http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/masking_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/masking_4.q.out b/ql/src/test/results/clientpositive/masking_4.q.out index 60cbd0f..54861b0 100644 --- a/ql/src/test/results/clientpositive/masking_4.q.out +++ b/ql/src/test/results/clientpositive/masking_4.q.out @@ -210,12 +210,16 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: int), UDFToDouble(_col0) (type: double) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-2 Map Reduce @@ -228,20 +232,20 @@ STAGE PLANS: 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: string) - outputColumnNames: _col0 + expressions: key (type: string), UDFToDouble(key) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col1 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col1 (type: double) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: string) TableScan Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col1 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) + Map-reduce partition columns: _col1 (type: double) Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Reduce Operator Tree: @@ -249,21 +253,25 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(_col0) (type: double) - outputColumnNames: _col0, _col1 + 0 _col1 (type: double) + 1 _col1 (type: double) + outputColumnNames: _col0, _col2 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - Group By Operator - keys: _col0 (type: string), _col1 (type: int) - mode: hash + Select Operator + expressions: _col0 (type: string), _col2 (type: int) outputColumnNames: _col0, _col1 Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Group By Operator + keys: _col0 (type: string), _col1 (type: int) + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-1 Map Reduce
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/mergejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mergejoin.q.out b/ql/src/test/results/clientpositive/mergejoin.q.out index b20ea45..2108434 100644 --- a/ql/src/test/results/clientpositive/mergejoin.q.out +++ b/ql/src/test/results/clientpositive/mergejoin.q.out @@ -3399,8 +3399,8 @@ NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 NULL NULL NULL 98 val_98 2008-04-08 98 val_98 2008-04-08 -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-2:MAPRED' is a cross product +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select * from (select * from tab_n9 where tab_n9.key = 0)a join @@ -3927,8 +3927,8 @@ NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08 NULL NULL NULL NULL NULL NULL 97 val_97 2008-04-08 NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08 NULL NULL NULL NULL NULL NULL 98 val_98 2008-04-08 -Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product -Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[14][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +Warning: Shuffle Join JOIN[10][tables = [$hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from (select * from tab_n9 where tab_n9.key = 0)a join http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/mergejoins.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mergejoins.q.out b/ql/src/test/results/clientpositive/mergejoins.q.out index dcae432..1841e63 100644 --- a/ql/src/test/results/clientpositive/mergejoins.q.out +++ b/ql/src/test/results/clientpositive/mergejoins.q.out @@ -218,24 +218,24 @@ STAGE PLANS: Map Reduce Map Operator Tree: TableScan - alias: a_n0 + alias: b_n0 filterExpr: key is not null (type: boolean) 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 Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 + expressions: key (type: string), value (type: string), (UDFToDouble(key) < 10.0D) (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 500 Data size: 5312 Basic stats: 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 - value expressions: _col1 (type: string) + value expressions: _col1 (type: string), _col2 (type: boolean) TableScan - alias: b_n0 + alias: a_n0 filterExpr: key is not null (type: boolean) Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator @@ -272,24 +272,28 @@ STAGE PLANS: Join Operator condition map: Inner Join 0 to 1 - Left Outer Join 1 to 2 + Left Outer Join 0 to 2 filter predicates: - 0 - 1 {(UDFToDouble(KEY.reducesinkkey0) < 10.0D)} + 0 {VALUE._col1} + 1 2 keys: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 + outputColumnNames: _col0, _col1, _col3, _col4, _col5, _col6 Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false + Select Operator + expressions: _col3 (type: string), _col4 (type: string), _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1100 Data size: 11686 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 + File Output Operator + compressed: false + Statistics: Num rows: 1100 Data size: 11686 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 http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out