http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out index 788854a..6488e9e 100644 --- a/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out +++ b/ql/src/test/results/clientpositive/llap/dynpart_sort_optimization_acid.q.out @@ -92,19 +92,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -113,10 +113,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -185,19 +185,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part - Statistics: Num rows: 1600 Data size: 312400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 444727 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 147200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col3 (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -207,10 +207,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), VALUE._col1 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -372,19 +372,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part_sdpo - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -393,10 +393,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -465,19 +465,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_part_sdpo - Statistics: Num rows: 1600 Data size: 312400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 444727 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 147200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1355 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string) outputColumnNames: _col0, _col3 - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: +++ Map-reduce partition columns: _col3 (type: string) - Statistics: Num rows: 800 Data size: 347200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2170 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -486,11 +486,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), KEY._col3 (type: string), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, '_bucket_number' - Statistics: Num rows: 800 Data size: 286400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 800 Data size: 286400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1790 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -661,19 +661,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -682,10 +682,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -755,19 +755,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 3200 Data size: 48800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 313367 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 6400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 455 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), hr (type: int) outputColumnNames: _col0, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col4 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -777,10 +777,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), VALUE._col2 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -879,19 +879,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 902167 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (value = 'bar') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), _col2 (type: int) Execution mode: llap LLAP IO: may be used (ACID table) @@ -901,10 +901,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col0 (type: string), VALUE._col1 (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1073,19 +1073,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 1600 Data size: 30800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1600 Data size: 150327 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) outputColumnNames: _col0 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: + Map-reduce partition columns: UDFToInteger(_col0) (type: int) - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1094,10 +1094,10 @@ STAGE PLANS: Select Operator expressions: KEY.reducesinkkey0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), 11 (type: int) outputColumnNames: _col0, _col1, _col2, _col3, _col4 - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 800 Data size: 15400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 469 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1167,19 +1167,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 3200 Data size: 48800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 313367 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 6400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 455 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), hr (type: int) outputColumnNames: _col0, _col4 - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: '2008-04-08' (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: '2008-04-08' (type: string), _col4 (type: int) - Statistics: Num rows: 1600 Data size: 556800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1740 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1188,11 +1188,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), 