Repository: hive Updated Branches: refs/heads/master 6fa9f6339 -> 65f02d2f9
http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out index b256f4f..889f23c 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_multiskew_3.q.out @@ -194,14 +194,55 @@ OPTIMIZED SQL: SELECT CAST('145' AS STRING) AS `key`, `value`, CAST('1' AS STRIN FROM `default`.`fact_daily_n3` WHERE `ds` = '1' AND `hr` = '1' AND `key` = '145' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n3 + filterExpr: ((ds = '1') and (hr = '1') and (key = '145')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = '145') (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '145' (type: string), value (type: string), '1' (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: hr=1 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -248,21 +289,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n3 name: default.fact_daily_n3 + Truncated Path -> Alias: + /fact_daily_n3/ds=1/hr=1 [fact_daily_n3] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n3 - filterExpr: ((ds = '1') and (hr = '1') and (key = '145')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = '145') (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '145' (type: string), value (type: string), '1' (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: select * from fact_daily_n3 where ds = '1' and hr='1' and key='145' PREHOOK: type: QUERY @@ -313,14 +347,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, CAST('val_484' AS STRING) FROM `default`.`fact_daily_n3` WHERE `ds` = '1' AND `hr` = '2' AND `key` = '484' AND `value` = 'val_484' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n3 + filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = '484') and (value = 'val_484')) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '484' (type: string), 'val_484' (type: string), '1' (type: string), '2' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: value=val_484 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -367,21 +442,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n3 name: default.fact_daily_n3 + Truncated Path -> Alias: + /fact_daily_n3/ds=1/hr=2/key=484/value=val_484 [fact_daily_n3] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n3 - filterExpr: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = '484') and (value = 'val_484')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '484' (type: string), 'val_484' (type: string), '1' (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT * FROM fact_daily_n3 WHERE ds='1' and hr='2' and (key='484' and value='val_484') PREHOOK: type: QUERY @@ -404,14 +472,55 @@ OPTIMIZED SQL: SELECT CAST('327' AS STRING) AS `key`, CAST('val_327' AS STRING) FROM `default`.`fact_daily_n3` WHERE `ds` = '1' AND `hr` = '3' AND `key` = '327' AND `value` = 'val_327' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n3 + filterExpr: ((key = '327') and (value = 'val_327')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((key = '327') and (value = 'val_327')) (type: boolean) + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '327' (type: string), 'val_327' (type: string), '1' (type: string), '3' (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: value=val_327 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -458,21 +567,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n3 name: default.fact_daily_n3 + Truncated Path -> Alias: + /fact_daily_n3/ds=1/hr=3/key=327/value=val_327 [fact_daily_n3] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n3 - filterExpr: ((key = '327') and (value = 'val_327')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((key = '327') and (value = 'val_327')) (type: boolean) - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '327' (type: string), 'val_327' (type: string), '1' (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT * FROM fact_daily_n3 WHERE ds='1' and hr='3' and (key='327' and value='val_327') PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out index d4304b1..dcff8a5 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_1.q.out @@ -135,14 +135,55 @@ OPTIMIZED SQL: SELECT CAST(484 AS INTEGER) AS `x` FROM `default`.`fact_daily_n4` WHERE `ds` = '1' AND `x` = 484 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n4 + filterExpr: ((ds = '1') and (x = 484)) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x = 484) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 484 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: x=484 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -186,21 +227,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n4 name: default.fact_daily_n4 + Truncated Path -> Alias: + /fact_tz/ds=1/x=484 [fact_daily_n4] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n4 - filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 484 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT x FROM fact_daily_n4 WHERE ds='1' and x=484 PREHOOK: type: QUERY @@ -221,14 +255,55 @@ OPTIMIZED SQL: SELECT CAST(495 AS INTEGER) AS `x` FROM `default`.`fact_daily_n4` WHERE `ds` = '1' AND `x` = 495 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n4 + filterExpr: ((ds = '1') and (x = 495)) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x = 495) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 495 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -272,21 +347,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n4 name: default.fact_daily_n4 + Truncated Path -> Alias: + /fact_tz/ds=1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily_n4] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n4 - filterExpr: ((ds = '1') and (x = 495)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x = 495) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 495 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT x FROM fact_daily_n4 WHERE ds='1' and x=495 PREHOOK: type: QUERY @@ -307,14 +375,55 @@ OPTIMIZED SQL: SELECT CAST(1 AS INTEGER) AS `x` FROM `default`.