key","value"] + <-Map 30 [CONTAINS] llap + Reduce Output Operator [RS_80] + PartitionCols:_col1, _col0 + Select Operator [SEL_76] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_148] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_74] (rows=500/500 width=178) + Output:["key","value"] PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -853,7 +833,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_22] - Merge Join Operator [MERGEJOIN_38] (rows=1009/1646 width=8) + Merge Join Operator [MERGEJOIN_38] (rows=1029/1646 width=8) Conds:Union 2._col0=RS_19._col0(Inner) <-Map 7 [SIMPLE_EDGE] llap SHUFFLE [RS_19] @@ -942,7 +922,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 4 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_28] - Merge Join Operator [MERGEJOIN_50] (rows=1368/3768 width=8) + Merge Join Operator [MERGEJOIN_50] (rows=1396/3768 width=8) Conds:Union 3._col0=RS_25._col0(Inner) <-Map 9 [SIMPLE_EDGE] llap SHUFFLE [RS_25] @@ -1106,24 +1086,24 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 16 <- Union 17 (CONTAINS) -Map 18 <- Union 17 (CONTAINS) -Map 19 <- Union 17 (CONTAINS) +Map 13 <- Union 14 (CONTAINS) +Map 15 <- Union 14 (CONTAINS) +Map 17 <- Union 18 (CONTAINS) +Map 19 <- Union 18 (CONTAINS) +Map 20 <- Union 18 (CONTAINS) Map 22 <- Union 23 (CONTAINS) Map 24 <- Union 23 (CONTAINS) Map 25 <- Union 23 (CONTAINS) Map 26 <- Union 23 (CONTAINS) -Map 9 <- Union 2 (CONTAINS) Reducer 11 <- Map 10 (SIMPLE_EDGE), Map 21 (SIMPLE_EDGE) -Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Union 23 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 14 <- Map 13 (SIMPLE_EDGE), Union 17 (SIMPLE_EDGE) -Reducer 15 <- Map 20 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 13 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Union 5 (CUSTOM_SIMPLE_EDGE) -Reducer 8 <- Union 5 (CUSTOM_SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Union 23 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Union 14 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Union 4 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Union 4 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Map 1 (SIMPLE_EDGE), Map 16 (SIMPLE_EDGE) +Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 18 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-5 Stats Work{} @@ -1133,38 +1113,38 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 6 llap + Reducer 5 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Union 5 [CUSTOM_SIMPLE_EDGE] + <-Union 4 [CUSTOM_SIMPLE_EDGE] <-Reducer 12 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_72] (rows=192/820 width=175) + Select Operator [SEL_72] (rows=193/820 width=175) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_124] (rows=192/820 width=175) + Merge Join Operator [MERGEJOIN_121] (rows=193/820 width=175) Conds:RS_69._col1=Union 23._col0(Inner),Output:["_col0","_col3"] <-Reducer 11 [SIMPLE_EDGE] llap SHUFFLE [RS_69] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_123] (rows=39/115 width=264) + Merge Join Operator [MERGEJOIN_118] (rows=39/115 width=264) Conds:RS_66._col0=RS_67._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 10 [SIMPLE_EDGE] llap SHUFFLE [RS_66] PartitionCols:_col0 - Select Operator [SEL_10] (rows=25/25 width=175) + Select Operator [SEL_5] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_106] (rows=25/25 width=175) + Filter Operator [FIL_102] (rows=25/25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25/25 width=175) + TableScan [TS_3] (rows=25/25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 21 [SIMPLE_EDGE] llap SHUFFLE [RS_67] PartitionCols:_col0 Select Operator [SEL_51] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_114] (rows=25/25 width=175) + Filter Operator [FIL_111] (rows=25/25 width=175) predicate:key is not null TableScan [TS_49] (rows=25/25 width=175) default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] @@ -1174,7 +1154,7 @@ Stage-5 PartitionCols:_col0 Select Operator [SEL_54] (rows=25/25 width=89) Output:["_col0"] - Filter Operator [FIL_115] (rows=25/25 width=89) + Filter Operator [FIL_112] (rows=25/25 width=89) predicate:value is not null TableScan [TS_52] (rows=25/25 width=89) Output:["value"] @@ -1183,7 +1163,7 @@ Stage-5 PartitionCols:_col0 Select Operator [SEL_57] (rows=500/500 width=91) Output:["_col0"] - Filter Operator [FIL_116] (rows=500/500 width=91) + Filter Operator [FIL_113] (rows=500/500 width=91) predicate:value is not null TableScan [TS_55] (rows=500/500 width=91) Output:["value"] @@ -1192,7 +1172,7 @@ Stage-5 PartitionCols:_col0 Select Operator [SEL_61] (rows=500/500 width=91) Output:["_col0"] - Filter Operator [FIL_117] (rows=500/500 width=91) + Filter Operator [FIL_114] (rows=500/500 width=91) predicate:value is not null TableScan [TS_59] (rows=500/500 width=91) Output:["value"] @@ -1201,175 +1181,175 @@ Stage-5 PartitionCols:_col0 Select Operator [SEL_64] (rows=500/500 width=91) Output:["_col0"] - Filter Operator [FIL_118] (rows=500/500 width=91) + Filter Operator [FIL_115] (rows=500/500 width=91) predicate:value is not null TableScan [TS_62] (rows=500/500 width=91) Output:["value"] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] table:{"name:":"default.b"} Please refer to the previous Select Operator [SEL_72] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] table:{"name:":"default.c"} Please refer to the previous Select Operator [SEL_72] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] - <-Reducer 15 [CONTAINS] llap + <-Reducer 3 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_44] (rows=2682/5421 width=178) + Select Operator [SEL_20] (rows=66/170 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_122] (rows=2682/5421 width=178) - Conds:RS_41._col1=RS_42._col0(Inner),Output:["_col1","_col4"] - <-Map 20 [SIMPLE_EDGE] llap - SHUFFLE [RS_42] - PartitionCols:_col0 - Select Operator [SEL_37] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_112] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_35] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_41] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_121] (rows=1658/2097 width=87) - Conds:Union 17._col0=RS_39._col1(Inner),Output:["_col1"] - <-Map 13 [SIMPLE_EDGE] llap - SHUFFLE [RS_39] - PartitionCols:_col1 - Select Operator [SEL_34] (rows=500/500 width=178) + Merge Join Operator [MERGEJOIN_119] (rows=66/170 width=177) + Conds:RS_17._col3=Union 14._col0(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_17] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_116] (rows=39/37 width=266) + Conds:RS_14._col0=RS_15._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_14] + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_111] (rows=500/500 width=178) - predicate:(key is not null and value is not null) - TableScan [TS_11] (rows=500/500 width=178) + Filter Operator [FIL_101] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500/500 width=178) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Union 17 [SIMPLE_EDGE] - <-Map 16 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_23] (rows=25/25 width=89) - Output:["_col0"] - Filter Operator [FIL_108] (rows=25/25 width=89) - predicate:value is not null - TableScan [TS_21] (rows=25/25 width=89) - Output:["value"] - <-Map 18 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_26] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_109] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_24] (rows=500/500 width=91) - Output:["value"] - <-Map 19 [CONTAINS] llap - Reduce Output Operator [RS_38] - PartitionCols:_col0 - Select Operator [SEL_30] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_110] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=91) - Output:["value"] + <-Map 10 [SIMPLE_EDGE] llap + SHUFFLE [RS_15] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_8] (rows=25/25 width=89) + Output:["_col0"] + Filter Operator [FIL_103] (rows=25/25 width=89) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=89) + Output:["value"] + <-Map 15 [CONTAINS] llap + Reduce Output Operator [RS_18] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_104] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=91) + Output:["value"] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - <-Reducer 4 [CONTAINS] llap + Please refer to the previous Select Operator [SEL_20] + <-Reducer 9 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_20] (rows=67/170 width=177) + Select Operator [SEL_44] (rows=2640/5421 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_120] (rows=67/170 width=177) - Conds:RS_17._col1=RS_18._col0(Inner),Output:["_col1","_col4"] - <-Map 13 [SIMPLE_EDGE] llap - SHUFFLE [RS_18] - PartitionCols:_col0 - Select Operator [SEL_13] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_107] (rows=500/500 width=178) - predicate:key is not null - Please refer to the previous TableScan [TS_11] - <-Reducer 3 [SIMPLE_EDGE] llap - SHUFFLE [RS_17] + Merge Join Operator [MERGEJOIN_120] (rows=2640/5421 width=178) + Conds:RS_41._col1=Union 18._col0(Inner),Output:["_col0","_col3"] + <-Reducer 8 [SIMPLE_EDGE] llap + SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_119] (rows=42/108 width=86) - Conds:Union 2._col0=RS_15._col1(Inner),Output:["_col1"] - <-Map 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_15] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_10] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_14] - PartitionCols:_col0 - Select Operator [SEL_2] (rows=25/25 width=89) - Output:["_col0"] - Filter Operator [FIL_104] (rows=25/25 width=89) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=89) - Output:["value"] - <-Map 9 [CONTAINS] llap - Reduce Output Operator [RS_14] - PartitionCols:_col0 - Select Operator [SEL_5] (rows=500/500 width=91) - Output:["_col0"] - Filter Operator [FIL_105] (rows=500/500 width=91) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=91) - Output:["value"] + Merge Join Operator [MERGEJOIN_117] (rows=791/1028 width=269) + Conds:RS_38._col0=RS_39._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_38] + PartitionCols:_col0 + Select Operator [SEL_23] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_105] (rows=500/500 width=178) + predicate:(key is not null and value is not null) + Please refer to the previous TableScan [TS_0] + <-Map 16 [SIMPLE_EDGE] llap + SHUFFLE [RS_39] + PartitionCols:_col0 + Select Operator [SEL_26] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_106] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_24] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Union 18 [SIMPLE_EDGE] + <-Map 17 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_29] (rows=25/25 width=89) + Output:["_col0"] + Filter Operator [FIL_107] (rows=25/25 width=89) + predicate:value is not null + TableScan [TS_27] (rows=25/25 width=89) + Output:["value"] + <-Map 19 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_32] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_108] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_30] (rows=500/500 width=91) + Output:["value"] + <-Map 20 [CONTAINS] llap + Reduce Output Operator [RS_42] + PartitionCols:_col0 + Select Operator [SEL_36] (rows=500/500 width=91) + Output:["_col0"] + Filter Operator [FIL_109] (rows=500/500 width=91) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=91) + Output:["value"] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_2] - Select Operator [SEL_1] (rows=2941/6411 width=178) + Select Operator [SEL_1] (rows=2899/6411 width=178) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - Reducer 7 llap + Please refer to the previous Select Operator [SEL_44] + Reducer 6 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <- Please refer to the previous Union 5 [CUSTOM_SIMPLE_EDGE] - Reducer 8 llap + <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] + Reducer 7 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <- Please refer to the previous Union 5 [CUSTOM_SIMPLE_EDGE] + <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] Stage-6 Stats Work{} Stage-1 @@ -1458,32 +1438,32 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 13 <- Union 2 (CONTAINS) -Map 20 <- Union 21 (CONTAINS) -Map 25 <- Union 21 (CONTAINS) -Map 26 <- Union 23 (CONTAINS) +Map 16 <- Union 17 (CONTAINS) +Map 19 <- Union 17 (CONTAINS) +Map 21 <- Union 22 (CONTAINS) +Map 26 <- Union 22 (CONTAINS) +Map 27 <- Union 24 (CONTAINS) Map 29 <- Union 30 (CONTAINS) Map 36 <- Union 30 (CONTAINS) Map 37 <- Union 32 (CONTAINS) Map 38 <- Union 34 (CONTAINS) -Reducer 10 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 12 <- Reducer 9 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Map 28 (SIMPLE_EDGE) -Reducer 16 <- Reducer 15 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 18 <- Map 17 (SIMPLE_EDGE), Reducer 24 (SIMPLE_EDGE) -Reducer 19 <- Map 27 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 22 <- Union 21 (SIMPLE_EDGE), Union 23 (CONTAINS) -Reducer 24 <- Union 23 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) +Reducer 10 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) +Reducer 11 <- Map 1 (SIMPLE_EDGE), Map 20 (SIMPLE_EDGE) +Reducer 12 <- Reducer 11 (SIMPLE_EDGE), Reducer 25 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 14 <- Map 13 (SIMPLE_EDGE), Map 28 (SIMPLE_EDGE) +Reducer 15 <- Reducer 14 (SIMPLE_EDGE), Reducer 35 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 18 <- Union 17 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 23 <- Union 22 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 25 <- Union 24 (SIMPLE_EDGE) +Reducer 3 <- Reducer 18 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) Reducer 31 <- Union 30 (SIMPLE_EDGE), Union 32 (CONTAINS) Reducer 33 <- Union 32 (SIMPLE_EDGE), Union 34 (CONTAINS) Reducer 35 <- Union 34 (SIMPLE_EDGE) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 17 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 7 (CUSTOM_SIMPLE_EDGE) Stage-5 Stats Work{} @@ -1497,40 +1477,40 @@ Stage-5 File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) + Select Operator [SEL_1] (rows=2899/319 width=178) Output:["key","value"] - Group By Operator [GBY_112] (rows=2941/319 width=178) + Group By Operator [GBY_112] (rows=2899/319 width=178) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 16 [CONTAINS] llap + <-Union 6 [SIMPLE_EDGE] + <-Reducer 15 [CONTAINS] llap Reduce Output Operator [RS_111] PartitionCols:_col0, _col1 - Select Operator [SEL_107] (rows=192/304 width=175) + Select Operator [SEL_107] (rows=193/304 width=175) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_164] (rows=192/304 width=175) + Merge Join Operator [MERGEJOIN_161] (rows=193/304 width=175) Conds:RS_104._col1=RS_105._col1(Inner),Output:["_col0","_col3"] - <-Reducer 15 [SIMPLE_EDGE] llap + <-Reducer 14 [SIMPLE_EDGE] llap SHUFFLE [RS_104] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_163] (rows=39/115 width=264) + Merge Join Operator [MERGEJOIN_158] (rows=39/115 width=264) Conds:RS_101._col0=RS_102._col0(Inner),Output:["_col0","_col1","_col3"] - <-Map 14 [SIMPLE_EDGE] llap + <-Map 13 [SIMPLE_EDGE] llap SHUFFLE [RS_101] PartitionCols:_col0 - Select Operator [SEL_14] (rows=25/25 width=175) + Select Operator [SEL_5] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_146] (rows=25/25 width=175) + Filter Operator [FIL_142] (rows=25/25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_12] (rows=25/25 width=175) + TableScan [TS_3] (rows=25/25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 28 [SIMPLE_EDGE] llap SHUFFLE [RS_102] PartitionCols:_col0 Select Operator [SEL_70] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_154] (rows=25/25 width=175) + Filter Operator [FIL_151] (rows=25/25 width=175) predicate:key is not null TableScan [TS_68] (rows=25/25 width=175) default@src1,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] @@ -1547,7 +1527,7 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_94] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=500/500 width=178) + Filter Operator [FIL_155] (rows=500/500 width=178) predicate:value is not null TableScan [TS_92] (rows=500/500 width=178) Output:["key","value"] @@ -1564,7 +1544,7 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_85] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_157] (rows=500/500 width=178) + Filter Operator [FIL_154] (rows=500/500 width=178) predicate:value is not null TableScan [TS_83] (rows=500/500 width=178) Output:["key","value"] @@ -1581,7 +1561,7 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_73] (rows=25/25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_155] (rows=25/25 width=175) + Filter Operator [FIL_152] (rows=25/25 width=175) predicate:value is not null TableScan [TS_71] (rows=25/25 width=175) Output:["key","value"] @@ -1590,155 +1570,155 @@ Stage-5 PartitionCols:_col1, _col0 Select Operator [SEL_76] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_156] (rows=500/500 width=178) + Filter Operator [FIL_153] (rows=500/500 width=178) predicate:value is not null TableScan [TS_74] (rows=500/500 width=178) Output:["key","value"] - <-Reducer 7 [CONTAINS] llap + <-Reducer 5 [CONTAINS] llap Reduce Output Operator [RS_111] PartitionCols:_col0, _col1 - Group By Operator [GBY_63] (rows=2749/309 width=178) + Group By Operator [GBY_63] (rows=2706/309 width=178) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 19 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 12 [CONTAINS] llap Reduce Output Operator [RS_62] PartitionCols:_col0, _col1 - Select Operator [SEL_58] (rows=2682/1056 width=178) + Select Operator [SEL_58] (rows=2640/1056 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_162] (rows=2682/1056 width=178) - Conds:RS_55._col2=RS_56._col0(Inner),Output:["_col2","_col5"] - <-Map 27 [SIMPLE_EDGE] llap - SHUFFLE [RS_56] - PartitionCols:_col0 - Select Operator [SEL_51] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_152] (rows=500/500 width=178) - predicate:key is not null - TableScan [TS_49] (rows=500/500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 18 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_160] (rows=2640/1056 width=178) + Conds:RS_55._col1=RS_56._col1(Inner),Output:["_col0","_col3"] + <-Reducer 11 [SIMPLE_EDGE] llap SHUFFLE [RS_55] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_161] (rows=1658/512 width=87) - Conds:RS_52._col1=RS_53._col1(Inner),Output:["_col2"] - <-Map 17 [SIMPLE_EDGE] llap - SHUFFLE [RS_53] - PartitionCols:_col1 - Select Operator [SEL_48] (rows=500/500 width=178) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_157] (rows=791/1028 width=269) + Conds:RS_52._col0=RS_53._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] llap + SHUFFLE [RS_52] + PartitionCols:_col0 + Select Operator [SEL_27] (rows=500/500 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_151] (rows=500/500 width=178) + Filter Operator [FIL_145] (rows=500/500 width=178) predicate:(key is not null and value is not null) - TableScan [TS_15] (rows=500/500 width=178) + TableScan [TS_0] (rows=500/500 width=178) default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 24 [SIMPLE_EDGE] llap - SHUFFLE [RS_52] - PartitionCols:_col1 - Select Operator [SEL_45] (rows=1025/319 width=178) - Output:["_col1"] - Group By Operator [GBY_44] (rows=1025/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 23 [SIMPLE_EDGE] - <-Map 26 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_39] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_150] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_37] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 22 [CONTAINS] llap - Reduce Output Operator [RS_43] - PartitionCols:_col1, _col0 - Select Operator [SEL_36] (rows=525/319 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_35] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 21 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_27] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_25] (rows=25/25 width=175) - Output:["key","value"] - <-Map 25 [CONTAINS] llap - Reduce Output Operator [RS_34] - PartitionCols:_col1, _col0 - Select Operator [SEL_30] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_28] (rows=500/500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + <-Map 20 [SIMPLE_EDGE] llap + SHUFFLE [RS_53] + PartitionCols:_col0 + Select Operator [SEL_30] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=500/500 width=178) + predicate:key is not null + TableScan [TS_28] (rows=500/500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 25 [SIMPLE_EDGE] llap + SHUFFLE [RS_56] + PartitionCols:_col1 + Select Operator [SEL_51] (rows=1025/319 width=178) + Output:["_col1"] + Group By Operator [GBY_50] (rows=1025/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 24 [SIMPLE_EDGE] + <-Map 27 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_45] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_149] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_43] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 23 [CONTAINS] llap + Reduce Output Operator [RS_49] + PartitionCols:_col1, _col0 + Select Operator [SEL_42] (rows=525/319 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_41] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 22 [SIMPLE_EDGE] + <-Map 21 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_33] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_147] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_31] (rows=25/25 width=175) + Output:["key","value"] + <-Map 26 [CONTAINS] llap + Reduce Output Operator [RS_40] + PartitionCols:_col1, _col0 + Select Operator [SEL_36] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_148] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_34] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_62] PartitionCols:_col0, _col1 - Select Operator [SEL_24] (rows=67/61 width=177) + Select Operator [SEL_24] (rows=66/61 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_160] (rows=67/61 width=177) - Conds:RS_21._col2=RS_22._col0(Inner),Output:["_col2","_col5"] - <-Map 17 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_159] (rows=66/61 width=177) + Conds:RS_21._col3=RS_22._col1(Inner),Output:["_col1","_col2"] + <-Reducer 18 [SIMPLE_EDGE] llap SHUFFLE [RS_22] - PartitionCols:_col0 - Select Operator [SEL_17] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_147] (rows=500/500 width=178) - predicate:key is not null - Please refer to the previous TableScan [TS_15] - <-Reducer 4 [SIMPLE_EDGE] llap + PartitionCols:_col1 + Select Operator [SEL_17] (rows=525/319 width=178) + Output:["_col1"] + Group By Operator [GBY_16] (rows=525/319 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 17 [SIMPLE_EDGE] + <-Map 16 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_8] (rows=25/25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_143] (rows=25/25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25/25 width=175) + Output:["key","value"] + <-Map 19 [CONTAINS] llap + Reduce Output Operator [RS_15] + PartitionCols:_col1, _col0 + Select Operator [SEL_11] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_144] (rows=500/500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500/500 width=178) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_21] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_159] (rows=42/52 width=86) - Conds:RS_18._col1=RS_19._col1(Inner),Output:["_col2"] - <-Map 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_19] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_14] - <-Reducer 3 [SIMPLE_EDGE] llap + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_156] (rows=39/37 width=266) + Conds:RS_18._col0=RS_19._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_18] - PartitionCols:_col1 - Select Operator [SEL_11] (rows=525/319 width=178) - Output:["_col1"] - Group By Operator [GBY_10] (rows=525/319 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_2] (rows=25/25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_144] (rows=25/25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25/25 width=175) - Output:["key","value"] - <-Map 13 [CONTAINS] llap - Reduce Output Operator [RS_9] - PartitionCols:_col1, _col0 - Select Operator [SEL_5] (rows=500/500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_145] (rows=500/500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500/500 width=178) - Output:["key","value"] - Reducer 11 llap + PartitionCols:_col0 + Select Operator [SEL_2] (rows=500/500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_141] (rows=500/500 width=178) + predicate:key is not null + Please refer to the previous TableScan [TS_0] + <-Map 13 [SIMPLE_EDGE] llap + SHUFFLE [RS_19] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_5] + Reducer 8 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) + Select Operator [SEL_1] (rows=2899/319 width=178) Output:["key","value"] Please refer to the previous Group By Operator [GBY_112] - Reducer 12 llap + Reducer 9 llap File Output Operator [FS_5] Group By Operator [GBY_3] (rows=1/1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0, 'hll')","compute_stats(VALUE._col2, 'hll')"] - <-Reducer 9 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 7 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=2941/319 width=178) + Select Operator [SEL_1] (rows=2899/319 width=178) Output:["key","value"] Please refer to the previous Group By Operator [GBY_112] Stage-6 @@ -1827,9 +1807,9 @@ Stage-4 <-Reducer 5 [CUSTOM_SIMPLE_EDGE] llap File Output Operator [FS_18] table:{"name:":"default.dest1"} - Select Operator [SEL_16] (rows=309/310 width=272) + Select Operator [SEL_16] (rows=316/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_15] (rows=309/310 width=96) + Group By Operator [GBY_15] (rows=316/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Reducer 4 [SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_14] @@ -1857,7 +1837,7 @@ Stage-4 TableScan [TS_0] (rows=500/500 width=10) default@src,s1,Tbl:COMPLETE,Col:COMPLETE PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=309/310 width=272) + Select Operator [SEL_1] (rows=316/310 width=272) Output:["key","value"] Please refer to the previous Select Operator [SEL_16] Reducer 7 llap @@ -1915,9 +1895,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=261/4122 width=260) + Select Operator [SEL_7] (rows=250/4122 width=260) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_9] (rows=261/4122 width=260) + Merge Join Operator [MERGEJOIN_9] (rows=250/4122 width=260) Conds:RS_3.key=RS_3.key(Unique),RS_3.key=RS_3.key(Unique),RS_3.key=RS_3.key(Unique),Output:["_col0","_col5","_col10"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] @@ -2017,9 +1997,9 @@ Stage-4 <-Reducer 4 [CUSTOM_SIMPLE_EDGE] llap File Output Operator [FS_16] table:{"name:":"default.dest1"} - Select Operator [SEL_14] (rows=309/310 width=272) + Select Operator [SEL_14] (rows=316/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_13] (rows=309/310 width=96) + Group By Operator [GBY_13] (rows=316/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 8 [CONTAINS] llap @@ -2058,7 +2038,7 @@ Stage-4 PartitionCols:_col0, _col1 Please refer to the previous Select Operator [SEL_4] PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=309/310 width=272) + Select Operator [SEL_1] (rows=316/310 width=272) Output:["key","value"] Please refer to the previous Select Operator [SEL_14] Reducer 7 llap @@ -2153,9 +2133,9 @@ Stage-4 <-Reducer 4 [CUSTOM_SIMPLE_EDGE] llap File Output Operator [FS_14] table:{"name:":"default.dest1"} - Select Operator [SEL_12] (rows=309/310 width=272) + Select Operator [SEL_12] (rows=316/310 width=272) Output:["_col0","_col1"] - Group By Operator [GBY_11] (rows=309/310 width=96) + Group By Operator [GBY_11] (rows=316/310 width=96) Output:["_col0","_col1"],aggregations:["count(DISTINCT KEY._col1:0._col0)"],keys:KEY._col0 <-Union 3 [SIMPLE_EDGE] <-Map 8 [CONTAINS] llap @@ -2184,7 +2164,7 @@ Stage-4 PartitionCols:_col0, _col1 Please refer to the previous Select Operator [SEL_4] PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=309/310 width=272) + Select Operator [SEL_1] (rows=316/310 width=272) Output:["key","value"] Please refer to the previous Select Operator [SEL_12] Reducer 7 llap diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 872f9c9..13e3d44 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -1713,9 +1713,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_19] - Select Operator [SEL_18] (rows=366 width=178) + Select Operator [SEL_18] (rows=365 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=366 width=179) + Filter Operator [FIL_17] (rows=365 width=179) predicate:_col3 is null Merge Join Operator [MERGEJOIN_22] (rows=500 width=179) Conds:RS_14._col1=RS_15._col0(Left Outer),Output:["_col0","_col1","_col3"] @@ -1777,9 +1777,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_18] - Select Operator [SEL_17] (rows=183 width=178) + Select Operator [SEL_17] (rows=185 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=183 width=179) + Filter Operator [FIL_16] (rows=185 width=179) predicate:_col4 is null Merge Join Operator [MERGEJOIN_21] (rows=250 width=179) Conds:RS_13._col0, _col1=RS_14._col0, _col1(Left Outer),Output:["_col0","_col1","_col4"] @@ -1852,7 +1852,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -1904,7 +1904,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0, _col1=RS_9._col0, _col1(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -1946,7 +1946,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_17] (rows=131 width=178) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -2067,16 +2067,16 @@ Stage-0 <-Reducer 3 [SIMPLE_EDGE] llap SHUFFLE [RS_27] PartitionCols:_col2 - Filter Operator [FIL_37] (rows=66 width=186) + Filter Operator [FIL_37] (rows=65 width=186) predicate:_col2 is not null - Group By Operator [GBY_14] (rows=66 width=186) + Group By Operator [GBY_14] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=66 width=186) + Group By Operator [GBY_12] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col0, _col1 - Merge Join Operator [MERGEJOIN_43] (rows=133 width=178) + Merge Join Operator [MERGEJOIN_43] (rows=131 width=178) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_9] @@ -2671,7 +2671,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_24] (rows=40 width=86) + Merge Join Operator [MERGEJOIN_24] (rows=39 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -2732,7 +2732,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_24] (rows=40 width=86) + Merge Join Operator [MERGEJOIN_24] (rows=39 width=86) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -2793,7 +2793,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Map Join Operator [MAPJOIN_24] (rows=40 width=86) + Map Join Operator [MAPJOIN_24] (rows=39 width=86) Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col0"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_6] @@ -2842,16 +2842,16 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_18] Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_15] (rows=10 width=94) + Select Operator [SEL_15] (rows=9 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=10 width=94) + Group By Operator [GBY_14] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_13] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=10 width=94) + Group By Operator [GBY_12] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_26] (rows=20 width=86) + Merge Join Operator [MERGEJOIN_26] (rows=19 width=86) Conds:RS_8._col0=RS_9._col0(Left Semi),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] @@ -5329,9 +5329,9 @@ Stage-3 <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap File Output Operator [FS_11] table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) + Select Operator [SEL_9] (rows=791 width=95) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_16] (rows=809 width=178) + Merge Join Operator [MERGEJOIN_16] (rows=791 width=178) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] @@ -5353,7 +5353,7 @@ Stage-3 default@src,src2,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] PARTITION_ONLY_SHUFFLE [RS_2] PartitionCols:rand() - Select Operator [SEL_1] (rows=809 width=95) + Select Operator [SEL_1] (rows=791 width=95) Output:["key","value"] Please refer to the previous Select Operator [SEL_9] @@ -5573,7 +5573,7 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_10] - Merge Join Operator [MERGEJOIN_15] (rows=809 width=356) + Merge Join Operator [MERGEJOIN_15] (rows=791 width=356) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out index 6d77406..2f2ddc1 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_2.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_2.q.out @@ -192,9 +192,9 @@ Stage-0 Stage-1 Reducer 3 llap File Output Operator [FS_16] - Select Operator [SEL_15] (rows=64 width=268) + Select Operator [SEL_15] (rows=63 width=268) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_26] (rows=64 width=268) + Merge Join Operator [MERGEJOIN_26] (rows=63 width=268) Conds:RS_12._col3=RS_35._col0(Inner),Output:["_col1","_col2","_col4"] <-Map 5 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_35] @@ -208,7 +208,7 @@ Stage-0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_12] PartitionCols:_col3 - Merge Join Operator [MERGEJOIN_25] (rows=40 width=266) + Merge Join Operator [MERGEJOIN_25] (rows=39 width=266) Conds:RS_29._col0=RS_32._col0(Inner),Output:["_col1","_col2","_col3"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_29] @@ -443,146 +443,141 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) +Map 12 <- Union 10 (CONTAINS) Map 13 <- Union 14 (CONTAINS) Map 16 <- Union 14 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 10 <- Map 9 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE) -Reducer 11 <- Map 17 (SIMPLE_EDGE), Reducer 10 (SIMPLE_EDGE), Union 6 (CONTAINS) +Map 9 <- Union 10 (CONTAINS) +Reducer 11 <- Union 10 (SIMPLE_EDGE) Reducer 15 <- Union 14 (SIMPLE_EDGE) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 9 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 12 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 3 <- Reducer 11 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE) +Reducer 6 <- Map 1 (SIMPLE_EDGE), Map 8 (SIMPLE_EDGE) +Reducer 7 <- Reducer 15 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Union 4 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 vectorized, llap - File Output Operator [FS_101] - Group By Operator [GBY_100] (rows=28 width=177) + Reducer 5 vectorized, llap + File Output Operator [FS_96] + Group By Operator [GBY_95] (rows=33 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=28 width=177) + Group By Operator [GBY_55] (rows=33 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_51] (rows=33 width=177) + Select Operator [SEL_25] (rows=33 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_85] (rows=33 width=177) - Conds:RS_48._col2=RS_111._col0(Inner),Output:["_col1","_col2"] - <-Map 17 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_111] - PartitionCols:_col0 - Select Operator [SEL_110] (rows=500 width=87) - Output:["_col0"] - Filter Operator [FIL_109] (rows=500 width=87) - predicate:key is not null - TableScan [TS_42] (rows=500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 10 [SIMPLE_EDGE] llap - SHUFFLE [RS_48] + Merge Join Operator [MERGEJOIN_82] (rows=33 width=177) + Conds:RS_22._col2=RS_94._col1(Inner),Output:["_col1","_col4"] + <-Reducer 11 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_94] + PartitionCols:_col1 + Select Operator [SEL_93] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_92] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 10 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_107] + PartitionCols:_col0, _col1 + Group By Operator [GBY_106] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_105] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_104] (rows=500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500 width=178) + Output:["key","value"] + <-Map 9 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_103] + PartitionCols:_col0, _col1 + Group By Operator [GBY_102] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_101] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_100] (rows=25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25 width=175) + Output:["key","value"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_22] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_84] (rows=21 width=177) - Conds:RS_108._col1=RS_96._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_96] - PartitionCols:_col1 - Select Operator [SEL_94] (rows=25 width=175) + Merge Join Operator [MERGEJOIN_80] (rows=39 width=175) + Conds:RS_86._col0=RS_90._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_86] + PartitionCols:_col0 + Select Operator [SEL_85] (rows=500 width=87) + Output:["_col0"] + Filter Operator [FIL_84] (rows=500 width=87) + predicate:key is not null + TableScan [TS_0] (rows=500 width=87) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] + <-Map 8 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_90] + PartitionCols:_col0 + Select Operator [SEL_89] (rows=25 width=175) Output:["_col0","_col1"] - Filter Operator [FIL_93] (rows=25 width=175) + Filter Operator [FIL_88] (rows=25 width=175) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=175) + TableScan [TS_3] (rows=25 width=175) default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_108] - PartitionCols:_col1 - Select Operator [SEL_107] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_106] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_115] - PartitionCols:_col0, _col1 - Group By Operator [GBY_114] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_113] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_112] (rows=25 width=175) - predicate:value is not null - TableScan [TS_26] (rows=25 width=175) - Output:["key","value"] - <-Map 16 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_119] - PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_117] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_116] (rows=500 width=178) - predicate:value is not null - TableScan [TS_29] (rows=500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + <-Reducer 7 [CONTAINS] llap Reduce Output Operator [RS_56] PartitionCols:_col0, _col1 - Group By Operator [GBY_55] (rows=28 width=177) + Group By Operator [GBY_55] (rows=33 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=33 width=177) + Select Operator [SEL_51] (rows=33 width=177) Output:["_col0","_col1"] Merge Join Operator [MERGEJOIN_83] (rows=33 width=177) - Conds:RS_22._col2=RS_99._col0(Inner),Output:["_col1","_col2"] - <-Map 12 [SIMPLE_EDGE] vectorized, llap + Conds:RS_48._col2=RS_99._col1(Inner),Output:["_col1","_col4"] + <-Reducer 15 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_99] - PartitionCols:_col0 - Select Operator [SEL_98] (rows=500 width=87) - Output:["_col0"] - Filter Operator [FIL_97] (rows=500 width=87) - predicate:key is not null - TableScan [TS_16] (rows=500 width=87) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Reducer 4 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] + PartitionCols:_col1 + Select Operator [SEL_98] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_97] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_111] + PartitionCols:_col0, _col1 + Group By Operator [GBY_110] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_109] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_108] (rows=25 width=175) + predicate:value is not null + TableScan [TS_32] (rows=25 width=175) + Output:["key","value"] + <-Map 16 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_115] + PartitionCols:_col0, _col1 + Group By Operator [GBY_114] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_113] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_112] (rows=500 width=178) + predicate:value is not null + TableScan [TS_35] (rows=500 width=178) + Output:["key","value"] + <-Reducer 6 [SIMPLE_EDGE] llap + SHUFFLE [RS_48] PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_82] (rows=21 width=177) - Conds:RS_92._col1=RS_95._col1(Inner),Output:["_col1","_col2"] - <-Map 9 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_95] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_94] - <-Reducer 3 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_92] - PartitionCols:_col1 - Select Operator [SEL_91] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_90] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_89] - PartitionCols:_col0, _col1 - Group By Operator [GBY_88] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_87] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_86] (rows=25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25 width=175) - Output:["key","value"] - <-Map 8 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_105] - PartitionCols:_col0, _col1 - Group By Operator [GBY_104] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_103] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_102] (rows=500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500 width=178) - Output:["key","value"] + Merge Join Operator [MERGEJOIN_81] (rows=39 width=175) + Conds:RS_87._col0=RS_91._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_87] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_85] + <-Map 8 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_91] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_89] PREHOOK: query: explain SELECT x.key, y.value @@ -613,281 +608,266 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Union 2 (CONTAINS) -Map 17 <- Union 18 (CONTAINS) -Map 22 <- Union 18 (CONTAINS) -Map 23 <- Union 20 (CONTAINS) -Map 25 <- Union 26 (CONTAINS) -Map 32 <- Union 26 (CONTAINS) -Map 33 <- Union 28 (CONTAINS) -Map 34 <- Union 30 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 13 <- Map 24 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 14 <- Map 11 (SIMPLE_EDGE), Reducer 31 (SIMPLE_EDGE) -Reducer 15 <- Map 16 (SIMPLE_EDGE), Reducer 14 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) -Reducer 21 <- Union 20 (SIMPLE_EDGE) +Map 12 <- Union 13 (CONTAINS) +Map 15 <- Union 13 (CONTAINS) +Map 16 <- Union 17 (CONTAINS) +Map 21 <- Union 17 (CONTAINS) +Map 22 <- Union 19 (CONTAINS) +Map 23 <- Union 24 (CONTAINS) +Map 30 <- Union 24 (CONTAINS) +Map 31 <- Union 26 (CONTAINS) +Map 32 <- Union 28 (CONTAINS) +Reducer 10 <- Reducer 20 (SIMPLE_EDGE), Reducer 9 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 14 <- Union 13 (SIMPLE_EDGE) +Reducer 18 <- Union 17 (SIMPLE_EDGE), Union 19 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) +Reducer 20 <- Union 19 (SIMPLE_EDGE) +Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Union 28 (SIMPLE_EDGE), Union 30 (CONTAINS) -Reducer 3 <- Union 2 (SIMPLE_EDGE) -Reducer 31 <- Union 30 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE) -Reducer 5 <- Map 16 (SIMPLE_EDGE), Reducer 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) -Reducer 9 <- Union 8 (SIMPLE_EDGE) +Reducer 29 <- Union 28 (SIMPLE_EDGE) +Reducer 3 <- Reducer 14 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE), Union 4 (CONTAINS) +Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) +Reducer 8 <- Reducer 2 (SIMPLE_EDGE), Reducer 29 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 9 <- Map 1 (SIMPLE_EDGE), Map 11 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 9 vectorized, llap - File Output Operator [FS_191] - Group By Operator [GBY_190] (rows=48 width=177) + Reducer 7 vectorized, llap + File Output Operator [FS_180] + Group By Operator [GBY_179] (rows=47 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 8 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] llap - Reduce Output Operator [RS_119] - PartitionCols:_col0, _col1 - Group By Operator [GBY_118] (rows=48 width=177) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_114] (rows=56 width=177) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_170] (rows=56 width=177) - Conds:RS_111._col2=RS_186._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_186] - PartitionCols:_col0 - Select Operator [SEL_184] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_183] (rows=500 width=178) - predicate:key is not null - TableScan [TS_16] (rows=500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 14 [SIMPLE_EDGE] llap - SHUFFLE [RS_111] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_169] (rows=35 width=86) - Conds:RS_204._col1=RS_182._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_182] - PartitionCols:_col1 - Select Operator [SEL_179] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_178] (rows=25 width=175) - predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=175) - default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 31 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_204] - PartitionCols:_col1 - Select Operator [SEL_203] (rows=440 width=178) - Output:["_col1"] - Group By Operator [GBY_202] (rows=440 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 30 [SIMPLE_EDGE] - <-Map 34 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_244] - PartitionCols:_col0, _col1 - Group By Operator [GBY_243] (rows=440 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_242] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_241] (rows=500 width=178) - predicate:value is not null - TableScan [TS_92] (rows=500 width=178) - Output:["key","value"] - <-Reducer 29 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_232] - PartitionCols:_col0, _col1 - Group By Operator [GBY_231] (rows=440 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_230] (rows=381 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_229] (rows=381 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 28 [SIMPLE_EDGE] - <-Map 33 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_240] - PartitionCols:_col0, _col1 - Group By Operator [GBY_239] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_238] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_237] (rows=500 width=178) - predicate:value is not null - TableScan [TS_82] (rows=500 width=178) - Output:["key","value"] - <-Reducer 27 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_228] - PartitionCols:_col0, _col1 - Group By Operator [GBY_227] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_226] (rows=262 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_225] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 26 [SIMPLE_EDGE] - <-Map 25 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_224] - PartitionCols:_col0, _col1 - Group By Operator [GBY_223] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_222] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_221] (rows=25 width=175) - predicate:value is not null - TableScan [TS_69] (rows=25 width=175) - Output:["key","value"] - <-Map 32 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_236] - PartitionCols:_col0, _col1 - Group By Operator [GBY_235] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_234] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_233] (rows=500 width=178) - predicate:value is not null - TableScan [TS_72] (rows=500 width=178) - Output:["key","value"] - <-Reducer 7 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_189] + <-Union 6 [SIMPLE_EDGE] + <-Reducer 5 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_178] PartitionCols:_col0, _col1 - Group By Operator [GBY_188] (rows=48 width=177) + Group By Operator [GBY_177] (rows=47 width=177) Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_187] (rows=40 width=177) + Group By Operator [GBY_176] (rows=40 width=177) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 4 [SIMPLE_EDGE] + <-Reducer 10 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 Group By Operator [GBY_65] (rows=40 width=177) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_61] (rows=48 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_168] (rows=48 width=177) - Conds:RS_58._col2=RS_201._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_201] - PartitionCols:_col0 - Select Operator [SEL_200] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_199] (rows=500 width=178) - predicate:key is not null - TableScan [TS_52] (rows=500 width=178) - default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_163] (rows=48 width=177) + Conds:RS_58._col3=RS_186._col1(Inner),Output:["_col1","_col2"] + <-Reducer 20 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_186] + PartitionCols:_col1 + Select Operator [SEL_185] (rows=381 width=178) + Output:["_col1"] + Group By Operator [GBY_184] (rows=381 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 19 [SIMPLE_EDGE] + <-Map 22 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_210] + PartitionCols:_col0, _col1 + Group By Operator [GBY_209] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_208] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_207] (rows=500 width=178) + predicate:value is not null + TableScan [TS_45] (rows=500 width=178) + Output:["key","value"] + <-Reducer 18 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_202] + PartitionCols:_col0, _col1 + Group By Operator [GBY_201] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_200] (rows=262 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_199] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 17 [SIMPLE_EDGE] + <-Map 16 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_198] + PartitionCols:_col0, _col1 + Group By Operator [GBY_197] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_196] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_195] (rows=25 width=175) + predicate:value is not null + TableScan [TS_32] (rows=25 width=175) + Output:["key","value"] + <-Map 21 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_206] + PartitionCols:_col0, _col1 + Group By Operator [GBY_205] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_204] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_203] (rows=500 width=178) + predicate:value is not null + TableScan [TS_35] (rows=500 width=178) + Output:["key","value"] + <-Reducer 9 [SIMPLE_EDGE] llap SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_167] (rows=30 width=86) - Conds:RS_198._col1=RS_181._col1(Inner),Output:["_col2"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_160] (rows=39 width=266) + Conds:RS_168._col0=RS_172._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_168] + PartitionCols:_col0 + Select Operator [SEL_166] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_165] (rows=500 width=178) + predicate:key is not null + TableScan [TS_0] (rows=500 width=178) + default@src,y,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] <-Map 11 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_181] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_179] - <-Reducer 21 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_198] - PartitionCols:_col1 - Select Operator [SEL_197] (rows=381 width=178) - Output:["_col1"] - Group By Operator [GBY_196] (rows=381 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_220] - PartitionCols:_col0, _col1 - Group By Operator [GBY_219] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_218] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_217] (rows=500 width=178) - predicate:value is not null - TableScan [TS_39] (rows=500 width=178) - Output:["key","value"] - <-Reducer 19 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_212] - PartitionCols:_col0, _col1 - Group By Operator [GBY_211] (rows=381 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_210] (rows=262 width=178) - Output:["_col0","_col1"] - Group By Operator [GBY_209] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_208] - PartitionCols:_col0, _col1 - Group By Operator [GBY_207] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_206] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_205] (rows=25 width=175) - predicate:value is not null - TableScan [TS_26] (rows=25 width=175) - Output:["key","value"] - <-Map 22 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_216] - PartitionCols:_col0, _col1 - Group By Operator [GBY_215] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_214] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_213] (rows=500 width=178) - predicate:value is not null - TableScan [TS_29] (rows=500 width=178) - Output:["key","value"] - <-Reducer 5 [CONTAINS] llap + SHUFFLE [RS_172] + PartitionCols:_col0 + Select Operator [SEL_170] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_169] (rows=25 width=175) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25 width=175) + default@src1,x,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] + <-Reducer 3 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 Group By Operator [GBY_65] (rows=40 width=177) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_25] (rows=33 width=177) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_166] (rows=33 width=177) - Conds:RS_22._col2=RS_185._col0(Inner),Output:["_col2","_col5"] - <-Map 16 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_185] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_184] - <-Reducer 4 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_162] (rows=33 width=177) + Conds:RS_22._col3=RS_175._col1(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_22] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_165] (rows=21 width=86) - Conds:RS_177._col1=RS_180._col1(Inner),Output:["_col2"] + PartitionCols:_col3 + Merge Join Operator [MERGEJOIN_159] (rows=39 width=266) + Conds:RS_167._col0=RS_171._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_167] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_166] <-Map 11 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_180] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_179] - <-Reducer 3 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_177] - PartitionCols:_col1 - Select Operator [SEL_176] (rows=262 width=178) - Output:["_col1"] - Group By Operator [GBY_175] (rows=262 width=178) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_174] - PartitionCols:_col0, _col1 - Group By Operator [GBY_173] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_172] (rows=25 width=175) - Output:["_col0","_col1"] - Filter Operator [FIL_171] (rows=25 width=175) - predicate:value is not null - TableScan [TS_0] (rows=25 width=175) - Output:["key","value"] - <-Map 10 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_195] - PartitionCols:_col0, _col1 - Group By Operator [GBY_194] (rows=262 width=178) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_193] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_192] (rows=500 width=178) - predicate:value is not null - TableScan [TS_3] (rows=500 width=178) - Output:["key","value"] + SHUFFLE [RS_171] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_170] + <-Reducer 14 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_175] + PartitionCols:_col1 + Select Operator [SEL_174] (rows=262 width=178) + Output:["_col1"] + Group By Operator [GBY_173] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 13 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_190] + PartitionCols:_col0, _col1 + Group By Operator [GBY_189] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_188] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_187] (rows=25 width=175) + predicate:value is not null + TableScan [TS_6] (rows=25 width=175) + Output:["key","value"] + <-Map 15 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_194] + PartitionCols:_col0, _col1 + Group By Operator [GBY_193] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_192] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_191] (rows=500 width=178) + predicate:value is not null + TableScan [TS_9] (rows=500 width=178) + Output:["key","value"] + <-Reducer 8 [CONTAINS] llap + Reduce Output Operator [RS_119] + PartitionCols:_col0, _col1 + Group By Operator [GBY_118] (rows=47 width=177) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_114] (rows=55 width=177) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_164] (rows=55 width=177) + Conds:RS_111._col3=RS_183._col1(Inner),Output:["_col1","_col2"] + <-Reducer 2 [SIMPLE_EDGE] llap + SHUFFLE [RS_111] + PartitionCols:_col3 + Please refer to the previous Merge Join Operator [MERGEJOIN_159] + <-Reducer 29 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_183] + PartitionCols:_col1 + Select Operator [SEL_182] (rows=440 width=178) + Output:["_col1"] + Group By Operator [GBY_181] (rows=440 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 28 [SIMPLE_EDGE] + <-Map 32 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_234] + PartitionCols:_col0, _col1 + Group By Operator [GBY_233] (rows=440 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_232] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_231] (rows=500 width=178) + predicate:value is not null + TableScan [TS_98] (rows=500 width=178) + Output:["key","value"] + <-Reducer 27 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_222] + PartitionCols:_col0, _col1 + Group By Operator [GBY_221] (rows=440 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_220] (rows=381 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_219] (rows=381 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 26 [SIMPLE_EDGE] + <-Map 31 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_230] + PartitionCols:_col0, _col1 + Group By Operator [GBY_229] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_228] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_227] (rows=500 width=178) + predicate:value is not null + TableScan [TS_88] (rows=500 width=178) + Output:["key","value"] + <-Reducer 25 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_218] + PartitionCols:_col0, _col1 + Group By Operator [GBY_217] (rows=381 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_216] (rows=262 width=178) + Output:["_col0","_col1"] + Group By Operator [GBY_215] (rows=262 width=178) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 24 [SIMPLE_EDGE] + <-Map 23 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_214] + PartitionCols:_col0, _col1 + Group By Operator [GBY_213] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_212] (rows=25 width=175) + Output:["_col0","_col1"] + Filter Operator [FIL_211] (rows=25 width=175) + predicate:value is not null + TableScan [TS_75] (rows=25 width=175) + Output:["key","value"] + <-Map 30 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_226] + PartitionCols:_col0, _col1 + Group By Operator [GBY_225] (rows=262 width=178) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_224] (rows=500 width=178) + Output:["_col0","_col1"] + Filter Operator [FIL_223] (rows=500 width=178) + predicate:value is not null + TableScan [TS_78] (rows=500 width=178) + Output:["key","value"] PREHOOK: query: EXPLAIN SELECT x.key, z.value, y.value @@ -1133,135 +1113,132 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 12 <- Union 10 (CONTAINS) -Map 6 <- Union 2 (CONTAINS) -Map 9 <- Union 10 (CONTAINS) -Reducer 11 <- Map 13 (BROADCAST_EDGE), Map 14 (BROADCAST_EDGE), Union 10 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 3 <- Map 7 (BROADCAST_EDGE), Map 8 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (SIMPLE_EDGE) +Map 1 <- Map 2 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 13 <- Union 11 (CONTAINS) +Map 3 <- Union 4 (CONTAINS) +Map 8 <- Union 4 (CONTAINS) +Map 9 <- Map 2 (BROADCAST_EDGE) +Reducer 12 <- Map 9 (BROADCAST_EDGE), Union 11 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 5 <- Map 1 (BROADCAST_EDGE), Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 5 vectorized, llap - File Output Operator [FS_108] - Group By Operator [GBY_107] (rows=550 width=10) + Reducer 7 vectorized, llap + File Output Operator [FS_107] + Group By Operator [GBY_106] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 4 [SIMPLE_EDGE] - <-Reducer 11 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_129] + <-Union 6 [SIMPLE_EDGE] + <-Reducer 12 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_125] PartitionCols:_col0, _col1 - Group By Operator [GBY_128] (rows=1100 width=10) + Group By Operator [GBY_124] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_127] (rows=550 width=10) + Select Operator [SEL_123] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_126] (rows=550 width=10) - Conds:MAPJOIN_125._col2=RS_122._col0(Inner),Output:["_col1","_col2"] - <-Map 14 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_122] - PartitionCols:_col0 - Select Operator [SEL_121] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_120] (rows=500 width=10) - predicate:key is not null - TableScan [TS_42] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Map Join Operator [MAPJOIN_125] (rows=288 width=10) - Conds:SEL_124._col1=RS_119._col1(Inner),Output:["_col1","_col2"] - <-Map 13 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_119] - PartitionCols:_col1 - Select Operator [SEL_118] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_117] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_39] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_124] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_123] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 10 [SIMPLE_EDGE] - <-Map 12 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_133] - PartitionCols:_col0, _col1 - Group By Operator [GBY_132] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_131] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_130] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Map 9 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_116] - PartitionCols:_col0, _col1 - Group By Operator [GBY_115] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_114] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_113] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Reducer 3 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_106] + Map Join Operator [MAPJOIN_122] (rows=605 width=10) + Conds:RS_119._col2=SEL_121._col1(Inner),Output:["_col1","_col4"] + <-Map 9 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_119] + PartitionCols:_col2 + Map Join Operator [MAPJOIN_118] (rows=550 width=10) + Conds:SEL_117._col0=RS_95._col0(Inner),Output:["_col1","_col2"] + <-Map 2 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_95] + PartitionCols:_col0 + Select Operator [SEL_93] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_92] (rows=25 width=7) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25 width=7) + default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_117] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_116] (rows=500 width=10) + predicate:key is not null + TableScan [TS_26] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] + <-Select Operator [SEL_121] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_120] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_115] + PartitionCols:_col0, _col1 + Group By Operator [GBY_114] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_113] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_112] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 13 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_129] + PartitionCols:_col0, _col1 + Group By Operator [GBY_128] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_127] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_126] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 5 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_105] PartitionCols:_col0, _col1 - Group By Operator [GBY_105] (rows=1100 width=10) + Group By Operator [GBY_104] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_104] (rows=550 width=10) + Select Operator [SEL_103] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_103] (rows=550 width=10) - Conds:MAPJOIN_102._col2=RS_99._col0(Inner),Output:["_col1","_col2"] - <-Map 8 [BROADCAST_EDGE] vectorized, llap + Map Join Operator [MAPJOIN_102] (rows=605 width=10) + Conds:RS_99._col2=SEL_101._col1(Inner),Output:["_col1","_col4"] + <-Map 1 [BROADCAST_EDGE] vectorized, llap BROADCAST [RS_99] - PartitionCols:_col0 - Select Operator [SEL_98] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_97] (rows=500 width=10) - predicate:key is not null - TableScan [TS_16] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Map Join Operator [MAPJOIN_102] (rows=288 width=10) - Conds:SEL_101._col1=RS_96._col1(Inner),Output:["_col1","_col2"] - <-Map 7 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_96] - PartitionCols:_col1 - Select Operator [SEL_95] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_94] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_101] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_100] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_93] - PartitionCols:_col0, _col1 - Group By Operator [GBY_92] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_91] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_90] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 6 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_112] - PartitionCols:_col0, _col1 - Group By Operator [GBY_111] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_110] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_109] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] + PartitionCols:_col2 + Map Join Operator [MAPJOIN_98] (rows=550 width=10) + Conds:SEL_97._col0=RS_94._col0(Inner),Output:["_col1","_col2"] + <-Map 2 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_94] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_93] + <-Select Operator [SEL_97] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_96] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key"] + <-Select Operator [SEL_101] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_100] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 4 [SIMPLE_EDGE] + <-Map 3 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_91] + PartitionCols:_col0, _col1 + Group By Operator [GBY_90] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_89] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_88] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 8 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_111] + PartitionCols:_col0, _col1 + Group By Operator [GBY_110] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_109] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_108] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] PREHOOK: query: explain SELECT x.key, y.value @@ -1292,262 +1269,253 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 11 <- Union 12 (CONTAINS) -Map 16 <- Union 12 (CONTAINS) -Map 17 <- Union 14 (CONTAINS) -Map 20 <- Union 21 (CONTAINS) -Map 27 <- Union 21 (CONTAINS) -Map 28 <- Union 23 (CONTAINS) -Map 29 <- Union 25 (CONTAINS) -Map 8 <- Union 2 (CONTAINS) -Reducer 13 <- Union 12 (SIMPLE_EDGE), Union 14 (CONTAINS) -Reducer 15 <- Map 18 (BROADCAST_EDGE), Map 19 (BROADCAST_EDGE), Union 14 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 22 <- Union 21 (SIMPLE_EDGE), Union 23 (CONTAINS) -Reducer 24 <- Union 23 (SIMPLE_EDGE), Union 25 (CONTAINS) -Reducer 26 <- Map 10 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE), Union 25 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 3 <- Map 10 (BROADCAST_EDGE), Map 9 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) -Reducer 7 <- Union 6 (SIMPLE_EDGE) +Map 1 <- Map 2 (BROADCAST_EDGE) +Map 10 <- Union 4 (CONTAINS) +Map 11 <- Map 2 (BROADCAST_EDGE) +Map 12 <- Union 13 (CONTAINS) +Map 17 <- Union 13 (CONTAINS) +Map 18 <- Union 15 (CONTAINS) +Map 19 <- Union 20 (CONTAINS) +Map 26 <- Union 20 (CONTAINS) +Map 27 <- Union 22 (CONTAINS) +Map 28 <- Union 24 (CONTAINS) +Map 3 <- Union 4 (CONTAINS) +Reducer 14 <- Union 13 (SIMPLE_EDGE), Union 15 (CONTAINS) +Reducer 16 <- Map 11 (BROADCAST_EDGE), Union 15 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 21 <- Union 20 (SIMPLE_EDGE), Union 22 (CONTAINS) +Reducer 23 <- Union 22 (SIMPLE_EDGE), Union 24 (CONTAINS) +Reducer 25 <- Map 1 (BROADCAST_EDGE), Union 24 (SIMPLE_EDGE), Union 8 (CONTAINS) +Reducer 5 <- Map 1 (BROADCAST_EDGE), Union 4 (SIMPLE_EDGE), Union 6 (CONTAINS) +Reducer 7 <- Union 6 (SIMPLE_EDGE), Union 8 (CONTAINS) +Reducer 9 <- Union 8 (SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 7 vectorized, llap - File Output Operator [FS_200] - Group By Operator [GBY_199] (rows=550 width=10) + Reducer 9 vectorized, llap + File Output Operator [FS_193] + Group By Operator [GBY_192] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 6 [SIMPLE_EDGE] - <-Reducer 26 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_252] + <-Union 8 [SIMPLE_EDGE] + <-Reducer 25 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_241] PartitionCols:_col0, _col1 - Group By Operator [GBY_251] (rows=1100 width=10) + Group By Operator [GBY_240] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_250] (rows=550 width=10) + Select Operator [SEL_239] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_249] (rows=550 width=10) - Conds:MAPJOIN_248._col2=RS_188._col0(Inner),Output:["_col2","_col5"] - <-Map 10 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_188] - PartitionCols:_col0 - Select Operator [SEL_186] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_185] (rows=500 width=10) - predicate:key is not null - TableScan [TS_16] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_248] (rows=484 width=10) - Conds:SEL_247._col1=RS_184._col1(Inner),Output:["_col2"] - <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_184] - PartitionCols:_col1 - Select Operator [SEL_182] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_181] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_247] (rows=440 width=10) - Output:["_col1"] - Group By Operator [GBY_246] (rows=440 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 25 [SIMPLE_EDGE] - <-Map 29 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_264] - PartitionCols:_col0, _col1 - Group By Operator [GBY_263] (rows=881 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_262] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_261] (rows=500 width=10) - predicate:value is not null - TableScan [TS_92] (rows=500 width=10) - Output:["key","value"] - <-Reducer 24 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_245] - PartitionCols:_col0, _col1 - Group By Operator [GBY_244] (rows=881 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_243] (rows=381 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_242] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 23 [SIMPLE_EDGE] - <-Map 28 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_260] - PartitionCols:_col0, _col1 - Group By Operator [GBY_259] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_258] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_257] (rows=500 width=10) - predicate:value is not null - TableScan [TS_82] (rows=500 width=10) - Output:["key","value"] - <-Reducer 22 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_241] - PartitionCols:_col0, _col1 - Group By Operator [GBY_240] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_239] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_238] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 21 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_237] - PartitionCols:_col0, _col1 - Group By Operator [GBY_236] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_235] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_234] (rows=25 width=7) - predicate:value is not null - TableScan [TS_69] (rows=25 width=7) - Output:["key","value"] - <-Map 27 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_256] - PartitionCols:_col0, _col1 - Group By Operator [GBY_255] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_254] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_253] (rows=500 width=10) - predicate:value is not null - TableScan [TS_72] (rows=500 width=10) - Output:["key","value"] - <-Reducer 5 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_198] - PartitionCols:_col0, _col1 - Group By Operator [GBY_197] (rows=1100 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_196] (rows=550 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 4 [SIMPLE_EDGE] - <-Reducer 15 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_225] - PartitionCols:_col0, _col1 - Group By Operator [GBY_224] (rows=1100 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_223] (rows=550 width=10) + Map Join Operator [MAPJOIN_238] (rows=605 width=10) + Conds:RS_182._col3=SEL_237._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_182] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_180] (rows=550 width=10) + Conds:SEL_179._col0=RS_176._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 2 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_176] + PartitionCols:_col0 + Select Operator [SEL_175] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_174] (rows=25 width=7) + predicate:(key is not null and value is not null) + TableScan [TS_3] (rows=25 width=7) + default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_179] (rows=500 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_222] (rows=550 width=10) - Conds:MAPJOIN_221._col2=RS_218._col0(Inner),Output:["_col2","_col5"] - <-Map 19 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_218] - PartitionCols:_col0 - Select Operator [SEL_217] (rows=500 width=10) + Filter Operator [FIL_178] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_237] (rows=440 width=10) + Output:["_col1"] + Group By Operator [GBY_236] (rows=440 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 24 [SIMPLE_EDGE] + <-Map 28 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_253] + PartitionCols:_col0, _col1 + Group By Operator [GBY_252] (rows=881 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_251] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_216] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Map Join Operator [MAPJOIN_221] (rows=419 width=10) - Conds:SEL_220._col1=RS_215._col1(Inner),Output:["_col2"] - <-Map 18 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_215] - PartitionCols:_col1 - Select Operator [SEL_214] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_213] (rows=25 width=7) - predicate:(key is not null and value is not null) - TableScan [TS_49] (rows=25 width=7) - default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_220] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_219] (rows=381 width=10) + Filter Operator [FIL_250] (rows=500 width=10) + predicate:value is not null + TableScan [TS_98] (rows=500 width=10) + Output:["key","value"] + <-Reducer 23 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_235] + PartitionCols:_col0, _col1 + Group By Operator [GBY_234] (rows=881 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_233] (rows=381 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_232] (rows=381 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 14 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_233] + <-Union 22 [SIMPLE_EDGE] + <-Map 27 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_249] PartitionCols:_col0, _col1 - Group By Operator [GBY_232] (rows=762 width=10) + Group By Operator [GBY_248] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_231] (rows=500 width=10) + Select Operator [SEL_247] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_230] (rows=500 width=10) + Filter Operator [FIL_246] (rows=500 width=10) predicate:value is not null - TableScan [TS_39] (rows=500 width=10) + TableScan [TS_88] (rows=500 width=10) Output:["key","value"] - <-Reducer 13 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_212] + <-Reducer 21 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_231] PartitionCols:_col0, _col1 - Group By Operator [GBY_211] (rows=762 width=10) + Group By Operator [GBY_230] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_210] (rows=262 width=10) + Select Operator [SEL_229] (rows=262 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_209] (rows=262 width=10) + Group By Operator [GBY_228] (rows=262 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 12 [SIMPLE_EDGE] - <-Map 11 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_208] + <-Union 20 [SIMPLE_EDGE] + <-Map 19 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_227] PartitionCols:_col0, _col1 - Group By Operator [GBY_207] (rows=525 width=10) + Group By Operator [GBY_226] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_206] (rows=25 width=7) + Select Operator [SEL_225] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_205] (rows=25 width=7) + Filter Operator [FIL_224] (rows=25 width=7) predicate:value is not null - TableScan [TS_26] (rows=25 width=7) + TableScan [TS_75] (rows=25 width=7) Output:["key","value"] - <-Map 16 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_229] + <-Map 26 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_245] PartitionCols:_col0, _col1 - Group By Operator [GBY_228] (rows=525 width=10) + Group By Operator [GBY_244] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_227] (rows=500 width=10) + Select Operator [SEL_243] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_226] (rows=500 width=10) + Filter Operator [FIL_242] (rows=500 width=10) predicate:value is not null - TableScan [TS_29] (rows=500 width=10) + TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 3 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_195] + <-Reducer 7 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_191] + PartitionCols:_col0, _col1 + Group By Operator [GBY_190] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Group By Operator [GBY_189] (rows=605 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 6 [SIMPLE_EDGE] + <-Reducer 16 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_215] PartitionCols:_col0, _col1 - Group By Operator [GBY_194] (rows=1100 width=10) + Group By Operator [GBY_214] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_193] (rows=550 width=10) + Select Operator [SEL_213] (rows=605 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_192] (rows=550 width=10) - Conds:MAPJOIN_191._col2=RS_187._col0(Inner),Output:["_col2","_col5"] - <-Map 10 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_187] - PartitionCols:_col0 - Please refer to the previous Select Operator [SEL_186] - <-Map Join Operator [MAPJOIN_191] (rows=288 width=10) - Conds:SEL_190._col1=RS_183._col1(Inner),Output:["_col2"] - <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_183] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_182] - <-Select Operator [SEL_190] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_189] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_180] - PartitionCols:_col0, _col1 - Group By Operator [GBY_179] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_178] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_177] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 8 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_204] - PartitionCols:_col0, _col1 - Group By Operator [GBY_203] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_202] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_201] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] + Map Join Operator [MAPJOIN_212] (rows=605 width=10) + Conds:RS_209._col3=SEL_211._col1(Inner),Output:["_col1","_col2"] + <-Map 11 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_209] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_208] (rows=550 width=10) + Conds:SEL_207._col0=RS_177._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 2 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_177] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_175] + <-Select Operator [SEL_207] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_206] (rows=500 width=10) + predicate:key is not null + TableScan [TS_26] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Select Operator [SEL_211] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_210] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 15 [SIMPLE_EDGE] + <-Map 18 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_223] + PartitionCols:_col0, _col1 + Group By Operator [GBY_222] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_221] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_220] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 14 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_205] + PartitionCols:_col0, _col1 + Group By Operator [GBY_204] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_203] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_202] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 13 [SIMPLE_EDGE] + <-Map 12 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_201] + PartitionCols:_col0, _col1 + Group By Operator [GBY_200] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_199] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_198] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 17 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_219] + PartitionCols:_col0, _col1 + Group By Operator [GBY_218] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_217] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_216] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 5 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_188] + PartitionCols:_col0, _col1 + Group By Operator [GBY_187] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_186] (rows=605 width=10) + Output:["_col0","_col1"] + Map Join Operator [MAPJOIN_185] (rows=605 width=10) + Conds:RS_181._col3=SEL_184._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_181] + PartitionCols:_col3 + Please refer to the previous Map Join Operator [MAPJOIN_180] + <-Select Operator [SEL_184] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_183] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 4 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_197] + PartitionCols:_col0, _col1 + Group By Operator [GBY_196] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_195] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_194] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + <-Map 3 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_173] + PartitionCols:_col0, _col1 + Group By Operator [GBY_172] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_171] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_170] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] PREHOOK: query: CREATE TABLE srcbucket_mapjoin(key int, value string) partitioned by (ds string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -2016,207 +1984,202 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 6 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 10 <- Union 11 (CONTAINS) -Map 12 <- Union 11 (CONTAINS) -Map 13 <- Union 11 (CONTAINS) -Map 16 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 17 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 18 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 19 <- Map 6 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 5 <- Map 6 (BROADCAST_EDGE), Union 2 (CONTAINS) +Map 1 <- Map 6 (BROADCAST_EDGE) +Map 11 <- Union 12 (CONTAINS) +Map 13 <- Union 12 (CONTAINS) +Map 14 <- Union 12 (CONTAINS) +Map 16 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 17 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 18 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 19 <- Map 6 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 6 <- Map 15 (BROADCAST_EDGE) -Reducer 3 <- Map 7 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 11 (SIMPLE_EDGE) -Reducer 9 <- Map 14 (SIMPLE_EDGE), Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS) +Map 7 <- Union 8 (CONTAINS) +Map 9 <- Union 8 (CONTAINS) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 3 (CONTAINS), Union 8 (SIMPLE_EDGE) +Reducer 4 <- Map 1 (SIMPLE_EDGE), Map 10 (SIMPLE_EDGE) +Reducer 5 <- Reducer 4 (SIMPLE_EDGE), Union 12 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Union 4 + Union 3 <-Map 16 [CONTAINS] vectorized, llap - File Output Operator [FS_169] - Select Operator [SEL_168] (rows=1677 width=10) + File Output Operator [FS_163] + Select Operator [SEL_162] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_167] (rows=1677 width=10) - Conds:RS_135._col1=SEL_166._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_161] (rows=1677 width=10) + Conds:RS_130._col1=SEL_160._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_135] + BROADCAST [RS_130] PartitionCols:_col1 - Map Join Operator [MAPJOIN_133] (rows=27 width=7) - Conds:SEL_131._col0=RS_129._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_129] (rows=27 width=7) + Conds:SEL_127._col0=RS_125._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 15 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_129] + BROADCAST [RS_125] PartitionCols:_col0 - Select Operator [SEL_128] (rows=25 width=7) + Select Operator [SEL_124] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_127] (rows=25 width=7) + Filter Operator [FIL_123] (rows=25 width=7) predicate:key is not null TableScan [TS_49] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_131] (rows=25 width=7) + <-Select Operator [SEL_127] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_130] (rows=25 width=7) + Filter Operator [FIL_126] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_166] (rows=25 width=7) + <-Select Operator [SEL_160] (rows=25 width=7) Output:["_col0"] - Filter Operator [FIL_165] (rows=25 width=7) + Filter Operator [FIL_159] (rows=25 width=7) predicate:value is not null TableScan [TS_52] (rows=25 width=7) Output:["value"] <-Map 17 [CONTAINS] vectorized, llap - File Output Operator [FS_174] - Select Operator [SEL_173] (rows=1677 width=10) + File Output Operator [FS_168] + Select Operator [SEL_167] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_172] (rows=1677 width=10) - Conds:RS_136._col1=SEL_171._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_166] (rows=1677 width=10) + Conds:RS_131._col1=SEL_165._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_136] + BROADCAST [RS_131] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_133] - <-Select Operator [SEL_171] (rows=500 width=10) + Please refer to the previous Map Join Operator [MAPJOIN_129] + <-Select Operator [SEL_165] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_170] (rows=500 width=10) + Filter Operator [FIL_164] (rows=500 width=10) predicate:value is not null TableScan [TS_55] (rows=500 width=10) Output:["value"] <-Map 18 [CONTAINS] vectorized, llap - File Output Operator [FS_179] - Select Operator [SEL_178] (rows=1677 width=10) + File Output Operator [FS_173] + Select Operator [SEL_172] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_177] (rows=1677 width=10) - Conds:RS_137._col1=SEL_176._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_171] (rows=1677 width=10) + Conds:RS_132._col1=SEL_170._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_137] + BROADCAST [RS_132] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_133] - <-Select Operator [SEL_176] (rows=500 width=10) + Please refer to the previous Map Join Operator [MAPJOIN_129] + <-Select Operator [SEL_170] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_175] (rows=500 width=10) + Filter Operator [FIL_169] (rows=500 width=10) predicate:value is not null TableScan [TS_59] (rows=500 width=10) Output:["value"] <-Map 19 [CONTAINS] vectorized, llap - File Output Operator [FS_184] - Select Operator [SEL_183] (rows=1677 width=10) + File Output Operator [FS_178] + Select Operator [SEL_177] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_182] (rows=1677 width=10) - Conds:RS_138._col1=SEL_181._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_176] (rows=1677 width=10) + Conds:RS_133._col1=SEL_175._col0(Inner),Output:["_col0","_col3"] <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_138] + BROADCAST [RS_133] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_133] - <-Select Operator [SEL_181] (rows=500 width=10) + Please refer to the previous Map Join Operator [MAPJOIN_129] + <-Select Operator [SEL_175] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_180] (rows=500 width=10) + Filter Operator [FIL_174] (rows=500 width=10) predicate:value is not null TableScan [TS_62] (rows=500 width=10) Output:["value"] - <-Reducer 3 [CONTAINS] llap + <-Reducer 2 [CONTAINS] llap File Output Operator [FS_74] - Select Operator [SEL_20] (rows=634 width=10) + Select Operator [SEL_20] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_115] (rows=634 width=10) - Conds:Union 2._col1=RS_147._col0(Inner),Output:["_col1","_col4"] - <-Map 7 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_147] - PartitionCols:_col0 - Select Operator [SEL_145] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_143] (rows=500 width=10) - predicate:key is not null - TableScan [TS_11] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_142] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_141] (rows=577 width=10) - Conds:SEL_140._col0=RS_132._col1(Inner),Output:["_col1"] - <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_132] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_131] - <-Select Operator [SEL_140] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_139] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["value"] - <-Map 5 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_152] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_151] (rows=577 width=10) - Conds:SEL_150._col0=RS_134._col1(Inner),Output:["_col1"] - <-Map 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_134] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_131] - <-Select Operator [SEL_150] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_149] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["value"] - <-Reducer 9 [CONTAINS] llap + Merge Join Operator [MERGEJOIN_114] (rows=605 width=10) + Conds:RS_140._col3=Union 8._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_140] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_138] (rows=550 width=10) + Conds:SEL_136._col0=RS_128._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 6 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_128] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_127] + <-Select Operator [SEL_136] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_134] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 8 [SIMPLE_EDGE] + <-Map 7 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_146] + PartitionCols:_col0 + Select Operator [SEL_145] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_144] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["value"] + <-Map 9 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_149] + PartitionCols:_col0 + Select Operator [SEL_148] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_147] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["value"] + <-Reducer 5 [CONTAINS] llap File Output Operator [FS_74] - Select Operator [SEL_44] (rows=1239 width=10) + Select Operator [SEL_44] (rows=1127 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_117] (rows=1239 width=10) - Conds:RS_41._col1=RS_155._col0(Inner),Output:["_col1","_col4"] - <-Map 14 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_155] - PartitionCols:_col0 - Select Operator [SEL_154] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_153] (rows=500 width=10) - predicate:key is not null - TableScan [TS_35] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 8 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_115] (rows=1127 width=10) + Conds:RS_41._col1=Union 12._col0(Inner),Output:["_col0","_col3"] + <-Reducer 4 [SIMPLE_EDGE] llap SHUFFLE [RS_41] PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_116] (rows=1127 width=10) - Conds:Union 11._col0=RS_148._col1(Inner),Output:["_col1"] - <-Map 7 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_148] - PartitionCols:_col1 - Select Operator [SEL_146] (rows=500 width=10) + Merge Join Operator [MERGEJOIN_112] (rows=550 width=10) + Conds:RS_139._col0=RS_143._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_139] + PartitionCols:_col0 + Select Operator [SEL_137] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_144] (rows=500 width=10) + Filter Operator [FIL_135] (rows=500 width=10) predicate:(key is not null and value is not null) - Please refer to the previous TableScan [TS_11] - <-Union 11 [SIMPLE_EDGE] - <-Map 10 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_158] - PartitionCols:_col0 - Select Operator [SEL_157] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_156] (rows=25 width=7) - predicate:value is not null - TableScan [TS_21] (rows=25 width=7) - Output:["value"] - <-Map 12 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_161] - PartitionCols:_col0 - Select Operator [SEL_160] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_159] (rows=500 width=10) - predicate:value is not null - TableScan [TS_24] (rows=500 width=10) - Output:["value"] - <-Map 13 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_164] - PartitionCols:_col0 - Select Operator [SEL_163] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_162] (rows=500 width=10) - predicate:value is not null - TableScan [TS_28] (rows=500 width=10) - Output:["value"] + Please refer to the previous TableScan [TS_0] + <-Map 10 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_143] + PartitionCols:_col0 + Select Operator [SEL_142] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_141] (rows=500 width=10) + predicate:key is not null + TableScan [TS_24] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 12 [SIMPLE_EDGE] + <-Map 11 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_152] + PartitionCols:_col0 + Select Operator [SEL_151] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_150] (rows=25 width=7) + predicate:value is not null + TableScan [TS_27] (rows=25 width=7) + Output:["value"] + <-Map 13 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_155] + PartitionCols:_col0 + Select Operator [SEL_154] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_153] (rows=500 width=10) + predicate:value is not null + TableScan [TS_30] (rows=500 width=10) + Output:["value"] + <-Map 14 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_158] + PartitionCols:_col0 + Select Operator [SEL_157] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_156] (rows=500 width=10) + predicate:value is not null + TableScan [TS_34] (rows=500 width=10) + Output:["value"] PREHOOK: query: explain SELECT x.key, y.value @@ -2247,279 +2210,280 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 10 <- Map 22 (BROADCAST_EDGE) -Map 14 <- Union 15 (CONTAINS) -Map 19 <- Union 15 (CONTAINS) -Map 20 <- Union 17 (CONTAINS) +Map 1 <- Map 9 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 13 <- Union 11 (CONTAINS) +Map 15 <- Union 16 (CONTAINS) +Map 20 <- Union 16 (CONTAINS) +Map 21 <- Union 18 (CONTAINS) Map 23 <- Union 24 (CONTAINS) Map 30 <- Union 24 (CONTAINS) Map 31 <- Union 26 (CONTAINS) Map 32 <- Union 28 (CONTAINS) -Map 9 <- Union 2 (CONTAINS) -Reducer 12 <- Map 11 (SIMPLE_EDGE), Reducer 18 (SIMPLE_EDGE) -Reducer 13 <- Map 21 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 16 <- Union 15 (SIMPLE_EDGE), Union 17 (CONTAINS) -Reducer 18 <- Union 17 (SIMPLE_EDGE) +Map 9 <- Map 22 (BROADCAST_EDGE) +Reducer 12 <- Union 11 (SIMPLE_EDGE) +Reducer 17 <- Union 16 (SIMPLE_EDGE), Union 18 (CONTAINS) +Reducer 19 <- Union 18 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 12 (SIMPLE_EDGE), Union 3 (CONTAINS) Reducer 25 <- Union 24 (SIMPLE_EDGE), Union 26 (CONTAINS) Reducer 27 <- Union 26 (SIMPLE_EDGE), Union 28 (CONTAINS) -Reducer 29 <- Map 10 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 3 <- Map 10 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE) -Reducer 4 <- Map 11 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 8 <- Union 7 (SIMPLE_EDGE) +Reducer 29 <- Map 9 (BROADCAST_EDGE), Union 28 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE) +Reducer 7 <- Map 1 (SIMPLE_EDGE), Map 14 (SIMPLE_EDGE) +Reducer 8 <- Reducer 19 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 8 vectorized, llap - File Output Operator [FS_197] - Group By Operator [GBY_196] (rows=530 width=10) + Reducer 6 vectorized, llap + File Output Operator [FS_190] + Group By Operator [GBY_189] (rows=544 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 7 [SIMPLE_EDGE] + <-Union 5 [SIMPLE_EDGE] <-Reducer 29 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_241] + Reduce Output Operator [RS_238] PartitionCols:_col0, _col1 - Group By Operator [GBY_240] (rows=1061 width=10) + Group By Operator [GBY_237] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_239] (rows=484 width=10) + Select Operator [SEL_236] (rows=484 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_238] (rows=484 width=10) - Conds:RS_182._col1=SEL_237._col1(Inner),Output:["_col0","_col3"] - <-Map 10 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_182] + Map Join Operator [MAPJOIN_235] (rows=484 width=10) + Conds:RS_175._col1=SEL_234._col1(Inner),Output:["_col0","_col3"] + <-Map 9 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_175] PartitionCols:_col1 - Map Join Operator [MAPJOIN_181] (rows=27 width=7) - Conds:SEL_179._col0=RS_177._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_174] (rows=27 width=7) + Conds:SEL_172._col0=RS_170._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 22 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_177] + BROADCAST [RS_170] PartitionCols:_col0 - Select Operator [SEL_176] (rows=25 width=7) + Select Operator [SEL_169] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_175] (rows=25 width=7) + Filter Operator [FIL_168] (rows=25 width=7) predicate:key is not null TableScan [TS_72] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_179] (rows=25 width=7) + <-Select Operator [SEL_172] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_178] (rows=25 width=7) + Filter Operator [FIL_171] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_237] (rows=440 width=10) + <-Select Operator [SEL_234] (rows=440 width=10) Output:["_col1"] - Group By Operator [GBY_236] (rows=440 width=10) + Group By Operator [GBY_233] (rows=440 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 28 [SIMPLE_EDGE] <-Map 32 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_253] + Reduce Output Operator [RS_250] PartitionCols:_col0, _col1 - Group By Operator [GBY_252] (rows=881 width=10) + Group By Operator [GBY_249] (rows=881 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_251] (rows=500 width=10) + Select Operator [SEL_248] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_250] (rows=500 width=10) + Filter Operator [FIL_247] (rows=500 width=10) predicate:value is not null TableScan [TS_98] (rows=500 width=10) Output:["key","value"] <-Reducer 27 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_235] + Reduce Output Operator [RS_232] PartitionCols:_col0, _col1 - Group By Operator [GBY_234] (rows=881 width=10) + Group By Operator [GBY_231] (rows=881 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_233] (rows=381 width=10) + Select Operator [SEL_230] (rows=381 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_232] (rows=381 width=10) + Group By Operator [GBY_229] (rows=381 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 26 [SIMPLE_EDGE] <-Map 31 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_249] + Reduce Output Operator [RS_246] PartitionCols:_col0, _col1 - Group By Operator [GBY_248] (rows=762 width=10) + Group By Operator [GBY_245] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_247] (rows=500 width=10) + Select Operator [SEL_244] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_246] (rows=500 width=10) + Filter Operator [FIL_243] (rows=500 width=10) predicate:value is not null TableScan [TS_88] (rows=500 width=10) Output:["key","value"] <-Reducer 25 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_231] + Reduce Output Operator [RS_228] PartitionCols:_col0, _col1 - Group By Operator [GBY_230] (rows=762 width=10) + Group By Operator [GBY_227] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_229] (rows=262 width=10) + Select Operator [SEL_226] (rows=262 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_228] (rows=262 width=10) + Group By Operator [GBY_225] (rows=262 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 24 [SIMPLE_EDGE] <-Map 23 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_227] + Reduce Output Operator [RS_224] PartitionCols:_col0, _col1 - Group By Operator [GBY_226] (rows=525 width=10) + Group By Operator [GBY_223] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_225] (rows=25 width=7) + Select Operator [SEL_222] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_224] (rows=25 width=7) + Filter Operator [FIL_221] (rows=25 width=7) predicate:value is not null TableScan [TS_75] (rows=25 width=7) Output:["key","value"] <-Map 30 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_245] + Reduce Output Operator [RS_242] PartitionCols:_col0, _col1 - Group By Operator [GBY_244] (rows=525 width=10) + Group By Operator [GBY_241] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_243] (rows=500 width=10) + Select Operator [SEL_240] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_242] (rows=500 width=10) + Filter Operator [FIL_239] (rows=500 width=10) predicate:value is not null TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 6 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_195] + <-Reducer 4 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_188] PartitionCols:_col0, _col1 - Group By Operator [GBY_194] (rows=1061 width=10) + Group By Operator [GBY_187] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_193] (rows=577 width=10) + Group By Operator [GBY_186] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 5 [SIMPLE_EDGE] - <-Reducer 13 [CONTAINS] llap + <-Union 3 [SIMPLE_EDGE] + <-Reducer 2 [CONTAINS] llap + Reduce Output Operator [RS_66] + PartitionCols:_col0, _col1 + Group By Operator [GBY_65] (rows=1210 width=10) + Output:["_col0","_col1"],keys:_col0, _col1 + Select Operator [SEL_25] (rows=605 width=10) + Output:["_col0","_col1"] + Merge Join Operator [MERGEJOIN_162] (rows=605 width=10) + Conds:RS_182._col3=RS_185._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_182] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_180] (rows=550 width=10) + Conds:SEL_178._col0=RS_173._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 9 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_173] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_172] + <-Select Operator [SEL_178] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_176] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Reducer 12 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_185] + PartitionCols:_col1 + Select Operator [SEL_184] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_183] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_200] + PartitionCols:_col0, _col1 + Group By Operator [GBY_199] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_198] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_197] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 13 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_204] + PartitionCols:_col0, _col1 + Group By Operator [GBY_203] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_202] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_201] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + <-Reducer 8 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_61] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_165] (rows=605 width=10) - Conds:RS_58._col2=RS_207._col0(Inner),Output:["_col2","_col5"] - <-Map 21 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_207] - PartitionCols:_col0 - Select Operator [SEL_206] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_205] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 12 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_163] (rows=605 width=10) + Conds:RS_58._col1=RS_196._col1(Inner),Output:["_col0","_col3"] + <-Reducer 19 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_196] + PartitionCols:_col1 + Select Operator [SEL_195] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_194] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 18 [SIMPLE_EDGE] + <-Map 21 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_220] + PartitionCols:_col0, _col1 + Group By Operator [GBY_219] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_218] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_217] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 17 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_212] + PartitionCols:_col0, _col1 + Group By Operator [GBY_211] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_210] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_209] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 16 [SIMPLE_EDGE] + <-Map 15 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_208] + PartitionCols:_col0, _col1 + Group By Operator [GBY_207] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_206] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_205] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 20 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_216] + PartitionCols:_col0, _col1 + Group By Operator [GBY_215] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_214] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_213] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 7 [SIMPLE_EDGE] llap SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_164] (rows=550 width=10) - Conds:RS_204._col1=RS_192._col1(Inner),Output:["_col2"] - <-Map 11 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_192] - PartitionCols:_col1 - Select Operator [SEL_190] (rows=500 width=10) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_160] (rows=550 width=10) + Conds:RS_181._col0=RS_193._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_181] + PartitionCols:_col0 + Select Operator [SEL_179] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_188] (rows=500 width=10) + Filter Operator [FIL_177] (rows=500 width=10) predicate:(key is not null and value is not null) - TableScan [TS_16] (rows=500 width=10) + Please refer to the previous TableScan [TS_0] + <-Map 14 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_193] + PartitionCols:_col0 + Select Operator [SEL_192] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_191] (rows=500 width=10) + predicate:key is not null + TableScan [TS_29] (rows=500 width=10) default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 18 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_204] - PartitionCols:_col1 - Select Operator [SEL_203] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_202] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 17 [SIMPLE_EDGE] - <-Map 20 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_223] - PartitionCols:_col0, _col1 - Group By Operator [GBY_222] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_221] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_220] (rows=500 width=10) - predicate:value is not null - TableScan [TS_39] (rows=500 width=10) - Output:["key","value"] - <-Reducer 16 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_215] - PartitionCols:_col0, _col1 - Group By Operator [GBY_214] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_213] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_212] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 15 [SIMPLE_EDGE] - <-Map 14 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_211] - PartitionCols:_col0, _col1 - Group By Operator [GBY_210] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_209] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_208] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Map 19 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_219] - PartitionCols:_col0, _col1 - Group By Operator [GBY_218] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_217] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_216] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Reducer 4 [CONTAINS] llap - Reduce Output Operator [RS_66] - PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) - Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) - Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_163] (rows=550 width=10) - Conds:RS_186._col2=RS_191._col0(Inner),Output:["_col2","_col5"] - <-Map 11 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_191] - PartitionCols:_col0 - Select Operator [SEL_189] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_187] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_16] - <-Reducer 3 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_186] - PartitionCols:_col2 - Map Join Operator [MAPJOIN_185] (rows=288 width=10) - Conds:SEL_184._col1=RS_180._col1(Inner),Output:["_col2"] - <-Map 10 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_180] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_179] - <-Select Operator [SEL_184] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_183] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_174] - PartitionCols:_col0, _col1 - Group By Operator [GBY_173] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_172] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_171] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 9 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_201] - PartitionCols:_col0, _col1 - Group By Operator [GBY_200] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_199] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_198] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] PREHOOK: query: CREATE TABLE a(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE @@ -2586,22 +2550,23 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 9 (BROADCAST_EDGE), Union 2 (CONTAINS) -Map 13 <- Union 14 (CONTAINS) -Map 15 <- Union 14 (CONTAINS) -Map 16 <- Union 14 (CONTAINS) -Map 19 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 20 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 21 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 22 <- Map 9 (BROADCAST_EDGE), Union 4 (CONTAINS) -Map 8 <- Map 9 (BROADCAST_EDGE), Union 2 (CONTAINS) +Map 1 <- Map 9 (BROADCAST_EDGE) +Map 10 <- Union 11 (CONTAINS) +Map 12 <- Union 11 (CONTAINS) +Map 14 <- Union 15 (CONTAINS) +Map 16 <- Union 15 (CONTAINS) +Map 17 <- Union 15 (CONTAINS) +Map 19 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 20 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 21 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) +Map 22 <- Map 9 (BROADCAST_EDGE), Union 3 (CONTAINS) Map 9 <- Map 18 (BROADCAST_EDGE) -Reducer 11 <- Map 10 (SIMPLE_EDGE), Union 14 (SIMPLE_EDGE) -Reducer 12 <- Map 17 (SIMPLE_EDGE), Reducer 11 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 3 <- Map 10 (SIMPLE_EDGE), Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS) -Reducer 5 <- Union 4 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Union 4 (CUSTOM_SIMPLE_EDGE) -Reducer 7 <- Union 4 (CUSTOM_SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Union 11 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 4 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 5 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 6 <- Union 3 (CUSTOM_SIMPLE_EDGE) +Reducer 7 <- Map 1 (SIMPLE_EDGE), Map 13 (SIMPLE_EDGE) +Reducer 8 <- Reducer 7 (SIMPLE_EDGE), Union 15 (SIMPLE_EDGE), Union 3 (CONTAINS) Stage-5 Stats Work{} @@ -2611,48 +2576,48 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 5 llap + Reducer 4 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Union 4 [CUSTOM_SIMPLE_EDGE] + <-Union 3 [CUSTOM_SIMPLE_EDGE] <-Map 19 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_140._col1=SEL_54._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_135._col1=SEL_54._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_140] + BROADCAST [RS_135] PartitionCols:_col1 - Map Join Operator [MAPJOIN_138] (rows=27 width=7) - Conds:SEL_136._col0=RS_134._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_134] (rows=27 width=7) + Conds:SEL_132._col0=RS_130._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 18 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_134] + BROADCAST [RS_130] PartitionCols:_col0 - Select Operator [SEL_133] (rows=25 width=7) + Select Operator [SEL_129] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_132] (rows=25 width=7) + Filter Operator [FIL_128] (rows=25 width=7) predicate:key is not null TableScan [TS_49] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_136] (rows=25 width=7) + <-Select Operator [SEL_132] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_135] (rows=25 width=7) + Filter Operator [FIL_131] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_8] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Select Operator [SEL_54] (rows=25 width=7) Output:["_col0"] - Filter Operator [FIL_115] (rows=25 width=7) + Filter Operator [FIL_112] (rows=25 width=7) predicate:value is not null TableScan [TS_52] (rows=25 width=7) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2661,7 +2626,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2670,7 +2635,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 20 [CONTAINS] llap @@ -2678,22 +2643,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_141._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_136._col1=SEL_57._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_141] + BROADCAST [RS_136] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_138] + Please refer to the previous Map Join Operator [MAPJOIN_134] <-Select Operator [SEL_57] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_116] (rows=500 width=10) + Filter Operator [FIL_113] (rows=500 width=10) predicate:value is not null TableScan [TS_55] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2702,7 +2667,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2711,7 +2676,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 21 [CONTAINS] llap @@ -2719,22 +2684,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_142._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_137._col1=SEL_61._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_142] + BROADCAST [RS_137] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_138] + Please refer to the previous Map Join Operator [MAPJOIN_134] <-Select Operator [SEL_61] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_117] (rows=500 width=10) + Filter Operator [FIL_114] (rows=500 width=10) predicate:value is not null TableScan [TS_59] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2743,7 +2708,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2752,7 +2717,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] <-Map 22 [CONTAINS] llap @@ -2760,22 +2725,22 @@ Stage-5 table:{"name:":"default.a"} Select Operator [SEL_72] (rows=1677 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_124] (rows=1677 width=10) - Conds:RS_143._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] + Map Join Operator [MAPJOIN_121] (rows=1677 width=10) + Conds:RS_138._col1=SEL_64._col0(Inner),Output:["_col0","_col3"] <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_143] + BROADCAST [RS_138] PartitionCols:_col1 - Please refer to the previous Map Join Operator [MAPJOIN_138] + Please refer to the previous Map Join Operator [MAPJOIN_134] <-Select Operator [SEL_64] (rows=500 width=10) Output:["_col0"] - Filter Operator [FIL_118] (rows=500 width=10) + Filter Operator [FIL_115] (rows=500 width=10) predicate:value is not null TableScan [TS_62] (rows=500 width=10) Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_77] @@ -2784,7 +2749,7 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] File Output Operator [FS_79] @@ -2793,171 +2758,165 @@ Stage-5 Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] Please refer to the previous Select Operator [SEL_72] - <-Reducer 12 [CONTAINS] llap + <-Reducer 2 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_44] (rows=1239 width=10) + Select Operator [SEL_20] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_122] (rows=1239 width=10) - Conds:RS_41._col1=RS_160._col0(Inner),Output:["_col1","_col4"] - <-Map 17 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_160] - PartitionCols:_col0 - Select Operator [SEL_159] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_158] (rows=500 width=10) - predicate:key is not null - TableScan [TS_35] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 11 [SIMPLE_EDGE] llap - SHUFFLE [RS_41] - PartitionCols:_col1 - Merge Join Operator [MERGEJOIN_121] (rows=1127 width=10) - Conds:Union 14._col0=RS_153._col1(Inner),Output:["_col1"] - <-Map 10 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_153] - PartitionCols:_col1 - Select Operator [SEL_151] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_149] (rows=500 width=10) - predicate:(key is not null and value is not null) - TableScan [TS_11] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Union 14 [SIMPLE_EDGE] - <-Map 13 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_163] - PartitionCols:_col0 - Select Operator [SEL_162] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_161] (rows=25 width=7) - predicate:value is not null - TableScan [TS_21] (rows=25 width=7) - Output:["value"] - <-Map 15 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_166] - PartitionCols:_col0 - Select Operator [SEL_165] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_164] (rows=500 width=10) - predicate:value is not null - TableScan [TS_24] (rows=500 width=10) - Output:["value"] - <-Map 16 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_169] - PartitionCols:_col0 - Select Operator [SEL_168] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_167] (rows=500 width=10) - predicate:value is not null - TableScan [TS_28] (rows=500 width=10) - Output:["value"] + Merge Join Operator [MERGEJOIN_119] (rows=605 width=10) + Conds:RS_145._col3=Union 11._col0(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_145] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_143] (rows=550 width=10) + Conds:SEL_141._col0=RS_133._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 9 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_133] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_132] + <-Select Operator [SEL_141] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_139] (rows=500 width=10) + predicate:key is not null + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 11 [SIMPLE_EDGE] + <-Map 10 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_151] + PartitionCols:_col0 + Select Operator [SEL_150] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_149] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["value"] + <-Map 12 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_154] + PartitionCols:_col0 + Select Operator [SEL_153] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_152] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_44] + Please refer to the previous Select Operator [SEL_20] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_44] - <-Reducer 3 [CONTAINS] llap + Please refer to the previous Select Operator [SEL_20] + <-Reducer 8 [CONTAINS] llap File Output Operator [FS_75] table:{"name:":"default.a"} - Select Operator [SEL_20] (rows=634 width=10) + Select Operator [SEL_44] (rows=1127 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_120] (rows=634 width=10) - Conds:Union 2._col1=RS_152._col0(Inner),Output:["_col1","_col4"] - <-Map 10 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_152] - PartitionCols:_col0 - Select Operator [SEL_150] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_148] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_11] - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_147] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_146] (rows=577 width=10) - Conds:SEL_145._col0=RS_137._col1(Inner),Output:["_col1"] - <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_137] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_136] - <-Select Operator [SEL_145] (rows=25 width=7) - Output:["_col0"] - Filter Operator [FIL_144] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["value"] - <-Map 8 [CONTAINS] vectorized, llap + Merge Join Operator [MERGEJOIN_120] (rows=1127 width=10) + Conds:RS_41._col1=Union 15._col0(Inner),Output:["_col0","_col3"] + <-Reducer 7 [SIMPLE_EDGE] llap + SHUFFLE [RS_41] + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_117] (rows=550 width=10) + Conds:RS_144._col0=RS_148._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_144] + PartitionCols:_col0 + Select Operator [SEL_142] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_140] (rows=500 width=10) + predicate:(key is not null and value is not null) + Please refer to the previous TableScan [TS_0] + <-Map 13 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_148] + PartitionCols:_col0 + Select Operator [SEL_147] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_146] (rows=500 width=10) + predicate:key is not null + TableScan [TS_24] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Union 15 [SIMPLE_EDGE] + <-Map 14 [CONTAINS] vectorized, llap Reduce Output Operator [RS_157] - PartitionCols:_col1 - Map Join Operator [MAPJOIN_156] (rows=577 width=10) - Conds:SEL_155._col0=RS_139._col1(Inner),Output:["_col1"] - <-Map 9 