'foo' (type: string), 'bar' (type: string), '2008-04-08' (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 1600 Data size: 435200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1360 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 435200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1360 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1291,19 +1291,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 902167 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (value = 'bar') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1375 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col1 (type: string), _col2 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: _col1 (type: string), _col2 (type: int) - Statistics: Num rows: 1600 Data size: 422400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1320 Basic stats: COMPLETE Column stats: PARTIAL Execution mode: llap LLAP IO: may be used (ACID table) Reducer 2 @@ -1312,11 +1312,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), KEY._col1 (type: string), KEY._col2 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, '_bucket_number' - Statistics: Num rows: 1600 Data size: 579200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1810 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 579200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1810 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1485,19 +1485,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo_no_cp - Statistics: Num rows: 1600 Data size: 318800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 1600 Data size: 598664 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 800 Data size: 150400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1860 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 800 Data size: 280800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - Statistics: Num rows: 800 Data size: 280800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), 'bar' (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -1507,11 +1507,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 800 Data size: 359200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 800 Data size: 359200 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat @@ -1581,19 +1581,19 @@ STAGE PLANS: Map Operator Tree: TableScan alias: acid_2l_part_sdpo_no_cp - Statistics: Num rows: 3200 Data size: 637600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 3200 Data size: 1197144 Basic stats: COMPLETE Column stats: PARTIAL Filter Operator predicate: (key = 'foo') (type: boolean) - Statistics: Num rows: 1600 Data size: 300800 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 1860 Basic stats: COMPLETE Column stats: PARTIAL Select Operator expressions: ROW__ID (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), key (type: string), ds (type: string), hr (type: int) outputColumnNames: _col0, _col1, _col3, _col4 - Statistics: Num rows: 1600 Data size: 561600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL Reduce Output Operator key expressions: _col3 (type: string), _col4 (type: int), '_bucket_number' (type: string), _col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>) sort order: ++++ Map-reduce partition columns: _col3 (type: string), _col4 (type: int) - Statistics: Num rows: 1600 Data size: 561600 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 2675 Basic stats: COMPLETE Column stats: PARTIAL value expressions: _col1 (type: string), 'bar' (type: string) Execution mode: llap LLAP IO: may be used (ACID table) @@ -1603,11 +1603,11 @@ STAGE PLANS: Select Operator expressions: KEY._col0 (type: struct<transactionid:bigint,bucketid:int,rowid:bigint>), VALUE._col1 (type: string), VALUE._col2 (type: string), KEY._col3 (type: string), KEY._col4 (type: int), KEY.'_bucket_number' (type: string) outputColumnNames: _col0, _col1, _col2, _col3, _col4, '_bucket_number' - Statistics: Num rows: 1600 Data size: 718400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL File Output Operator compressed: false Dp Sort State: PARTITION_BUCKET_SORTED - Statistics: Num rows: 1600 Data size: 718400 Basic stats: COMPLETE Column stats: PARTIAL + Statistics: Num rows: 5 Data size: 3165 Basic stats: COMPLETE Column stats: PARTIAL table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat output format: org.apache.hadoop.hive.ql.io.orc.OrcOutputFormat