`fact_daily_n4` WHERE `ds` = '1' AND `x` = 1 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n4 + filterExpr: ((ds = '1') and (x = 1)) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x = 1) (type: boolean) + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 1 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -358,21 +467,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n4 name: default.fact_daily_n4 + Truncated Path -> Alias: + /fact_tz/ds=1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily_n4] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n4 - filterExpr: ((ds = '1') and (x = 1)) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x = 1) (type: boolean) - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 1 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 80 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT x FROM fact_daily_n4 WHERE ds='1' and x=1 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out index 465805a..3251dc4 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_2.q.out @@ -138,14 +138,55 @@ OPTIMIZED SQL: SELECT CAST(484 AS INTEGER) AS `x` FROM `default`.`fact_daily_n5` WHERE `ds` = '1' AND `x` = 484 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n5 + filterExpr: ((ds = '1') and (x = 484)) (type: boolean) + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x = 484) (type: boolean) + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 484 (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: x=484 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -189,21 +230,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n5 name: default.fact_daily_n5 + Truncated Path -> Alias: + /fact_tz/ds=1/x=484 [fact_daily_n5] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n5 - filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 484 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: select x from (select * from fact_daily_n5 where ds = '1') subq where x = 484 PREHOOK: type: QUERY @@ -224,14 +258,55 @@ OPTIMIZED SQL: SELECT CAST(484 AS INTEGER) AS `x1`, `y` AS `y1` FROM `default`.`fact_daily_n5` WHERE `ds` = '1' AND `x` = 484 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n5 + filterExpr: ((ds = '1') and (x = 484)) (type: boolean) + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x = 484) (type: boolean) + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: 484 (type: int), y (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1 + columns.types int:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: x=484 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -275,21 +350,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n5 name: default.fact_daily_n5 + Truncated Path -> Alias: + /fact_tz/ds=1/x=484 [fact_daily_n5] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n5 - filterExpr: ((ds = '1') and (x = 484)) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x = 484) (type: boolean) - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: 484 (type: int), y (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 240 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: select x1, y1 from(select x as x1, y as y1 from fact_daily_n5 where ds ='1') subq where x1 = 484 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out index bab5179..a61d9d8 100644 --- a/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out +++ b/ql/src/test/results/clientpositive/list_bucket_query_oneskew_3.q.out @@ -158,14 +158,55 @@ OPTIMIZED SQL: SELECT `x` FROM `default`.`fact_daily_n0` WHERE `ds` = '1' AND `x` <> 86 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: fact_daily_n0 + filterExpr: ((ds = '1') and (x <> 86)) (type: boolean) + Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (x <> 86) (type: boolean) + Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + Select Operator + expressions: x (type: int) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0 + columns.types int + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -209,21 +250,108 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.fact_daily_n0 name: default.fact_daily_n0 +#### A masked pattern was here #### + Partition + base file name: x=238 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 1 + properties: + bucket_count -1 + column.name.delimiter , + columns x,y,z + columns.comments + columns.types int:string:string +#### A masked pattern was here #### + name default.fact_daily_n0 + numFiles 3 + partition_columns ds + partition_columns.types string + serialization.ddl struct fact_daily_n0 { i32 x, string y, string z} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 117 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + EXTERNAL TRUE + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns x,y,z + columns.comments + columns.types int:string:string +#### A masked pattern was here #### + name default.fact_daily_n0 + partition_columns ds + partition_columns.types string + serialization.ddl struct fact_daily_n0 { i32 x, string y, string z} + 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.fact_daily_n0 + name: default.fact_daily_n0 +#### A masked pattern was here #### + Partition + base file name: x=484 + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + partition values: + ds 1 + properties: + bucket_count -1 + column.name.delimiter , + columns x,y,z + columns.comments + columns.types int:string:string +#### A masked pattern was here #### + name default.fact_daily_n0 + numFiles 3 + partition_columns ds + partition_columns.types string + serialization.ddl struct fact_daily_n0 { i32 x, string y, string z} + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + totalSize 117 +#### A masked pattern was here #### + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + input format: org.apache.hadoop.mapred.TextInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat + properties: + EXTERNAL TRUE + bucket_count -1 + bucketing_version 2 + column.name.delimiter , + columns x,y,z + columns.comments + columns.types int:string:string +#### A masked pattern was here #### + name default.fact_daily_n0 + partition_columns ds + partition_columns.types string + serialization.ddl struct fact_daily_n0 { i32 x, string y, string z} + 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.fact_daily_n0 + name: default.fact_daily_n0 + Truncated Path -> Alias: + /fact_tz/ds=1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [fact_daily_n0] + /fact_tz/ds=1/x=238 [fact_daily_n0] + /fact_tz/ds=1/x=484 [fact_daily_n0] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: fact_daily_n0 - filterExpr: ((ds = '1') and (x <> 86)) (type: boolean) - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (x <> 86) (type: boolean) - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE - Select Operator - expressions: x (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 1170 Basic stats: PARTIAL Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT x FROM fact_daily_n0 WHERE ds='1' and not (x = 86) PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/nonmr_fetch.