b/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out index 50d407f..761e7c0 100644 --- a/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out +++ b/ql/src/test/results/clientpositive/multi_insert_with_join2.q.out @@ -92,12 +92,12 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) TableScan alias: b filterExpr: ((id = 'Id_1') and (val = 'val_103')) (type: boolean) @@ -117,10 +117,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 'Id_1' (type: string), _col1 (type: string), 'Id_1' (type: string), 'val_103' (type: string) + expressions: 'Id_1' (type: string), _col0 (type: string), 'Id_1' (type: string), 'val_103' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE File Output Operator @@ -226,12 +226,12 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: val (type: string) - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col0 (type: string) TableScan alias: b filterExpr: ((val = 'val_104') and (id = 'Id_2')) (type: boolean) @@ -251,10 +251,10 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col1 + outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: 'Id_2' (type: string), _col1 (type: string), 'Id_2' (type: string), 'val_104' (type: string) + expressions: 'Id_2' (type: string), _col0 (type: string), 'Id_2' (type: string), 'val_104' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 1 Data size: 25 Basic stats: COMPLETE Column stats: NONE File Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/outer_join_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/outer_join_ppr.q.out b/ql/src/test/results/clientpositive/outer_join_ppr.q.out index ea85034..fc0ea34 100644 --- a/ql/src/test/results/clientpositive/outer_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/outer_join_ppr.q.out @@ -26,11 +26,11 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` +OPTIMIZED SQL: SELECT * FROM (SELECT `key`, `value` FROM `default`.`src` WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcpart` WHERE `key` > 15 AND `ds` = '2008-04-08' AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: @@ -343,11 +343,11 @@ POSTHOOK: Input: default@srcpart POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` +OPTIMIZED SQL: SELECT * FROM (SELECT `key`, `value` FROM `default`.`src` WHERE `key` < 20 AND `key` > 15) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`srcpart` WHERE `key` > 15 AND `ds` = '2008-04-08' AND `key` < 20) AS `t2` ON `t0`.`key` = `t2`.`key` STAGE DEPENDENCIES: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/pcr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/pcr.q.out b/ql/src/test/results/clientpositive/pcr.q.out index 95f560f..d71ef67 100644 --- a/ql/src/test/results/clientpositive/pcr.q.out +++ b/ql/src/test/results/clientpositive/pcr.q.out @@ -2430,15 +2430,15 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@pcr_t1 POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-08' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-08' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -2553,30 +2553,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce @@ -2714,15 +2710,15 @@ POSTHOOK: Input: default@pcr_t1 POSTHOOK: Input: default@pcr_t1@ds=2000-04-08 POSTHOOK: Input: default@pcr_t1@ds=2000-04-09 #### A masked pattern was here #### -OPTIMIZED SQL: SELECT `t4`.`key`, `t4`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t4`.`key1`, `t4`.`value1`, CAST('2000-04-09' AS STRING) AS `ds1` -FROM (SELECT `t0`.`key`, `t0`.`value`, `t2`.`key` AS `key1`, `t2`.`value` AS `value1` -FROM (SELECT `key`, `value`, CAST('2000-04-08' AS STRING) AS `ds` +OPTIMIZED SQL: SELECT `t3`.`key`, `t3`.`value`, CAST('2000-04-08' AS STRING) AS `ds`, `t3`.`key0` AS `key1`, `t3`.`value0` AS `value1`, CAST('2000-04-09' AS STRING) AS `ds1` +FROM (SELECT * +FROM (SELECT `key`, `value` FROM `default`.`pcr_t1` WHERE `ds` = '2000-04-08' AND `key` IS NOT NULL) AS `t0` -INNER JOIN (SELECT `key`, `value`, CAST('2000-04-09' AS STRING) AS `ds` +INNER JOIN (SELECT `key`, `value` FROM `default`.`pcr_t1` WHERE `ds` = '2000-04-09' AND `key` IS NOT NULL) AS `t2` ON `t0`.`key` = `t2`.`key` -ORDER BY `t0`.`key`) AS `t4` +ORDER BY `t0`.`key`) AS `t3` STAGE DEPENDENCIES: Stage-1 is a root stage Stage-2 depends on stages: Stage-1 @@ -2886,30 +2882,26 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col3, _col4 + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: int), _col1 (type: string), _col3 (type: int), _col4 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - GlobalTableId: 0 + File Output Operator + compressed: false + GlobalTableId: 0 #### A masked pattern was here #### - NumFilesPerFileSink: 1 - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - properties: - column.name.delimiter , - columns _col0,_col1,_col2,_col3 - columns.types int,string,int,string - escape.delim \ - serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe - TotalFiles: 1 - GatherStats: false - MultiFileSpray: false + NumFilesPerFileSink: 1 + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + column.name.delimiter , + columns _col0,_col1,_col2,_col3 + columns.types int,string,int,string + escape.delim \ + serialization.lib org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false Stage: Stage-2 Map Reduce http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query1.q.out b/ql/src/test/results/clientpositive/perf/spark/query1.q.out index e0fd19e..75da726 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query1.