http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/empty_join.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/empty_join.q.out b/ql/src/test/results/clientpositive/llap/empty_join.q.out index 19aa89f..a5168e6 100644 --- a/ql/src/test/results/clientpositive/llap/empty_join.q.out +++ b/ql/src/test/results/clientpositive/llap/empty_join.q.out @@ -63,31 +63,31 @@ Stage-0 Stage-1 Map 1 llap File Output Operator [FS_14] - Map Join Operator [MAPJOIN_22] (rows=2 width=1) + Map Join Operator [MAPJOIN_22] (rows=2 width=4) Conds:SEL_2._col0=RS_10._col0(Left Outer),SEL_2._col0=RS_11._col0(Inner),Output:["_col0","_col1","_col2"] <-Map 2 [BROADCAST_EDGE] llap BROADCAST [RS_10] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=0) + Select Operator [SEL_5] (rows=1 width=4) Output:["_col0"] - Filter Operator [FIL_20] (rows=1 width=0) + Filter Operator [FIL_20] (rows=1 width=4) predicate:id is not null - TableScan [TS_3] (rows=1 width=0) - default@test_2,t2,Tbl:PARTIAL,Col:NONE,Output:["id"] + TableScan [TS_3] (rows=1 width=4) + default@test_2,t2,Tbl:COMPLETE,Col:NONE,Output:["id"] <-Map 3 [BROADCAST_EDGE] llap BROADCAST [RS_11] PartitionCols:_col0 - Select Operator [SEL_8] (rows=1 width=1) + Select Operator [SEL_8] (rows=1 width=4) Output:["_col0"] - Filter Operator [FIL_21] (rows=1 width=1) + Filter Operator [FIL_21] (rows=1 width=4) predicate:id is not null - TableScan [TS_6] (rows=1 width=1) + TableScan [TS_6] (rows=1 width=4) default@test_3,t3,Tbl:COMPLETE,Col:NONE,Output:["id"] - <-Select Operator [SEL_2] (rows=1 width=1) + <-Select Operator [SEL_2] (rows=1 width=4) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=1) + Filter Operator [FIL_19] (rows=1 width=4) predicate:id is not null - TableScan [TS_0] (rows=1 width=1) + TableScan [TS_0] (rows=1 width=4) default@test_1,t1,Tbl:COMPLETE,Col:NONE,Output:["id"] PREHOOK: query: SELECT t1.id, t2.id, t3.id http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/except_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/except_distinct.q.out b/ql/src/test/results/clientpositive/llap/except_distinct.q.out index 7d2222b..c21bed8 100644 --- a/ql/src/test/results/clientpositive/llap/except_distinct.q.out +++ b/ql/src/test/results/clientpositive/llap/except_distinct.q.out @@ -701,42 +701,42 @@ STAGE PLANS: Map Operator Tree: TableScan alias: a - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: int) outputColumnNames: value - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: value (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 15 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Map 5 Map Operator Tree: TableScan alias: b - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: int) outputColumnNames: key - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: key (type: int) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 5 Data size: 20 Basic stats: COMPLETE Column stats: NONE Execution mode: llap LLAP IO: no inputs Reducer 2 @@ -746,32 +746,32 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), 2 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), (_col1 * _col2) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), sum(_col2) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Reducer 4 Execution mode: llap @@ -781,17 +781,17 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((_col1 > 0) and ((_col1 * 2) = _col2)) (type: boolean) - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat @@ -803,32 +803,32 @@ STAGE PLANS: keys: KEY._col0 (type: int) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col0 (type: int) mode: complete outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), 1 (type: bigint), _col1 (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: int), _col2 (type: bigint), (_col1 * _col2) (type: bigint) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col1), sum(_col2) keys: _col0 (type: int) mode: hash outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: int) sort order: + Map-reduce partition columns: _col0 (type: int) - Statistics: Num rows: 2 Data size: 6 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint), _col2 (type: bigint) Union 3 Vertex: Union 3 http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/explainuser_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out index 22d8e95..48c02a2 100644 --- a/ql/src/test/results/clientpositive/llap/explainuser_1.q.out +++ b/ql/src/test/results/clientpositive/llap/explainuser_1.q.out @@ -131,15 +131,15 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Group By Operator [GBY_6] (rows=1 width=16) + Group By Operator [GBY_6] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_5] - Group By Operator [GBY_4] (rows=1 width=16) + Group By Operator [GBY_4] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_2] (rows=500 width=102) + Select Operator [SEL_2] (rows=500 width=272) Output:["_col0","_col1"] - TableScan [TS_0] (rows=500 width=102) + TableScan [TS_0] (rows=500 width=272) default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: alter table src_orc_merge_test_part partition (ds='2012-01-03', ts='2012-01-03+14:46:31') concatenate @@ -190,15 +190,15 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Group By Operator [GBY_6] (rows=1 width=16) + Group By Operator [GBY_6] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_5] - Group By Operator [GBY_4] (rows=1 width=16) + Group By Operator [GBY_4] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(_col0)","sum(_col1)"] - Select Operator [SEL_2] (rows=500 width=102) + Select Operator [SEL_2] (rows=500 width=272) Output:["_col0","_col1"] - TableScan [TS_0] (rows=500 width=102) + TableScan [TS_0] (rows=500 width=272) default@src_orc_merge_test_part,src_orc_merge_test_part,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: drop table src_orc_merge_test_part @@ -2883,16 +2883,16 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=2 width=19) + Group By Operator [GBY_4] (rows=2 width=16) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col2)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:_col0 - Group By Operator [GBY_2] (rows=4 width=19) + Group By Operator [GBY_2] (rows=4 width=16) Output:["_col0","_col1","_col2","_col3","_col4","_col5"],aggregations:["count(DISTINCT b)","count(DISTINCT c)","sum(d)"],keys:a, b, c - Select Operator [SEL_1] (rows=4 width=19) + Select Operator [SEL_1] (rows=4 width=16) Output:["a","b","c","d"] - TableScan [TS_0] (rows=4 width=19) + TableScan [TS_0] (rows=4 width=16) default@abcd,abcd,Tbl:COMPLETE,Col:NONE,Output:["a","b","c","d"] PREHOOK: query: explain select a, count(distinct b), count(distinct c), sum(d) from abcd group by a @@ -2910,14 +2910,14 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_5] - Group By Operator [GBY_3] (rows=2 width=19) + Group By Operator [GBY_3] (rows=2 width=16) Output:["_col0","_col1","_col2","_col3"],aggregations:["count(DISTINCT KEY._col1:0._col0)","count(DISTINCT KEY._col1:1._col0)","sum(VALUE._col0)"],keys:KEY._col0 <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:a - Select Operator [SEL_1] (rows=4 width=19) + Select Operator [SEL_1] (rows=4 width=16) Output:["a","b","c","d"] - TableScan [TS_0] (rows=4 width=19) + TableScan [TS_0] (rows=4 width=16) default@abcd,abcd,Tbl:COMPLETE,Col:NONE,Output:["a","b","c","d"] PREHOOK: query: explain create table src_rc_merge_test(key int, value string) stored as rcfile @@ -3025,13 +3025,13 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=1 width=16) + Group By Operator [GBY_4] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] - Select Operator [SEL_1] (rows=5 width=6) + Select Operator [SEL_1] (rows=5 width=188) Output:["_col0","_col1"] - TableScan [TS_0] (rows=5 width=6) + TableScan [TS_0] (rows=5 width=188) default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: alter table tgt_rc_merge_test concatenate @@ -3097,13 +3097,13 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Group By Operator [GBY_4] (rows=1 width=16) + Group By Operator [GBY_4] (rows=1 width=204) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_3] - Select Operator [SEL_1] (rows=5 width=6) + Select Operator [SEL_1] (rows=5 width=188) Output:["_col0","_col1"] - TableScan [TS_0] (rows=5 width=6) + TableScan [TS_0] (rows=5 width=188) default@tgt_rc_merge_test,tgt_rc_merge_test,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: drop table src_rc_merge_test @@ -3380,9 +3380,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=3 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=3 width=8) Conds:RS_2.key=RS_3.value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] @@ -3410,9 +3410,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_11] - Select Operator [SEL_10] (rows=6 width=9) + Select Operator [SEL_10] (rows=6 width=8) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_21] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_21] (rows=6 width=8) Conds:RS_4.key=RS_6.value(Inner),RS_4.key=RS_8.key(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -3451,9 +3451,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=6 width=9) + Select Operator [SEL_7] (rows=6 width=8) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_9] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_9] (rows=6 width=8) Conds:RS_3.key=RS_4.value(Inner),RS_3.key=RS_5.key(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] @@ -3486,9 +3486,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_11] - Select Operator [SEL_10] (rows=6 width=9) + Select Operator [SEL_10] (rows=6 width=8) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_15] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_15] (rows=6 width=8) Conds:RS_4.key, value=RS_6.value, key(Inner),RS_4.key, value=RS_8.key, value(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] @@ -3527,9 +3527,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_8] - Select Operator [SEL_7] (rows=6 width=9) + Select Operator [SEL_7] (rows=6 width=8) Output:["_col0","_col1","_col2","_col3","_col4","_col5"] - Merge Join Operator [MERGEJOIN_9] (rows=6 width=9) + Merge Join Operator [MERGEJOIN_9] (rows=6 