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/nonmr_fetch.q.out b/ql/src/test/results/clientpositive/nonmr_fetch.q.out index cd8d78b..366dc1e 100644 --- a/ql/src/test/results/clientpositive/nonmr_fetch.q.out +++ b/ql/src/test/results/clientpositive/nonmr_fetch.q.out @@ -127,33 +127,109 @@ POSTHOOK: Input: default@src 278 98 484 +PREHOOK: query: explain select * from srcpart where ds='2008-04-08' AND key > 100 limit 10 +PREHOOK: type: QUERY +POSTHOOK: query: explain select * from srcpart where ds='2008-04-08' AND key > 100 limit 10 +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: ((ds = '2008-04-08') and (UDFToDouble(key) > 100.0D)) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0D) (type: boolean) + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 333 Data size: 3537 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + + Stage: Stage-0 + Fetch Operator + limit: 10 + Processor Tree: + ListSink + +PREHOOK: query: select * from srcpart where ds='2008-04-08' AND key > 100 limit 10 +PREHOOK: type: QUERY +PREHOOK: Input: default@srcpart +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +POSTHOOK: query: select * from srcpart where ds='2008-04-08' AND key > 100 limit 10 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@srcpart +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=12 +#### A masked pattern was here #### +238 val_238 2008-04-08 11 +311 val_311 2008-04-08 11 +165 val_165 2008-04-08 11 +409 val_409 2008-04-08 11 +255 val_255 2008-04-08 11 +278 val_278 2008-04-08 11 +484 val_484 2008-04-08 11 +265 val_265 2008-04-08 11 +193 val_193 2008-04-08 11 +401 val_401 2008-04-08 11 PREHOOK: query: explain select * from srcpart where key > 100 limit 10 PREHOOK: type: QUERY POSTHOOK: query: explain select * from srcpart where key > 100 limit 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) > 100.0D) (type: boolean) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Limit + Number of rows: 10 + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + Stage: Stage-0 Fetch Operator limit: 10 Processor Tree: - TableScan - alias: srcpart - filterExpr: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(key) > 100.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Limit - Number of rows: 10 - Statistics: Num rows: 10 Data size: 100 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: select * from srcpart where key > 100 limit 10 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/ppr_pushdown3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out index 56e90d7..f802ff7 100644 --- a/ql/src/test/results/clientpositive/ppr_pushdown3.q.out +++ b/ql/src/test/results/clientpositive/ppr_pushdown3.q.out @@ -3,25 +3,38 @@ PREHOOK: type: QUERY POSTHOOK: query: explain select * from srcpart where key < 10 POSTHOOK: type: QUERY STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: srcpart + filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (UDFToDouble(key) < 10.0D) (type: boolean) + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - TableScan - alias: srcpart - filterExpr: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (UDFToDouble(key) < 10.0D) (type: boolean) - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), ds (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: select * from srcpart where key < 10 PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out index 232d188..3f6efd9 100644 --- a/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out +++ b/ql/src/test/results/clientpositive/rand_partitionpruner3.q.out @@ -6,14 +6,54 @@ OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` FROM `default`.`srcpart` WHERE RAND(1) < 0.1 AND `ds` = '2008-04-08' AND `key` <= 50 AND `key` >= 10 AND `hr` LIKE '%2' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: a + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D) and (rand(1) < 0.1D)) (type: boolean) + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -60,20 +100,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=12 [a] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: a - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D) and (rand(1) < 0.1D)) (type: boolean) - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 18 Data size: 191 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: select a.* from srcpart a where rand(1) < 0.1 and a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY @@ -98,14 +132,55 @@ OPTIMIZED SQL: SELECT `key`, `value`, CAST('2008-04-08' AS STRING) AS `ds`, `hr` FROM `default`.`srcpart` WHERE `ds` = '2008-04-08' AND `key` <= 50 AND `key` >= 10 AND `hr` LIKE '%2' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: a + filterExpr: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2,_col3 + columns.types string:string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: hr=12 input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat partition values: @@ -152,21 +227,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe name: default.srcpart name: default.srcpart + Truncated Path -> Alias: + /srcpart/ds=2008-04-08/hr=12 [a] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: a - filterExpr: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: ((UDFToDouble(key) <= 50.0D) and (UDFToDouble(key) >= 10.0D)) (type: boolean) - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string), '2008-04-08' (type: string), hr (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: select a.