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query1.q.out @@ -309,14 +309,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col6 + outputColumnNames: _col1, _col2, _col5 Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(17,2)), _col6 (type: string) + value expressions: _col2 (type: decimal(17,2)), _col5 (type: string) Reducer 5 Reduce Operator Tree: Join Operator @@ -325,13 +325,13 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col1 (type: int) - outputColumnNames: _col2, _col6, _col7 + outputColumnNames: _col2, _col5, _col6 Statistics: Num rows: 96800003 Data size: 83249958789 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (_col2 > _col7) (type: boolean) + predicate: (_col2 > _col6) (type: boolean) Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col6 (type: string) + expressions: _col5 (type: string) outputColumnNames: _col0 Statistics: Num rows: 32266667 Data size: 27749985689 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query11.q.out b/ql/src/test/results/clientpositive/perf/spark/query11.q.out index 823ad71..28ce6d0 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query11.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query11.q.out @@ -190,15 +190,15 @@ STAGE PLANS: predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), (ws_ext_list_price - ws_ext_discount_amt) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: decimal(8,2)) Execution mode: vectorized Map 13 Map Operator Tree: @@ -249,15 +249,15 @@ STAGE PLANS: predicate: (ws_bill_customer_sk is not null and ws_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), ws_ext_discount_amt (type: decimal(7,2)), ws_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: ws_sold_date_sk (type: int), ws_bill_customer_sk (type: int), (ws_ext_list_price - ws_ext_discount_amt) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 144002668 Data size: 19580198212 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: decimal(8,2)) Execution mode: vectorized Map 19 Map Operator Tree: @@ -308,15 +308,15 @@ STAGE PLANS: predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), (ss_ext_list_price - ss_ext_discount_amt) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: decimal(8,2)) Execution mode: vectorized Map 25 Map Operator Tree: @@ -406,15 +406,15 @@ STAGE PLANS: predicate: (ss_customer_sk is not null and ss_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), ss_ext_discount_amt (type: decimal(7,2)), ss_ext_list_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3 + expressions: ss_sold_date_sk (type: int), ss_customer_sk (type: int), (ss_ext_list_price - ss_ext_discount_amt) (type: decimal(8,2)) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 575995635 Data size: 50814502088 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: decimal(8,2)) Execution mode: vectorized Reducer 10 Reduce Operator Tree: @@ -424,14 +424,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col2 (type: decimal(8,2)) Reducer 11 Reduce Operator Tree: Join Operator @@ -440,24 +440,20 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + Group By Operator + aggregations: sum(_col2) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) + value expressions: _col7 (type: decimal(18,2)) Reducer 12 Execution mode: vectorized Reduce Operator Tree: @@ -492,14 +488,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col2 (type: decimal(8,2)) Reducer 17 Reduce Operator Tree: Join Operator @@ -508,24 +504,20 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + Group By Operator + aggregations: sum(_col2) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) + value expressions: _col7 (type: decimal(18,2)) Reducer 18 Execution mode: vectorized Reduce Operator Tree: @@ -543,15 +535,15 @@ STAGE PLANS: predicate: (_col7 > 0) (type: boolean) Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col0 (type: string), _col7 (type: decimal(18,2)) - outputColumnNames: _col0, _col1 + expressions: _col0 (type: string), _col7 (type: decimal(18,2)), _col7 is not null (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 29040539 Data size: 3948673454 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: decimal(18,2)) + value expressions: _col1 (type: decimal(18,2)), _col2 (type: boolean) Reducer 2 Reduce Operator Tree: Join Operator @@ -560,14 +552,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 158402938 Data size: 21538218500 