width=8) Conds:RS_3.key, value=RS_4.value, key(Inner),RS_3.key, value=RS_5.key, value(Inner),Output:["_col0","_col1","_col5","_col6","_col10","_col11"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_3] @@ -3562,9 +3562,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=3 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=3 width=8) Conds:RS_2.key=RS_3.value(Left Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] @@ -3592,9 +3592,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=3 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=3 width=8) Conds:RS_2.key=RS_3.value(Right Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] @@ -3622,9 +3622,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=3 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=3 width=8) Conds:RS_2.key=RS_3.value(Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] @@ -3652,9 +3652,9 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=3 width=9) + Select Operator [SEL_5] (rows=3 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=3 width=9) + Merge Join Operator [MERGEJOIN_7] (rows=3 width=8) Conds:RS_2.key=RS_3.value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] @@ -3748,19 +3748,19 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=28 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=28 width=8) Conds:RS_2.key=RS_3.key(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) + TableScan [TS_0] (rows=26 width=8) default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) + TableScan [TS_1] (rows=26 width=8) default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key AND a.value <=> b.value @@ -3778,19 +3778,19 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=28 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=28 width=8) Conds:RS_2.key, value=RS_3.key, value(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key, value - TableScan [TS_0] (rows=26 width=7) + TableScan [TS_0] (rows=26 width=8) default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key, value - TableScan [TS_1] (rows=26 width=7) + TableScan [TS_1] (rows=26 width=8) default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(a) */ * FROM smb_input1 a RIGHT OUTER JOIN smb_input1 b ON a.key <=> b.key @@ -3808,19 +3808,19 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=28 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=28 width=8) Conds:RS_2.key=RS_3.key(Right Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) + TableScan [TS_0] (rows=26 width=8) default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) + TableScan [TS_1] (rows=26 width=8) default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a JOIN smb_input1 b ON a.key <=> b.key @@ -3838,19 +3838,19 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=28 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=28 width=8) Conds:RS_2.key=RS_3.key(Inner),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) + TableScan [TS_0] (rows=26 width=8) default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) + TableScan [TS_1] (rows=26 width=8) default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: explain select /*+ MAPJOIN(b) */ * FROM smb_input1 a LEFT OUTER JOIN smb_input1 b ON a.key <=> b.key @@ -3868,19 +3868,19 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_6] - Select Operator [SEL_5] (rows=28 width=7) + Select Operator [SEL_5] (rows=28 width=8) Output:["_col0","_col1","_col2","_col3"] - Merge Join Operator [MERGEJOIN_7] (rows=28 width=7) + Merge Join Operator [MERGEJOIN_7] (rows=28 width=8) Conds:RS_2.key=RS_3.key(Left Outer),Output:["_col0","_col1","_col5","_col6"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_2] PartitionCols:key - TableScan [TS_0] (rows=26 width=7) + TableScan [TS_0] (rows=26 width=8) default@smb_input1,a,Tbl:COMPLETE,Col:NONE,Output:["key","value"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_3] PartitionCols:key - TableScan [TS_1] (rows=26 width=7) + TableScan [TS_1] (rows=26 width=8) default@smb_input1,b,Tbl:COMPLETE,Col:NONE,Output:["key","value"] PREHOOK: query: drop table sales @@ -3952,27 +3952,27 @@ Stage-0 Stage-1 Reducer 2 llap File Output Operator [FS_12] - Merge Join Operator [MERGEJOIN_17] (rows=2 width=15) + Merge Join Operator [MERGEJOIN_17] (rows=2 width=11) Conds:RS_8._col1=RS_9._col0(Left Semi),Output:["_col0","_col1"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_8] PartitionCols:_col1 - Select Operator [SEL_2] (rows=1 width=13) + Select Operator [SEL_2] (rows=1 width=188) Output:["_col0","_col1"] - Filter Operator [FIL_15] (rows=1 width=13) + Filter Operator [FIL_15] (rows=1 width=188) predicate:id is not null - TableScan [TS_0] (rows=1 width=13) + TableScan [TS_0] (rows=1 width=188) default@sales,sales,Tbl:COMPLETE,Col:NONE,Output:["name","id"] <-Map 3 [SIMPLE_EDGE] llap SHUFFLE [RS_9] PartitionCols:_col0 - Group By Operator [GBY_7] (rows=2 width=14) + Group By Operator [GBY_7] (rows=2 width=10) Output:["_col0"],keys:_col0 - Select Operator [SEL_5] (rows=2 width=14) + Select Operator [SEL_5] (rows=2 width=10) Output:["_col0"] - Filter Operator [FIL_16] (rows=2 width=14) + Filter Operator [FIL_16] (rows=2 width=10) predicate:id is not null - TableScan [TS_3] (rows=2 width=14) + TableScan [TS_3] (rows=2 width=10) default@things,things,Tbl:COMPLETE,Col:NONE,Output:["id"] PREHOOK: query: drop table sales @@ -5307,49 +5307,51 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) +Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 1 llap - File Output Operator [FS_18] - Map Join Operator [MAPJOIN_35] (rows=3 width=33) - Conds:SEL_2._col0=RS_13._col0(Inner),RS_13._col0=RS_14._col0(Inner),RS_14._col0=RS_15._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 2 [BROADCAST_EDGE] llap - BROADCAST [RS_13] + Map 3 llap + File Output Operator [FS_21] + Map Join Operator [MAPJOIN_37] (rows=2 width=404) + Conds:RS_16._col0=RS_17._col0(Inner),RS_17._col0=MAPJOIN_36._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_16] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=1 width=30) + Filter Operator [FIL_32] (rows=1 width=368) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 3 [BROADCAST_EDGE] llap - BROADCAST [RS_14] + TableScan [TS_0] (rows=1 width=368) + default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_17] PartitionCols:_col0 - Select Operator [SEL_8] (rows=1 width=20) + Select Operator [SEL_5] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_33] (rows=1 width=20) + Filter Operator [FIL_33] (rows=1 width=368) predicate:key is not null - TableScan [TS_6] (rows=1 width=20) - default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col0 - Select Operator [SEL_11] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=368) + default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Map Join Operator [MAPJOIN_36] (rows=1 width=404) + Conds:SEL_8._col0=RS_13._col0(Inner),Output:["_col0","_col1","_col2","_col3"] + <-Map 4 [BROADCAST_EDGE] llap + BROADCAST [RS_13] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=1 width=368) + Output:["_col0","_col1"] + Filter Operator [FIL_35] (rows=1 width=368) + predicate:key is not null + TableScan [TS_9] (rows=1 width=368) + default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Select Operator [SEL_8] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_34] (rows=1 width=30) + Filter Operator [FIL_34] (rows=1 width=368) predicate:key is not null - TableScan [TS_9] (rows=1 width=30) - default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_31] (rows=1 width=30) - predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_6] (rows=1 width=368) + default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] PREHOOK: query: explain select /*+ STREAMTABLE(a,c) */ * @@ -5366,49 +5368,51 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 2 (BROADCAST_EDGE), Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) +Map 3 <- Map 1 (BROADCAST_EDGE), Map 2 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Map 1 llap - File Output Operator [FS_18] - Map Join Operator [MAPJOIN_35] (rows=3 width=33) - Conds:SEL_2._col0=RS_13._col0(Inner),RS_13._col0=RS_14._col0(Inner),RS_14._col0=RS_15._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] - <-Map 2 [BROADCAST_EDGE] llap - BROADCAST [RS_13] + Map 3 llap + File Output Operator [FS_21] + Map Join Operator [MAPJOIN_37] (rows=2 width=404) + Conds:RS_16._col0=RS_17._col0(Inner),RS_17._col0=MAPJOIN_36._col0(Inner),Output:["_col0","_col1","_col2","_col3","_col4","_col5","_col6","_col7"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_16] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_32] (rows=1 width=30) + Filter Operator [FIL_32] (rows=1 width=368) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 3 [BROADCAST_EDGE] llap - BROADCAST [RS_14] + TableScan [TS_0] (rows=1 width=368) + default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Map 2 [BROADCAST_EDGE] llap + BROADCAST [RS_17] PartitionCols:_col0 - Select Operator [SEL_8] (rows=1 width=20) + Select Operator [SEL_5] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_33] (rows=1 width=20) + Filter Operator [FIL_33] (rows=1 width=368) predicate:key is not null - TableScan [TS_6] (rows=1 width=20) - default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_15] - PartitionCols:_col0 - Select Operator [SEL_11] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=368) + default@t2,b,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Map Join Operator [MAPJOIN_36] (rows=1 width=404) + Conds:SEL_8._col0=RS_13._col0(Inner),Output:["_col0","_col1","_col2","_col3"] + <-Map 4 [BROADCAST_EDGE] llap + BROADCAST [RS_13] + PartitionCols:_col0 + Select Operator [SEL_11] (rows=1 