* from srcpart a where a.ds = '2008-04-08' and not(key > 50 or key < 10) and a.hr like '%2' PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out index 27d21f3..60e5cd8 100644 --- a/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out +++ b/ql/src/test/results/clientpositive/truncate_column_list_bucket.q.out @@ -57,14 +57,55 @@ OPTIMIZED SQL: SELECT CAST('484' AS STRING) AS `key`, `value`, CAST('1' AS STRIN FROM `default`.`test_tab_n3` WHERE `part` = '1' AND `key` = '484' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: test_tab_n3 + filterExpr: ((part = '1') and (key = '484')) (type: boolean) + Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = '484') (type: boolean) + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '484' (type: string), value (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: key=484 input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat partition values: @@ -109,21 +150,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.test_tab_n3 name: default.test_tab_n3 + Truncated Path -> Alias: + /test_tab_n3/part=1/key=484 [test_tab_n3] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: test_tab_n3 - filterExpr: ((part = '1') and (key = '484')) (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = '484') (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '484' (type: string), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT * FROM test_tab_n3 WHERE part = '1' AND key = '484' PREHOOK: type: QUERY @@ -144,14 +178,55 @@ OPTIMIZED SQL: SELECT CAST('0' AS STRING) AS `key`, `value`, CAST('1' AS STRING) FROM `default`.`test_tab_n3` WHERE `part` = '1' AND `key` = '0' STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: - Stage: Stage-0 - Fetch Operator - limit: -1 - Partition Description: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: test_tab_n3 + filterExpr: ((part = '1') and (key = '0')) (type: boolean) + Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE + GatherStats: false + Filter Operator + isSamplingPred: false + predicate: (key = '0') (type: boolean) + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: '0' (type: string), value (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + GlobalTableId: 0 +#### A masked pattern was here #### + NumFilesPerFileSink: 1 + Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE +#### A masked pattern was here #### + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + properties: + columns _col0,_col1,_col2 + columns.types string:string:string + escape.delim \ + hive.serialization.extend.additional.nesting.levels true + serialization.escape.crlf true + serialization.format 1 + serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + TotalFiles: 1 + GatherStats: false + MultiFileSpray: false + Execution mode: vectorized + Path -> Alias: +#### A masked pattern was here #### + Path -> Partition: +#### A masked pattern was here #### Partition + base file name: HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME input format: org.apache.hadoop.hive.ql.io.RCFileInputFormat output format: org.apache.hadoop.hive.ql.io.RCFileOutputFormat partition values: @@ -196,21 +271,14 @@ STAGE PLANS: serde: org.apache.hadoop.hive.serde2.columnar.ColumnarSerDe name: default.test_tab_n3 name: default.test_tab_n3 + Truncated Path -> Alias: + /test_tab_n3/part=1/HIVE_DEFAULT_LIST_BUCKETING_DIR_NAME [test_tab_n3] + + Stage: Stage-0 + Fetch Operator + limit: -1 Processor Tree: - TableScan - alias: test_tab_n3 - filterExpr: ((part = '1') and (key = '0')) (type: boolean) - Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE - GatherStats: false - Filter Operator - isSamplingPred: false - predicate: (key = '0') (type: boolean) - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: '0' (type: string), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink PREHOOK: query: SELECT * FROM test_tab_n3 WHERE part = '1' AND key = '0' PREHOOK: type: QUERY http://git-wip-us.apache.org/repos/asf/hive/blob/65f02d2f/ql/src/test/results/clientpositive/union_view.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/union_view.q.out b/ql/src/test/results/clientpositive/union_view.q.out index ba98ef0..8d844b8 100644 --- a/ql/src/test/results/clientpositive/union_view.q.out +++ b/ql/src/test/results/clientpositive/union_view.q.out @@ -23,67 +23,106 @@ POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@src_union_3_n0 STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src_union_1_n0 + filterExpr: ((key = 86) and (ds = '1')) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = 86) (type: boolean) + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 86 (type: int), value (type: string), '1' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - TableScan - alias: src_union_1_n0 - filterExpr: ((key = 86) and (ds = '1')) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 86) (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 86 (type: int), value (type: string), '1' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src_union_2_n0 + filterExpr: ((key = 86) and (ds = '2')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 86 (type: int), value (type: string), '2' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - TableScan - alias: src_union_2_n0 - filterExpr: ((key = 86) and (ds = '2')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 86 (type: int), value (type: string), '2' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink STAGE DEPENDENCIES: - Stage-0 is a root stage + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 STAGE PLANS: + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src_union_3_n0 + filterExpr: ((key = 86) and (ds = '3')) (type: boolean) + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (key = 86) (type: boolean) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 86 (type: int), value (type: string), '3' (type: string) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Execution mode: vectorized + Stage: Stage-0 Fetch Operator limit: -1 Processor Tree: - TableScan - alias: src_union_3_n0 - filterExpr: ((key = 86) and (ds = '3')) (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: (key = 86) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: 86 (type: int), value (type: string), '3' (type: string) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - ListSink + ListSink 86 val_86 1 86 val_86 2