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_139] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_136] - <-Select Operator [SEL_155] (rows=500 width=10) - Output:["_col0"] - Filter Operator [FIL_154] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["value"] + PartitionCols:_col0 + Select Operator [SEL_156] (rows=25 width=7) + Output:["_col0"] + Filter Operator [FIL_155] (rows=25 width=7) + predicate:value is not null + TableScan [TS_27] (rows=25 width=7) + Output:["value"] + <-Map 16 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_160] + PartitionCols:_col0 + Select Operator [SEL_159] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_158] (rows=500 width=10) + predicate:value is not null + TableScan [TS_30] (rows=500 width=10) + Output:["value"] + <-Map 17 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_163] + PartitionCols:_col0 + Select Operator [SEL_162] (rows=500 width=10) + Output:["_col0"] + Filter Operator [FIL_161] (rows=500 width=10) + predicate:value is not null + TableScan [TS_34] (rows=500 width=10) + Output:["value"] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_77] table:{"name:":"default.b"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] File Output Operator [FS_79] table:{"name:":"default.c"} - Please refer to the previous Select Operator [SEL_20] + Please refer to the previous Select Operator [SEL_44] Reduce Output Operator [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=3550 width=10) + Select Operator [SEL_1] (rows=3409 width=10) Output:["key","value"] - Please refer to the previous Select Operator [SEL_20] - Reducer 6 llap + Please refer to the previous Select Operator [SEL_44] + Reducer 5 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] - Reducer 7 llap + <- Please refer to the previous Union 3 [CUSTOM_SIMPLE_EDGE] + Reducer 6 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <- Please refer to the previous Union 4 [CUSTOM_SIMPLE_EDGE] + <- Please refer to the previous Union 3 [CUSTOM_SIMPLE_EDGE] Stage-6 Stats Work{} Stage-1 @@ -3006,30 +2965,31 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Union 2 (CONTAINS) -Map 12 <- Union 2 (CONTAINS) -Map 13 <- Map 25 (BROADCAST_EDGE) -Map 17 <- Union 18 (CONTAINS) -Map 22 <- Union 18 (CONTAINS) -Map 23 <- Union 20 (CONTAINS) +Map 1 <- Map 12 (BROADCAST_EDGE) +Map 12 <- Map 25 (BROADCAST_EDGE) +Map 13 <- Union 14 (CONTAINS) +Map 16 <- Union 14 (CONTAINS) +Map 18 <- Union 19 (CONTAINS) +Map 23 <- Union 19 (CONTAINS) +Map 24 <- Union 21 (CONTAINS) Map 26 <- Union 27 (CONTAINS) Map 33 <- Union 27 (CONTAINS) Map 34 <- Union 29 (CONTAINS) Map 35 <- Union 31 (CONTAINS) -Reducer 10 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) -Reducer 11 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) -Reducer 15 <- Map 14 (SIMPLE_EDGE), Reducer 21 (SIMPLE_EDGE) -Reducer 16 <- Map 24 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 19 <- Union 18 (SIMPLE_EDGE), Union 20 (CONTAINS) -Reducer 21 <- Union 20 (SIMPLE_EDGE) +Reducer 10 <- Map 1 (SIMPLE_EDGE), Map 17 (SIMPLE_EDGE) +Reducer 11 <- Reducer 10 (SIMPLE_EDGE), Reducer 22 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 15 <- Union 14 (SIMPLE_EDGE) +Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 15 (SIMPLE_EDGE), Union 3 (CONTAINS) +Reducer 20 <- Union 19 (SIMPLE_EDGE), Union 21 (CONTAINS) +Reducer 22 <- Union 21 (SIMPLE_EDGE) Reducer 28 <- Union 27 (SIMPLE_EDGE), Union 29 (CONTAINS) -Reducer 3 <- Map 13 (BROADCAST_EDGE), Union 2 (SIMPLE_EDGE) Reducer 30 <- Union 29 (SIMPLE_EDGE), Union 31 (CONTAINS) -Reducer 32 <- Map 13 (BROADCAST_EDGE), Union 31 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 4 <- Map 14 (SIMPLE_EDGE), Reducer 3 (SIMPLE_EDGE), Union 5 (CONTAINS) -Reducer 6 <- Union 5 (SIMPLE_EDGE), Union 7 (CONTAINS) -Reducer 8 <- Union 7 (SIMPLE_EDGE) -Reducer 9 <- Reducer 8 (CUSTOM_SIMPLE_EDGE) +Reducer 32 <- Map 12 (BROADCAST_EDGE), Union 31 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 4 <- Union 3 (SIMPLE_EDGE), Union 5 (CONTAINS) +Reducer 6 <- Union 5 (SIMPLE_EDGE) +Reducer 7 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 8 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) +Reducer 9 <- Reducer 6 (CUSTOM_SIMPLE_EDGE) Stage-5 Stats Work{} @@ -3039,281 +2999,281 @@ Stage-5 Stage-4 Dependency Collection{} Stage-3 - Reducer 10 llap + Reducer 7 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] - Group By Operator [GBY_120] (rows=530 width=10) + Group By Operator [GBY_120] (rows=544 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 7 [SIMPLE_EDGE] + <-Union 5 [SIMPLE_EDGE] <-Reducer 32 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_248] + Reduce Output Operator [RS_245] PartitionCols:_col0, _col1 - Group By Operator [GBY_247] (rows=1061 width=10) + Group By Operator [GBY_244] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_246] (rows=484 width=10) + Select Operator [SEL_243] (rows=484 width=10) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_245] (rows=484 width=10) - Conds:RS_187._col1=SEL_244._col1(Inner),Output:["_col0","_col3"] - <-Map 13 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_187] + Map Join Operator [MAPJOIN_242] (rows=484 width=10) + Conds:RS_180._col1=SEL_241._col1(Inner),Output:["_col0","_col3"] + <-Map 12 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_180] PartitionCols:_col1 - Map Join Operator [MAPJOIN_186] (rows=27 width=7) - Conds:SEL_184._col0=RS_182._col0(Inner),Output:["_col0","_col1","_col3"] + Map Join Operator [MAPJOIN_179] (rows=27 width=7) + Conds:SEL_177._col0=RS_175._col0(Inner),Output:["_col0","_col1","_col3"] <-Map 25 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_182] + BROADCAST [RS_175] PartitionCols:_col0 - Select Operator [SEL_181] (rows=25 width=7) + Select Operator [SEL_174] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_180] (rows=25 width=7) + Filter Operator [FIL_173] (rows=25 width=7) predicate:key is not null TableScan [TS_72] (rows=25 width=7) default@src1,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_184] (rows=25 width=7) + <-Select Operator [SEL_177] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_183] (rows=25 width=7) + Filter Operator [FIL_176] (rows=25 width=7) predicate:(key is not null and value is not null) - TableScan [TS_13] (rows=25 width=7) + TableScan [TS_3] (rows=25 width=7) default@src1,x,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Select Operator [SEL_244] (rows=440 width=10) + <-Select Operator [SEL_241] (rows=440 width=10) Output:["_col1"] - Group By Operator [GBY_243] (rows=440 width=10) + Group By Operator [GBY_240] (rows=440 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 31 [SIMPLE_EDGE] <-Map 35 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_260] + Reduce Output Operator [RS_257] PartitionCols:_col0, _col1 - Group By Operator [GBY_259] (rows=881 width=10) + Group By Operator [GBY_256] (rows=881 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_258] (rows=500 width=10) + Select Operator [SEL_255] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_257] (rows=500 width=10) + Filter Operator [FIL_254] (rows=500 width=10) predicate:value is not null TableScan [TS_98] (rows=500 width=10) Output:["key","value"] <-Reducer 30 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_242] + Reduce Output Operator [RS_239] PartitionCols:_col0, _col1 - Group By Operator [GBY_241] (rows=881 width=10) + Group By Operator [GBY_238] (rows=881 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_240] (rows=381 width=10) + Select Operator [SEL_237] (rows=381 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_239] (rows=381 width=10) + Group By Operator [GBY_236] (rows=381 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 29 [SIMPLE_EDGE] <-Map 34 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_256] + Reduce Output Operator [RS_253] PartitionCols:_col0, _col1 - Group By Operator [GBY_255] (rows=762 width=10) + Group By Operator [GBY_252] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_254] (rows=500 width=10) + Select Operator [SEL_251] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_253] (rows=500 width=10) + Filter Operator [FIL_250] (rows=500 width=10) predicate:value is not null TableScan [TS_88] (rows=500 width=10) Output:["key","value"] <-Reducer 28 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_238] + Reduce Output Operator [RS_235] PartitionCols:_col0, _col1 - Group By Operator [GBY_237] (rows=762 width=10) + Group By Operator [GBY_234] (rows=762 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_236] (rows=262 width=10) + Select Operator [SEL_233] (rows=262 width=10) Output:["_col0","_col1"] - Group By Operator [GBY_235] (rows=262 width=10) + Group By Operator [GBY_232] (rows=262 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 <-Union 27 [SIMPLE_EDGE] <-Map 26 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_234] + Reduce Output Operator [RS_231] PartitionCols:_col0, _col1 - Group By Operator [GBY_233] (rows=525 width=10) + Group By Operator [GBY_230] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_232] (rows=25 width=7) + Select Operator [SEL_229] (rows=25 width=7) Output:["_col0","_col1"] - Filter Operator [FIL_231] (rows=25 width=7) + Filter Operator [FIL_228] (rows=25 width=7) predicate:value is not null TableScan [TS_75] (rows=25 width=7) Output:["key","value"] <-Map 33 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_252] + Reduce Output Operator [RS_249] PartitionCols:_col0, _col1 - Group By Operator [GBY_251] (rows=525 width=10) + Group By Operator [GBY_248] (rows=525 width=10) Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_250] (rows=500 width=10) + Select Operator [SEL_247] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_249] (rows=500 width=10) + Filter Operator [FIL_246] (rows=500 width=10) predicate:value is not null TableScan [TS_78] (rows=500 width=10) Output:["key","value"] - <-Reducer 6 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_200] + <-Reducer 4 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_193] PartitionCols:_col0, _col1 - Group By Operator [GBY_199] (rows=1061 width=10) + Group By Operator [GBY_192] (rows=1089 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Group By Operator [GBY_198] (rows=577 width=10) + Group By Operator [GBY_191] (rows=605 width=10) Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 5 [SIMPLE_EDGE] - <-Reducer 16 [CONTAINS] llap + <-Union 3 [SIMPLE_EDGE] + <-Reducer 11 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 Select Operator [SEL_61] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_170] (rows=605 width=10) - Conds:RS_58._col2=RS_214._col0(Inner),Output:["_col2","_col5"] - <-Map 24 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_214] - PartitionCols:_col0 - Select Operator [SEL_213] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_212] (rows=500 width=10) - predicate:key is not null - TableScan [TS_52] (rows=500 width=10) - default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 15 [SIMPLE_EDGE] llap + Merge Join Operator [MERGEJOIN_168] (rows=605 width=10) + Conds:RS_58._col1=RS_203._col1(Inner),Output:["_col0","_col3"] + <-Reducer 10 [SIMPLE_EDGE] llap SHUFFLE [RS_58] - PartitionCols:_col2 - Merge Join Operator [MERGEJOIN_169] (rows=550 width=10) - Conds:RS_211._col1=RS_197._col1(Inner),Output:["_col2"] - <-Map 14 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_197] - PartitionCols:_col1 - Select Operator [SEL_195] (rows=500 width=10) + PartitionCols:_col1 + Merge Join Operator [MERGEJOIN_165] (rows=550 width=10) + Conds:RS_186._col0=RS_200._col0(Inner),Output:["_col0","_col1","_col3"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_186] + PartitionCols:_col0 + Select Operator [SEL_184] (rows=500 width=10) Output:["_col0","_col1"] - Filter Operator [FIL_193] (rows=500 width=10) + Filter Operator [FIL_182] (rows=500 width=10) predicate:(key is not null and value is not null) - TableScan [TS_16] (rows=500 width=10) + TableScan [TS_0] (rows=500 width=10) + default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] + <-Map 17 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_200] + PartitionCols:_col0 + Select Operator [SEL_199] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_198] (rows=500 width=10) + predicate:key is not null + TableScan [TS_29] (rows=500 width=10) default@src,y,Tbl:COMPLETE,Col:NONE,Output:["key","value"] - <-Reducer 21 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_211] - PartitionCols:_col1 - Select Operator [SEL_210] (rows=381 width=10) - Output:["_col1"] - Group By Operator [GBY_209] (rows=381 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 20 [SIMPLE_EDGE] - <-Map 23 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_230] - PartitionCols:_col0, _col1 - Group By Operator [GBY_229] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_228] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_227] (rows=500 width=10) - predicate:value is not null - TableScan [TS_39] (rows=500 width=10) - Output:["key","value"] - <-Reducer 19 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_222] - PartitionCols:_col0, _col1 - Group By Operator [GBY_221] (rows=762 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_220] (rows=262 width=10) - Output:["_col0","_col1"] - Group By Operator [GBY_219] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 18 [SIMPLE_EDGE] - <-Map 17 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_218] - PartitionCols:_col0, _col1 - Group By Operator [GBY_217] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_216] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_215] (rows=25 width=7) - predicate:value is not null - TableScan [TS_26] (rows=25 width=7) - Output:["key","value"] - <-Map 22 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_226] - PartitionCols:_col0, _col1 - Group By Operator [GBY_225] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_224] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_223] (rows=500 width=10) - predicate:value is not null - TableScan [TS_29] (rows=500 width=10) - Output:["key","value"] - <-Reducer 4 [CONTAINS] llap + <-Reducer 22 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_203] + PartitionCols:_col1 + Select Operator [SEL_202] (rows=381 width=10) + Output:["_col1"] + Group By Operator [GBY_201] (rows=381 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 21 [SIMPLE_EDGE] + <-Map 24 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_227] + PartitionCols:_col0, _col1 + Group By Operator [GBY_226] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_225] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_224] (rows=500 width=10) + predicate:value is not null + TableScan [TS_45] (rows=500 width=10) + Output:["key","value"] + <-Reducer 20 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_219] + PartitionCols:_col0, _col1 + Group By Operator [GBY_218] (rows=762 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_217] (rows=262 width=10) + Output:["_col0","_col1"] + Group By Operator [GBY_216] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 19 [SIMPLE_EDGE] + <-Map 18 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_215] + PartitionCols:_col0, _col1 + Group By Operator [GBY_214] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_213] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_212] (rows=25 width=7) + predicate:value is not null + TableScan [TS_32] (rows=25 width=7) + Output:["key","value"] + <-Map 23 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_223] + PartitionCols:_col0, _col1 + Group By Operator [GBY_222] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_221] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_220] (rows=500 width=10) + predicate:value is not null + TableScan [TS_35] (rows=500 width=10) + Output:["key","value"] + <-Reducer 2 [CONTAINS] llap Reduce Output Operator [RS_66] PartitionCols:_col0, _col1 - Group By Operator [GBY_65] (rows=1155 width=10) + Group By Operator [GBY_65] (rows=1210 width=10) Output:["_col0","_col1"],keys:_col0, _col1 - Select Operator [SEL_25] (rows=550 width=10) + Select Operator [SEL_25] (rows=605 width=10) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_168] (rows=550 width=10) - Conds:RS_191._col2=RS_196._col0(Inner),Output:["_col2","_col5"] - <-Map 14 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_196] - PartitionCols:_col0 - Select Operator [SEL_194] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_192] (rows=500 width=10) - predicate:key is not null - Please refer to the previous TableScan [TS_16] - <-Reducer 3 [SIMPLE_EDGE] vectorized, llap - SHUFFLE [RS_191] - PartitionCols:_col2 - Map Join Operator [MAPJOIN_190] (rows=288 width=10) - Conds:SEL_189._col1=RS_185._col1(Inner),Output:["_col2"] - <-Map 13 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_185] - PartitionCols:_col1 - Please refer to the previous Select Operator [SEL_184] - <-Select Operator [SEL_189] (rows=262 width=10) - Output:["_col1"] - Group By Operator [GBY_188] (rows=262 width=10) - Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 - <-Union 2 [SIMPLE_EDGE] - <-Map 1 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_179] - PartitionCols:_col0, _col1 - Group By Operator [GBY_178] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_177] (rows=25 width=7) - Output:["_col0","_col1"] - Filter Operator [FIL_176] (rows=25 width=7) - predicate:value is not null - TableScan [TS_0] (rows=25 width=7) - Output:["key","value"] - <-Map 12 [CONTAINS] vectorized, llap - Reduce Output Operator [RS_208] - PartitionCols:_col0, _col1 - Group By Operator [GBY_207] (rows=525 width=10) - Output:["_col0","_col1"],keys:_col1, _col0 - Select Operator [SEL_206] (rows=500 width=10) - Output:["_col0","_col1"] - Filter Operator [FIL_205] (rows=500 width=10) - predicate:value is not null - TableScan [TS_3] (rows=500 width=10) - Output:["key","value"] - Reducer 11 llap + Merge Join Operator [MERGEJOIN_167] (rows=605 width=10) + Conds:RS_187._col3=RS_190._col1(Inner),Output:["_col1","_col2"] + <-Map 1 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_187] + PartitionCols:_col3 + Map Join Operator [MAPJOIN_185] (rows=550 width=10) + Conds:SEL_183._col0=RS_178._col0(Inner),Output:["_col1","_col2","_col3"] + <-Map 12 [BROADCAST_EDGE] vectorized, llap + BROADCAST [RS_178] + PartitionCols:_col0 + Please refer to the previous Select Operator [SEL_177] + <-Select Operator [SEL_183] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_181] (rows=500 width=10) + predicate:key is not null + Please refer to the previous TableScan [TS_0] + <-Reducer 15 [SIMPLE_EDGE] vectorized, llap + SHUFFLE [RS_190] + PartitionCols:_col1 + Select Operator [SEL_189] (rows=262 width=10) + Output:["_col1"] + Group By Operator [GBY_188] (rows=262 width=10) + Output:["_col0","_col1"],keys:KEY._col0, KEY._col1 + <-Union 14 [SIMPLE_EDGE] + <-Map 13 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_207] + PartitionCols:_col0, _col1 + Group By Operator [GBY_206] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_205] (rows=25 width=7) + Output:["_col0","_col1"] + Filter Operator [FIL_204] (rows=25 width=7) + predicate:value is not null + TableScan [TS_6] (rows=25 width=7) + Output:["key","value"] + <-Map 16 [CONTAINS] vectorized, llap + Reduce Output Operator [RS_211] + PartitionCols:_col0, _col1 + Group By Operator [GBY_210] (rows=525 width=10) + Output:["_col0","_col1"],keys:_col1, _col0 + Select Operator [SEL_209] (rows=500 width=10) + Output:["_col0","_col1"] + Filter Operator [FIL_208] (rows=500 width=10) + predicate:value is not null + TableScan [TS_9] (rows=500 width=10) + Output:["key","value"] + Reducer 8 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] Please refer to the previous Group By Operator [GBY_120] Reducer 9 llap File Output Operator [FS_6] Group By Operator [GBY_4] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(VALUE._col0)","compute_stats(VALUE._col1)"] - <-Reducer 8 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 6 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] Group By Operator [GBY_2] (rows=1 width=880) Output:["_col0","_col1"],aggregations:["compute_stats(key, 'hll')","compute_stats(value, 'hll')"] - Select Operator [SEL_1] (rows=530 width=10) + Select Operator [SEL_1] (rows=544 width=10) Output:["key","value"] Please refer to the previous Group By Operator [GBY_120] Stage-6 diff --git a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out index c75e82c..95098b9 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_4.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_4.q.out @@ -26,11 +26,11 @@ Stage-0 Stage-1 Reducer 3 vectorized, llap File Output Operator [FS_25] - Select Operator [SEL_24] (rows=2076 width=553) + Select Operator [SEL_24] (rows=2048 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_17] (rows=2076 width=553) + Merge Join Operator [MERGEJOIN_17] (rows=2048 width=552) Conds:RS_20._col2=RS_23._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_20] @@ -111,7 +111,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_11] Group By Operator [GBY_10] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_19] (rows=2076 width=8) + Merge Join Operator [MERGEJOIN_19] (rows=2048 width=8) Conds:RS_22._col0=RS_25._col0(Inner) <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_22] @@ -180,18 +180,18 @@ Stage-0 Stage-1 Reducer 4 vectorized, llap File Output Operator [FS_31] - Select Operator [SEL_30] (rows=623 width=11) + Select Operator [SEL_30] (rows=631 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_29] - Group By Operator [GBY_28] (rows=623 width=11) + Group By Operator [GBY_28] (rows=631 width=11) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] llap SHUFFLE [RS_11] PartitionCols:_col0 - Group By Operator [GBY_10] (rows=623 width=11) + Group By Operator [GBY_10] (rows=631 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Merge Join Operator [MERGEJOIN_21] (rows=2076 width=3) + Merge Join Operator [MERGEJOIN_21] (rows=2048 width=3) Conds:RS_24._col1=RS_27._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] vectorized, llap SHUFFLE [RS_24] diff --git a/ql/src/test/results/clientpositive/llap/groupby1.q.out b/ql/src/test/results/clientpositive/llap/groupby1.q.out index a678d27..e1cc298 100644 --- a/ql/src/test/results/clientpositive/llap/groupby1.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby1.q.out @@ -67,14 +67,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col1 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 3708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 3708 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 3792 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/groupby2.q.out b/ql/src/test/results/clientpositive/llap/groupby2.q.out index 646a5f5..74e2bb3 100644 --- a/ql/src/test/results/clientpositive/llap/groupby2.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby2.q.out @@ -70,14 +70,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 309 Data size: 61800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 63200 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), concat(_col0, _col2) (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -86,11 +86,11 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string) outputColumnNames: key, c1, c2 - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 309 Data size: 114948 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 117552 Basic stats: COMPLETE Column stats: COMPLETE value expressions: key (type: string), c1 (type: int), c2 (type: string) Reducer 4 Execution mode: llap diff --git a/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out index bb6bec2..39dd4d5 100644 --- a/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out +++ b/ql/src/test/results/clientpositive/llap/groupby_resolution.q.out @@ -38,10 +38,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -93,10 +93,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -164,10 +164,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -235,10 +235,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out index b8df0d0..e98f3ba 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_1.q.out @@ -56,7 +56,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -177,7 +177,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -296,7 +296,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -413,7 +413,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -527,7 +527,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -638,7 +638,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out index 67555c0..ed7d8c9 100644 --- a/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/hybridgrace_hashjoin_2.q.out @@ -73,7 +73,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -204,7 +204,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -349,7 +349,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -502,7 +502,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -685,7 +685,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -746,7 +746,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -935,7 +935,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -996,7 +996,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1180,7 +1180,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1192,7 +1192,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1375,7 +1375,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1387,7 +1387,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/join1.q.out b/ql/src/test/results/clientpositive/llap/join1.q.out index 93feb56..a98fb48 100644 --- a/ql/src/test/results/clientpositive/llap/join1.q.out +++ b/ql/src/test/results/clientpositive/llap/join1.q.out @@ -78,14 +78,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -94,7 +94,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out index 7664912..a5dfd39 100644 --- a/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/llap/join32_lessSize.q.out @@ -67,13 +67,13 @@ STAGE PLANS: input vertices: 1 Map 4 Position of Big Table: 0 - Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 40 Data size: 10640 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 10374 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 value expressions: _col1 (type: string), _col2 (type: string) auto parallelism: true @@ -300,17 +300,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 Position of Big Table: 1 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col4 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -341,7 +341,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 64 Data size: 17152 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16884 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -569,8 +569,7 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 5 (BROADCAST_EDGE) - Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE) Reducer 3 <- Map 7 (SIMPLE_EDGE), Reducer 2 (SIMPLE_EDGE) Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### @@ -589,27 +588,15 @@ STAGE PLANS: expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE - Map Join Operator - condition map: - Inner Join 0 to 1 - Estimated key counts: Map 5 => 25 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 5 - Position of Big Table: 0 - Statistics: Num rows: 39 Data size: 10296 Basic stats: COMPLETE Column stats: COMPLETE - Reduce Output Operator - key expressions: _col1 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 39 Data size: 10296 Basic stats: COMPLETE Column stats: COMPLETE - tag: 0 - value expressions: _col0 (type: string), _col3 (type: string) - auto parallelism: true + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 25 Data size: 4375 Basic stats: COMPLETE Column stats: COMPLETE + tag: 0 + value expressions: _col1 (type: string) + auto parallelism: true Execution mode: vectorized, llap LLAP IO: no inputs Path -> Alias: @@ -746,24 +733,25 @@ STAGE PLANS: Map 6 Map Operator Tree: TableScan - alias: w - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + alias: y + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + predicate: key is not null (type: boolean) + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE - tag: 1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + tag: 2 + value expressions: _col1 (type: string) auto parallelism: true Execution mode: vectorized, llap LLAP IO: no inputs @@ -819,29 +807,28 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [w] + /src [y] Map 7 Map Operator Tree: TableScan - alias: y - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + alias: w + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + predicate: value is not null (type: boolean) + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + expressions: value (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 45500 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 - value expressions: _col1 (type: string) auto parallelism: true Execution mode: vectorized, llap LLAP IO: no inputs @@ -897,7 +884,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [y] + /src [w] Reducer 2 Execution mode: llap Needs Tagging: false @@ -905,20 +892,22 @@ STAGE PLANS: Merge Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 - Position of Big Table: 1 - Statistics: Num rows: 63 Data size: 11025 Basic stats: COMPLETE Column stats: COMPLETE + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 + Position of Big Table: 2 + Statistics: Num rows: 61 Data size: 21655 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col0 (type: string) + key expressions: _col1 (type: string) null sort order: a sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 63 Data size: 11025 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col1 (type: string) + Statistics: Num rows: 61 Data size: 21655 Basic stats: COMPLETE Column stats: COMPLETE tag: 0 - value expressions: _col3 (type: string) + value expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) auto parallelism: true Reducer 3 Execution mode: llap @@ -928,21 +917,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 + outputColumnNames: _col0, _col3, _col5 Position of Big Table: 0 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -973,7 +962,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 101 Data size: 26866 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 99 Data size: 26334 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -1305,17 +1294,17 @@ STAGE PLANS: input vertices: 1 Map 5 Position of Big Table: 0 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -1464,17 +1453,17 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 Position of Big Table: 0 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -1505,7 +1494,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -1977,17 +1966,17 @@ STAGE PLANS: 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 Position of Big Table: 0 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -2018,7 +2007,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -2074,17 +2063,17 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col1, _col2 Position of Big Table: 1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE tag: 1 value expressions: _col0 (type: string) auto parallelism: true @@ -2327,16 +2316,16 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -2370,14 +2359,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2386,7 +2375,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash @@ -2617,16 +2606,16 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6825 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -2660,14 +2649,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col3, _col4 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col3 (type: string), _col0 (type: string), _col4 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2676,7 +2665,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) outputColumnNames: key, value, val2 - Statistics: Num rows: 64 Data size: 17024 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 63 Data size: 16758 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll'), compute_stats(val2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out b/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out index c343154..996b789 100644 --- a/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out +++ b/ql/src/test/results/clientpositive/llap/join_max_hashtable.q.out @@ -39,10 +39,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -116,10 +116,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -223,11 +223,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -309,11 +309,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -396,11 +396,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -482,11 +482,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -539,10 +539,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -616,10 +616,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out index 4db4f12..76a8bf6 100644 --- a/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_join_transpose.q.out @@ -66,7 +66,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -167,7 +167,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Statistics: Num rows: 1 Data size: 356 Basic stats: COMPLETE Column stats: COMPLETE @@ -930,7 +930,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 @@ -1032,7 +1032,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 1 Offset of rows: 1 diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out index 79311d0..85b2877 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown.q.out @@ -399,12 +399,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized, llap LLAP IO: all inputs @@ -415,7 +415,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE @@ -1074,7 +1074,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out index d6f624c..86c0e2c 100644 --- a/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/llap/limit_pushdown3.q.out @@ -428,12 +428,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: vectorized, llap LLAP IO: all inputs @@ -444,11 +444,11 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 Execution mode: vectorized, llap @@ -456,7 +456,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: double) outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 128 Basic stats: COMPLETE Column stats: COMPLETE @@ -1013,11 +1013,11 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 value expressions: _col1 (type: double) Reducer 3 @@ -1026,7 +1026,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Statistics: Num rows: 20 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/llap_smb.q.out b/ql/src/test/results/clientpositive/llap/llap_smb.q.out index d526fd3..0588bcf 100644 --- a/ql/src/test/results/clientpositive/llap/llap_smb.