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col2 (type: decimal(8,2)) Reducer 22 Reduce Operator Tree: Join Operator @@ -576,14 +568,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 633595212 Data size: 55895953508 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)), _col3 (type: decimal(7,2)) + value expressions: _col2 (type: decimal(8,2)) Reducer 23 Reduce Operator Tree: Join Operator @@ -592,24 +584,20 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + Group By Operator + aggregations: sum(_col2) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) + value expressions: _col7 (type: decimal(18,2)) Reducer 24 Execution mode: vectorized Reduce Operator Tree: @@ -637,24 +625,20 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col7, _col8, _col9, _col10, _col11, _col12, _col13 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string), _col12 (type: string), _col13 (type: string), (_col3 - _col2) (type: decimal(8,2)) + Group By Operator + aggregations: sum(_col2) + keys: _col5 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: string), _col9 (type: string), _col10 (type: string), _col11 (type: string) + mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col7) - keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7 + Reduce Output Operator + key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) + sort order: +++++++ + Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - sort order: +++++++ - Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string), _col4 (type: string), _col5 (type: string), _col6 (type: string) - Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE - value expressions: _col7 (type: decimal(18,2)) + value expressions: _col7 (type: decimal(18,2)) Reducer 4 Execution mode: vectorized Reduce Operator Tree: @@ -686,13 +670,13 @@ STAGE PLANS: 1 _col0 (type: string) 2 _col0 (type: string) 3 _col0 (type: string) - outputColumnNames: _col1, _col3, _col5, _col7, _col8 + outputColumnNames: _col1, _col3, _col5, _col6, _col8, _col9 Statistics: Num rows: 1149975359 Data size: 101451160012 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > (_col8 / _col3))) ELSE ((null > (_col8 / _col3))) END) ELSE (CASE WHEN (_col5 is not null) THEN (((_col1 / _col5) > null)) ELSE (null) END) END (type: boolean) + predicate: CASE WHEN (_col3 is not null) THEN (CASE WHEN (_col6) THEN (((_col1 / _col5) > (_col9 / _col3))) ELSE ((null > (_col9 / _col3))) END) ELSE (CASE WHEN (_col6) THEN (((_col1 / _col5) > null)) ELSE (null) END) END (type: boolean) Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col7 (type: string) + expressions: _col8 (type: string) outputColumnNames: _col0 Statistics: Num rows: 574987679 Data size: 50725579961 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query12.q.out b/ql/src/test/results/clientpositive/perf/spark/query12.q.out index 903fcee..6ec6b73 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query12.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query12.q.out @@ -170,11 +170,11 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10 + outputColumnNames: _col2, _col5, _col6, _col7, _col8, _col9 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col2) - keys: _col10 (type: string), _col9 (type: string), _col6 (type: string), _col7 (type: string), _col8 (type: decimal(7,2)) + keys: _col9 (type: string), _col8 (type: string), _col5 (type: string), _col6 (type: string), _col7 (type: decimal(7,2)) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 174243235 Data size: 23692040863 Basic stats: COMPLETE Column stats: NONE http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query13.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query13.q.out b/ql/src/test/results/clientpositive/perf/spark/query13.q.out index 4d530fc..2b6c19d 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query13.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query13.q.out @@ -114,8 +114,7 @@ POSTHOOK: Input: default@store_sales #### A masked pattern was here #### STAGE DEPENDENCIES: Stage-2 is a root stage - Stage-3 depends on stages: Stage-2 - Stage-1 depends on stages: Stage-3 + Stage-1 depends on stages: Stage-2 Stage-0 depends on stages: Stage-1 STAGE PLANS: @@ -123,6 +122,26 @@ STAGE PLANS: Spark #### A masked pattern was here #### Vertices: + Map 7 + Map Operator Tree: + TableScan + alias: store + filterExpr: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: s_store_sk is not null (type: boolean) + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: s_store_sk (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + Spark HashTable Sink Operator + keys: + 0 _col5 (type: int) + 1 _col0 (type: int) + Execution mode: vectorized + Local Work: + Map Reduce Local Work Map 8 Map Operator Tree: TableScan @@ -133,8 +152,8 @@ STAGE PLANS: predicate: ((hd_dep_count) IN (3, 1) and hd_demo_sk is not null) (type: boolean) Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hd_demo_sk (type: int), hd_dep_count (type: int) - outputColumnNames: _col0, _col1 + expressions: hd_demo_sk (type: int), (hd_dep_count = 3) (type: boolean), (hd_dep_count = 1) (type: boolean) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 7200 Data size: 770400 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: @@ -144,40 +163,34 @@ STAGE PLANS: Local Work: Map Reduce Local Work - Stage: Stage-3 + Stage: Stage-1 Spark + Edges: + Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 45), Map 6 (PARTITION-LEVEL SORT, 45) + Reducer 3 <- Map 9 (PARTITION-LEVEL SORT, 218), Reducer 2 (PARTITION-LEVEL SORT, 218) + Reducer 4 <- Map 10 (PARTITION-LEVEL SORT, 55), Reducer 3 (PARTITION-LEVEL SORT, 55) + Reducer 5 <- Reducer 4 (GROUP, 1) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: store - filterExpr: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + alias: date_dim + filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: s_store_sk is not null (type: boolean) - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE + predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: s_store_sk (type: int) + expressions: d_date_sk (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1704 Data size: 3256276 Basic stats: COMPLETE Column stats: NONE - Spark HashTable Sink Operator - keys: - 0 _col0 (type: int) - 1 _col4 (type: int) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized - Local Work: - Map Reduce Local Work - - Stage: Stage-1 - Spark - Edges: - Reducer 3 <- Map 2 (PARTITION-LEVEL SORT, 49), Map 7 (PARTITION-LEVEL SORT, 49) - Reducer 4 <- Map 9 (PARTITION-LEVEL SORT, 218), Reducer 3 (PARTITION-LEVEL SORT, 218) - Reducer 5 <- Map 10 (PARTITION-LEVEL SORT, 28), Reducer 4 (PARTITION-LEVEL SORT, 28) - Reducer 6 <- Reducer 5 (GROUP, 1) -#### A masked pattern was here #### - Vertices: Map 10 Map Operator Tree: TableScan @@ -188,17 +201,17 @@ STAGE PLANS: predicate: ((cd_education_status) IN ('4 yr Degree', 'Primary', 'Advanced Degree') and (cd_marital_status) IN ('M', 'D', 'U') and cd_demo_sk is not null) (type: boolean) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cd_demo_sk (type: int), cd_marital_status (type: string), cd_education_status (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: cd_demo_sk (type: int), (cd_marital_status = 'M') (type: boolean), (cd_education_status = '4 yr Degree') (type: boolean), (cd_marital_status = 'D') (type: boolean), (cd_education_status = 'Primary') (type: boolean), (cd_marital_status = 'U') (type: boolean), (cd_education_status = 'Advanced Degree') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6 Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 1861800 Data size: 717186159 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean), _col4 (type: boolean), _col5 (type: boolean), _col6 (type: boolean) Execution mode: vectorized - Map 2 + Map 6 Map Operator Tree: TableScan alias: store_sales @@ -208,46 +221,15 @@ STAGE PLANS: predicate: ((ss_net_profit BETWEEN 100 AND 200 or ss_net_profit BETWEEN 150 AND 300 or ss_net_profit BETWEEN 50 AND 250) and (ss_sales_price BETWEEN 100 AND 150 or ss_sales_price BETWEEN 50 AND 100 or ss_sales_price BETWEEN 150 AND 200) and ss_addr_sk is not null and ss_cdemo_sk is not null and ss_hdemo_sk is not null and ss_sold_date_sk is not null and ss_store_sk is not null) (type: boolean) Statistics: Num rows: 63999513 Data size: 5646055611 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ss_sold_date_sk (type: int), ss_cdemo_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_sales_price (type: decimal(7,2)), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_net_profit (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9 + expressions: ss_sold_date_sk (type: int), ss_cdemo_sk (type: int), ss_hdemo_sk (type: int), ss_addr_sk (type: int), ss_store_sk (type: int), ss_quantity (type: int), ss_ext_sales_price (type: decimal(7,2)), ss_ext_wholesale_cost (type: decimal(7,2)), ss_net_profit BETWEEN 100 AND 200 (type: boolean), ss_net_profit BETWEEN 150 AND 300 (type: boolean), ss_net_profit BETWEEN 50 AND 250 (type: boolean), ss_sales_price BETWEEN 100 AND 150 (type: boolean), ss_sales_price BETWEEN 50 AND 100 (type: boolean), ss_sales_price BETWEEN 150 AND 200 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13 Statistics: Num rows: 63999513 Data size: 5646055611 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: int) - 1 _col4 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col6, _col7, _col8, _col9, _col10 - input vertices: - 0 Map 1 - Statistics: Num rows: 70399465 Data size: 6210661306 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: int) - sort order: + - Map-reduce partition columns: _col1 (type: int) - Statistics: Num rows: 70399465 Data size: 6210661306 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col3 (type: int), _col4 (type: int), _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)) - Execution mode: vectorized - Local Work: - Map Reduce Local Work - Map 7 - Map Operator Tree: - TableScan - alias: date_dim - filterExpr: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 73049 Data size: 81741831 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((d_year = 2001) and d_date_sk is not null) (type: boolean) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: d_date_sk (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 36524 Data size: 40870356 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 63999513 Data size: 5646055611 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: int), _col2 (type: int), _col3 (type: int), _col4 (type: int), _col5 (type: int), _col6 (type: decimal(7,2)), _col7 (type: decimal(7,2)), _col8 (type: boolean), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean) Execution mode: vectorized Map 9 Map Operator Tree: @@ -259,17 +241,17 @@ STAGE PLANS: predicate: ((ca_country = 'United States') and (ca_state) IN ('KY', 'GA', 'NM', 'MT', 'OR', 'IN', 'WI', 'MO', 'WV') and ca_address_sk is not null) (type: boolean) Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ca_address_sk (type: int), ca_state (type: string) - outputColumnNames: _col0, _col1 + expressions: ca_address_sk (type: int), (ca_state) IN ('KY', 'GA', 'NM') (type: boolean), (ca_state) IN ('MT', 'OR', 'IN') (type: boolean), (ca_state) IN ('WI', 'MO', 'WV') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 20000000 Data size: 20297597642 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) + value expressions: _col1 (type: boolean), _col2 (type: boolean), _col3 (type: boolean) Execution mode: vectorized - Reducer 3 + Reducer 2 Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -277,27 +259,37 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: int) + 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col3, _col4, _col6, _col7, _col8, _col9, _col10 - Statistics: Num rows: 77439413 Data size: 6831727584 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 + Statistics: Num rows: 70399465 Data size: 6210661306 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col3 (type: int) + 0 _col5 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col4, _col6, _col7, _col8, _col9, _col10, _col14 + outputColumnNames: _col2, _col3, _col4, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14 input vertices: - 1 Map 8 - Statistics: Num rows: 85183356 Data size: 7514900505 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col4 (type: int) - sort order: + - Map-reduce partition columns: _col4 (type: int) + 1 Map 7 + Statistics: Num rows: 77439413 Data size: 6831727584 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col3 (type: int) + 1 _col0 (type: int) + outputColumnNames: _col2, _col4, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col17, _col18 + input vertices: + 1 Map 8 Statistics: Num rows: 85183356 Data size: 7514900505 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: int), _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col10 (type: decimal(7,2)), _col14 (type: int) - Reducer 4 + Reduce Output Operator + key expressions: _col4 (type: int) + sort order: + + Map-reduce partition columns: _col4 (type: int) + Statistics: Num rows: 85183356 Data size: 7514900505 Basic stats: COMPLETE Column stats: NONE + value expressions: _col2 (type: int), _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: boolean), _col10 (type: boolean), _col11 (type: boolean), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col17 (type: boolean), _col18 (type: boolean) + Reducer 3 Reduce Operator Tree: Join Operator condition map: @@ -305,18 +297,18 @@ STAGE PLANS: keys: 0 _col4 (type: int) 1 _col0 (type: int) - outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10, _col14, _col16 + outputColumnNames: _col2, _col6, _col7, _col8, _col9, _col10, _col11, _col12, _col13, _col14, _col17, _col18, _col20, _col21, _col22 Statistics: Num rows: 93701693 Data size: 8266390734 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col16) IN ('KY', 'GA', 'NM') and _col10 BETWEEN 100 AND 200) or ((_col16) IN ('MT', 'OR', 'IN') and _col10 BETWEEN 150 AND 300) or ((_col16) IN ('WI', 'MO', 'WV') and _col10 BETWEEN 50 AND 250)) (type: boolean) - Statistics: Num rows: 31233897 Data size: 2755463519 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col20 and _col9) or (_col21 and _col10) or (_col22 and _col11)) (type: boolean) + Statistics: Num rows: 70276269 Data size: 6199792984 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col2 (type: int) sort order: + Map-reduce partition columns: _col2 (type: int) - Statistics: Num rows: 31233897 Data size: 2755463519 Basic stats: COMPLETE Column stats: NONE - value expressions: _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)), _col14 (type: int) - Reducer 5 + Statistics: Num rows: 