width=368) + Output:["_col0","_col1"] + Filter Operator [FIL_35] (rows=1 width=368) + predicate:key is not null + TableScan [TS_9] (rows=1 width=368) + default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + <-Select Operator [SEL_8] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_34] (rows=1 width=30) + Filter Operator [FIL_34] (rows=1 width=368) predicate:key is not null - TableScan [TS_9] (rows=1 width=30) - default@t4,d,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_31] (rows=1 width=30) - predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] + TableScan [TS_6] (rows=1 width=368) + default@t3,c,Tbl:COMPLETE,Col:NONE,Output:["key","val"] PREHOOK: query: explain FROM T1 a JOIN src c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) PREHOOK: type: QUERY @@ -5443,11 +5447,11 @@ Stage-0 <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_6] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_2] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=368) Output:["_col0","_col1"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=368) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=368) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] <-Select Operator [SEL_5] (rows=500 width=87) Output:["_col0"] @@ -5539,24 +5543,24 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_11] PartitionCols:rand() - Select Operator [SEL_9] (rows=1 width=33) + Select Operator [SEL_9] (rows=1 width=202) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_21] (rows=1 width=33) + Map Join Operator [MAPJOIN_21] (rows=1 width=202) Conds:SEL_2._col0=RS_7._col0(Inner),Output:["_col0","_col1"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_5] (rows=1 width=184) Output:["_col0"] - Filter Operator [FIL_20] (rows=1 width=30) + Filter Operator [FIL_20] (rows=1 width=184) predicate:val is not null - TableScan [TS_3] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=184) default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["val"] - <-Select Operator [SEL_2] (rows=1 width=30) + <-Select Operator [SEL_2] (rows=1 width=184) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=184) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=184) default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] PREHOOK: query: explain select sum(hash(k.key)), sum(hash(v.val)) from T1 k join T1 v on k.key=v.key @@ -5566,44 +5570,44 @@ POSTHOOK: type: QUERY Plan optimized by CBO. Vertex dependency in root stage -Map 1 <- Map 4 (BROADCAST_EDGE) -Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) -Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +Map 2 <- Map 1 (BROADCAST_EDGE) +Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE) +Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) Stage-0 Fetch Operator limit:-1 Stage-1 - Reducer 3 llap + Reducer 4 llap File Output Operator [FS_16] Group By Operator [GBY_14] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] - <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap + <-Reducer 3 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_13] Group By Operator [GBY_12] (rows=1 width=16) Output:["_col0","_col1"],aggregations:["sum(VALUE._col0)","sum(VALUE._col1)"] - <-Map 1 [CUSTOM_SIMPLE_EDGE] llap + <-Map 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_11] PartitionCols:rand() - Select Operator [SEL_9] (rows=1 width=33) + Select Operator [SEL_9] (rows=1 width=202) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_21] (rows=1 width=33) - Conds:SEL_2._col0=RS_7._col0(Inner),Output:["_col0","_col2"] - <-Map 4 [BROADCAST_EDGE] llap - BROADCAST [RS_7] + Map Join Operator [MAPJOIN_21] (rows=1 width=202) + Conds:RS_6._col0=SEL_5._col0(Inner),Output:["_col0","_col2"] + <-Map 1 [BROADCAST_EDGE] llap + BROADCAST [RS_6] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) - Output:["_col0","_col1"] - Filter Operator [FIL_20] (rows=1 width=30) + Select Operator [SEL_2] (rows=1 width=184) + Output:["_col0"] + Filter Operator [FIL_19] (rows=1 width=184) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) - default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_2] (rows=1 width=30) - Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=184) + default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] + <-Select Operator [SEL_5] (rows=1 width=368) + Output:["_col0","_col1"] + Filter Operator [FIL_20] (rows=1 width=368) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) - default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"] + TableScan [TS_3] (rows=1 width=368) + default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["key","val"] PREHOOK: query: explain select count(1) from T1 a join T1 b on a.key = b.key PREHOOK: type: QUERY @@ -5631,22 +5635,22 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_10] PartitionCols:rand() - Map Join Operator [MAPJOIN_20] (rows=1 width=33) + Map Join Operator [MAPJOIN_20] (rows=1 width=202) Conds:SEL_2._col0=RS_7._col0(Inner) <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_7] PartitionCols:_col0 - Select Operator [SEL_5] (rows=1 width=30) + Select Operator [SEL_5] (rows=1 width=184) Output:["_col0"] - Filter Operator [FIL_19] (rows=1 width=30) + Filter Operator [FIL_19] (rows=1 width=184) predicate:key is not null - TableScan [TS_3] (rows=1 width=30) + TableScan [TS_3] (rows=1 width=184) default@t1,b,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Select Operator [SEL_2] (rows=1 width=30) + <-Select Operator [SEL_2] (rows=1 width=184) Output:["_col0"] - Filter Operator [FIL_18] (rows=1 width=30) + Filter Operator [FIL_18] (rows=1 width=184) predicate:key is not null - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=184) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key"] PREHOOK: query: explain FROM T1 a LEFT OUTER JOIN T2 c ON c.key+1=a.key select sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) @@ -5675,20 +5679,20 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=404) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=404) Conds:SEL_1.UDFToDouble(_col0)=RS_5.(UDFToDouble(_col0) + 1.0)(Left Outer),Output:["_col0","_col1","_col2"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_5] PartitionCols:(UDFToDouble(_col0) + 1.0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=184) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=184) default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] - <-Select Operator [SEL_1] (rows=1 width=30) + <-Select Operator [SEL_1] (rows=1 width=368) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=368) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] PREHOOK: query: explain FROM T1 a RIGHT OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) @@ -5717,20 +5721,20 @@ Stage-0 <-Map 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=404) Output:["_col0","_col1","_col2"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=404) Conds:RS_4.UDFToDouble(_col0)=SEL_3.(UDFToDouble(_col0) + 1.0)(Right Outer),Output:["_col0","_col1","_col2"] <-Map 1 [BROADCAST_EDGE] llap BROADCAST [RS_4] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_1] (rows=1 width=30) + Select Operator [SEL_1] (rows=1 width=368) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=368) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_3] (rows=1 width=30) + <-Select Operator [SEL_3] (rows=1 width=184) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=184) default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] PREHOOK: query: explain FROM T1 a FULL OUTER JOIN T2 c ON c.key+1=a.key select /*+ STREAMTABLE(a) */ sum(hash(a.key)), sum(hash(a.val)), sum(hash(c.key)) @@ -5759,23 +5763,23 @@ Stage-0 <-Reducer 2 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=404) Output:["_col0","_col1","_col2"] - Merge Join Operator [MERGEJOIN_15] (rows=1 width=33) + Merge Join Operator [MERGEJOIN_15] (rows=1 width=404) Conds:RS_4.UDFToDouble(_col0)=RS_5.(UDFToDouble(_col0) + 1.0)(Outer),Output:["_col0","_col1","_col2"] <-Map 1 [SIMPLE_EDGE] llap SHUFFLE [RS_4] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_1] (rows=1 width=30) + Select Operator [SEL_1] (rows=1 width=368) Output:["_col0","_col1"] - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=368) default@t1,a,Tbl:COMPLETE,Col:NONE,Output:["key","val"] <-Map 5 [SIMPLE_EDGE] llap SHUFFLE [RS_5] PartitionCols:(UDFToDouble(_col0) + 1.0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=184) Output:["_col0"] - TableScan [TS_2] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=184) default@t2,c,Tbl:COMPLETE,Col:NONE,Output:["key"] PREHOOK: query: explain select /*+ mapjoin(v)*/ sum(hash(k.key)), sum(hash(v.val)) from T1 k left outer join T1 v on k.key+1=v.key @@ -5804,19 +5808,19 @@ Stage-0 <-Map 1 [CUSTOM_SIMPLE_EDGE] llap PARTITION_ONLY_SHUFFLE [RS_9] PartitionCols:rand() - Select Operator [SEL_7] (rows=1 width=33) + Select Operator [SEL_7] (rows=1 width=202) Output:["_col0","_col1"] - Map Join Operator [MAPJOIN_17] (rows=1 width=33) + Map Join Operator [MAPJOIN_17] (rows=1 width=202) Conds:SEL_1.(UDFToDouble(_col0) + 1.0)=RS_5.UDFToDouble(_col0)(Left Outer),Output:["_col0","_col2"] <-Map 4 [BROADCAST_EDGE] llap BROADCAST [RS_5] PartitionCols:UDFToDouble(_col0) - Select Operator [SEL_3] (rows=1 width=30) + Select Operator [SEL_3] (rows=1 width=368) Output:["_col0","_col1"] - TableScan [TS_2] (rows=1 width=30) + TableScan [TS_2] (rows=1 width=368) default@t1,v,Tbl:COMPLETE,Col:NONE,Output:["key","val"] - <-Select Operator [SEL_1] (rows=1 width=30) + <-Select Operator [SEL_1] (rows=1 width=184) Output:["_col0"] - TableScan [TS_0] (rows=1 width=30) + TableScan [TS_0] (rows=1 width=184) default@t1,k,Tbl:COMPLETE,Col:NONE,Output:["key"]