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_smb.q.out @@ -234,7 +234,7 @@ STAGE PLANS: 0 id (type: bigint) 1 id (type: bigint) outputColumnNames: _col2, _col3 - Statistics: Num rows: 988 Data size: 7904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 993 Data size: 7944 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col2 (type: int), _col3 (type: smallint) diff --git a/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out b/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out index 2c13d5d..b361b1e 100644 --- a/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out +++ b/ql/src/test/results/clientpositive/llap/llap_vector_nohybridgrace.q.out @@ -65,7 +65,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Fast Hash Table and No Hybrid Hash Join IS true input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: @@ -244,7 +244,7 @@ STAGE PLANS: nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Fast Hash Table and No Hybrid Hash Join IS true input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/llapdecider.q.out b/ql/src/test/results/clientpositive/llap/llapdecider.q.out index b13134f..bf6151d 100644 --- a/ql/src/test/results/clientpositive/llap/llapdecider.q.out +++ b/ql/src/test/results/clientpositive/llap/llapdecider.q.out @@ -383,11 +383,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized @@ -395,10 +395,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -477,11 +477,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized, llap @@ -489,10 +489,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -570,11 +570,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized, llap @@ -582,10 +582,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -661,11 +661,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized @@ -673,10 +673,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -752,11 +752,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized @@ -764,10 +764,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -845,11 +845,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized @@ -857,10 +857,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -936,11 +936,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized @@ -948,10 +948,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1030,11 +1030,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string) Reducer 3 Execution mode: vectorized, llap @@ -1042,10 +1042,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 288004 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 281596 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out b/ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out index 0ffe74e..6dafe51 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin_decimal.q.out @@ -112,11 +112,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 1101 Data size: 246624 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1112 Data size: 249088 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: decimal(4,2)) sort order: + - Statistics: Num rows: 1101 Data size: 246624 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1112 Data size: 249088 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: decimal(4,0)) Execution mode: llap LLAP IO: all inputs @@ -145,10 +145,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: decimal(4,2)), VALUE._col0 (type: decimal(4,0)) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1101 Data size: 246624 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1112 Data size: 249088 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1101 Data size: 246624 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1112 Data size: 249088 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out index 8433e56..0ef6bbb 100644 --- a/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mapjoin_mapjoin.q.out @@ -580,9 +580,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 input vertices: 1 Map 3 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE @@ -590,7 +590,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 input vertices: @@ -613,13 +613,13 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -632,13 +632,13 @@ STAGE PLANS: Map 4 Map Operator Tree: TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator diff --git a/ql/src/test/results/clientpositive/llap/mergejoin.q.out b/ql/src/test/results/clientpositive/llap/mergejoin.q.out index 96be039..047a633 100644 --- a/ql/src/test/results/clientpositive/llap/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/mergejoin.q.out @@ -170,10 +170,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -520,7 +520,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1687,7 +1687,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2407,7 +2407,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -2693,7 +2693,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 3152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3031,7 +3031,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1009 Data size: 8072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3226,7 +3226,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 394 Data size: 3152 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3552,7 +3552,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 63 Data size: 504 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 512 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -3968,7 +3968,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 1009 Data size: 8072 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1029 Data size: 8232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -4210,7 +4210,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: 391 Data size: 3128 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 3192 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/mrr.q.out b/ql/src/test/results/clientpositive/llap/mrr.q.out index 737c738..cb25b8c 100644 --- a/ql/src/test/results/clientpositive/llap/mrr.q.out +++ b/ql/src/test/results/clientpositive/llap/mrr.q.out @@ -457,17 +457,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: @@ -475,27 +475,27 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: string) sort order: ++ - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -882,17 +882,17 @@ STAGE PLANS: outputColumnNames: _col1, _col2 input vertices: 0 Map 1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Reducer 3 @@ -902,27 +902,27 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: string) sort order: ++ - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string), KEY.reducesinkkey0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1360,15 +1360,15 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 10692 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 10098 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col3 (type: bigint), _col1 (type: bigint), _col4 (type: string), _col5 (type: bigint) outputColumnNames: _col0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint), _col3 (type: bigint), _col4 (type: string), _col5 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -1376,10 +1376,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint), KEY.reducesinkkey0 (type: string), VALUE._col1 (type: bigint), VALUE._col2 (type: string), VALUE._col3 (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 54 Data size: 15390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 14535 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out b/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out index 55cedb0..70a4d10 100644 --- a/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out +++ b/ql/src/test/results/clientpositive/llap/multiMapJoin2.q.out @@ -47,11 +47,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -94,11 +94,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 6 @@ -126,10 +126,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -350,21 +350,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -379,11 +379,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 80 Data size: 6960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 78 Data size: 6786 Basic stats: COMPLETE Column stats: COMPLETE Union 3 Vertex: Union 3 @@ -556,11 +556,11 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 52 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 6 @@ -593,17 +593,17 @@ STAGE PLANS: Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 52 Data size: 4512 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4425 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 52 Data size: 4524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4437 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 52 Data size: 4524 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 51 Data size: 4437 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -750,7 +750,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -808,7 +808,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -990,7 +990,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1048,7 +1048,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1230,7 +1230,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1454,7 +1454,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3393 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash @@ -1857,17 +1857,17 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 5 @@ -1896,17 +1896,17 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 7 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 6 diff --git a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out index 09a120a..5e8759c 100644 --- a/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out +++ b/ql/src/test/results/clientpositive/llap/offset_limit_ppd_optimizer.q.out @@ -403,12 +403,12 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + Map-reduce partition columns: _col0 (type: double) - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Execution mode: llap LLAP IO: all inputs @@ -419,7 +419,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 5570 Data size: 33272 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5528 Data size: 33024 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -937,7 +937,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 30591 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 307 Data size: 30393 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -1339,7 +1339,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 10 @@ -1383,7 +1383,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Offset of rows: 20 diff --git a/ql/src/test/results/clientpositive/llap/partialdhj.q.out b/ql/src/test/results/clientpositive/llap/partialdhj.q.out index 207d94d..fde5496 100644 --- a/ql/src/test/results/clientpositive/llap/partialdhj.q.out +++ b/ql/src/test/results/clientpositive/llap/partialdhj.q.out @@ -143,11 +143,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 0 Reducer 3 - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -336,11 +336,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 input vertices: 1 Reducer 5 - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true File Output Operator compressed: false - Statistics: Num rows: 25 Data size: 6675 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 26 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out b/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out index 9c271a7..13f2f9a 100644 --- a/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out +++ b/ql/src/test/results/clientpositive/llap/quotedid_smb.q.out @@ -89,10 +89,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 268 Data size: 95408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 270 Data size: 96120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 268 Data size: 95408 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 270 Data size: 96120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out index ea2587f..dec81dd 100644 --- a/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out +++ b/ql/src/test/results/clientpositive/llap/reduce_deduplicate_extended.q.out @@ -42,10 +42,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -313,18 +313,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0) keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -334,14 +334,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 3720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 3534 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1805 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 20 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1805 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -419,21 +419,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2596,10 +2596,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2779,10 +2779,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2860,12 +2860,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: llap Reduce Operator Tree: @@ -2874,14 +2874,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 40 Data size: 7440 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 7254 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3705 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 3800 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 3705 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2959,21 +2959,21 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3033,10 +3033,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -3093,10 +3093,10 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 29355 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30020 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/results_cache_1.q.out b/ql/src/test/results/clientpositive/llap/results_cache_1.q.out index b1423b9..6f5bfc3 100644 --- a/ql/src/test/results/clientpositive/llap/results_cache_1.q.out +++ b/ql/src/test/results/clientpositive/llap/results_cache_1.q.out @@ -64,7 +64,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -197,7 +197,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/results_cache_lifetime.q.out b/ql/src/test/results/clientpositive/llap/results_cache_lifetime.q.out index eeed7e3..8b8907b 100644 --- a/ql/src/test/results/clientpositive/llap/results_cache_lifetime.q.out +++ b/ql/src/test/results/clientpositive/llap/results_cache_lifetime.q.out @@ -83,7 +83,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/semijoin.q.out b/ql/src/test/results/clientpositive/llap/semijoin.q.out index 82cee33..f6382dc 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin.q.out @@ -2856,12 +2856,12 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 10609 Data size: 1888402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10918 Data size: 1943404 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 10609 Data size: 1888402 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 10918 Data size: 1943404 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 Execution mode: llap Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out index f2cef7a..679916d 100644 --- a/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out +++ b/ql/src/test/results/clientpositive/llap/semijoin_hint.q.out @@ -222,7 +222,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -272,7 +272,7 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -478,16 +478,16 @@ STAGE PLANS: 0 cstring (type: string) 1 value (type: string) outputColumnNames: str - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: str (type: string) sort order: + Map-reduce partition columns: str (type: string) - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: str (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4056 Data size: 705744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 715140 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=5000) mode: hash @@ -506,9 +506,9 @@ STAGE PLANS: keys: 0 str (type: string) 1 key1 (type: string) - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Select Operator - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1476,16 +1476,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 4056 Data size: 352872 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 357570 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 4056 Data size: 705744 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4110 Data size: 715140 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=5000) mode: hash @@ -1504,7 +1504,7 @@ STAGE PLANS: keys: 0 _col1 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 4461 Data size: 388159 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 4521 Data size: 393327 Basic stats: PARTIAL Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2190,7 +2190,7 @@ STAGE PLANS: outputColumnNames: _col0 Statistics: Num rows: 1000 Data size: 87000 Basic stats: PARTIAL Column stats: PARTIAL Group By Operator - aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=309) + aggregations: min(_col0), max(_col0), bloom_filter(_col0, expectedEntries=316) mode: hash outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL @@ -2238,7 +2238,7 @@ STAGE PLANS: Execution mode: vectorized, llap Reduce Operator Tree: Group By Operator - aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=309) + aggregations: min(VALUE._col0), max(VALUE._col1), bloom_filter(VALUE._col2, expectedEntries=316) mode: final outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 1 Data size: 639 Basic stats: PARTIAL Column stats: PARTIAL diff --git a/ql/src/test/results/clientpositive/llap/sharedworkext.q.out b/ql/src/test/results/clientpositive/llap/sharedworkext.q.out index 1837019..c734d00 100644 --- a/ql/src/test/results/clientpositive/llap/sharedworkext.q.out +++ b/ql/src/test/results/clientpositive/llap/sharedworkext.q.out @@ -88,22 +88,22 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col2 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: @@ -111,16 +111,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: llap Reduce Operator Tree: @@ -131,10 +131,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 528 Data size: 45936 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 493 Data size: 42891 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 528 Data size: 45936 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 493 Data size: 42891 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -146,16 +146,16 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator @@ -595,17 +595,17 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col1 (type: string), _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 3 Execution mode: vectorized, llap Reduce Operator Tree: @@ -613,28 +613,28 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: 0 (type: int), _col1 (type: string) sort order: ++ Map-reduce partition columns: 0 (type: int) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Reducer 4 Execution mode: vectorized, llap Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -655,19 +655,19 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 Execution mode: llap Reduce Operator Tree: @@ -678,10 +678,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -692,7 +692,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: string) outputColumnNames: _col1 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE PTF Operator Function definitions: Input definition @@ -713,19 +713,19 @@ STAGE PLANS: window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) isPivotResult: true - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: rank_window_0 is not null (type: boolean) - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: rank_window_0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 404 Data size: 1616 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 1580 Basic stats: COMPLETE Column stats: COMPLETE Stage: Stage-0 Fetch Operator diff --git a/ql/src/test/results/clientpositive/llap/skewjoin.q.out b/ql/src/test/results/clientpositive/llap/skewjoin.q.out index 67c6e21..104a65b 100644 --- a/ql/src/test/results/clientpositive/llap/skewjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/skewjoin.q.out @@ -142,14 +142,14 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: UDFToInteger(_col0) (type: int), _col2 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -158,7 +158,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 809 Data size: 76855 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 75145 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash @@ -688,7 +688,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2, _col3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash @@ -815,7 +815,7 @@ STAGE PLANS: 0 _col0 (type: string), UDFToDouble(substring(_col1, 5)) (type: double) 1 _col0 (type: string), (substring(_col1, 5) + 1) (type: double) outputColumnNames: _col2, _col3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col2)), sum(hash(_col3)) mode: hash @@ -971,7 +971,7 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 143 Data size: 25454 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 24030 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(hash(_col0)), sum(hash(_col3)) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out index d444b62..36c11ae 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_15.q.out @@ -227,12 +227,12 @@ STAGE PLANS: 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 Position of Big Table: 0 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -245,7 +245,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string), VALUE._col1 (type: int), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1900 Basic stats: COMPLETE Column stats: COMPLETE @@ -545,12 +545,12 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -563,7 +563,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE @@ -811,12 +811,12 @@ STAGE PLANS: 1 _col0 (type: int), _col1 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -829,7 +829,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 163350 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE @@ -1077,12 +1077,12 @@ STAGE PLANS: 1 _col0 (type: int), _col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 814 Data size: 161172 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 814 Data size: 161172 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 TopN: 10 TopN Hash Memory Usage: 0.1 @@ -1095,7 +1095,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: int), VALUE._col1 (type: string), VALUE._col2 (type: int), VALUE._col3 (type: int), VALUE._col4 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 809 Data size: 160182 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 814 Data size: 161172 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1980 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out b/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out index e17a7e5..eee3151 100644 --- a/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out +++ b/ql/src/test/results/clientpositive/llap/smb_mapjoin_6.q.out @@ -127,10 +127,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -139,7 +139,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') mode: hash @@ -1343,10 +1343,10 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1355,7 +1355,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: string), _col2 (type: int), _col3 (type: string) outputColumnNames: k1, v1, k2, v2 - Statistics: Num rows: 809 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 825 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(v1, 'hll'), compute_stats(k2, 'hll'), compute_stats(v2, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_corr.q.out b/ql/src/test/results/clientpositive/llap/subquery_corr.q.out index 740df7f..466de2a 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_corr.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_corr.q.out @@ -70,14 +70,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col1 > _col3)} - Statistics: Num rows: 134 Data size: 36046 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 35239 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -169,14 +169,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col1 <= _col3)} - Statistics: Num rows: 134 Data size: 36046 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 35239 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out index e5e90ea..30800c8 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_exists.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_exists.q.out @@ -81,10 +81,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -289,10 +289,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 72446 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_in.q.out b/ql/src/test/results/clientpositive/llap/subquery_in.q.out index 7e853ab..ace1798 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in.q.out @@ -74,10 +74,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -195,10 +195,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -688,10 +688,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -816,14 +816,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col1 <> _col3)} - Statistics: Num rows: 66 Data size: 17490 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 16960 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 66 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 11392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 11748 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 64 Data size: 11392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -950,14 +950,14 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3 residual filter predicates: {(_col3 > _col1)} - Statistics: Num rows: 67 Data size: 18023 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 17485 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 67 Data size: 11926 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11570 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 67 Data size: 11926 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11570 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2727,18 +2727,18 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 407 Data size: 35409 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2748,15 +2748,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 203 Data size: 19285 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -2948,18 +2948,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 404 Data size: 35148 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 34365 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -2969,15 +2969,15 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col1 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint) sort order: + Map-reduce partition columns: _col1 (type: bigint) - Statistics: Num rows: 202 Data size: 19190 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 18715 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -3479,10 +3479,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out index eba2a96..00fdb67 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_in_having.q.out @@ -628,18 +628,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -649,15 +649,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reducer 4 Execution mode: llap @@ -793,18 +793,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -855,10 +855,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 @@ -962,18 +962,18 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Execution mode: vectorized, llap LLAP IO: no inputs @@ -1031,10 +1031,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Semi Join 0 to 1 diff --git a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out index c573b8c..67f16b1 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_multi.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_multi.q.out @@ -3170,18 +3170,18 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 395 Data size: 70310 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -3191,15 +3191,15 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: _col2 is not null (type: boolean) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: bigint) sort order: + Map-reduce partition columns: _col2 (type: bigint) - Statistics: Num rows: 202 Data size: 37572 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 197 Data size: 36642 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Reducer 4 Execution mode: llap @@ -3229,7 +3229,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 134 Data size: 11658 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 11745 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -4063,10 +4063,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col4 - Statistics: Num rows: 500 Data size: 50040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 500 Data size: 50040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 50028 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: bigint), _col4 (type: boolean) Reducer 4 Execution mode: llap @@ -4078,12 +4078,12 @@ STAGE PLANS: 0 1 outputColumnNames: _col1, _col2, _col4, _col5 - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col4 is not null and (_col2 <> 0L)) or _col1 is not null or _col5 is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - Statistics: Num rows: 500 Data size: 52040 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 52028 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out index 7270564..5e385be 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_notin.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_notin.q.out @@ -101,10 +101,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97540 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97528 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -1519,10 +1519,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col4 - Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col1 = 0L) or (_col4 is null and _col0 is not null and (_col2 >= _col1))) (type: boolean) - Statistics: Num rows: 166 Data size: 17366 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 17358 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 @@ -3524,14 +3524,14 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col1 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -3796,12 +3796,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 95480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 500 Data size: 95480 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 95336 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -3813,14 +3813,14 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col1 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col7 - Statistics: Num rows: 500 Data size: 97100 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 96920 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not CASE WHEN ((_col3 = 0L)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col1 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (true) ELSE (false) END) (type: boolean) - Statistics: Num rows: 250 Data size: 48560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 48460 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 48560 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 48460 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string) @@ -4559,10 +4559,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 97164 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 97160 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 @@ -6993,12 +6993,12 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 500 Data size: 91672 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 91672 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 91688 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col3 (type: bigint), _col4 (type: bigint) Reducer 3 Execution mode: llap @@ -7011,10 +7011,10 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col3, _col4, _col6, _col7 residual filter predicates: {(_col1 > _col6)} - Statistics: Num rows: 500 Data size: 104497 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 104228 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: (not CASE WHEN ((_col3 = 0L)) THEN (false) WHEN (_col3 is null) THEN (false) WHEN (_col7 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col4 < _col3)) THEN (true) ELSE (false) END) (type: boolean) - Statistics: Num rows: 250 Data size: 52304 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 52114 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 diff --git a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out index 5891519..2aac44c 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_scalar.q.out @@ -5455,18 +5455,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 133 Data size: 23674 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -5476,10 +5476,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator sort order: - Statistics: Num rows: 66 Data size: 12276 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 12090 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) Reducer 4 Execution mode: llap @@ -5492,14 +5492,14 @@ STAGE PLANS: 1 outputColumnNames: _col0, _col1, _col2, _col3 residual filter predicates: {(_col2 > _col3)} - Statistics: Num rows: 22 Data size: 4268 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 4074 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 22 Data size: 4092 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 22 Data size: 4092 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 21 Data size: 3906 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/subquery_select.q.out b/ql/src/test/results/clientpositive/llap/subquery_select.q.out index fec9924..641fa9b 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_select.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_select.q.out @@ -1869,10 +1869,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 134 Data size: 23852 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 131 Data size: 23318 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2035,10 +2035,10 @@ STAGE PLANS: 0 _col0 (type: string), _col1 (type: string) 1 _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 108 Data size: 19224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 106 Data size: 18868 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 108 Data size: 19224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 106 Data size: 18868 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -2053,11 +2053,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 134 Data size: 36850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 37125 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 134 Data size: 36850 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 135 Data size: 37125 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/subquery_views.q.out b/ql/src/test/results/clientpositive/llap/subquery_views.q.out index 2c85309..8835713 100644 --- a/ql/src/test/results/clientpositive/llap/subquery_views.q.out +++ b/ql/src/test/results/clientpositive/llap/subquery_views.q.out @@ -232,19 +232,19 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) 2 _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col4, _col5, _col8 - Statistics: Num rows: 87 Data size: 17226 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 81 Data size: 16038 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 43 Data size: 8514 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7920 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Reducer 3 Execution mode: llap @@ -256,10 +256,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 43 Data size: 7654 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -307,18 +307,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col3 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col3 (type: string), _col1 (type: string) - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reduce Output Operator key expressions: _col3 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col3 (type: string), _col1 (type: string) - Statistics: Num rows: 67 Data size: 12194 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 11830 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: boolean) Reducer 7 Execution mode: llap @@ -332,24 +332,24 @@ STAGE PLANS: 1 _col0 (type: string), _col1 (type: string) 2 _col3 (type: string), _col1 (type: string) outputColumnNames: _col0, _col4, _col5, _col8 - Statistics: Num rows: 87 Data size: 9309 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 81 Data size: 8667 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: CASE WHEN ((_col4 = 0L)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean) - Statistics: Num rows: 43 Data size: 4601 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 4280 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 43 Data size: 3741 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 40 Data size: 3480 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 609 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 8 Data size: 696 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 7 Data size: 609 Basic stats: COMPLETE Column stats: COMPLETE Reducer 8 Execution mode: vectorized, llap Reduce Operator Tree: diff --git a/ql/src/test/results/clientpositive/llap/tez_bmj_schema_evolution.q.out b/ql/src/test/results/clientpositive/llap/tez_bmj_schema_evolution.q.out index 32c36dd..621391e 100644 --- a/ql/src/test/results/clientpositive/llap/tez_bmj_schema_evolution.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_bmj_schema_evolution.q.out @@ -103,11 +103,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 1618 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1650 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + - Statistics: Num rows: 1618 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1650 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: some inputs @@ -136,10 +136,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: int), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1618 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1650 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 153710 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1650 Data size: 156750 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out index fd6541e..39144bd 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_1.q.out @@ -77,11 +77,11 @@ STAGE PLANS: 0 _col2 (type: int) 1 _col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: int) sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: tinyint), _col1 (type: smallint), _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: tinyint), _col13 (type: smallint), _col14 (type: int), _col15 (type: bigint), _col16 (type: float), _col17 (type: double), _col18 (type: string), _col19 (type: string), _col20 (type: timestamp), _col21 (type: timestamp), _col22 (type: boolean), _col23 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -89,10 +89,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: tinyint), VALUE._col1 (type: smallint), KEY.reducesinkkey0 (type: int), VALUE._col2 (type: bigint), VALUE._col3 (type: float), VALUE._col4 (type: double), VALUE._col5 (type: string), VALUE._col6 (type: string), VALUE._col7 (type: timestamp), VALUE._col8 (type: timestamp), VALUE._col9 (type: boolean), VALUE._col10 (type: boolean), VALUE._col11 (type: tinyint), VALUE._col12 (type: smallint), VALUE._col13 (type: int), VALUE._col14 (type: bigint), VALUE._col15 (type: float), VALUE._col16 (type: double), VALUE._col17 (type: string), VALUE._col18 (type: string), VALUE._col19 (type: timestamp), VALUE._col20 (type: timestamp), VALUE._col21 (type: boolean), VALUE._col22 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col15, _col16, _col17, _col18, _col19, _col20, _col21, _col22, _col23 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 1131300 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -206,7 +206,7 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 16384 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -336,18 +336,18 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2048 Data size: 6812 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 3 Execution mode: vectorized, llap @@ -357,11 +357,11 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Reducer 4 Execution mode: vectorized, llap @@ -369,10 +369,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: smallint), VALUE._col0 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: ###Masked### Data size: ###Masked### Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 631 Data size: 7148 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out index ae9b37a..3373fc25 100644 --- a/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_dynpart_hashjoin_2.q.out @@ -105,11 +105,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -117,10 +117,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,11 +296,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -308,10 +308,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,11 +487,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -499,10 +499,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out index cce289d..122eb5c 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_hash.q.out @@ -82,7 +82,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 809 Data size: 6472 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 6328 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -207,7 +207,7 @@ STAGE PLANS: key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14944 Data size: 2660032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14658 Data size: 2609124 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -240,16 +240,16 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 12944 Data size: 2304032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12658 Data size: 2253124 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12944 Data size: 2304032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 12658 Data size: 2253124 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 14944 Data size: 2660032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14658 Data size: 2609124 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 4 Execution mode: llap @@ -261,18 +261,18 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 24181 Data size: 4304218 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 23872 Data size: 4249216 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: bigint) Reducer 5 Execution mode: vectorized, llap @@ -282,14 +282,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 12090 Data size: 2248740 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 2220096 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col2 (type: bigint) outputColumnNames: _col0, _col1 - Statistics: Num rows: 12090 Data size: 1148550 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 1133920 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 12090 Data size: 1148550 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 11936 Data size: 1133920 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out index b94b018..ff74455 100644 --- a/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_join_tests.q.out @@ -67,12 +67,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -84,11 +84,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: vectorized, llap @@ -96,10 +96,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out index b5e07d7..012b934 100644 --- a/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_joins_explain.q.out @@ -67,12 +67,12 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 40 Data size: 7120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 6942 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string) Reducer 3 Execution mode: llap @@ -84,11 +84,11 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: string), _col2 (type: string), _col3 (type: string) Reducer 4 Execution mode: vectorized, llap @@ -96,10 +96,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), VALUE._col1 (type: string), VALUE._col2 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 500 Data size: 100570 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 100392 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out index 76e2dd0..8312c3d 100644 --- a/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_smb_main.q.out @@ -66,10 +66,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 40 Data size: 14120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 39 Data size: 13767 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union.q.out b/ql/src/test/results/clientpositive/llap/tez_union.q.out index 1d18bd9..f60e8cf 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union.q.out @@ -42,10 +42,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1291 Data size: 229798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -82,7 +82,7 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1309 Data size: 233002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1291 Data size: 229798 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -264,7 +264,7 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 3236 Data size: 25888 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 3164 Data size: 25312 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -400,10 +400,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -431,10 +431,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Map 1 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -556,7 +556,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 4 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -569,15 +569,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -650,7 +650,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 6 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -663,15 +663,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -715,7 +715,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 8 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -728,15 +728,15 @@ STAGE PLANS: input vertices: 1 Map 9 2 Map 10 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col1 (type: string), _col0 (type: string), _col2 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col2 (type: string) sort order: + - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized, llap LLAP IO: no inputs @@ -794,10 +794,10 @@ STAGE PLANS: Select Operator