http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out index fdf92df..55822de 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_12.q.out @@ -134,7 +134,7 @@ POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket3out POSTHOOK: type: LOAD #### A masked pattern was here #### POSTHOOK: Output: default@bucket_medium@ds=2008-04-08 -Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 3' is a cross product PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key @@ -155,23 +155,23 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: a - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + alias: c + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false Path -> Alias: @@ -185,23 +185,23 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_small - numFiles 2 + name default.bucket_big + numFiles 4 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 - serialization.ddl struct bucket_small { string key, string value} + serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 114 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -209,75 +209,48 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE - bucket_count 2 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_small + name default.bucket_big partition_columns ds partition_columns.types string - serialization.ddl struct bucket_small { string key, string value} + serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_small - name: default.bucket_small - Truncated Path -> Alias: - /bucket_small/ds=2008-04-08 [$hdt$_1:a] - Map 5 - Map Operator Tree: - TableScan - alias: b - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: key is not null (type: boolean) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - null sort order: a - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE - tag: 1 - auto parallelism: false - Path -> Alias: -#### A masked pattern was here #### - Path -> Partition: + name: default.bucket_big + name: default.bucket_big #### A masked pattern was here #### Partition - base file name: ds=2008-04-08 + base file name: ds=2008-04-09 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: - ds 2008-04-08 + ds 2008-04-09 properties: - bucket_count 3 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_medium - numFiles 3 + name default.bucket_big + numFiles 4 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 - serialization.ddl struct bucket_medium { string key, string value} + serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 170 + totalSize 5812 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -285,46 +258,47 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE - bucket_count 3 + bucket_count 4 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_medium + name default.bucket_big partition_columns ds partition_columns.types string - serialization.ddl struct bucket_medium { string key, string value} + serialization.ddl struct bucket_big { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_medium - name: default.bucket_medium + name: default.bucket_big + name: default.bucket_big Truncated Path -> Alias: - /bucket_medium/ds=2008-04-08 [$hdt$_2:b] - Map 6 + /bucket_big/ds=2008-04-08 [$hdt$_0:c] + /bucket_big/ds=2008-04-09 [$hdt$_0:c] + Map 5 Map Operator Tree: TableScan - alias: c - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + alias: b + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE - tag: 2 + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE + tag: 1 auto parallelism: false Path -> Alias: #### A masked pattern was here #### @@ -337,23 +311,23 @@ STAGE PLANS: partition values: ds 2008-04-08 properties: - bucket_count 4 + bucket_count 3 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_big - numFiles 4 + name default.bucket_medium + numFiles 3 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 - serialization.ddl struct bucket_big { string key, string value} + serialization.ddl struct bucket_medium { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 170 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -361,48 +335,75 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 + bucket_count 3 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_big + name default.bucket_medium partition_columns ds partition_columns.types string - serialization.ddl struct bucket_big { string key, string value} + serialization.ddl struct bucket_medium { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_big - name: default.bucket_big + name: default.bucket_medium + name: default.bucket_medium + Truncated Path -> Alias: + /bucket_medium/ds=2008-04-08 [$hdt$_1:b] + Map 6 + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: key is not null (type: boolean) + Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + null sort order: a + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE + tag: 2 + auto parallelism: false + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: #### A masked pattern was here #### Partition - base file name: ds=2008-04-09 + base file name: ds=2008-04-08 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: - ds 2008-04-09 + ds 2008-04-08 properties: - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_big - numFiles 4 + name default.bucket_small + numFiles 2 numRows 0 partition_columns ds partition_columns.types string rawDataSize 0 - serialization.ddl struct bucket_big { string key, string value} + serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - totalSize 5812 + totalSize 114 #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe @@ -410,38 +411,37 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat properties: SORTBUCKETCOLSPREFIX TRUE - bucket_count 4 + bucket_count 2 bucket_field_name key column.name.delimiter , columns key,value columns.comments columns.types string:string #### A masked pattern was here #### - name default.bucket_big + name default.bucket_small partition_columns ds partition_columns.types string - serialization.ddl struct bucket_big { string key, string value} + serialization.ddl struct bucket_small { string key, string value} serialization.format 1 serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe #### A masked pattern was here #### serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe - name: default.bucket_big - name: default.bucket_big + name: default.bucket_small + name: default.bucket_small Truncated Path -> Alias: - /bucket_big/ds=2008-04-08 [$hdt$_0:c] - /bucket_big/ds=2008-04-09 [$hdt$_0:c] + /bucket_small/ds=2008-04-08 [$hdt$_2:a] Map 7 Map Operator Tree: TableScan alias: d - Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE GatherStats: false Select Operator - Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE tag: 1 auto parallelism: false Path -> Alias: @@ -509,11 +509,11 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) 2 _col0 (type: string) - Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE tag: 0 auto parallelism: false Reducer 3 @@ -525,16 +525,16 @@ STAGE PLANS: keys: 0 1 - Statistics: Num rows: 255 Data size: 459327 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1584 Data size: 1666368 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator null sort order: sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE tag: -1 value expressions: _col0 (type: bigint) auto parallelism: false @@ -545,13 +545,13 @@ STAGE PLANS: aggregations: count(VALUE._col0) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat @@ -575,7 +575,7 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Work 'Reducer 3' is a cross product +Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Work 'Reducer 3' is a cross product PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key PREHOOK: type: QUERY PREHOOK: Input: default@bucket_big