70276269 Data size: 6199792984 Basic stats: COMPLETE Column stats: NONE + value expressions: _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)), _col12 (type: boolean), _col13 (type: boolean), _col14 (type: boolean), _col17 (type: boolean), _col18 (type: boolean) + Reducer 4 Reduce Operator Tree: Join Operator condition map: @@ -324,17 +316,17 @@ STAGE PLANS: keys: 0 _col2 (type: int) 1 _col0 (type: int) - outputColumnNames: _col6, _col7, _col8, _col9, _col14, _col19, _col20 - Statistics: Num rows: 34357287 Data size: 3031009936 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col6, _col7, _col8, _col12, _col13, _col14, _col17, _col18, _col24, _col25, _col26, _col27, _col28, _col29 + Statistics: Num rows: 77303897 Data size: 6819772430 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((_col19 = 'D') and (_col20 = 'Primary') and _col7 BETWEEN 50 AND 100 and (_col14 = 1)) or ((_col19 = 'M') and (_col20 = '4 yr Degree') and _col7 BETWEEN 100 AND 150 and (_col14 = 3)) or ((_col19 = 'U') and (_col20 = 'Advanced Degree') and _col7 BETWEEN 150 AND 200 and (_col14 = 1))) (type: boolean) - Statistics: Num rows: 1431552 Data size: 126291937 Basic stats: COMPLETE Column stats: NONE + predicate: ((_col24 and _col25 and _col12 and _col17) or (_col26 and _col27 and _col13 and _col18) or (_col28 and _col29 and _col14 and _col18)) (type: boolean) + Statistics: Num rows: 14494479 Data size: 1278707181 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col6 (type: int), _col8 (type: decimal(7,2)), _col9 (type: decimal(7,2)) - outputColumnNames: _col6, _col8, _col9 - Statistics: Num rows: 1431552 Data size: 126291937 Basic stats: COMPLETE Column stats: NONE + expressions: _col6 (type: int), _col7 (type: decimal(7,2)), _col8 (type: decimal(7,2)) + outputColumnNames: _col6, _col7, _col8 + Statistics: Num rows: 14494479 Data size: 1278707181 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col6), count(_col6), sum(_col8), count(_col8), sum(_col9), count(_col9) + aggregations: sum(_col6), count(_col6), sum(_col7), count(_col7), sum(_col8), count(_col8) mode: hash outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE @@ -342,7 +334,7 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 256 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: bigint), _col1 (type: bigint), _col2 (type: decimal(17,2)), _col3 (type: bigint), _col4 (type: decimal(17,2)), _col5 (type: bigint) - Reducer 6 + Reducer 5 Execution mode: vectorized Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query15.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query15.q.out b/ql/src/test/results/clientpositive/perf/spark/query15.q.out index d0017e4..8b45053 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query15.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query15.q.out @@ -91,15 +91,15 @@ STAGE PLANS: predicate: ca_address_sk is not null (type: boolean) Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ca_address_sk (type: int), ca_state (type: string), ca_zip (type: string) - outputColumnNames: _col0, _col1, _col2 + expressions: ca_address_sk (type: int), ca_zip (type: string), (substr(ca_zip, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792') (type: boolean), (ca_state) IN ('CA', 'WA', 'GA') (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 40000000 Data size: 40595195284 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: string) + value expressions: _col1 (type: string), _col2 (type: boolean), _col3 (type: boolean) Execution mode: vectorized Map 7 Map Operator Tree: @@ -111,15 +111,15 @@ STAGE PLANS: predicate: (cs_bill_customer_sk is not null and cs_sold_date_sk is not null) (type: boolean) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_sales_price (type: decimal(7,2)) - outputColumnNames: _col0, _col1, _col2 + expressions: cs_sold_date_sk (type: int), cs_bill_customer_sk (type: int), cs_sales_price (type: decimal(7,2)), (cs_sales_price > 500) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 287989836 Data size: 38999608952 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: decimal(7,2)) + value expressions: _col1 (type: int), _col2 (type: decimal(7,2)), _col3 (type: boolean) Execution mode: vectorized Map 9 Map Operator Tree: @@ -148,14 +148,14 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col3, _col4 + outputColumnNames: _col0, _col3, _col4, _col5 Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) Statistics: Num rows: 88000001 Data size: 75681779077 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: string), _col4 (type: string) + value expressions: _col3 (type: string), _col4 (type: boolean), _col5 (type: boolean) Reducer 3 Reduce Operator Tree: Join Operator @@ -164,18 +164,18 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col1 (type: int) - outputColumnNames: _col3, _col4, _col7 + outputColumnNames: _col3, _col4, _col5, _col8, _col9 