expressions: VALUE._col0 (type: string), VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 6354 Data size: 1658394 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 5941 Data size: 1550601 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -996,10 +996,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 140766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1046,10 +1046,10 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 5 - Statistics: Num rows: 809 Data size: 70383 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 68817 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 140766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 137634 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1186,10 +1186,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1214,10 +1214,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3 input vertices: 1 Map 4 - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 576008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 563192 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1330,10 +1330,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 0 Union 2 - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1618 Data size: 281532 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1582 Data size: 275268 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/tez_union2.q.out b/ql/src/test/results/clientpositive/llap/tez_union2.q.out index 9db0a09..7cbee12 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union2.q.out @@ -61,12 +61,12 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 4 @@ -118,10 +118,10 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -142,21 +142,21 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 53766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 54984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 Union 5 diff --git a/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out b/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out index c443acf..aee89f9 100644 --- a/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_union_multiinsert.q.out @@ -188,14 +188,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -204,7 +204,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash @@ -1129,14 +1129,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -1145,7 +1145,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash @@ -2100,14 +2100,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 29664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 30336 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), UDFToString(_col1) (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -2116,7 +2116,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: key, value - Statistics: Num rows: 309 Data size: 84048 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 85952 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(key, 'hll'), compute_stats(value, 'hll') mode: hash diff --git a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out index ae9b37a..3373fc25 100644 --- a/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/llap/tez_vector_dynpart_hashjoin_2.q.out @@ -105,11 +105,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -117,10 +117,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -296,11 +296,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -308,10 +308,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -487,11 +487,11 @@ STAGE PLANS: 1 UDFToInteger(_col0) (type: int) 2 (UDFToInteger(_col0) + 0) (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: smallint), _col0 (type: tinyint), _col2 (type: int) sort order: +++ - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col3 (type: bigint), _col4 (type: float), _col5 (type: double), _col6 (type: string), _col7 (type: string), _col8 (type: timestamp), _col9 (type: timestamp), _col10 (type: boolean), _col11 (type: boolean) Reducer 3 Execution mode: vectorized, llap @@ -499,10 +499,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey1 (type: tinyint), KEY.reducesinkkey0 (type: smallint), KEY.reducesinkkey2 (type: int), VALUE._col0 (type: bigint), VALUE._col1 (type: float), VALUE._col2 (type: double), VALUE._col3 (type: string), VALUE._col4 (type: string), VALUE._col5 (type: timestamp), VALUE._col6 (type: timestamp), VALUE._col7 (type: boolean), VALUE._col8 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 1776 Data size: 312050 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1715 Data size: 293140 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out index 42d5528..e8e2223 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out @@ -651,315 +651,315 @@ POSTHOOK: query: select unionsrc.key, unionsrc.value FROM (select s1.key as key, POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: hdfs://### HDFS PATH ### -116 val_116 +104 val_104 +105 val_105 +113 val_113 118 val_118 +12 val_12 120 val_120 -131 val_131 133 val_133 -15 val_15 -150 val_150 -152 val_152 -153 val_153 +136 val_136 155 val_155 +158 val_158 160 val_160 -169 val_169 +162 val_162 +168 val_168 +17 val_17 +170 val_170 175 val_175 -176 val_176 -178 val_178 -183 val_183 +18 val_18 +180 val_180 186 val_186 -194 val_194 -202 val_202 -203 val_203 -213 val_213 -223 val_223 +19 val_19 +197 val_197 +200 val_200 +216 val_216 +218 val_218 +222 val_222 224 val_224 -226 val_226 228 val_228 +235 val_235 +237 val_237 239 val_239 244 val_244 247 val_247 -252 val_252 -255 val_255 256 val_256 -257 val_257 -266 val_266 -272 val_272 -274 val_274 -275 val_275 +263 val_263 +273 val_273 28 val_28 -284 val_284 +283 val_283 286 val_286 -289 val_289 -296 val_296 -302 val_302 +292 val_292 306 val_306 -307 val_307 -317 val_317 -321 val_321 -323 val_323 +308 val_308 +327 val_327 33 val_33 -338 val_338 -34 val_34 -35 val_35 -360 val_360 -365 val_365 -374 val_374 -377 val_377 -393 val_393 -399 val_399 -404 val_404 -406 val_406 +348 val_348 +353 val_353 +362 val_362 +366 val_366 +396 val_396 +397 val_397 +401 val_401 409 val_409 -41 val_41 -417 val_417 -418 val_418 -42 val_42 -431 val_431 +411 val_411 +419 val_419 +427 val_427 +43 val_43 +432 val_432 +436 val_436 439 val_439 -44 val_44 443 val_443 -448 val_448 -455 val_455 -459 val_459 +453 val_453 +460 val_460 462 val_462 -463 val_463 -470 val_470 -490 val_490 -491 val_491 -494 val_494 -5 val_5 -53 val_53 -66 val_66 -72 val_72 -76 val_76 -77 val_77 -80 val_80 +47 val_47 +472 val_472 +485 val_485 +496 val_496 +54 val_54 +64 val_64 +70 val_70 +8 val_8 +83 val_83 84 val_84 +85 val_85 90 val_90 -10 val_10 -105 val_105 -111 val_111 -113 val_113 -119 val_119 -129 val_129 -136 val_136 -143 val_143 -149 val_149 -163 val_163 -167 val_167 -174 val_174 +0 val_0 +103 val_103 +114 val_114 +125 val_125 +138 val_138 +146 val_146 +150 val_150 +152 val_152 +153 val_153 +156 val_156 +157 val_157 +165 val_165 +172 val_172 +177 val_177 +179 val_179 187 val_187 -197 val_197 -2 val_2 -200 val_200 -208 val_208 -209 val_209 -216 val_216 +195 val_195 +196 val_196 217 val_217 -218 val_218 -221 val_221 -230 val_230 -258 val_258 -26 val_26 -263 val_263 -273 val_273 -277 val_277 -281 val_281 -292 val_292 -30 val_30 -316 val_316 -335 val_335 -341 val_341 -342 val_342 -344 val_344 +242 val_242 +248 val_248 +252 val_252 +265 val_265 +27 val_27 +272 val_272 +280 val_280 +291 val_291 +305 val_305 +309 val_309 +311 val_311 +315 val_315 +317 val_317 +322 val_322 +333 val_333 +34 val_34 345 val_345 -362 val_362 -367 val_367 +35 val_35 +356 val_356 +364 val_364 368 val_368 +369 val_369 37 val_37 -392 val_392 -394 val_394 +373 val_373 +377 val_377 4 val_4 +402 val_402 +404 val_404 413 val_413 -437 val_437 +42 val_42 +430 val_430 +431 val_431 444 val_444 -446 val_446 +449 val_449 452 val_452 -453 val_453 +454 val_454 457 val_457 -460 val_460 +463 val_463 466 val_466 -468 val_468 -477 val_477 -479 val_479 -483 val_483 -487 val_487 -492 val_492 -493 val_493 -498 val_498 -51 val_51 -54 val_54 -64 val_64 +470 val_470 +475 val_475 +481 val_481 +489 val_489 +491 val_491 +57 val_57 65 val_65 -67 val_67 -82 val_82 -85 val_85 -87 val_87 +66 val_66 +74 val_74 +76 val_76 +78 val_78 +9 val_9 +92 val_92 95 val_95 -96 val_96 100 val_100 -103 val_103 -104 val_104 -11 val_11 -114 val_114 -137 val_137 +119 val_119 +128 val_128 +129 val_129 145 val_145 -156 val_156 -157 val_157 -162 val_162 -168 val_168 -17 val_17 -170 val_170 -180 val_180 -19 val_19 -190 val_190 -192 val_192 -196 val_196 +167 val_167 +174 val_174 +178 val_178 +181 val_181 +193 val_193 199 val_199 20 val_20 -207 val_207 +201 val_201 +213 val_213 214 val_214 219 val_219 -222 val_222 +221 val_221 +223 val_223 +226 val_226 233 val_233 241 val_241 +249 val_249 260 val_260 -27 val_27 -278 val_278 -280 val_280 -285 val_285 +262 val_262 +277 val_277 +281 val_281 +287 val_287 288 val_288 -305 val_305 -311 val_311 -318 val_318 -322 val_322 -327 val_327 -331 val_331 +298 val_298 +302 val_302 +310 val_310 +323 val_323 336 val_336 -348 val_348 +341 val_341 +344 val_344 351 val_351 -366 val_366 -369 val_369 375 val_375 -379 val_379 382 val_382 384 val_384 -389 val_389 +393 val_393 395 val_395 -396 val_396 -397 val_397 -400 val_400 -401 val_401 -407 val_407 -414 val_414 -421 val_421 -427 val_427 -430 val_430 +399 val_399 +403 val_403 +406 val_406 +418 val_418 435 val_435 -438 val_438 -454 val_454 -47 val_47 -472 val_472 +455 val_455 +459 val_459 +477 val_477 478 val_478 -480 val_480 -481 val_481 -485 val_485 -489 val_489 -57 val_57 -69 val_69 -74 val_74 -78 val_78 -8 val_8 +479 val_479 +482 val_482 +493 val_493 +494 val_494 +495 val_495 +497 val_497 +5 val_5 +58 val_58 +67 val_67 +77 val_77 +80 val_80 86 val_86 -9 val_9 -0 val_0 -12 val_12 -125 val_125 +97 val_97 +98 val_98 +10 val_10 +11 val_11 +111 val_111 +116 val_116 126 val_126 -128 val_128 +131 val_131 134 val_134 -138 val_138 -146 val_146 -158 val_158 +137 val_137 +143 val_143 +149 val_149 +15 val_15 +163 val_163 164 val_164 -165 val_165 166 val_166 -172 val_172 -177 val_177 -179 val_179 -18 val_18 -181 val_181 +169 val_169 +176 val_176 +183 val_183 189 val_189 +190 val_190 191 val_191 -193 val_193 -195 val_195 -201 val_201 +192 val_192 +194 val_194 +2 val_2 +202 val_202 +203 val_203 205 val_205 +207 val_207 +208 val_208 +209 val_209 229 val_229 -235 val_235 -237 val_237 +230 val_230 238 val_238 24 val_24 -242 val_242 -248 val_248 -249 val_249 -262 val_262 -265 val_265 +255 val_255 +257 val_257 +258 val_258 +26 val_26 +266 val_266 +274 val_274 +275 val_275 +278 val_278 282 val_282 -283 val_283 -287 val_287 -291 val_291 -298 val_298 -308 val_308 -309 val_309 -310 val_310 -315 val_315 +284 val_284 +285 val_285 +289 val_289 +296 val_296 +30 val_30 +307 val_307 +316 val_316 +318 val_318 +321 val_321 325 val_325 +331 val_331 332 val_332 -333 val_333 +335 val_335 +338 val_338 339 val_339 -353 val_353 -356 val_356 -364 val_364 -373 val_373 +342 val_342 +360 val_360 +365 val_365 +367 val_367 +374 val_374 378 val_378 +379 val_379 386 val_386 -402 val_402 -403 val_403 -411 val_411 -419 val_419 +389 val_389 +392 val_392 +394 val_394 +400 val_400 +407 val_407 +41 val_41 +414 val_414 +417 val_417 +421 val_421 424 val_424 429 val_429 -43 val_43 -432 val_432 -436 val_436 -449 val_449 +437 val_437 +438 val_438 +44 val_44 +446 val_446 +448 val_448 458 val_458 467 val_467 +468 val_468 469 val_469 -475 val_475 -482 val_482 +480 val_480 +483 val_483 484 val_484 -495 val_495 -496 val_496 -497 val_497 -58 val_58 -70 val_70 -83 val_83 -92 val_92 -97 val_97 -98 val_98 +487 val_487 +490 val_490 +492 val_492 +498 val_498 +51 val_51 +53 val_53 +69 val_69 +72 val_72 +82 val_82 +87 val_87 +96 val_96 PREHOOK: query: CREATE TABLE DEST1(key STRING, value STRING) STORED AS TEXTFILE PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -3790,13 +3790,13 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Execution mode: vectorized @@ -4021,14 +4021,14 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false GlobalTableId: 1 directory: hdfs://### HDFS PATH ### NumFilesPerFileSink: 1 Static Partition Specification: ds=2/ - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE Stats Publishing Key Prefix: hdfs://### HDFS PATH ### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -4057,7 +4057,7 @@ STAGE PLANS: Select Operator expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), '2' (type: string) outputColumnNames: k1, k2, k3, k4, ds - Statistics: Num rows: 332 Data size: 132706 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 132350 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: compute_stats(k1, 'hll'), compute_stats(k2, 'hll'), compute_stats(k3, 'hll'), compute_stats(k4, 'hll') keys: ds (type: string) @@ -4125,22 +4125,22 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col4, _col5 Position of Big Table: 0 - Statistics: Num rows: 166 Data size: 45390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 45034 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 166 Data size: 45390 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 166 Data size: 45034 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) mode: hash outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) null sort order: aaaa sort order: ++++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string) - Statistics: Num rows: 332 Data size: 104486 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 332 Data size: 104130 Basic stats: COMPLETE Column stats: COMPLETE tag: -1 auto parallelism: true Union 2 @@ -4236,329 +4236,329 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@dst_union22 POSTHOOK: Input: default@dst_union22@ds=2 POSTHOOK: Output: hdfs://### HDFS PATH ### -100 val_100 100 val_100 2 +11 val_11 11 val_11 2 +111 val_111 111 val_111 2 +126 val_126 126 val_126 2 +143 val_143 143 val_143 2 +160 val_160 160 val_160 2 +165 val_165 165 val_165 2 +166 val_166 166 val_166 2 +175 val_175 175 val_175 2 +18 val_18 18 val_18 2 +183 val_183 183 val_183 2 +187 val_187 187 val_187 2 +189 val_189 189 val_189 2 +192 val_192 192 val_192 2 +193 val_193 193 val_193 2 +196 val_196 196 val_196 2 +197 val_197 197 val_197 2 +199 val_199 199 val_199 2 +201 val_201 201 val_201 2 +202 val_202 202 val_202 2 +205 val_205 205 val_205 2 +207 val_207 207 val_207 2 +216 val_216 216 val_216 2 +218 val_218 218 val_218 2 +219 val_219 219 val_219 2 +221 val_221 221 val_221 2 +226 val_226 226 val_226 2 +228 val_228 228 val_228 2 +235 val_235 235 val_235 2 +242 val_242 242 val_242 2 +255 val_255 255 val_255 2 +27 val_27 27 val_27 2 +277 val_277 277 val_277 2 +28 val_28 28 val_28 2 +281 val_281 281 val_281 2 +283 val_283 283 val_283 2 +285 val_285 285 val_285 2 +291 val_291 291 val_291 2 +305 val_305 305 val_305 2 +308 val_308 308 val_308 2 +311 val_311 311 val_311 2 +327 val_327 327 val_327 2 +333 val_333 333 val_333 2 +341 val_341 341 val_341 2 +348 val_348 348 val_348 2 +35 val_35 NULL NULL 2 +35 val_35 35 val_35 2 +360 val_360 360 val_360 2 +37 val_37 37 val_37 2 +373 val_373 373 val_373 2 +374 val_374 374 val_374 2 +377 val_377 377 val_377 2 +384 val_384 384 val_384 2 +392 val_392 392 val_392 2 +393 val_393 393 val_393 2 +395 val_395 395 val_395 2 +397 val_397 397 val_397 2 +4 val_4 4 val_4 2 +400 val_400 400 val_400 2 +403 val_403 403 val_403 2 +407 val_407 407 val_407 2 +411 val_411 411 val_411 2 +427 val_427 427 val_427 2 +429 val_429 429 val_429 2 +439 val_439 439 val_439 2 +44 val_44 NULL NULL 2 +449 val_449 449 val_449 2 +452 val_452 452 val_452 2 +454 val_454 454 val_454 2 +462 val_462 462 val_462 2 +467 val_467 467 val_467 2 +47 val_47 47 val_47 2 +470 val_470 470 val_470 2 +483 val_483 483 val_483 2 +489 val_489 489 val_489 2 +490 val_490 490 val_490 2 +491 val_491 491 val_491 2 +493 val_493 493 val_493 2 +497 val_497 497 val_497 2 +51 val_51 51 val_51 2 +54 val_54 54 val_54 2 +67 val_67 67 val_67 2 +72 val_72 72 val_72 2 +77 val_77 77 val_77 2 +9 val_9 9 val_9 2 +0 val_0 0 val_0 2 103 val_103 103 val_103 2 +128 val_128 128 val_128 2 +131 val_131 131 val_131 2 +133 val_133 133 val_133 2 +138 val_138 138 val_138 2 +149 val_149 149 val_149 2 +152 val_152 152 val_152 2 +156 val_156 156 val_156 2 +158 val_158 158 val_158 2 +163 val_163 163 val_163 2 +169 val_169 169 val_169 2 +176 val_176 176 val_176 2 +190 val_190 190 val_190 2 +20 val_20 20 val_20 2 +214 val_214 214 val_214 2 +223 val_223 223 val_223 2 +229 val_229 229 val_229 2 +237 val_237 237 val_237 2 +238 val_238 238 val_238 2 +26 val_26 26 val_26 2 +262 val_262 262 val_262 2 +272 val_272 272 val_272 2 +275 val_275 275 val_275 2 +287 val_287 287 val_287 2 +30 val_30 NULL NULL 2 +310 val_310 310 val_310 2 +325 val_325 325 val_325 2 +33 val_33 NULL NULL 2 +331 val_331 331 val_331 2 +332 val_332 332 val_332 2 +34 val_34 34 val_34 2 +342 val_342 342 val_342 2 +353 val_353 353 val_353 2 +356 val_356 356 val_356 2 +362 val_362 362 val_362 2 +379 val_379 379 val_379 2 +382 val_382 382 val_382 2 +386 val_386 386 val_386 2 +389 val_389 389 val_389 2 +399 val_399 399 val_399 2 +401 val_401 401 val_401 2 +404 val_404 404 val_404 2 +417 val_417 417 val_417 2 +418 val_418 418 val_418 2 +42 val_42 NULL NULL 2 +43 val_43 NULL NULL 2 +430 val_430 430 val_430 2 +437 val_437 437 val_437 2 +438 val_438 438 val_438 2 +44 val_44 44 val_44 2 +448 val_448 448 val_448 2 +453 val_453 453 val_453 2 +455 val_455 455 val_455 2 +459 val_459 459 val_459 2 +468 val_468 468 val_468 2 +469 val_469 469 val_469 2 +47 val_47 NULL NULL 2 +479 val_479 479 val_479 2 +480 val_480 480 val_480 2 +481 val_481 481 val_481 2 +487 val_487 487 val_487 2 +495 val_495 495 val_495 2 +496 val_496 496 val_496 2 +58 val_58 58 val_58 2 +64 val_64 64 val_64 2 +66 val_66 66 val_66 2 +78 val_78 78 val_78 2 +8 val_8 8 val_8 2 +83 val_83 83 val_83 2 +85 val_85 85 val_85 2 +87 val_87 87 val_87 2 +90 val_90 90 val_90 2 +95 val_95 95 val_95 2 +97 val_97 97 val_97 2 104 val_104 104 val_104 2 -11 val_11 11 val_11 2 +113 val_113 113 val_113 2 114 val_114 114 val_114 2 116 val_116 116 val_116 2 -118 val_118 118 val_118 2 -120 val_120 120 val_120 2 -131 val_131 131 val_131 2 -133 val_133 133 val_133 2 +119 val_119 119 val_119 2 +125 val_125 125 val_125 2 +134 val_134 134 val_134 2 +136 val_136 136 val_136 2 137 val_137 137 val_137 2 -145 val_145 145 val_145 2 -15 val_15 15 val_15 2 -150 val_150 150 val_150 2 -152 val_152 152 val_152 2 153 val_153 153 val_153 2 -155 val_155 155 val_155 2 -156 val_156 156 val_156 2 -157 val_157 157 val_157 2 -160 val_160 160 val_160 2 162 val_162 162 val_162 2 +167 val_167 167 val_167 2 168 val_168 168 val_168 2 -169 val_169 169 val_169 2 17 val_17 17 val_17 2 -170 val_170 170 val_170 2 -175 val_175 175 val_175 2 -176 val_176 176 val_176 2 178 val_178 178 val_178 2 180 val_180 180 val_180 2 -183 val_183 183 val_183 2 186 val_186 186 val_186 2 -19 val_19 19 val_19 2 -190 val_190 190 val_190 2 -192 val_192 192 val_192 2 -194 val_194 194 val_194 2 -196 val_196 196 val_196 2 -199 val_199 199 val_199 2 -20 val_20 20 val_20 2 -202 val_202 202 val_202 2 +191 val_191 191 val_191 2 +2 val_2 2 val_2 2 +200 val_200 200 val_200 2 203 val_203 203 val_203 2 -207 val_207 207 val_207 2 -213 val_213 213 val_213 2 -214 val_214 214 val_214 2 -219 val_219 219 val_219 2 -222 val_222 222 val_222 2 -223 val_223 223 val_223 2 -224 val_224 224 val_224 2 -226 val_226 226 val_226 2 -228 val_228 228 val_228 2 -233 val_233 233 val_233 2 +230 val_230 230 val_230 2 239 val_239 239 val_239 2 241 val_241 241 val_241 2 244 val_244 244 val_244 2 247 val_247 247 val_247 2 252 val_252 252 val_252 2 -255 val_255 255 val_255 2 -256 val_256 256 val_256 2 -257 val_257 257 val_257 2 -260 val_260 260 val_260 2 -266 val_266 266 val_266 2 -27 val_27 27 val_27 2 -272 val_272 272 val_272 2 +26 val_26 NULL NULL 2 +263 val_263 263 val_263 2 +265 val_265 265 val_265 2 +27 val_27 NULL NULL 2 274 val_274 274 val_274 2 -275 val_275 275 val_275 2 278 val_278 278 val_278 2 28 val_28 NULL NULL 2 -28 val_28 28 val_28 2 -280 val_280 280 val_280 2 -284 val_284 284 val_284 2 -285 val_285 285 val_285 2 +282 val_282 282 val_282 2 286 val_286 286 val_286 2 -288 val_288 288 val_288 2 -289 val_289 289 val_289 2 -296 val_296 296 val_296 2 -302 val_302 302 val_302 2 -305 val_305 305 val_305 2 306 val_306 306 val_306 2 307 val_307 307 val_307 2 -311 val_311 311 val_311 2 +309 val_309 309 val_309 2 317 val_317 317 val_317 2 318 val_318 318 val_318 2 -321 val_321 321 val_321 2 322 val_322 322 val_322 2 -323 val_323 323 val_323 2 -327 val_327 327 val_327 2 -33 val_33 NULL NULL 2 33 val_33 33 val_33 2 -331 val_331 331 val_331 2 +335 val_335 335 val_335 2 336 val_336 336 val_336 2 338 val_338 338 val_338 2 34 val_34 NULL NULL 2 -34 val_34 34 val_34 2 -348 val_348 348 val_348 2 -35 val_35 NULL NULL 2 -35 val_35 35 val_35 2 351 val_351 351 val_351 2 -360 val_360 360 val_360 2 -365 val_365 365 val_365 2 -366 val_366 366 val_366 2 +367 val_367 367 val_367 2 369 val_369 369 val_369 2 -374 val_374 374 val_374 2 -375 val_375 375 val_375 2 -377 val_377 377 val_377 2 -379 val_379 379 val_379 2 -382 val_382 382 val_382 2 -384 val_384 384 val_384 2 -389 val_389 389 val_389 2 -393 val_393 393 val_393 2 -395 val_395 395 val_395 2 +394 val_394 394 val_394 2 396 val_396 396 val_396 2 -397 val_397 397 val_397 2 -399 val_399 399 val_399 2 -400 val_400 400 val_400 2 -401 val_401 401 val_401 2 -404 val_404 404 val_404 2 -406 val_406 406 val_406 2 -407 val_407 407 val_407 2 -409 val_409 409 val_409 2 -41 val_41 NULL NULL 2 -41 val_41 41 val_41 2 -414 val_414 414 val_414 2 -417 val_417 417 val_417 2 -418 val_418 418 val_418 2 -42 val_42 NULL NULL 2 -42 val_42 42 val_42 2 +402 val_402 402 val_402 2 +419 val_419 419 val_419 2 421 val_421 421 val_421 2 -427 val_427 427 val_427 2 -430 val_430 430 val_430 2 -431 val_431 431 val_431 2 +424 val_424 424 val_424 2 435 val_435 435 val_435 2 -438 val_438 438 val_438 2 -439 val_439 439 val_439 2 -44 val_44 NULL NULL 2 -44 val_44 44 val_44 2 -443 val_443 443 val_443 2 -448 val_448 448 val_448 2 -454 val_454 454 val_454 2 -455 val_455 455 val_455 2 -459 val_459 459 val_459 2 -462 val_462 462 val_462 2 -463 val_463 463 val_463 2 -47 val_47 47 val_47 2 -470 val_470 470 val_470 2 -472 val_472 472 val_472 2 -478 val_478 478 val_478 2 -480 val_480 480 val_480 2 -481 val_481 481 val_481 2 -485 val_485 485 val_485 2 -489 val_489 489 val_489 2 -490 val_490 490 val_490 2 -491 val_491 491 val_491 2 -494 val_494 494 val_494 2 -5 val_5 5 val_5 2 +436 val_436 436 val_436 2 +446 val_446 446 val_446 2 +458 val_458 458 val_458 2 +460 val_460 460 val_460 2 +477 val_477 477 val_477 2 +482 val_482 482 val_482 2 53 val_53 53 val_53 2 57 val_57 57 val_57 2 -66 val_66 66 val_66 2 +65 val_65 65 val_65 2 69 val_69 69 val_69 2 -72 val_72 72 val_72 2 +70 val_70 70 val_70 2 74 val_74 74 val_74 2 76 val_76 76 val_76 2 -77 val_77 77 val_77 2 -78 val_78 78 val_78 2 -8 val_8 8 val_8 2 -80 val_80 80 val_80 2 84 val_84 84 val_84 2 -86 val_86 86 val_86 2 -9 val_9 9 val_9 2 -90 val_90 90 val_90 2 -26 val_26 NULL NULL 2 -30 val_30 NULL NULL 2 -37 val_37 NULL NULL 2 -0 val_0 0 val_0 2 +96 val_96 96 val_96 2 10 val_10 10 val_10 2 +100 val_100 100 val_100 2 105 val_105 105 val_105 2 -111 val_111 111 val_111 2 -113 val_113 113 val_113 2 -119 val_119 119 val_119 2 +118 val_118 118 val_118 2 12 val_12 12 val_12 2 -125 val_125 125 val_125 2 -126 val_126 126 val_126 2 -128 val_128 128 val_128 2 +120 val_120 120 val_120 2 129 val_129 129 val_129 2 -134 val_134 134 val_134 2 -136 val_136 136 val_136 2 -138 val_138 138 val_138 2 -143 val_143 143 val_143 2 +145 val_145 145 val_145 2 146 val_146 146 val_146 2 -149 val_149 149 val_149 2 -158 val_158 158 val_158 2 -163 val_163 163 val_163 2 +15 val_15 15 val_15 2 +150 val_150 150 val_150 2 +155 val_155 155 val_155 2 +157 val_157 157 val_157 2 164 val_164 164 val_164 2 -165 val_165 165 val_165 2 -166 val_166 166 val_166 2 -167 val_167 167 val_167 2 +170 val_170 170 val_170 2 172 val_172 172 val_172 2 174 val_174 174 val_174 2 177 val_177 177 val_177 2 179 val_179 179 val_179 2 -18 val_18 18 val_18 2 -181 val_181 181 val_181 2 -187 val_187 187 val_187 2 -189 val_189 189 val_189 2 -191 val_191 191 val_191 2 -193 val_193 193 val_193 2 -195 val_195 195 val_195 2 -197 val_197 197 val_197 2 -2 val_2 2 val_2 2 -200 val_200 200 val_200 2 -201 val_201 201 val_201 2 -205 val_205 205 val_205 2 +181 val_181 181 val_181 2 +19 val_19 19 val_19 2 +194 val_194 194 val_194 2 +195 val_195 195 val_195 2 208 val_208 208 val_208 2 209 val_209 209 val_209 2 -216 val_216 216 val_216 2 +213 val_213 213 val_213 2 217 val_217 217 val_217 2 -218 val_218 218 val_218 2 -221 val_221 221 val_221 2 -229 val_229 229 val_229 2 -230 val_230 230 val_230 2 -235 val_235 235 val_235 2 -237 val_237 237 val_237 2 -238 val_238 238 val_238 2 +222 val_222 222 val_222 2 +224 val_224 224 val_224 2 +233 val_233 233 val_233 2 +24 val_24 NULL NULL 2 24 val_24 24 val_24 2 -242 val_242 242 val_242 2 248 val_248 248 val_248 2 249 val_249 249 val_249 2 +256 val_256 256 val_256 2 +257 val_257 257 val_257 2 258 val_258 258 val_258 2 -26 val_26 26 val_26 2 -262 val_262 262 val_262 2 -263 val_263 263 val_263 2 -265 val_265 265 val_265 2 -27 val_27 NULL NULL 2 +260 val_260 260 val_260 2 +266 val_266 266 val_266 2 273 val_273 273 val_273 2 -277 val_277 277 val_277 2 -281 val_281 281 val_281 2 -282 val_282 282 val_282 2 -283 val_283 283 val_283 2 -287 val_287 287 val_287 2 -291 val_291 291 val_291 2 +280 val_280 280 val_280 2 +284 val_284 284 val_284 2 +288 val_288 288 val_288 2 +289 val_289 289 val_289 2 292 val_292 292 val_292 2 +296 val_296 296 val_296 2 298 val_298 298 val_298 2 30 val_30 30 val_30 2 -308 val_308 308 val_308 2 -309 val_309 309 val_309 2 -310 val_310 310 val_310 2 +302 val_302 302 val_302 2 315 val_315 315 val_315 2 316 val_316 316 val_316 2 -325 val_325 325 val_325 2 -332 val_332 332 val_332 2 -333 val_333 333 val_333 2 -335 val_335 335 val_335 2 +321 val_321 321 val_321 2 +323 val_323 323 val_323 2 339 val_339 339 val_339 2 -341 val_341 341 val_341 2 -342 val_342 342 val_342 2 344 val_344 344 val_344 2 345 val_345 345 val_345 2 -353 val_353 353 val_353 2 -356 val_356 356 val_356 2 -362 val_362 362 val_362 2 364 val_364 364 val_364 2 -367 val_367 367 val_367 2 +365 val_365 365 val_365 2 +366 val_366 366 val_366 2 368 val_368 368 val_368 2 -37 val_37 37 val_37 2 -373 val_373 373 val_373 2 +37 val_37 NULL NULL 2 +375 val_375 375 val_375 2 378 val_378 378 val_378 2 -386 val_386 386 val_386 2 -392 val_392 392 val_392 2 -394 val_394 394 val_394 2 -4 val_4 4 val_4 2 -402 val_402 402 val_402 2 -403 val_403 403 val_403 2 -411 val_411 411 val_411 2 +406 val_406 406 val_406 2 +409 val_409 409 val_409 2 +41 val_41 NULL NULL 2 +41 val_41 41 val_41 2 413 val_413 413 val_413 2 -419 val_419 419 val_419 2 -424 val_424 424 val_424 2 -429 val_429 429 val_429 2 +414 val_414 414 val_414 2 +42 val_42 42 val_42 2 43 val_43 43 val_43 2 +431 val_431 431 val_431 2 432 val_432 432 val_432 2 -436 val_436 436 val_436 2 -437 val_437 437 val_437 2 +443 val_443 443 val_443 2 444 val_444 444 val_444 2 -446 val_446 446 val_446 2 -449 val_449 449 val_449 2 -452 val_452 452 val_452 2 -453 val_453 453 val_453 2 457 val_457 457 val_457 2 -458 val_458 458 val_458 2 -460 val_460 460 val_460 2 +463 val_463 463 val_463 2 466 val_466 466 val_466 2 -467 val_467 467 val_467 2 -468 val_468 468 val_468 2 -469 val_469 469 val_469 2 -47 val_47 NULL NULL 2 +472 val_472 472 val_472 2 475 val_475 475 val_475 2 -477 val_477 477 val_477 2 -479 val_479 479 val_479 2 -482 val_482 482 val_482 2 -483 val_483 483 val_483 2 +478 val_478 478 val_478 2 484 val_484 484 val_484 2 -487 val_487 487 val_487 2 +485 val_485 485 val_485 2 492 val_492 492 val_492 2 -493 val_493 493 val_493 2 -495 val_495 495 val_495 2 -496 val_496 496 val_496 2 -497 val_497 497 val_497 2 +494 val_494 494 val_494 2 498 val_498 498 val_498 2 -51 val_51 51 val_51 2 -54 val_54 54 val_54 2 -58 val_58 58 val_58 2 -64 val_64 64 val_64 2 -65 val_65 65 val_65 2 -67 val_67 67 val_67 2 -70 val_70 70 val_70 2 +5 val_5 5 val_5 2 +80 val_80 80 val_80 2 82 val_82 82 val_82 2 -83 val_83 83 val_83 2 -85 val_85 85 val_85 2 -87 val_87 87 val_87 2 +86 val_86 86 val_86 2 92 val_92 92 val_92 2 -95 val_95 95 val_95 2 -96 val_96 96 val_96 2 -97 val_97 97 val_97 2 98 val_98 98 val_98 2 -24 val_24 NULL NULL 2 -43 val_43 NULL NULL 2 PREHOOK: query: explain select s.key2, s.value2 from ( @@ -4677,315 +4677,315 @@ from ( POSTHOOK: type: QUERY POSTHOOK: Input: default@src POSTHOOK: Output: hdfs://### HDFS PATH ### -116 val_116 +104 val_104 +105 val_105 +113 val_113 118 val_118 +12 val_12 120 val_120 -131 val_131 133 val_133 -15 val_15 -150 val_150 -152 val_152 -153 val_153 +136 val_136 155 val_155 +158 val_158 160 val_160 -169 val_169 +162 val_162 +168 val_168 +17 val_17 +170 val_170 175 val_175 -176 val_176 -178 val_178 -183 val_183 +18 val_18 +180 val_180 186 val_186 -194 val_194 -202 val_202 -203 val_203 -213 val_213 -223 val_223 +19 val_19 +197 val_197 +200 val_200 +216 val_216 +218 val_218 +222 val_222 224 val_224 -226 val_226 228 val_228 +235 val_235 +237 val_237 239 val_239 244 val_244 247 val_247 -252 val_252 -255 val_255 256 val_256 -257 val_257 -266 val_266 -272 val_272 -274 val_274 -275 val_275 +263 val_263 +273 val_273 28 val_28 -284 val_284 +283 val_283 286 val_286 -289 val_289 -296 val_296 -302 val_302 +292 val_292 306 val_306 -307 val_307 -317 val_317 -321 val_321 -323 val_323 +308 val_308 +327 val_327 33 val_33 -338 val_338 -34 val_34 -35 val_35 -360 val_360 -365 val_365 -374 val_374 -377 val_377 -393 val_393 -399 val_399 -404 val_404 -406 val_406 +348 val_348 +353 val_353 +362 val_362 +366 val_366 +396 val_396 +397 val_397 +401 val_401 409 val_409 -41 val_41 -417 val_417 -418 val_418 -42 val_42 -431 val_431 +411 val_411 +419 val_419 +427 val_427 +43 val_43 +432 val_432 +436 val_436 439 val_439 -44 val_44 443 val_443 -448 val_448 -455 val_455 -459 val_459 +453 val_453 +460 val_460 462 val_462 -463 val_463 -470 val_470 -490 val_490 -491 val_491 -494 val_494 -5 val_5 -53 val_53 -66 val_66 -72 val_72 -76 val_76 -77 val_77 -80 val_80 +47 val_47 +472 val_472 +485 val_485 +496 val_496 +54 val_54 +64 val_64 +70 val_70 +8 val_8 +83 val_83 84 val_84 +85 val_85 90 val_90 -10 val_10 -105 val_105 -111 val_111 -113 val_113 -119 val_119 -129 val_129 -136 val_136 -143 val_143 -149 val_149 -163 val_163 -167 val_167 -174 val_174 +0 val_0 +103 val_103 +114 val_114 +125 val_125 +138 val_138 +146 val_146 +150 val_150 +152 val_152 +153 val_153 +156 val_156 +157 val_157 +165 val_165 +172 val_172 +177 val_177 +179 val_179 187 val_187 -197 val_197 -2 val_2 -200 val_200 -208 val_208 -209 val_209 -216 val_216 +195 val_195 +196 val_196 217 val_217 -218 val_218 -221 val_221 -230 val_230 -258 val_258 -26 val_26 -263 val_263 -273 val_273 -277 val_277 -281 val_281 -292 val_292 -30 val_30 -316 val_316 -335 val_335 -341 val_341 -342 val_342 -344 val_344 +242 val_242 +248 val_248 +252 val_252 +265 val_265 +27 val_27 +272 val_272 +280 val_280 +291 val_291 +305 val_305 +309 val_309 +311 val_311 +315 val_315 +317 val_317 +322 val_322 +333 val_333 +34 val_34 345 val_345 -362 val_362 -367 val_367 +35 val_35 +356 val_356 +364 val_364 368 val_368 +369 val_369 37 val_37 -392 val_392 -394 val_394 +373 val_373 +377 val_377 4 val_4 +402 val_402 +404 val_404 413 val_413 -437 val_437 +42 val_42 +430 val_430 +431 val_431 444 val_444 -446 val_446 +449 val_449 452 val_452 -453 val_453 +454 val_454 457 val_457 -460 val_460 +463 val_463 466 val_466 -468 val_468 -477 val_477 -479 val_479 -483 val_483 -487 val_487 -492 val_492 -493 val_493 -498 val_498 -51 val_51 -54 val_54 -64 val_64 +470 val_470 +475 val_475 +481 val_481 +489 val_489 +491 val_491 +57 val_57 65 val_65 -67 val_67 -82 val_82 -85 val_85 -87 val_87 +66 val_66 +74 val_74 +76 val_76 +78 val_78 +9 val_9 +92 val_92 95 val_95 -96 val_96 100 val_100 -103 val_103 -104 val_104 -11 val_11 -114 val_114 -137 val_137 +119 val_119 +128 val_128 +129 val_129 145 val_145 -156 val_156 -157 val_157 -162 val_162 -168 val_168 -17 val_17 -170 val_170 -180 val_180 -19 val_19 -190 val_190 -192 val_192 -196 val_196 +167 val_167 +174 val_174 +178 val_178 +181 val_181 +193 val_193 199 val_199 20 val_20 -207 val_207 +201 val_201 +213 val_213 214 val_214 219 val_219 -222 val_222 +221 val_221 +223 val_223 +226 val_226 233 val_233 241 val_241 +249 val_249 260 val_260 -27 val_27 -278 val_278 -280 val_280 -285 val_285 +262 val_262 +277 val_277 +281 val_281 +287 val_287 288 val_288 -305 val_305 -311 val_311 -318 val_318 -322 val_322 -327 val_327 -331 val_331 +298 val_298 +302 val_302 +310 val_310 +323 val_323 336 val_336 -348 val_348 +341 val_341 +344 val_344 351 val_351 -366 val_366 -369 val_369 375 val_375 -379 val_379 382 val_382 384 val_384 -389 val_389 +393 val_393 395 val_395 -396 val_396 -397 val_397 -400 val_400 -401 val_401 -407 val_407 -414 val_414 -421 val_421 -427 val_427 -430 val_430 +399 val_399 +403 val_403 +406 val_406 +418 val_418 435 val_435 -438 val_438 -454 val_454 -47 val_47 -472 val_472 +455 val_455 +459 val_459 +477 val_477 478 val_478 -480 val_480 -481 val_481 -485 val_485 -489 val_489 -57 val_57 -69 val_69 -74 val_74 -78 val_78 -8 val_8 +479 val_479 +482 val_482 +493 val_493 +494 val_494 +495 val_495 +497 val_497 +5 val_5 +58 val_58 +67 val_67 +77 val_77 +80 val_80 86 val_86 -9 val_9 -0 val_0 -12 val_12 -125 val_125 +97 val_97 +98 val_98 +10 val_10 +11 val_11 +111 val_111 +116 val_116 126 val_126 -128 val_128 +131 val_131 134 val_134 -138 val_138 -146 val_146 -158 val_158 +137 val_137 +143 val_143 +149 val_149 +15 val_15 +163 val_163 164 val_164 -165 val_165 166 val_166 -172 val_172 -177 val_177 -179 val_179 -18 val_18 -181 val_181 +169 val_169 +176 val_176 +183 val_183 189 val_189 +190 val_190 191 val_191 -193 val_193 -195 val_195 -201 val_201 +192 val_192 +194 val_194 +2 val_2 +202 val_202 +203 val_203 205 val_205 +207 val_207 +208 val_208 +209 val_209 229 val_229 -235 val_235 -237 val_237 +230 val_230 238 val_238 24 val_24 -242 val_242 -248 val_248 -249 val_249 -262 val_262 -265 val_265 -282 val_282 -283 val_283 -287 val_287 -291 val_291 -298 val_298 -308 val_308 -309 val_309 -310 val_310 -315 val_315 +255 val_255 +257 val_257 +258 val_258 +26 val_26 +266 val_266 +274 val_274 +275 val_275 +278 val_278 +282 val_282 +284 val_284 +285 val_285 +289 val_289 +296 val_296 +30 val_30 +307 val_307 +316 val_316 +318 val_318 +321 val_321 325 val_325 +331 val_331 332 val_332 -333 val_333 +335 val_335 +338 val_338 339 val_339 -353 val_353 -356 val_356 -364 val_364 -373 val_373 +342 val_342 +360 val_360 +365 val_365 +367 val_367 +374 val_374 378 val_378 +379 val_379 386 val_386 -402 val_402 -403 val_403 -411 val_411 -419 val_419 +389 val_389 +392 val_392 +394 val_394 +400 val_400 +407 val_407 +41 val_41 +414 val_414 +417 val_417 +421 val_421 424 val_424 429 val_429 -43 val_43 -432 val_432 -436 val_436 -449 val_449 +437 val_437 +438 val_438 +44 val_44 +446 val_446 +448 val_448 458 val_458 467 val_467 +468 val_468 469 val_469 -475 val_475 -482 val_482 +480 val_480 +483 val_483 484 val_484 -495 val_495 -496 val_496 -497 val_497 -58 val_58 -70 val_70 -83 val_83 -92 val_92 -97 val_97 -98 val_98 +487 val_487 +490 val_490 +492 val_492 +498 val_498 +51 val_51 +53 val_53 +69 val_69 +72 val_72 +82 val_82 +87 val_87 +96 val_96 PREHOOK: query: create table src2 as select key, count(1) as count from src group by key PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src @@ -6630,12 +6630,12 @@ STAGE PLANS: keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized Map 4 Map Operator Tree: @@ -6684,20 +6684,20 @@ STAGE PLANS: keys: KEY._col0 (type: string), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() keys: _col0 (type: string), _col1 (type: string) mode: complete outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: bigint), _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 404 Data size: 75144 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 75888 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -6719,21 +6719,21 @@ STAGE PLANS: keys: _col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 26883 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 27492 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 309 Data size: 53766 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 54984 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string), _col1 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: string), _col1 (type: string) - Statistics: Num rows: 404 Data size: 71912 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 408 Data size: 72624 Basic stats: COMPLETE Column stats: COMPLETE Union 2 Vertex: Union 2 Union 5 @@ -7358,315 +7358,315 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: hdfs://### HDFS PATH ### -1 116 val_116 +1 104 val_104 +1 105 val_105 +1 113 val_113 1 118 val_118 +1 12 val_12 1 120 val_120 -1 131 val_131 1 133 val_133 -1 15 val_15 -1 150 val_150 -1 152 val_152 -1 153 val_153 +1 136 val_136 1 155 val_155 +1 158 val_158 1 160 val_160 -1 169 val_169 +1 162 val_162 +1 168 val_168 +1 17 val_17 +1 170 val_170 1 175 val_175 -1 176 val_176 -1 178 val_178 -1 183 val_183 +1 18 val_18 +1 180 val_180 1 186 val_186 -1 194 val_194 -1 202 val_202 -1 203 val_203 -1 213 val_213 -1 223 val_223 +1 19 val_19 +1 197 val_197 +1 200 val_200 +1 216 val_216 +1 218 val_218 +1 222 val_222 1 224 val_224 -1 226 val_226 1 228 val_228 +1 235 val_235 +1 237 val_237 1 239 val_239 1 244 val_244 1 247 val_247 -1 252 val_252 -1 255 val_255 1 256 val_256 -1 257 val_257 -1 266 val_266 -1 272 val_272 -1 274 val_274 -1 275 val_275 +1 263 val_263 +1 273 val_273 1 28 val_28 -1 284 val_284 +1 283 val_283 1 286 val_286 -1 289 val_289 -1 296 val_296 -1 302 val_302 +1 292 val_292 1 306 val_306 -1 307 val_307 -1 317 val_317 -1 321 val_321 -1 323 val_323 +1 308 val_308 +1 327 val_327 1 33 val_33 -1 338 val_338 -1 34 val_34 -1 35 val_35 -1 360 val_360 -1 365 val_365 -1 374 val_374 -1 377 val_377 -1 393 val_393 -1 399 val_399 -1 404 val_404 -1 406 val_406 +1 348 val_348 +1 353 val_353 +1 362 val_362 +1 366 val_366 +1 396 val_396 +1 397 val_397 +1 401 val_401 1 409 val_409 -1 41 val_41 -1 417 val_417 -1 418 val_418 -1 42 val_42 -1 431 val_431 +1 411 val_411 +1 419 val_419 +1 427 val_427 +1 43 val_43 +1 432 val_432 +1 436 val_436 1 439 val_439 -1 44 val_44 1 443 val_443 -1 448 val_448 -1 455 val_455 -1 459 val_459 +1 453 val_453 +1 460 val_460 1 462 val_462 -1 463 val_463 -1 470 val_470 -1 490 val_490 -1 491 val_491 -1 494 val_494 -1 5 val_5 -1 53 val_53 -1 66 val_66 -1 72 val_72 -1 76 val_76 -1 77 val_77 -1 80 val_80 +1 47 val_47 +1 472 val_472 +1 485 val_485 +1 496 val_496 +1 54 val_54 +1 64 val_64 +1 70 val_70 +1 8 val_8 +1 83 val_83 1 84 val_84 +1 85 val_85 1 90 val_90 -1 10 val_10 -1 105 val_105 -1 111 val_111 -1 113 val_113 -1 119 val_119 -1 129 val_129 -1 136 val_136 -1 143 val_143 -1 149 val_149 -1 163 val_163 -1 167 val_167 -1 174 val_174 +1 0 val_0 +1 103 val_103 +1 114 val_114 +1 125 val_125 +1 138 val_138 +1 146 val_146 +1 150 val_150 +1 152 val_152 +1 153 val_153 +1 156 val_156 +1 157 val_157 +1 165 val_165 +1 172 val_172 +1 177 val_177 +1 179 val_179 1 187 val_187 -1 197 val_197 -1 2 val_2 -1 200 val_200 -1 208 val_208 -1 209 val_209 -1 216 val_216 +1 195 val_195 +1 196 val_196 1 217 val_217 -1 218 val_218 -1 221 val_221 -1 230 val_230 -1 258 val_258 -1 26 val_26 -1 263 val_263 -1 273 val_273 -1 277 val_277 -1 281 val_281 -1 292 val_292 -1 30 val_30 -1 316 val_316 -1 335 val_335 -1 341 val_341 -1 342 val_342 -1 344 val_344 +1 242 val_242 +1 248 val_248 +1 252 val_252 +1 265 val_265 +1 27 val_27 +1 272 val_272 +1 280 val_280 +1 291 val_291 +1 305 val_305 +1 309 val_309 +1 311 val_311 +1 315 val_315 +1 317 val_317 +1 322 val_322 +1 333 val_333 +1 34 val_34 1 345 val_345 -1 362 val_362 -1 367 val_367 +1 35 val_35 +1 356 val_356 +1 364 val_364 1 368 val_368 +1 369 val_369 1 37 val_37 -1 392 val_392 -1 394 val_394 +1 373 val_373 +1 377 val_377 1 4 val_4 +1 402 val_402 +1 404 val_404 1 413 val_413 -1 437 val_437 +1 42 val_42 +1 430 val_430 +1 431 val_431 1 444 val_444 -1 446 val_446 +1 449 val_449 1 452 val_452 -1 453 val_453 +1 454 val_454 1 457 val_457 -1 460 val_460 +1 463 val_463 1 466 val_466 -1 468 val_468 -1 477 val_477 -1 479 val_479 -1 483 val_483 -1 487 val_487 -1 492 val_492 -1 493 val_493 -1 498 val_498 -1 51 val_51 -1 54 val_54 -1 64 val_64 +1 470 val_470 +1 475 val_475 +1 481 val_481 +1 489 val_489 +1 491 val_491 +1 57 val_57 1 65 val_65 -1 67 val_67 -1 82 val_82 -1 85 val_85 -1 87 val_87 +1 66 val_66 +1 74 val_74 +1 76 val_76 +1 78 val_78 +1 9 val_9 +1 92 val_92 1 95 val_95 -1 96 val_96 1 100 val_100 -1 103 val_103 -1 104 val_104 -1 11 val_11 -1 114 val_114 -1 137 val_137 +1 119 val_119 +1 128 val_128 +1 129 val_129 1 145 