http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out index 6c25da4..6022afe 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out @@ -100,16 +100,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -117,7 +117,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -308,16 +308,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -325,7 +325,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out index 624a730..0aec72f 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out @@ -100,16 +100,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -117,7 +117,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -258,16 +258,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -275,7 +275,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -416,16 +416,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -433,7 +433,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 63 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 132 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out index 44f792a..e373de8 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out @@ -116,16 +116,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -133,7 +133,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -274,16 +274,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -291,7 +291,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -432,16 +432,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -449,7 +449,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 29 Data size: 3025 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 61 Data size: 30250 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out index 73525bc..beafb15 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out @@ -133,16 +133,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -150,7 +150,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -343,16 +343,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -360,7 +360,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -553,16 +553,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -570,7 +570,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 59 Data size: 6050 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 123 Data size: 60500 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out index abd6e65..0425126 100644 --- a/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out +++ b/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out @@ -133,16 +133,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -150,7 +150,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 1 - Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -343,16 +343,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -360,7 +360,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -553,16 +553,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE Sorted Merge Bucket Map Join Operator condition map: Inner Join 0 to 1 @@ -570,7 +570,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) Position of Big Table: 0 - Statistics: Num rows: 127 Data size: 12786 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 264 Data size: 127864 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out index 71063f9..854945d 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark1.q.out @@ -131,16 +131,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -215,16 +215,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -235,18 +235,18 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -439,16 +439,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -518,16 +518,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -538,17 +538,17 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out index 04a3a49..7855186 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out @@ -115,16 +115,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -199,16 +199,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -219,18 +219,18 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -423,16 +423,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -507,16 +507,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -527,18 +527,18 @@ STAGE PLANS: input vertices: 1 Map 2 Position of Big Table: 0 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out index 6ee414c..fb82ba7 100644 --- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out +++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out @@ -115,16 +115,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -199,16 +199,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -219,18 +219,18 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -423,16 +423,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 78 Data size: 30620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 _col0 (type: int) @@ -502,16 +502,16 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -522,17 +522,17 @@ STAGE PLANS: input vertices: 0 Map 1 Position of Big Table: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out index bec0451..aab6840 100644 --- a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out @@ -464,22 +464,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -546,17 +546,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -820,22 +820,22 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) null sort order: a sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -902,17 +902,17 @@ STAGE PLANS: 0 _col0 (type: int) 1 _col0 (type: int) outputColumnNames: _col0, _col1, _col3 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 1 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out index 9664fb8..119afb3 100644 --- a/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out @@ -150,12 +150,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 178 Data size: 69500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 178 Data size: 69500 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 key (type: int) @@ -276,12 +276,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 178 Data size: 69500 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 178 Data size: 69500 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -291,7 +291,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 1910 Data size: 7645 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 195 Data size: 76450 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out index 00161e3..1e9361f 100644 --- a/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out +++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out @@ -158,12 +158,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 key (type: int) @@ -289,12 +289,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -304,7 +304,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 2354 Data size: 9418 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 94182 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count() @@ -511,12 +511,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: b - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator keys: 0 key (type: int), part (type: string) @@ -642,12 +642,12 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE GatherStats: false Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 219 Data size: 85620 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -657,7 +657,7 @@ STAGE PLANS: input vertices: 1 Map 3 Position of Big Table: 0 - Statistics: Num rows: 2354 Data size: 9418 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 240 Data size: 94182 Basic stats: COMPLETE Column stats: NONE BucketMapJoin: true Group By Operator aggregations: count()