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((_col3) IN ('CA', 'WA', 'GA') or (_col7 > 500) or (substr(_col4, 1, 5)) IN ('85669', '86197', '88274', '83405', '86475', '85392', '85460', '80348', '81792')) (type: boolean) + predicate: (_col4 or _col5 or _col9) (type: boolean) Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col4 (type: string), _col7 (type: decimal(7,2)) - outputColumnNames: _col4, _col7 + expressions: _col3 (type: string), _col8 (type: decimal(7,2)) + outputColumnNames: _col3, _col8 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: sum(_col7) - keys: _col4 (type: string) + aggregations: sum(_col8) + keys: _col3 (type: string) mode: hash outputColumnNames: _col0, _col1 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE @@ -226,14 +226,14 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2 + outputColumnNames: _col1, _col2, _col3 Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int) sort order: + Map-reduce partition columns: _col1 (type: int) Statistics: Num rows: 316788826 Data size: 42899570777 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: decimal(7,2)) + value expressions: _col2 (type: decimal(7,2)), _col3 (type: boolean) Stage: Stage-0 Fetch Operator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/perf/spark/query17.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/perf/spark/query17.q.out b/ql/src/test/results/clientpositive/perf/spark/query17.q.out index ba78752..7505449 100644 --- a/ql/src/test/results/clientpositive/perf/spark/query17.q.out +++ b/ql/src/test/results/clientpositive/perf/spark/query17.q.out @@ -305,14 +305,14 @@ STAGE PLANS: keys: 0 _col2 (type: int), _col1 (type: int) 1 _col1 (type: int), _col2 (type: int) - outputColumnNames: _col3, _col7, _col8, _col9, _col10 + outputColumnNames: _col3, _col6, _col7, _col8, _col9 Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col7 (type: int), _col8 (type: int), _col9 (type: int) + key expressions: _col6 (type: int), _col7 (type: int), _col8 (type: int) sort order: +++ - Map-reduce partition columns: _col7 (type: int), _col8 (type: int), _col9 (type: int) + Map-reduce partition columns: _col6 (type: int), _col7 (type: int), _col8 (type: int) Statistics: Num rows: 348467716 Data size: 47189528877 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col10 (type: int) + value expressions: _col3 (type: int), _col9 (type: int) Reducer 14 Reduce Operator Tree: Join Operator @@ -353,14 +353,14 @@ STAGE PLANS: keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col9, _col10 + outputColumnNames: _col1, _col2, _col3, _col4, _col5, _col8, _col9 Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: int), _col2 (type: int), _col4 (type: int) sort order: +++ Map-reduce partition columns: _col1 (type: int), _col2 (type: int), _col4 (type: int) Statistics: Num rows: 696954748 Data size: 61485550191 Basic stats: COMPLETE Column stats: NONE - value expressions: _col3 (type: int), _col5 (type: int), _col9 (type: string), _col10 (type: string) + value expressions: _col3 (type: int), _col5 (type: int), _col8 (type: string), _col9 (type: string) Reducer 4 Local Work: Map Reduce Local Work @@ -370,8 +370,8 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col1 (type: int), _col2 (type: int), _col4 (type: int) - 1 _col7 (type: int), _col8 (type: int), _col9 (type: int) - outputColumnNames: _col3, _col5, _col9, _col10, _col14, _col21 + 1 _col6 (type: int), _col7 (type: int), _col8 (type: int) + outputColumnNames: _col3, _col5, _col8, _col9, _col13, _col19 Statistics: Num rows: 766650239 Data size: 67634106676 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -379,12 +379,12 @@ STAGE PLANS: keys: 0 _col3 (type: int) 1 _col0 (type: int) - outputColumnNames: _col5, _col9, _col10, _col14, _col21, _col25 + outputColumnNames: _col5, _col8, _col9, _col13, _col19, _col22 input vertices: 1 Map 16 Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col9 (type: string), _col10 (type: string), _col25 (type: string), _col5 (type: int), _col21 (type: int), _col14 (type: int), UDFToDouble(_col5) (type: double), (UDFToDouble(_col5) * UDFToDouble(_col5)) (type: double), UDFToDouble(_col21) (type: double), (UDFToDouble(_col21) * UDFToDouble(_col21)) (type: double), UDFToDouble(_col14) (type: double), (UDFToDouble(_col14) * UDFToDouble(_col14)) (type: double) + expressions: _col8 (type: string), _col9 (type: string), _col22 (type: string), _col5 (type: int), _col19 (type: int), _col13 (type: int), UDFToDouble(_col5) (type: double), (UDFToDouble(_col5) * UDFToDouble(_col5)) (type: double), UDFToDouble(_col19) (type: double), (UDFToDouble(_col19) * UDFToDouble(_col19)) (type: double), UDFToDouble(_col13) (type: double), (UDFToDouble(_col13) * UDFToDouble(_col13)) (type: double) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 Statistics: Num rows: 843315281 Data size: 74397518956 Basic stats: COMPLETE Column stats: NONE Group By Operator