val_145 -1 156 val_156 -1 157 val_157 -1 162 val_162 -1 168 val_168 -1 17 val_17 -1 170 val_170 -1 180 val_180 -1 19 val_19 -1 190 val_190 -1 192 val_192 -1 196 val_196 +1 167 val_167 +1 174 val_174 +1 178 val_178 +1 181 val_181 +1 193 val_193 1 199 val_199 1 20 val_20 -1 207 val_207 +1 201 val_201 +1 213 val_213 1 214 val_214 1 219 val_219 -1 222 val_222 +1 221 val_221 +1 223 val_223 +1 226 val_226 1 233 val_233 1 241 val_241 +1 249 val_249 1 260 val_260 -1 27 val_27 -1 278 val_278 -1 280 val_280 -1 285 val_285 +1 262 val_262 +1 277 val_277 +1 281 val_281 +1 287 val_287 1 288 val_288 -1 305 val_305 -1 311 val_311 -1 318 val_318 -1 322 val_322 -1 327 val_327 -1 331 val_331 +1 298 val_298 +1 302 val_302 +1 310 val_310 +1 323 val_323 1 336 val_336 -1 348 val_348 +1 341 val_341 +1 344 val_344 1 351 val_351 -1 366 val_366 -1 369 val_369 1 375 val_375 -1 379 val_379 1 382 val_382 1 384 val_384 -1 389 val_389 +1 393 val_393 1 395 val_395 -1 396 val_396 -1 397 val_397 -1 400 val_400 -1 401 val_401 -1 407 val_407 -1 414 val_414 -1 421 val_421 -1 427 val_427 -1 430 val_430 +1 399 val_399 +1 403 val_403 +1 406 val_406 +1 418 val_418 1 435 val_435 -1 438 val_438 -1 454 val_454 -1 47 val_47 -1 472 val_472 +1 455 val_455 +1 459 val_459 +1 477 val_477 1 478 val_478 -1 480 val_480 -1 481 val_481 -1 485 val_485 -1 489 val_489 -1 57 val_57 -1 69 val_69 -1 74 val_74 -1 78 val_78 -1 8 val_8 +1 479 val_479 +1 482 val_482 +1 493 val_493 +1 494 val_494 +1 495 val_495 +1 497 val_497 +1 5 val_5 +1 58 val_58 +1 67 val_67 +1 77 val_77 +1 80 val_80 1 86 val_86 -1 9 val_9 -1 0 val_0 -1 12 val_12 -1 125 val_125 +1 97 val_97 +1 98 val_98 +1 10 val_10 +1 11 val_11 +1 111 val_111 +1 116 val_116 1 126 val_126 -1 128 val_128 +1 131 val_131 1 134 val_134 -1 138 val_138 -1 146 val_146 -1 158 val_158 +1 137 val_137 +1 143 val_143 +1 149 val_149 +1 15 val_15 +1 163 val_163 1 164 val_164 -1 165 val_165 1 166 val_166 -1 172 val_172 -1 177 val_177 -1 179 val_179 -1 18 val_18 -1 181 val_181 +1 169 val_169 +1 176 val_176 +1 183 val_183 1 189 val_189 +1 190 val_190 1 191 val_191 -1 193 val_193 -1 195 val_195 -1 201 val_201 +1 192 val_192 +1 194 val_194 +1 2 val_2 +1 202 val_202 +1 203 val_203 1 205 val_205 +1 207 val_207 +1 208 val_208 +1 209 val_209 1 229 val_229 -1 235 val_235 -1 237 val_237 +1 230 val_230 1 238 val_238 1 24 val_24 -1 242 val_242 -1 248 val_248 -1 249 val_249 -1 262 val_262 -1 265 val_265 +1 255 val_255 +1 257 val_257 +1 258 val_258 +1 26 val_26 +1 266 val_266 +1 274 val_274 +1 275 val_275 +1 278 val_278 1 282 val_282 -1 283 val_283 -1 287 val_287 -1 291 val_291 -1 298 val_298 -1 308 val_308 -1 309 val_309 -1 310 val_310 -1 315 val_315 +1 284 val_284 +1 285 val_285 +1 289 val_289 +1 296 val_296 +1 30 val_30 +1 307 val_307 +1 316 val_316 +1 318 val_318 +1 321 val_321 1 325 val_325 +1 331 val_331 1 332 val_332 -1 333 val_333 +1 335 val_335 +1 338 val_338 1 339 val_339 -1 353 val_353 -1 356 val_356 -1 364 val_364 -1 373 val_373 +1 342 val_342 +1 360 val_360 +1 365 val_365 +1 367 val_367 +1 374 val_374 1 378 val_378 +1 379 val_379 1 386 val_386 -1 402 val_402 -1 403 val_403 -1 411 val_411 -1 419 val_419 +1 389 val_389 +1 392 val_392 +1 394 val_394 +1 400 val_400 +1 407 val_407 +1 41 val_41 +1 414 val_414 +1 417 val_417 +1 421 val_421 1 424 val_424 1 429 val_429 -1 43 val_43 -1 432 val_432 -1 436 val_436 -1 449 val_449 +1 437 val_437 +1 438 val_438 +1 44 val_44 +1 446 val_446 +1 448 val_448 1 458 val_458 1 467 val_467 +1 468 val_468 1 469 val_469 -1 475 val_475 -1 482 val_482 +1 480 val_480 +1 483 val_483 1 484 val_484 -1 495 val_495 -1 496 val_496 -1 497 val_497 -1 58 val_58 -1 70 val_70 -1 83 val_83 -1 92 val_92 -1 97 val_97 -1 98 val_98 +1 487 val_487 +1 490 val_490 +1 492 val_492 +1 498 val_498 +1 51 val_51 +1 53 val_53 +1 69 val_69 +1 72 val_72 +1 82 val_82 +1 87 val_87 +1 96 val_96 PREHOOK: query: SELECT count(1) as counts, key, @@ -7717,315 +7717,315 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 POSTHOOK: Output: hdfs://### HDFS PATH ### -1 116 val_116 +1 104 val_104 +1 105 val_105 +1 113 val_113 1 118 val_118 +1 12 val_12 1 120 val_120 -1 131 val_131 1 133 val_133 -1 15 val_15 -1 150 val_150 -1 152 val_152 -1 153 val_153 +1 136 val_136 1 155 val_155 +1 158 val_158 1 160 val_160 -1 169 val_169 +1 162 val_162 +1 168 val_168 +1 17 val_17 +1 170 val_170 1 175 val_175 -1 176 val_176 -1 178 val_178 -1 183 val_183 +1 18 val_18 +1 180 val_180 1 186 val_186 -1 194 val_194 -1 202 val_202 -1 203 val_203 -1 213 val_213 -1 223 val_223 +1 19 val_19 +1 197 val_197 +1 200 val_200 +1 216 val_216 +1 218 val_218 +1 222 val_222 1 224 val_224 -1 226 val_226 1 228 val_228 +1 235 val_235 +1 237 val_237 1 239 val_239 1 244 val_244 1 247 val_247 -1 252 val_252 -1 255 val_255 1 256 val_256 -1 257 val_257 -1 266 val_266 -1 272 val_272 -1 274 val_274 -1 275 val_275 +1 263 val_263 +1 273 val_273 1 28 val_28 -1 284 val_284 +1 283 val_283 1 286 val_286 -1 289 val_289 -1 296 val_296 -1 302 val_302 +1 292 val_292 1 306 val_306 -1 307 val_307 -1 317 val_317 -1 321 val_321 -1 323 val_323 +1 308 val_308 +1 327 val_327 1 33 val_33 -1 338 val_338 -1 34 val_34 -1 35 val_35 -1 360 val_360 -1 365 val_365 -1 374 val_374 -1 377 val_377 -1 393 val_393 -1 399 val_399 -1 404 val_404 -1 406 val_406 +1 348 val_348 +1 353 val_353 +1 362 val_362 +1 366 val_366 +1 396 val_396 +1 397 val_397 +1 401 val_401 1 409 val_409 -1 41 val_41 -1 417 val_417 -1 418 val_418 -1 42 val_42 -1 431 val_431 +1 411 val_411 +1 419 val_419 +1 427 val_427 +1 43 val_43 +1 432 val_432 +1 436 val_436 1 439 val_439 -1 44 val_44 1 443 val_443 -1 448 val_448 -1 455 val_455 -1 459 val_459 +1 453 val_453 +1 460 val_460 1 462 val_462 -1 463 val_463 -1 470 val_470 -1 490 val_490 -1 491 val_491 -1 494 val_494 -1 5 val_5 -1 53 val_53 -1 66 val_66 -1 72 val_72 -1 76 val_76 -1 77 val_77 -1 80 val_80 +1 47 val_47 +1 472 val_472 +1 485 val_485 +1 496 val_496 +1 54 val_54 +1 64 val_64 +1 70 val_70 +1 8 val_8 +1 83 val_83 1 84 val_84 +1 85 val_85 1 90 val_90 -1 10 val_10 -1 105 val_105 -1 111 val_111 -1 113 val_113 -1 119 val_119 -1 129 val_129 -1 136 val_136 -1 143 val_143 -1 149 val_149 -1 163 val_163 -1 167 val_167 -1 174 val_174 +1 0 val_0 +1 103 val_103 +1 114 val_114 +1 125 val_125 +1 138 val_138 +1 146 val_146 +1 150 val_150 +1 152 val_152 +1 153 val_153 +1 156 val_156 +1 157 val_157 +1 165 val_165 +1 172 val_172 +1 177 val_177 +1 179 val_179 1 187 val_187 -1 197 val_197 -1 2 val_2 -1 200 val_200 -1 208 val_208 -1 209 val_209 -1 216 val_216 +1 195 val_195 +1 196 val_196 1 217 val_217 -1 218 val_218 -1 221 val_221 -1 230 val_230 -1 258 val_258 -1 26 val_26 -1 263 val_263 -1 273 val_273 -1 277 val_277 -1 281 val_281 -1 292 val_292 -1 30 val_30 -1 316 val_316 -1 335 val_335 -1 341 val_341 -1 342 val_342 -1 344 val_344 +1 242 val_242 +1 248 val_248 +1 252 val_252 +1 265 val_265 +1 27 val_27 +1 272 val_272 +1 280 val_280 +1 291 val_291 +1 305 val_305 +1 309 val_309 +1 311 val_311 +1 315 val_315 +1 317 val_317 +1 322 val_322 +1 333 val_333 +1 34 val_34 1 345 val_345 -1 362 val_362 -1 367 val_367 +1 35 val_35 +1 356 val_356 +1 364 val_364 1 368 val_368 +1 369 val_369 1 37 val_37 -1 392 val_392 -1 394 val_394 +1 373 val_373 +1 377 val_377 1 4 val_4 +1 402 val_402 +1 404 val_404 1 413 val_413 -1 437 val_437 +1 42 val_42 +1 430 val_430 +1 431 val_431 1 444 val_444 -1 446 val_446 +1 449 val_449 1 452 val_452 -1 453 val_453 +1 454 val_454 1 457 val_457 -1 460 val_460 +1 463 val_463 1 466 val_466 -1 468 val_468 -1 477 val_477 -1 479 val_479 -1 483 val_483 -1 487 val_487 -1 492 val_492 -1 493 val_493 -1 498 val_498 -1 51 val_51 -1 54 val_54 -1 64 val_64 +1 470 val_470 +1 475 val_475 +1 481 val_481 +1 489 val_489 +1 491 val_491 +1 57 val_57 1 65 val_65 -1 67 val_67 -1 82 val_82 -1 85 val_85 -1 87 val_87 +1 66 val_66 +1 74 val_74 +1 76 val_76 +1 78 val_78 +1 9 val_9 +1 92 val_92 1 95 val_95 -1 96 val_96 1 100 val_100 -1 103 val_103 -1 104 val_104 -1 11 val_11 -1 114 val_114 -1 137 val_137 +1 119 val_119 +1 128 val_128 +1 129 val_129 1 145 val_145 -1 156 val_156 -1 157 val_157 -1 162 val_162 -1 168 val_168 -1 17 val_17 -1 170 val_170 -1 180 val_180 -1 19 val_19 -1 190 val_190 -1 192 val_192 -1 196 val_196 +1 167 val_167 +1 174 val_174 +1 178 val_178 +1 181 val_181 +1 193 val_193 1 199 val_199 1 20 val_20 -1 207 val_207 +1 201 val_201 +1 213 val_213 1 214 val_214 1 219 val_219 -1 222 val_222 +1 221 val_221 +1 223 val_223 +1 226 val_226 1 233 val_233 1 241 val_241 +1 249 val_249 1 260 val_260 -1 27 val_27 -1 278 val_278 -1 280 val_280 -1 285 val_285 +1 262 val_262 +1 277 val_277 +1 281 val_281 +1 287 val_287 1 288 val_288 -1 305 val_305 -1 311 val_311 -1 318 val_318 -1 322 val_322 -1 327 val_327 -1 331 val_331 +1 298 val_298 +1 302 val_302 +1 310 val_310 +1 323 val_323 1 336 val_336 -1 348 val_348 +1 341 val_341 +1 344 val_344 1 351 val_351 -1 366 val_366 -1 369 val_369 1 375 val_375 -1 379 val_379 1 382 val_382 1 384 val_384 -1 389 val_389 +1 393 val_393 1 395 val_395 -1 396 val_396 -1 397 val_397 -1 400 val_400 -1 401 val_401 -1 407 val_407 -1 414 val_414 -1 421 val_421 -1 427 val_427 -1 430 val_430 +1 399 val_399 +1 403 val_403 +1 406 val_406 +1 418 val_418 1 435 val_435 -1 438 val_438 -1 454 val_454 -1 47 val_47 -1 472 val_472 +1 455 val_455 +1 459 val_459 +1 477 val_477 1 478 val_478 -1 480 val_480 -1 481 val_481 -1 485 val_485 -1 489 val_489 -1 57 val_57 -1 69 val_69 -1 74 val_74 -1 78 val_78 -1 8 val_8 +1 479 val_479 +1 482 val_482 +1 493 val_493 +1 494 val_494 +1 495 val_495 +1 497 val_497 +1 5 val_5 +1 58 val_58 +1 67 val_67 +1 77 val_77 +1 80 val_80 1 86 val_86 -1 9 val_9 -1 0 val_0 -1 12 val_12 -1 125 val_125 +1 97 val_97 +1 98 val_98 +1 10 val_10 +1 11 val_11 +1 111 val_111 +1 116 val_116 1 126 val_126 -1 128 val_128 +1 131 val_131 1 134 val_134 -1 138 val_138 -1 146 val_146 -1 158 val_158 +1 137 val_137 +1 143 val_143 +1 149 val_149 +1 15 val_15 +1 163 val_163 1 164 val_164 -1 165 val_165 1 166 val_166 -1 172 val_172 -1 177 val_177 -1 179 val_179 -1 18 val_18 -1 181 val_181 +1 169 val_169 +1 176 val_176 +1 183 val_183 1 189 val_189 +1 190 val_190 1 191 val_191 -1 193 val_193 -1 195 val_195 -1 201 val_201 +1 192 val_192 +1 194 val_194 +1 2 val_2 +1 202 val_202 +1 203 val_203 1 205 val_205 +1 207 val_207 +1 208 val_208 +1 209 val_209 1 229 val_229 -1 235 val_235 -1 237 val_237 +1 230 val_230 1 238 val_238 1 24 val_24 -1 242 val_242 -1 248 val_248 -1 249 val_249 -1 262 val_262 -1 265 val_265 +1 255 val_255 +1 257 val_257 +1 258 val_258 +1 26 val_26 +1 266 val_266 +1 274 val_274 +1 275 val_275 +1 278 val_278 1 282 val_282 -1 283 val_283 -1 287 val_287 -1 291 val_291 -1 298 val_298 -1 308 val_308 -1 309 val_309 -1 310 val_310 -1 315 val_315 +1 284 val_284 +1 285 val_285 +1 289 val_289 +1 296 val_296 +1 30 val_30 +1 307 val_307 +1 316 val_316 +1 318 val_318 +1 321 val_321 1 325 val_325 +1 331 val_331 1 332 val_332 -1 333 val_333 +1 335 val_335 +1 338 val_338 1 339 val_339 -1 353 val_353 -1 356 val_356 -1 364 val_364 -1 373 val_373 +1 342 val_342 +1 360 val_360 +1 365 val_365 +1 367 val_367 +1 374 val_374 1 378 val_378 +1 379 val_379 1 386 val_386 -1 402 val_402 -1 403 val_403 -1 411 val_411 -1 419 val_419 +1 389 val_389 +1 392 val_392 +1 394 val_394 +1 400 val_400 +1 407 val_407 +1 41 val_41 +1 414 val_414 +1 417 val_417 +1 421 val_421 1 424 val_424 1 429 val_429 -1 43 val_43 -1 432 val_432 -1 436 val_436 -1 449 val_449 +1 437 val_437 +1 438 val_438 +1 44 val_44 +1 446 val_446 +1 448 val_448 1 458 val_458 1 467 val_467 +1 468 val_468 1 469 val_469 -1 475 val_475 -1 482 val_482 +1 480 val_480 +1 483 val_483 1 484 val_484 -1 495 val_495 -1 496 val_496 -1 497 val_497 -1 58 val_58 -1 70 val_70 -1 83 val_83 -1 92 val_92 -1 97 val_97 -1 98 val_98 +1 487 val_487 +1 490 val_490 +1 492 val_492 +1 498 val_498 +1 51 val_51 +1 53 val_53 +1 69 val_69 +1 72 val_72 +1 82 val_82 +1 87 val_87 +1 96 val_96 PREHOOK: query: create table jackson_sev_same as select * from src PREHOOK: type: CREATETABLE_AS_SELECT PREHOOK: Input: default@src @@ -9060,10 +9060,10 @@ POSTHOOK: query: select * from union_out POSTHOOK: type: QUERY POSTHOOK: Input: default@union_out POSTHOOK: Output: hdfs://### HDFS PATH ### -2 1 -4 3 +4 +2 PREHOOK: query: create table union_subq_union30(key int, value string) PREHOOK: type: CREATETABLE PREHOOK: Output: database:default @@ -11909,16 +11909,16 @@ POSTHOOK: Input: default@src10_2 POSTHOOK: Input: default@src10_3 POSTHOOK: Input: default@src10_4 POSTHOOK: Output: hdfs://### HDFS PATH ### -255 val_255 409 val_409 +165 val_165 27 val_27 -278 val_278 311 val_311 86 val_86 -165 val_165 +98 val_98 238 val_238 +255 val_255 +278 val_278 484 val_484 -98 val_98 PREHOOK: query: explain SELECT * FROM ( SELECT sub1.key,sub1.value FROM (SELECT * FROM src10_1) sub1 JOIN (SELECT * FROM src10_2) sub0 ON (sub0.key = sub1.key) @@ -12112,13 +12112,13 @@ POSTHOOK: Input: default@src10_2 POSTHOOK: Input: default@src10_3 POSTHOOK: Input: default@src10_4 POSTHOOK: Output: hdfs://### HDFS PATH ### -255 val_255 409 val_409 +165 val_165 27 val_27 -278 val_278 311 val_311 86 val_86 -165 val_165 +98 val_98 238 val_238 +255 val_255 +278 val_278 484 val_484 -98 val_98 diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out index cb5b912..6f010f9 100644 --- a/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out +++ b/ql/src/test/results/clientpositive/llap/unionDistinct_3.q.out @@ -1780,10 +1780,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 66 Data size: 35904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 35360 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 66 Data size: 35904 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 65 Data size: 35360 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -1929,12 +1929,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 10 @@ -1950,12 +1950,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 11 @@ -1971,12 +1971,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map 12 @@ -1992,12 +1992,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized, llap LLAP IO: no inputs Map 13 @@ -2013,12 +2013,12 @@ STAGE PLANS: keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: vectorized, llap LLAP IO: no inputs Reducer 3 @@ -2028,17 +2028,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Reducer 5 Execution mode: vectorized, llap Reduce Operator Tree: @@ -2046,17 +2046,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 309 Data size: 56856 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 316 Data size: 58144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Reducer 7 Execution mode: vectorized, llap Reduce Operator Tree: @@ -2064,17 +2064,17 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 160 Data size: 29440 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 163 Data size: 29992 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Reducer 9 Execution mode: vectorized, llap Reduce Operator Tree: @@ -2082,16 +2082,16 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 85 Data size: 15640 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16008 Basic stats: COMPLETE Column stats: PARTIAL Group By Operator aggregations: count(1) keys: _col0 (type: string) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 85 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16704 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 85 Data size: 16320 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 87 Data size: 16704 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out b/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out index 4f80cbf..66b6bd8 100644 --- a/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out +++ b/ql/src/test/results/clientpositive/llap/union_fast_stats.q.out @@ -179,7 +179,7 @@ Table Parameters: bucketing_version 2 numFiles 3 numRows 5 - rawDataSize 1069 + rawDataSize 1300 totalSize 4033 #### A masked pattern was here #### @@ -513,7 +513,7 @@ Table Parameters: numFiles 1 numRows 5 rawDataSize 1069 - totalSize 3245 + totalSize 3247 #### A masked pattern was here #### # Storage Information @@ -566,7 +566,7 @@ Table Parameters: numFiles 1 numRows 15 rawDataSize 3320 - totalSize 3245 + totalSize 3247 #### A masked pattern was here #### # Storage Information @@ -631,7 +631,7 @@ Table Parameters: numFiles 2 numRows 20 rawDataSize 4389 - totalSize 4618 + totalSize 4620 #### A masked pattern was here #### # Storage Information diff --git a/ql/src/test/results/clientpositive/llap/union_top_level.q.out b/ql/src/test/results/clientpositive/llap/union_top_level.q.out index f2bc8c8..0085342 100644 --- a/ql/src/test/results/clientpositive/llap/union_top_level.q.out +++ b/ql/src/test/results/clientpositive/llap/union_top_level.q.out @@ -274,15 +274,15 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Reducer 3 @@ -291,7 +291,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE @@ -312,15 +312,15 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col1, _col2 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col2 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: string) sort order: + - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: string) Reducer 6 @@ -329,7 +329,7 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 809 Data size: 144002 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 791 Data size: 140798 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Statistics: Num rows: 10 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE diff --git a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out index 861ae9a..58f697e 100644 --- a/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_cast_constant.q.out @@ -154,7 +154,7 @@ STAGE PLANS: keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 256 Data size: 39936 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -163,7 +163,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 256 Data size: 39936 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: bigint), _col2 (type: bigint), _col3 (type: double), _col4 (type: bigint), _col5 (type: decimal(12,0)), _col6 (type: bigint) Execution mode: vectorized, llap @@ -199,7 +199,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 - Statistics: Num rows: 256 Data size: 39936 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 40092 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), (_col1 / _col2) (type: double), (_col3 / _col4) (type: double), CAST( (_col5 / _col6) AS decimal(6,4)) (type: decimal(6,4)) outputColumnNames: _col0, _col1, _col2, _col3 @@ -208,7 +208,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 7, 8, 11] selectExpressions: LongColDivideLongColumn(col 1:bigint, col 2:bigint) -> 7:double, DoubleColDivideLongColumn(col 3:double, col 4:bigint) -> 8:double, CastDecimalToDecimal(col 10:decimal(32,20))(children: DecimalColDivideDecimalColumn(col 5:decimal(12,0), col 9:decimal(19,0))(children: CastLongToDecimal(col 6:bigint) -> 9:decimal(19,0)) -> 10:decimal(32,20)) -> 11:decimal(6,4) - Statistics: Num rows: 256 Data size: 33792 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -216,7 +216,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 256 Data size: 33792 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: decimal(6,4)) Reducer 3 @@ -235,7 +235,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3] - Statistics: Num rows: 256 Data size: 33792 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 257 Data size: 33924 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out index 90086ea..42fcdbd 100644 --- a/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_count_distinct.q.out @@ -1274,7 +1274,7 @@ STAGE PLANS: keys: ws_order_number (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 169 Data size: 676 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -1283,7 +1283,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 169 Data size: 676 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -1315,7 +1315,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 169 Data size: 676 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 170 Data size: 680 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index 98e6e54..b99a4ac 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out @@ -155,10 +155,10 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2, _col3, _col5 input vertices: 1 Reducer 6 - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Filter Operator predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 500 Data size: 98620 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 500 Data size: 98584 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: string), _col1 (type: string) outputColumnNames: _col0, _col1 diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out index dc8f47e..b269f9b 100644 --- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join.q.out @@ -51,7 +51,7 @@ STAGE PLANS: outputColumnNames: _col0 input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 87720 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 86492 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 @@ -60,7 +60,7 @@ STAGE PLANS: 1 _col0 (type: tinyint) input vertices: 1 Map 4 - Statistics: Num rows: 2423154 Data size: 19385232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2393450 Data size: 19147600 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash diff --git a/ql/src/test/results/clientpositive/llap/vector_llap_text_1.q.out b/ql/src/test/results/clientpositive/llap/vector_llap_text_1.q.out index d5d8e53..4f6b8b4 100644 --- a/ql/src/test/results/clientpositive/llap/vector_llap_text_1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_llap_text_1.q.out @@ -233,7 +233,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col3 input vertices: 0 Map 1 - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 @@ -241,7 +241,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 4, 1] - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int), _col1 (type: string), _col2 (type: string) sort order: +++ @@ -251,7 +251,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [] - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Execution mode: vectorized, llap LLAP IO: no inputs @@ -295,7 +295,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 391 Data size: 72726 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 399 Data size: 74214 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 10 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out index 7be4d7d..7e439fa 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_limit.q.out @@ -897,7 +897,7 @@ STAGE PLANS: keys: cdouble (type: double) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -908,7 +908,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [1] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -956,7 +956,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: bigint), _col0 (type: double) sort order: ++ @@ -966,7 +966,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.3 Reducer 3 Execution mode: vectorized, llap @@ -991,7 +991,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [1, 0] - Statistics: Num rows: 4159 Data size: 58120 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 4127 Data size: 57672 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out index a6a0371..67665bb 100644 --- a/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorization_short_regress.q.out @@ -2207,7 +2207,7 @@ STAGE PLANS: keys: _col0 (type: smallint) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1141 Data size: 76436 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 77440 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + @@ -2216,7 +2216,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 76436 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 77440 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: bigint), _col8 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2251,7 +2251,7 @@ STAGE PLANS: keys: KEY._col0 (type: smallint) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8 - Statistics: Num rows: 1141 Data size: 76436 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 77440 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: smallint), (UDFToInteger(_col0) % -75) (type: int), power(((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END), 0.5) (type: double), (-1.389 / CAST( _col0 AS decimal(5,0))) (type: decimal(10,9)), _col4 (type: bigint), (UDFToDouble((UDFToInteger(_col0) % -75)) / UDFToDouble(_col4)) (type: double), (- (UDFToInteger(_col0) % -75)) (type: int), ((_col5 - ((_col6 * _col6) / _col7)) / _col7) (type: double), (- (- (UDFToInteger(_col0) % -75))) (type: int), _col8 (type: bigint), (_col8 - -89010L) (type: bigint) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10 @@ -2260,7 +2260,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 9, 10, 16, 4, 18, 19, 17, 14, 8, 20] selectExpressions: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 9:int, FuncPowerDoubleToDouble(col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 14:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 11:double)(children: DoubleColDivideLongColumn(col 10:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 10:double) -> 11:double) -> 10:double, IfExprNullCondExpr(col 12:boolean, null, col 13:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 12:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 13:bigint) -> 14:bigint) -> 11:double) -> 10:double, DecimalScalarDivideDecimalColumn(val -1.389, col 15:decimal(5,0))(children: CastLongToDecimal(col 0:smallint) -> 15:decimal(5,0)) -> 16:decimal(10,9), DoubleColDivideDoubleColumn(col 11:double, col 17:double)(children: CastLongToDouble(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 14:int) -> 11:double, CastLongToDouble(col 4:bigint) -> 17:double) -> 18:double, LongColUnaryMinus(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 14:int) -> 19:int, DoubleColDivideLongColumn(col 11:double, col 7:bigint)(children: DoubleColSubtractDoubleColumn(col 5:double, col 17:double)(children: DoubleColDivideLongColumn(col 11:double, col 7:bigint)(children: DoubleColMultiplyDoubleColumn(col 6:double, col 6:double) -> 11:double) -> 17:double) -> 11:double) -> 17:double, LongColUnaryMinus(col 20:int)(children: LongColUnaryMinus(col 14:int)(children: LongColModuloLongScalar(col 0:int, val -75)(children: col 0:smallint) -> 14:int) -> 20:int) -> 14:int, LongColSubtractLongScalar(col 8:bigint, val -89010) -> 20:bigint - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: smallint), _col1 (type: int), _col2 (type: double), _col3 (type: decimal(10,9)), _col4 (type: bigint), _col5 (type: double), _col6 (type: int), _col7 (type: double), _col8 (type: int), _col9 (type: bigint), _col10 (type: bigint) sort order: +++++++++++ @@ -2268,7 +2268,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE TopN Hash Memory Usage: 0.1 Reducer 3 Execution mode: vectorized, llap @@ -2286,7 +2286,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10] - Statistics: Num rows: 1141 Data size: 199664 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1156 Data size: 202288 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 20 Limit Vectorization: @@ -2484,7 +2484,7 @@ STAGE PLANS: keys: _col0 (type: double) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1136 Data size: 52232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2493,7 +2493,7 @@ STAGE PLANS: className: VectorReduceSinkMultiKeyOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 52232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: bigint), _col4 (type: bigint), _col5 (type: double) Execution mode: vectorized, llap LLAP IO: all inputs @@ -2528,7 +2528,7 @@ STAGE PLANS: keys: KEY._col0 (type: double) mode: mergepartial outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 1136 Data size: 52232 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 51824 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END) (type: double), (2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), _col4 (type: bigint), ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D) (type: double), ((- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) * ((2563.58D * ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) + -5638.15D)) (type: double), _col5 (type: double), ((_col1 - ((_col2 * _col2) / _col3)) / _col3) (type: double), (_col0 - (- ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END))) (type: double), power(((_col1 - ((_col2 * _col2) / _col3)) / _col3), 0.5) (type: double), (_col0 + ((_col1 - ((_col2 * _col2) / _col3)) / CASE WHEN ((_col3 = 1L)) THEN (null) ELSE ((_col3 - 1)) END)) (type: double), (_col0 * 762.0D) (type: double), _col2 (type: double), (-863.257D % (_col0 * 762.0D)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 @@ -2537,7 +2537,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 7, 6, 11, 4, 17, 20, 5, 23, 26, 14, 29, 30, 2, 34] selectExpressions: DoubleColDivideLongColumn(col 6:double, col 10:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 7:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 7:double) -> 6:double, IfExprNullCondExpr(col 8:boolean, null, col 9:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 8:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 9:bigint) -> 10:bigint) -> 7:double, DoubleScalarMultiplyDoubleColumn(val 2563.58, col 11:double)(children: DoubleColDivideLongColumn(col 6:double, col 13:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 11:double)(children: DoubleColDivideLongColumn(col 6:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 6:double) -> 11:double) -> 6:double, IfExprNullCondExpr(col 10:boolean, null, col 12:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 10:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 12:bigint) -> 13:bigint) -> 11:double) -> 6:double, DoubleColUnaryMinus(col 14:double)(children: DoubleColDivideLongColumn(col 11:double, col 16:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 14:double)(children: DoubleColDivideLongColumn(col 11:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 11:double) -> 14:double) -> 11:double, IfExprNullCondExpr(col 13:boolean, null, col 15:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 13:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 15:bigint) -> 16:bigint) -> 14:double) -> 11:double, DoubleColAddDoubleScalar(col 14:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 17:double)(children: DoubleColDivideLongColumn(col 14:double, col 19:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 17:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 17:double) -> 14:double, IfExprNullCondExpr(col 16:boolean, null, col 18:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 16:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 18:bigint) -> 19:bigint) -> 17:double) -> 14:double) -> 17:double, DoubleColMultiplyDoubleColumn(col 14:double, col 23:double)(children: DoubleColUnaryMinus(col 20:double)(children: DoubleColDivideLongColumn(col 14:double, col 22:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 20:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 20:double) -> 14:double, IfExprNullCondExpr(col 19:boolean, null, col 21:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 19:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 21:bigint) -> 22:bigint) -> 20:double) -> 14:double, DoubleColAddDoubleScalar(col 20:double, val -5638.15)(children: DoubleScalarMultiplyDoubleColumn(val 2563.58, col 23:double)(children: DoubleColDivideLongColumn(col 20:double, col 25:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 23:double)(children: DoubleColDivideLongColumn(col 20:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 20:double) -> 23:double) -> 20:double, IfExprNullCondExpr(col 22:boolean, null, col 24:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 22:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 24:bigint) -> 25:bigint) -> 23:double) -> 20:double) -> 23:double) -> 20:double, DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 23:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 23:double) -> 14:double) -> 23:double, DoubleColSubtractDoubleColumn(col 0:double, col 14:double)(children: DoubleColUnaryMinus(col 26:double)(children: DoubleColDivideLongColumn(col 14:double, col 28:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 26:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 26:double) -> 14:double, IfExprNullCondExpr(col 25:boolean, null, col 27:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 25:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 27:bigint) -> 28:bigint) -> 26:double) -> 14:double) -> 26:double, FuncPowerDoubleToDouble(col 29:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 29:double)(children: DoubleColDivideLongColumn(col 14:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 14:double) -> 29:double) -> 14:double) -> 29:double) -> 14:double, DoubleColAddDoubleColumn(col 0:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 32:bigint)(children: DoubleColSubtractDoubleColumn(col 1:double, col 30:double)(children: DoubleColDivideLongColumn(col 29:double, col 3:bigint)(children: DoubleColMultiplyDoubleColumn(col 2:double, col 2:double) -> 29:double) -> 30:double) -> 29:double, IfExprNullCondExpr(col 28:boolean, null, col 31:bigint)(children: LongColEqualLongScalar(col 3:bigint, val 1) -> 28:boolean, LongColSubtractLongScalar(col 3:bigint, val 1) -> 31:bigint) -> 32:bigint) -> 30:double) -> 29:double, DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 30:double, DoubleScalarModuloDoubleColumn(val -863.257, col 33:double)(children: DoubleColMultiplyDoubleScalar(col 0:double, val 762.0) -> 33:double) -> 34:double - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: double) sort order: + @@ -2545,7 +2545,7 @@ STAGE PLANS: className: VectorReduceSinkObjectHashOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col1 (type: double), _col2 (type: double), _col3 (type: double), _col4 (type: bigint), _col5 (type: double), _col6 (type: double), _col7 (type: double), _col8 (type: double), _col9 (type: double), _col10 (type: double), _col11 (type: double), _col12 (type: double), _col13 (type: double), _col14 (type: double) Reducer 3 Execution mode: vectorized, llap @@ -2563,13 +2563,13 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 13] - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false File Sink Vectorization: className: VectorFileSinkOperator native: false - Statistics: Num rows: 1136 Data size: 143112 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1127 Data size: 141984 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_context.q.out b/ql/src/test/results/clientpositive/llap/vectorized_context.q.out index 8907c7f..3edc12b 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_context.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_context.q.out @@ -133,7 +133,7 @@ STAGE PLANS: outputColumnNames: _col0, _col2 input vertices: 1 Map 2 - Statistics: Num rows: 6124 Data size: 49032 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6062 Data size: 48288 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -143,17 +143,17 @@ STAGE PLANS: outputColumnNames: _col2, _col5 input vertices: 1 Map 3 - Statistics: Num rows: 6173 Data size: 625962 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6049 Data size: 612818 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col5 (type: string), _col2 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6173 Data size: 625962 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6049 Data size: 612818 Basic stats: COMPLETE Column stats: COMPLETE Limit Number of rows: 100 - Statistics: Num rows: 100 Data size: 10208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 100 Data size: 10200 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false - Statistics: Num rows: 100 Data size: 10208 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 100 Data size: 10200 Basic stats: COMPLETE Column stats: COMPLETE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat diff --git a/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out b/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out index 9198ac2..de3c6e6 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_distinct_gby.q.out @@ -209,7 +209,7 @@ STAGE PLANS: keys: cint (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 6030 Data size: 18008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6105 Data size: 18232 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col0 (type: int) sort order: + @@ -220,7 +220,7 @@ STAGE PLANS: native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumnNums: [] - Statistics: Num rows: 6030 Data size: 18008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6105 Data size: 18232 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -265,7 +265,7 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 6030 Data size: 18008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6105 Data size: 18232 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), UDFToDouble(_col0) (type: double), (UDFToDouble(_col0) * UDFToDouble(_col0)) (type: double) outputColumnNames: _col0, _col1, _col2 @@ -274,7 +274,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [0, 1, 4] selectExpressions: CastLongToDouble(col 0:int) -> 1:double, DoubleColMultiplyDoubleColumn(col 2:double, col 3:double)(children: CastLongToDouble(col 0:int) -> 2:double, CastLongToDouble(col 0:int) -> 3:double) -> 4:double - Statistics: Num rows: 6030 Data size: 18008 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 6105 Data size: 18232 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col0), count(_col0), sum(_col2), sum(_col1) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out index 8abd234..b30fbf3 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out @@ -58,7 +58,7 @@ STAGE PLANS: outputColumnNames: _col0, _col1 input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 @@ -67,7 +67,7 @@ STAGE PLANS: native: true projectedOutputColumnNums: [2, 2, 13] selectExpressions: LongColAddLongColumn(col 2:int, col 2:int) -> 13:int - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) Group By Vectorization: diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index 80e1cab..f876656 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -54,7 +54,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 1284939 Data size: 10267240 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1268540 Data size: 10136048 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: sum(_col1) mode: hash diff --git a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out index 498f9b9..690f0ae 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out @@ -118,11 +118,11 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 18694 Data size: 130960 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 129120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), sum(_col2), count(_col2) mode: hash diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 74f52f5..a696961 100644 --- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -536,24 +536,24 @@ STAGE PLANS: Stage: Stage-9 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_1:src + $hdt$_1:src1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_1:src + $hdt$_1:src1 TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) Stage: Stage-7 @@ -573,9 +573,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false @@ -590,24 +590,24 @@ STAGE PLANS: Stage: Stage-8 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_2:src1 + $hdt$_2:src Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_2:src1 + $hdt$_2:src TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Stage: Stage-3 @@ -618,7 +618,7 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out index c5af083..7b6870d 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out @@ -4335,38 +4335,38 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 _col1 (type: string) + 1 _col1 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work Map 3 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col1 (type: string) + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4391,9 +4391,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -4401,14 +4401,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 input vertices: 1 Map 3 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -4445,38 +4445,38 @@ STAGE PLANS: Map 2 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 _col1 (type: string) + 1 _col1 (type: string) Execution mode: vectorized Local Work: Map Reduce Local Work Map 3 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col1 (type: string) - 1 _col1 (type: string) + 0 _col0 (type: int) + 1 _col0 (type: int) Execution mode: vectorized Local Work: Map Reduce Local Work @@ -4501,9 +4501,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 input vertices: 1 Map 2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE @@ -4511,14 +4511,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 input vertices: 1 Map 3 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out index 0d977cd..6e03634 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out @@ -188,16 +188,12 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Execution mode: vectorized Map 4 Map Operator Tree: @@ -207,15 +203,11 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 5 Map Operator Tree: @@ -225,16 +217,12 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: key (type: int) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -242,8 +230,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 key (type: int) + 1 key (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -259,11 +247,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 1 value (type: string) + outputColumnNames: _col0, _col12 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col12 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -304,16 +292,12 @@ STAGE PLANS: Filter Operator predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: value (type: string) Execution mode: vectorized Map 4 Map Operator Tree: @@ -323,15 +307,11 @@ STAGE PLANS: Filter Operator predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + Reduce Output Operator + key expressions: key (type: int) + sort order: + + Map-reduce partition columns: key (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map 5 Map Operator Tree: @@ -341,16 +321,12 @@ STAGE PLANS: Filter Operator predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + Reduce Output Operator + key expressions: value (type: string) + sort order: + + Map-reduce partition columns: value (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: key (type: int) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -358,8 +334,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) + 0 key (type: int) + 1 key (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -375,11 +351,11 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 1 value (type: string) + outputColumnNames: _col0, _col12 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col12 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -1906,48 +1882,48 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Execution mode: vectorized Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Execution mode: vectorized Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -1955,28 +1931,28 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -2023,48 +1999,48 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: int) Execution mode: vectorized Map 4 Map Operator Tree: TableScan - alias: c + alias: b Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int) - outputColumnNames: _col0 + expressions: key (type: int), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: int) + key expressions: _col1 (type: string) sort order: + - Map-reduce partition columns: _col0 (type: int) + Map-reduce partition columns: _col1 (type: string) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: int) Execution mode: vectorized Map 5 Map Operator Tree: TableScan - alias: b + alias: c Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: int), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: int) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) Execution mode: vectorized Reducer 2 Reduce Operator Tree: @@ -2072,28 +2048,28 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: int) - 1 _col0 (type: int) - outputColumnNames: _col0, _col1 + 0 _col1 (type: string) + 1 _col1 (type: string) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: int) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) + value expressions: _col2 (type: int) Reducer 3 Reduce Operator Tree: Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col0, _col3 + 0 _col0 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col0, _col2 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: int), _col3 (type: int) + expressions: _col0 (type: int), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE File Output Operator diff --git a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out index b5a3e87..b453d39 100644 --- a/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out +++ b/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out @@ -488,26 +488,25 @@ JOIN src y ON (x.key = y.key) JOIN src1 z ON (x.key = z.key) POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-4 is a root stage - Stage-3 depends on stages: Stage-4 + Stage-3 is a root stage Stage-1 depends on stages: Stage-3 Stage-0 depends on stages: Stage-1 Stage-2 depends on stages: Stage-0 STAGE PLANS: - Stage: Stage-4 + Stage: Stage-3 Spark #### A masked pattern was here #### Vertices: - Map 2 + Map 1 Map Operator Tree: TableScan - alias: z + alias: x Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: (key is not null and value is not null) (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) @@ -517,7 +516,8 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - Position of Big Table: 0 + 2 _col0 (type: string) + Position of Big Table: 2 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -573,42 +573,27 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src1 [$hdt$_3:z] - - Stage: Stage-3 - Spark -#### A masked pattern was here #### - Vertices: - Map 1 + /src1 [$hdt$_2:x] + Map 2 Map Operator Tree: TableScan - alias: x + alias: z Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 + Spark HashTable Sink Operator keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col3 - input vertices: - 1 Map 2 - Position of Big Table: 0 - Statistics: Num rows: 27 Data size: 210 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - Position of Big Table: 1 + 2 _col0 (type: string) + Position of Big Table: 2 Execution mode: vectorized Local Work: Map Reduce Local Work @@ -664,24 +649,24 @@ STAGE PLANS: name: default.src1 name: default.src1 Truncated Path -> Alias: - /src1 [$hdt$_2:x] + /src1 [$hdt$_3:z] Map 4 Map Operator Tree: TableScan - alias: y + alias: w Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: value (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Position of Big Table: 0 Execution mode: vectorized @@ -739,7 +724,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_0:y] + /src [$hdt$_0:w] Stage: Stage-1 Spark @@ -748,49 +733,52 @@ STAGE PLANS: Map 3 Map Operator Tree: TableScan - alias: w + alias: y Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) - outputColumnNames: _col0 + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 + Inner Join 0 to 2 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3 + 2 _col0 (type: string) + outputColumnNames: _col0, _col1, _col3, _col5 input vertices: 0 Map 1 - Position of Big Table: 1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + 1 Map 2 + Position of Big Table: 2 + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col3, _col6 + outputColumnNames: _col0, _col3, _col5 input vertices: 1 Map 4 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col3 (type: string), _col6 (type: string) + expressions: _col0 (type: string), _col3 (type: string), _col5 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -873,7 +861,7 @@ STAGE PLANS: name: default.src name: default.src Truncated Path -> Alias: - /src [$hdt$_1:w] + /src [$hdt$_1:y] Stage: Stage-0 Move Operator diff --git a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out index ec632a6..fff2f31 100644 --- a/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/spark/mapjoin_mapjoin.q.out @@ -566,18 +566,18 @@ STAGE PLANS: Map 5 Map Operator Tree: TableScan - alias: src1 + alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: key is not null (type: boolean) + predicate: value is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: key (type: string) + expressions: value (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) Execution mode: vectorized Local Work: @@ -603,22 +603,22 @@ STAGE PLANS: outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: string) Execution mode: vectorized Map 4 Map Operator Tree: TableScan - alias: src + alias: src1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: value is not null (type: boolean) + predicate: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: value (type: string) + expressions: key (type: string) outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator @@ -635,15 +635,15 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col1, _col2 Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string) + 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 input vertices: diff --git a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out index 4a36dd4..4975300 100644 --- a/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/spark/spark_explainuser_1.q.out @@ -1693,9 +1693,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_19] - Select Operator [SEL_18] (rows=366 width=178) + Select Operator [SEL_18] (rows=365 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_17] (rows=366 width=179) + Filter Operator [FIL_17] (rows=365 width=179) predicate:_col3 is null Join Operator [JOIN_16] (rows=500 width=179) Output:["_col0","_col1","_col3"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col1","1":"_col0"} @@ -1758,9 +1758,9 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_18] - Select Operator [SEL_17] (rows=183 width=178) + Select Operator [SEL_17] (rows=185 width=178) Output:["_col0","_col1"] - Filter Operator [FIL_16] (rows=183 width=179) + Filter Operator [FIL_16] (rows=185 width=179) predicate:_col4 is null Join Operator [JOIN_15] (rows=250 width=179) Output:["_col0","_col1","_col4"],condition map:[{"":"{\"type\":\"Left Outer\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} @@ -1834,7 +1834,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -1886,7 +1886,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0, _col1","1":"_col0, _col1"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -1928,7 +1928,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_12] - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -2049,16 +2049,16 @@ Stage-0 <-Reducer 3 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_27] PartitionCols:_col2 - Filter Operator [FIL_15] (rows=66 width=186) + Filter Operator [FIL_15] (rows=65 width=186) predicate:_col2 is not null - Group By Operator [GBY_14] (rows=66 width=186) + Group By Operator [GBY_14] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count(VALUE._col0)"],keys:KEY._col0, KEY._col1 <-Reducer 2 [GROUP] GROUP [RS_13] PartitionCols:_col0, _col1 - Group By Operator [GBY_12] (rows=66 width=186) + Group By Operator [GBY_12] (rows=65 width=186) Output:["_col0","_col1","_col2"],aggregations:["count()"],keys:_col0, _col1 - Join Operator [JOIN_10] (rows=133 width=178) + Join Operator [JOIN_10] (rows=131 width=178) Output:["_col0","_col1"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -2660,7 +2660,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_8] (rows=40 width=86) + Join Operator [JOIN_8] (rows=39 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -2721,7 +2721,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_8] (rows=40 width=86) + Join Operator [JOIN_8] (rows=39 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -2781,7 +2781,7 @@ Stage-0 PartitionCols:_col0 Group By Operator [GBY_10] (rows=16 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Map Join Operator [MAPJOIN_22] (rows=40 width=86) + Map Join Operator [MAPJOIN_22] (rows=39 width=86) Conds:SEL_5._col0=SEL_5._col0(Inner),Output:["_col0"] <-Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] @@ -2833,16 +2833,16 @@ Stage-0 GROUP [RS_18] Group By Operator [GBY_17] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_15] (rows=10 width=94) + Select Operator [SEL_15] (rows=9 width=94) Output:["_col0","_col1"] - Group By Operator [GBY_14] (rows=10 width=94) + Group By Operator [GBY_14] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count(VALUE._col0)"],keys:KEY._col0 <-Reducer 2 [GROUP] GROUP [RS_13] PartitionCols:_col0 - Group By Operator [GBY_12] (rows=10 width=94) + Group By Operator [GBY_12] (rows=9 width=94) Output:["_col0","_col1"],aggregations:["count()"],keys:_col0 - Join Operator [JOIN_10] (rows=20 width=86) + Join Operator [JOIN_10] (rows=19 width=86) Output:["_col0"],condition map:[{"":"{\"type\":\"Left Semi\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_8] @@ -5241,9 +5241,9 @@ Stage-2 Reducer 2 File Output Operator [FS_11] table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) + Select Operator [SEL_9] (rows=791 width=95) Output:["_col0","_col1"] - Join Operator [JOIN_8] (rows=809 width=178) + Join Operator [JOIN_8] (rows=791 width=178) Output:["_col0","_col2"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] @@ -5267,7 +5267,7 @@ Stage-2 Map 4 File Output Operator [FS_11] table:{"name:":"default.dest_j1"} - Select Operator [SEL_9] (rows=809 width=95) + Select Operator [SEL_9] (rows=791 width=95) Output:["_col0","_col1"] Map Join Operator [MAPJOIN_16] Conds:TS_14.reducesinkkey0=TS_14.reducesinkkey0(Inner),Output:["_col0","_col2"] @@ -5522,7 +5522,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_10] - Join Operator [JOIN_8] (rows=809 width=356) + Join Operator [JOIN_8] (rows=791 width=356) Output:["_col0","_col1","_col2","_col3"],condition map:[{"":"{\"type\":\"Inner\",\"left\":0,\"right\":1}"}],keys:{"0":"_col0","1":"_col0"} <-Map 1 [PARTITION-LEVEL SORT] PARTITION-LEVEL SORT [RS_6] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out index e7966cb..f3ef206 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_1.q.out @@ -251,7 +251,7 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=309/309 width=95) + Group By Operator [GBY_3] (rows=316/309 width=95) Output:["_col0","_col1"],aggregations:["count(KEY._col0)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_2] @@ -298,7 +298,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=267/0 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=262/0 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -347,7 +347,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=267/1019 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=262/1019 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -451,9 +451,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_10] - Select Operator [SEL_9] (rows=809/1028 width=178) + Select Operator [SEL_9] (rows=791/1028 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_15] (rows=809/1028 width=178) + Merge Join Operator [MERGEJOIN_15] (rows=791/1028 width=178) Conds:RS_6._col0=RS_7._col0(Inner),Output:["_col0","_col2"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -513,9 +513,9 @@ Stage-0 Stage-1 Reducer 2 File Output Operator [FS_9] - Transform Operator [SCR_8] (rows=809/1028 width=178) + Transform Operator [SCR_8] (rows=791/1028 width=178) command:cat - Merge Join Operator [MERGEJOIN_14] (rows=809/1028 width=178) + Merge Join Operator [MERGEJOIN_14] (rows=791/1028 width=178) Conds:RS_3.key=RS_5.key(Inner),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_3] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out index b2cfb06..f7cfd06 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_3.q.out @@ -847,9 +847,9 @@ Stage-0 Stage-1 Map 2 vectorized File Output Operator [FS_34] - Select Operator [SEL_33] (rows=391/480 width=186) + Select Operator [SEL_33] (rows=399/480 width=186) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_32] (rows=391/480 width=186) + Map Join Operator [MAPJOIN_32] (rows=399/480 width=186) BucketMapJoin:true,Conds:RS_29._col0=SEL_31._col0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col3"] <-Map 1 [CUSTOM_EDGE] vectorized MULTICAST [RS_29] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out index 5c17512..9d14557 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_4.q.out @@ -44,11 +44,11 @@ Stage-0 Stage-1 Reducer 3 File Output Operator [FS_12] - Select Operator [SEL_11] (rows=2076/10 width=553) + Select Operator [SEL_11] (rows=2048/10 width=552) Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_17] (rows=2076/10 width=553) + Merge Join Operator [MERGEJOIN_17] (rows=2048/10 width=552) Conds:RS_6._col2=RS_7._col2(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7","_col8","_col9","_col10","_col11","_col12","_col13","_col14","_col15","_col16","_col17","_col18","_col19","_col20","_col21","_col22","_col23"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -143,7 +143,7 @@ Stage-0 Output:["_col0"],aggregations:["count()"] <-Reducer 2 [CUSTOM_SIMPLE_EDGE] PARTITION_ONLY_SHUFFLE [RS_10] - Merge Join Operator [MERGEJOIN_18] (rows=2076/10 width=8) + Merge Join Operator [MERGEJOIN_18] (rows=2048/10 width=8) Conds:RS_6._col0=RS_7._col0(Inner) <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] @@ -232,16 +232,16 @@ Stage-0 Stage-1 Reducer 4 File Output Operator [FS_15] - Select Operator [SEL_14] (rows=623/5 width=11) + Select Operator [SEL_14] (rows=631/5 width=11) Output:["_col0","_col1"] <-Reducer 3 [SIMPLE_EDGE] SHUFFLE [RS_13] - Group By Operator [GBY_11] (rows=623/5 width=11) + Group By Operator [GBY_11] (rows=631/5 width=11) Output:["_col0","_col1"],aggregations:["count()"],keys:KEY._col0 <-Reducer 2 [SIMPLE_EDGE] SHUFFLE [RS_10] PartitionCols:_col0 - Merge Join Operator [MERGEJOIN_20] (rows=2076/10 width=3) + Merge Join Operator [MERGEJOIN_20] (rows=2048/10 width=3) Conds:RS_6._col1=RS_7._col0(Inner),Output:["_col0"] <-Map 1 [SIMPLE_EDGE] SHUFFLE [RS_6] diff --git a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out index 8add8c0..c3b7da3 100644 --- a/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out +++ b/ql/src/test/results/clientpositive/tez/explainanalyze_5.q.out @@ -114,9 +114,9 @@ Stage-3 <-Reducer 4 [CUSTOM_SIMPLE_EDGE] File Output Operator [FS_19] table:{"name:":"default.src_multi2"} - Select Operator [SEL_18] (rows=849/508 width=178) + Select Operator [SEL_18] (rows=830/508 width=178) Output:["_col0","_col1"] - Merge Join Operator [MERGEJOIN_26] (rows=849/508 width=178) + Merge Join Operator [MERGEJOIN_26] (rows=830/508 width=178) Conds:RS_15._col0=RS_16._col0(Inner),Output:["_col0","_col3"] <-Map 7 [SIMPLE_EDGE] SHUFFLE [RS_16] @@ -154,7 +154,7 @@ Stage-3 TableScan [TS_3] (rows=25/25 width=175) Output:["key","value"] PARTITION_ONLY_SHUFFLE [RS_2] - Select Operator [SEL_1] (rows=849/508 width=178) + Select Operator [SEL_1] (rows=830/508 width=178) Output:["key","value"] Please refer to the previous Select Operator [SEL_18] diff --git a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out index 6f15c01..4ee60a4 100644 --- a/ql/src/test/results/clientpositive/tez/explainuser_3.q.out +++ b/ql/src/test/results/clientpositive/tez/explainuser_3.q.out @@ -675,9 +675,9 @@ Stage-0 Stage-1 Map 2 vectorized File Output Operator [FS_34] - Select Operator [SEL_33] (rows=391 width=186) + Select Operator [SEL_33] (rows=399 width=186) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_32] (rows=391 width=186) + Map Join Operator [MAPJOIN_32] (rows=399 width=186) BucketMapJoin:true,Conds:RS_29._col0=SEL_31._col0(Inner),HybridGraceHashJoin:true,Output:["_col0","_col1","_col3"] <-Map 1 [CUSTOM_EDGE] vectorized MULTICAST [RS_29] diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out index db2d3c8..910a812 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_1.q.out @@ -56,7 +56,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -175,7 +175,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -293,7 +293,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -408,7 +408,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 18694 Data size: 149552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 18464 Data size: 147712 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -521,7 +521,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -630,7 +630,7 @@ STAGE PLANS: 1 _col0 (type: int) input vertices: 1 Map 3 - Statistics: Num rows: 25044 Data size: 200352 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 24737 Data size: 197896 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out index 3bacb4a..a3a77f9 100644 --- a/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out +++ b/ql/src/test/results/clientpositive/tez/hybridgrace_hashjoin_2.q.out @@ -72,7 +72,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -200,7 +200,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -343,7 +343,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -492,7 +492,7 @@ STAGE PLANS: 0 Map 1 2 Map 4 3 Map 5 - Statistics: Num rows: 1694 Data size: 13552 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 1584 Data size: 12672 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -671,7 +671,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -729,7 +729,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -915,7 +915,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 6 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 250 Data size: 2000 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -974,7 +974,7 @@ STAGE PLANS: input vertices: 0 Map 7 2 Map 10 - Statistics: Num rows: 261 Data size: 2088 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 265 Data size: 2120 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -1157,7 +1157,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 @@ -1169,7 +1169,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count() mode: hash @@ -1347,7 +1347,7 @@ STAGE PLANS: input vertices: 0 Map 1 2 Map 4 - Statistics: Num rows: 20 Data size: 1780 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 19 Data size: 1691 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Map Join Operator condition map: @@ -1360,7 +1360,7 @@ STAGE PLANS: input vertices: 1 Map 5 2 Map 6 - Statistics: Num rows: 204 Data size: 1632 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 196 Data size: 1568 Basic stats: COMPLETE Column stats: COMPLETE HybridGraceHashJoin: true Group By Operator aggregations: count() diff --git a/ql/src/test/results/clientpositive/tez/tez-tag.q.out b/ql/src/test/results/clientpositive/tez/tez-tag.q.out index 9f6e5d5..36f30aa 100644 --- a/ql/src/test/results/clientpositive/tez/tez-tag.q.out +++ b/ql/src/test/results/clientpositive/tez/tez-tag.q.out @@ -190,7 +190,7 @@ Stage-0 PARTITION_ONLY_SHUFFLE [RS_17] Group By Operator [GBY_16] (rows=1 width=8) Output:["_col0"],aggregations:["count()"] - Merge Join Operator [MERGEJOIN_30] (rows=63 width=8) + Merge Join Operator [MERGEJOIN_30] (rows=64 width=8) Conds:RS_12._col0=RS_13._col0(Inner) <-Map 6 [SIMPLE_EDGE] SHUFFLE [RS_13] diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java index 4e4dfb7..b630fa3 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/NumDistinctValueEstimatorFactory.java @@ -25,6 +25,7 @@ import org.apache.hadoop.hive.common.ndv.fm.FMSketch; import org.apache.hadoop.hive.common.ndv.fm.FMSketchUtils; import org.apache.hadoop.hive.common.ndv.hll.HyperLogLog; +import org.apache.hadoop.hive.common.ndv.hll.HyperLogLogUtils; public class NumDistinctValueEstimatorFactory { @@ -44,7 +45,7 @@ public static NumDistinctValueEstimator getNumDistinctValueEstimator(byte[] buf) if (isFMSketch(buf)) { return FMSketchUtils.deserializeFM(buf); } else { - return HyperLogLog.builder().build().deserialize(buf); + return HyperLogLogUtils.deserializeHLL(buf); } } catch (IOException e) { throw new RuntimeException(e); @@ -56,7 +57,7 @@ public static NumDistinctValueEstimator getEmptyNumDistinctValueEstimator( if (n instanceof FMSketch) { return new FMSketch(((FMSketch) n).getNumBitVectors()); } else { - return HyperLogLog.builder().build(); + return HyperLogLog.builder().setSizeOptimized().build(); } } @@ -65,7 +66,7 @@ public static NumDistinctValueEstimator getEmptyNumDistinctValueEstimator(String if ("fm".equals(func.toLowerCase())) { return new FMSketch(numBitVectors); } else if ("hll".equals(func.toLowerCase())) { - return HyperLogLog.builder().build(); + return HyperLogLog.builder().setSizeOptimized().build(); } else { throw new RuntimeException("Can not recognize " + func); } diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java index 12897fc..422bfbe 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLDenseRegister.java @@ -62,6 +62,31 @@ public boolean add(long hashcode) { return set(registerIdx, (byte) lr); } + // this is a lossy invert of the function above, which produces a hashcode + // which collides with the current winner of the register (we lose all higher + // bits, but we get all bits useful for lesser p-bit options) + + // +-------------|-------------+ + // |xxxx100000000|1000000000000| (lr=9 + idx=1024) + // +-------------|-------------+ + // \ + // +---------------|-----------+ + // |xxxx10000000010|00000000000| (lr=2 + idx=0) + // +---------------|-----------+ + + // This shows the relevant bits of the original hash value + // and how the conversion is moving bits from the index value + // over to the leading zero computation + + public void extractLowBitsTo(HLLRegister dest) { + for (int idx = 0; idx < register.length; idx++) { + byte lr = register[idx]; // this can be a max of 65, never > 127 + if (lr != 0) { + dest.add((long) ((1 << (p + lr - 1)) | idx)); + } + } + } + public boolean set(int idx, byte value) { boolean updated = false; if (idx < register.length && value > register[idx]) { diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java index 82085dd..deaca9d 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HLLSparseRegister.java @@ -19,6 +19,7 @@ package org.apache.hadoop.hive.common.ndv.hll; import java.util.Map; +import java.util.Map.Entry; import java.util.TreeMap; public class HLLSparseRegister implements HLLRegister { @@ -199,6 +200,18 @@ public boolean set(int key, byte value) { return sparseMap; } + // this is effectively the same as the dense register impl. + public void extractLowBitsTo(HLLRegister dest) { + for (Entry entry : sparseMap.entrySet()) { + int idx = entry.getKey(); + byte lr = entry.getValue(); // this can be a max of 65, never > 127 + if (lr != 0) { + // should be a no-op for sparse + dest.add((long) ((1 << (p + lr - 1)) | idx)); + } + } + } + public int getP() { return p; } diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java index 8bdb47b..ec33691 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLog.java @@ -18,10 +18,8 @@ package org.apache.hadoop.hive.common.ndv.hll; -import java.io.ByteArrayInputStream; import java.io.ByteArrayOutputStream; import java.io.IOException; -import java.io.InputStream; import java.nio.ByteBuffer; import java.nio.charset.Charset; import java.util.Map; @@ -163,6 +161,13 @@ public HyperLogLogBuilder setNumRegisterIndexBits(int b) { return this; } + public HyperLogLogBuilder setSizeOptimized() { + // allowing this to be increased via config breaks the merge impl + // p=10 = ~1kb per vector or smaller + this.numRegisterIndexBits = 10; + return this; + } + public HyperLogLogBuilder setEncoding(EncodingType enc) { this.encoding = enc; return this; @@ -440,12 +445,23 @@ public void setHLLDenseRegister(byte[] reg) { * @throws IllegalArgumentException */ public void merge(HyperLogLog hll) { - if (p != hll.p || chosenHashBits != hll.chosenHashBits) { + if (chosenHashBits != hll.chosenHashBits) { throw new IllegalArgumentException( "HyperLogLog cannot be merged as either p or hashbits are different. Current: " + toString() + " Provided: " + hll.toString()); } + if (p > hll.p) { + throw new IllegalArgumentException( + "HyperLogLog cannot merge a smaller p into a larger one : " + + toString() + " Provided: " + hll.toString()); + } + + if (p != hll.p) { + // invariant: p > hll.p + hll = hll.squash(p); + } + EncodingType otherEncoding = hll.getEncoding(); if (encoding.equals(EncodingType.SPARSE) && otherEncoding.equals(EncodingType.SPARSE)) { @@ -473,7 +489,37 @@ public void merge(HyperLogLog hll) { } /** - * Converts sparse to dense hll register + * Reduces the accuracy of the HLL provided to a smaller size + * @param p0 + * - new p size for the new HyperLogLog (smaller or no change) + * @return reduced (or same) HyperLogLog instance + */ + public HyperLogLog squash(final int p0) { + if (p0 > p) { + throw new IllegalArgumentException( + "HyperLogLog cannot be be squashed to be bigger. Current: " + + toString() + " Provided: " + p0); + } + + if (p0 == p) { + return this; + } + + final HyperLogLog hll = new HyperLogLogBuilder() + .setNumRegisterIndexBits(p0).setEncoding(EncodingType.DENSE) + .enableNoBias(noBias).build(); + final HLLDenseRegister result = hll.denseRegister; + + if (encoding == EncodingType.SPARSE) { + sparseRegister.extractLowBitsTo(result); + } else if (encoding == EncodingType.DENSE) { + denseRegister.extractLowBitsTo(result); + } + return hll; + } + + /** + * Converts sparse to dense hll register. * @param sparseRegister * - sparse register to be converted * @return converted dense register @@ -585,14 +631,7 @@ public void reset() { @Override public NumDistinctValueEstimator deserialize(byte[] buf) { - InputStream is = new ByteArrayInputStream(buf); - try { - HyperLogLog result = HyperLogLogUtils.deserializeHLL(is); - is.close(); - return result; - } catch (IOException e) { - throw new RuntimeException(e); - } + return HyperLogLogUtils.deserializeHLL(buf); } @Override diff --git a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java index 4e6510b..aeba2e9 100644 --- a/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java +++ b/standalone-metastore/src/main/java/org/apache/hadoop/hive/common/ndv/hll/HyperLogLogUtils.java @@ -18,6 +18,7 @@ package org.apache.hadoop.hive.common.ndv.hll; +import java.io.ByteArrayInputStream; import java.io.EOFException; import java.io.IOException; import java.io.InputStream; @@ -126,7 +127,7 @@ public static void serializeHLL(OutputStream out, HyperLogLog hll) throws IOExce } /** - * Refer serializeHLL() for format of serialization. This funtions + * Refer serializeHLL() for format of serialization. This function * deserializes the serialized hyperloglogs * @param in * - input stream @@ -198,6 +199,22 @@ public static HyperLogLog deserializeHLL(InputStream in) throws IOException { return result; } + /** + * This function deserializes the serialized hyperloglogs from a byte array. + * @param buf - to deserialize + * @return HyperLogLog + */ + public static HyperLogLog deserializeHLL(final byte[] buf) { + InputStream is = new ByteArrayInputStream(buf); // TODO: use faster non-sync inputstream + try { + HyperLogLog result = deserializeHLL(is); + is.close(); + return result; + } catch (IOException e) { + throw new RuntimeException(e); + } + } + private static void bitpackHLLRegister(OutputStream out, byte[] register, int bitWidth) throws IOException { int bitsLeft = 8; diff --git a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java index 617d9c3..e014fb5 100644 --- a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java +++ b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLog.java @@ -37,14 +37,18 @@ public void testHLLDenseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.DENSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.DENSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.DENSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; + double delta4 = threshold * (4*size) / 100; assertEquals((double) size, (double) hll.count(), delta); assertEquals((double) size, (double) hll2.count(), delta); @@ -63,8 +67,13 @@ public void testHLLDenseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match + // valid merge -- register set size gets bigger (also 4k items hll.merge(hll4); + assertEquals((double) 4 * size, (double) hll.count(), delta4); + assertEquals(EncodingType.DENSE, hll.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -74,14 +83,18 @@ public void testHLLSparseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 500; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; + double delta4 = threshold * (4*size) / 100; assertEquals((double) size, (double) hll.count(), delta); assertEquals((double) size, (double) hll2.count(), delta); @@ -100,8 +113,13 @@ public void testHLLSparseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.SPARSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match + // valid merge -- register set size gets bigger & dense automatically hll.merge(hll4); + assertEquals((double) 4 * size, (double) hll.count(), delta4); + assertEquals(EncodingType.DENSE, hll.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -111,11 +129,14 @@ public void testHLLSparseDenseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.DENSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.DENSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.DENSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -137,8 +158,13 @@ public void testHLLSparseDenseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll2 to DENSE + hll2.merge(hll4); + assertEquals((double) 2 * size, (double) hll2.count(), delta); + assertEquals(EncodingType.DENSE, hll2.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test(expected = IllegalArgumentException.class) @@ -148,11 +174,14 @@ public void testHLLDenseSparseMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -174,8 +203,14 @@ public void testHLLDenseSparseMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll3 to DENSE + hll3.merge(hll4); + assertEquals((double) 2 * size, (double) hll3.count(), delta); + assertEquals(EncodingType.DENSE, hll3.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); + } @Test(expected = IllegalArgumentException.class) @@ -185,11 +220,14 @@ public void testHLLSparseOverflowMerge() { HyperLogLog hll3 = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).build(); HyperLogLog hll4 = HyperLogLog.builder().setNumRegisterIndexBits(16) .setEncoding(EncodingType.SPARSE).build(); + HyperLogLog hll5 = HyperLogLog.builder().setNumRegisterIndexBits(12) + .setEncoding(EncodingType.SPARSE).build(); int size = 1000; for (int i = 0; i < size; i++) { hll.addLong(i); hll2.addLong(size + i); hll3.addLong(2 * size + i); + hll4.addLong(3 * size + i); } double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; double delta = threshold * size / 100; @@ -211,8 +249,13 @@ public void testHLLSparseOverflowMerge() { assertEquals((double) 3 * size, (double) hll.count(), delta); assertEquals(EncodingType.DENSE, hll.getEncoding()); - // invalid merge -- register set size doesn't match - hll.merge(hll4); + // merge should convert hll2 to DENSE + hll2.merge(hll4); + assertEquals((double) 2 * size, (double) hll2.count(), delta); + assertEquals(EncodingType.DENSE, hll2.getEncoding()); + + // invalid merge -- smaller register merge to bigger + hll.merge(hll5); } @Test @@ -227,4 +270,69 @@ public void testHLLSparseMoreRegisterBits() { double delta = threshold * size / 100; assertEquals((double) size, (double) hll.count(), delta); } + + @Test + public void testHLLSquash() { + + int[] sizes = new int[] { 500, 1000, 2300, 4096}; + int minBits = 9; + for (final int size : sizes) { + + HyperLogLog hlls[] = new HyperLogLog[16]; + for (int k = minBits; k < hlls.length; k++) { + final HyperLogLog hll = HyperLogLog.builder() + .setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(k).build(); + for (int i = 0; i < size; i++) { + hll.addLong(i); + } + hlls[k] = hll; + } + + for (int k = minBits; k < hlls.length; k++) { + for (int j = k + 1; j < hlls.length; j++) { + final HyperLogLog large = hlls[j]; + final HyperLogLog small = hlls[k]; + final HyperLogLog mush = large + .squash(small.getNumRegisterIndexBits()); + assertEquals(small.count(), mush.count(), 0); + double delta = Math.ceil(small.getStandardError()*size); + assertEquals((double) size, (double) mush.count(), delta); + } + } + } + } + + @Test + public void testHLLDenseDenseSquash() { + HyperLogLog p14HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(14).build(); + HyperLogLog p10HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(10).build(); + int size = 1_000_000; + for (int i = 0; i < size; i++) { + p14HLL.addLong(i); + } + + for (int i = 0; i < 10_000; i++) { + p10HLL.addLong(i); + } + + p14HLL.squash(p10HLL.getNumRegisterIndexBits()); + assertEquals((double) size, p14HLL.count(), longRangeTolerance * size / 100.0); + } + + @Test + public void testHLLSparseDenseSquash() { + HyperLogLog p14HLL = HyperLogLog.builder().setEncoding(EncodingType.SPARSE).setNumRegisterIndexBits(14).build(); + HyperLogLog p10HLL = HyperLogLog.builder().setEncoding(EncodingType.DENSE).setNumRegisterIndexBits(10).build(); + int size = 2000; + for (int i = 0; i < size; i++) { + p14HLL.addLong(i); + } + + for (int i = 0; i < 10_000; i++) { + p10HLL.addLong(i); + } + + p14HLL.squash(p10HLL.getNumRegisterIndexBits()); + assertEquals((double) size, p14HLL.count(), longRangeTolerance * size / 100.0); + } } diff --git a/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java new file mode 100644 index 0000000..2007c6f --- /dev/null +++ b/standalone-metastore/src/test/java/org/apache/hadoop/hive/common/ndv/hll/TestHyperLogLogMerge.java @@ -0,0 +1,147 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor license agreements. See the NOTICE file + * distributed with this work for additional information + * regarding copyright ownership. The ASF licenses this file + * to you under the Apache License, Version 2.0 (the + * "License"); you may not use this file except in compliance + * with the License. You may obtain a copy of the License at + * + * http://www.apache.org/licenses/LICENSE-2.0 + * + * Unless required by applicable law or agreed to in writing, software + * distributed under the License is distributed on an "AS IS" BASIS, + * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. + * See the License for the specific language governing permissions and + * limitations under the License. + */ +package org.apache.hadoop.hive.common.ndv.hll; + +import static org.junit.Assert.assertEquals; + +import java.util.Arrays; +import java.util.Collection; + +import org.junit.Test; +import org.junit.runner.RunWith; +import org.junit.runners.Parameterized; + +@RunWith(Parameterized.class) +public class TestHyperLogLogMerge { + // 5% tolerance for estimated count + private float longRangeTolerance = 5.0f; + private float shortRangeTolerance = 2.0f; + + int size; + + @Parameterized.Parameters + public static Collection data() { + return Arrays.asList(new Object[][] { + { 1_000 }, { 10_000 }, { 100_000 }, { 1_000_000 }, { 10_000_000 } + // { 100_000_000 }, { 1_000_000_000 } 1B passed but is super slow + }); + } + + public TestHyperLogLogMerge(int size) { + this.size = size; + } + + @Test + public void testHLLMergeDisjoint() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = size; i < 2 * size; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = 2 * size; + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + @Test + public void testHLLMerge25PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.75 * size); + int end = (int) (size * 1.75); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.75 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + @Test + public void testHLLMerge50PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.5 * size); + int end = (int) (size * 1.5); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.5 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + + @Test + public void testHLLMerge75PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + int start = (int) (0.25 * size); + int end = (int) (size * 1.25); + for (int i = start; i < end; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = (long) (1.25 * size); + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + + + @Test + public void testHLLMerge100PercentOverlap() { + HyperLogLog hll1 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll1.addLong(i); + } + HyperLogLog hll2 = HyperLogLog.builder().setNumRegisterIndexBits(16).build(); + for (int i = 0; i < size; i++) { + hll2.addLong(i); + } + hll1.merge(hll2); + double threshold = size > 40000 ? longRangeTolerance : shortRangeTolerance; + double delta = threshold * size / 100; + long expected = size; + long actual = hll1.count(); + assertEquals(expected, actual, delta); + } + +}