http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index 10b4168..5fbc4f6 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -825,10 +825,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -950,7 +950,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds is not null and hr is not null) (type: boolean) + filterExpr: (hr is not null and ds is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -966,10 +966,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -1322,29 +1322,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1355,6 +1355,21 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Target column: hr + Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: llap @@ -1365,7 +1380,7 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1440,16 +1455,16 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: (UDFToDouble(_col0) * 2.0) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1494,7 +1509,7 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1565,29 +1580,29 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToDouble(_col0) (type: double) sort order: + Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1608,7 +1623,7 @@ STAGE PLANS: keys: 0 UDFToDouble(_col0) (type: double) 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1679,20 +1694,20 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (UDFToDouble(hr) * 2.0) is not null (type: boolean) + filterExpr: (hr is not null and (UDFToDouble(hr) * 2.0) is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: (UDFToDouble(_col0) * 2.0) (type: double) sort order: + Map-reduce partition columns: (UDFToDouble(_col0) * 2.0) (type: double) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1722,7 +1737,7 @@ STAGE PLANS: keys: 0 (UDFToDouble(_col0) * 2.0) (type: double) 1 _col0 (type: double) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1810,25 +1825,25 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToString((UDFToDouble(hr) * 2.0)) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) sort order: + Map-reduce partition columns: UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and UDFToString(hr) is not null) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and UDFToString(hr) is not null) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToString(hr) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -1864,7 +1879,7 @@ STAGE PLANS: keys: 0 UDFToString((UDFToDouble(_col0) * 2.0)) (type: string) 1 UDFToString(_col0) (type: string) - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1928,7 +1943,6 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -1952,13 +1966,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 4 Map Operator Tree: @@ -1988,9 +2006,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 - 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: string) + 1 _col0 (type: string) + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2023,11 +2041,26 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator + expressions: _col0 (type: string) + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: + Group By Operator + keys: _col0 (type: string) + mode: hash + outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: ds + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Target column: ds + Target Vertex: Map 1 Stage: Stage-0 Fetch Operator @@ -2035,18 +2068,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Shuffle Join MERGEJOIN[21][tables = [$hdt$_0, $hdt$_1]] in Stage 'Reducer 2' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' 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 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' 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 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -2217,10 +2253,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -2485,6 +2521,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[5]) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2559,6 +2596,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[6]) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -2670,6 +2708,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[12]) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4004,10 +4043,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + filterExpr: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and ds is not null) and hr is not null) (type: boolean) + predicate: ((((date = '2008-04-08') and (UDFToDouble(hour) = 11.0)) and hr is not null) and ds is not null) (type: boolean) Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) @@ -4233,15 +4272,15 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: UDFToDouble(hr) is not null (type: boolean) + filterExpr: (hr is not null and UDFToDouble(hr) is not null) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -4250,7 +4289,7 @@ STAGE PLANS: 1 UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -4266,10 +4305,10 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_double_hour - filterExpr: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + filterExpr: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 2 Data size: 188 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((UDFToDouble(hour) = 11.0) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) + predicate: (((UDFToDouble(hour) = 11.0) and hr is not null) and UDFToDouble(UDFToInteger((hr / 2.0))) is not null) (type: boolean) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: double) @@ -4280,6 +4319,21 @@ STAGE PLANS: sort order: + Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: UDFToDouble(UDFToInteger((_col0 / 2.0))) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart + Partition key expr: UDFToDouble(hr) + Statistics: Num rows: 1 Data size: 94 Basic stats: COMPLETE Column stats: NONE + Target column: hr + Target Vertex: Map 1 Execution mode: vectorized, llap Reducer 2 Execution mode: vectorized, uber @@ -4346,11 +4400,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (UDFToDouble(hr) * 2.0) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -4359,7 +4413,7 @@ STAGE PLANS: 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -4459,7 +4513,6 @@ POSTHOOK: Input: default@srcpart@ds=2008-04-08/hr=11 POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 #### A masked pattern was here #### 1000 -Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: -- parent is reduce tasks EXPLAIN select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' PREHOOK: type: QUERY @@ -4482,13 +4535,17 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart - filterExpr: (ds = '2008-04-08') (type: boolean) - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + filterExpr: ds is not null (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + expressions: ds (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: - Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Execution mode: llap Map 2 Map Operator Tree: @@ -4519,26 +4576,25 @@ STAGE PLANS: mode: mergepartial outputColumnNames: _col0 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Select Operator - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - input vertices: - 0 Map 1 - Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + input vertices: + 0 Map 1 + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE + HybridGraceHashJoin: true + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + value expressions: _col0 (type: bigint) Reducer 4 Execution mode: vectorized, uber Reduce Operator Tree: @@ -4561,18 +4617,21 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[21][bigTable=?] in task 'Reducer 3' is a cross product PREHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' 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 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +PREHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### POSTHOOK: query: select count(*) from srcpart join (select ds as ds, ds as `date` from srcpart group by ds) s on (srcpart.ds = s.ds) where s.`date` = '2008-04-08' 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 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=11 +POSTHOOK: Input: default@srcpart@ds=2008-04-09/hr=12 #### A masked pattern was here #### 1000 PREHOOK: query: select count(*) from srcpart where ds = '2008-04-08' @@ -4745,6 +4804,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[5]) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4800,6 +4860,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[6]) (type: boolean) Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -4890,6 +4951,7 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart + filterExpr: (ds) IN (RS[12]) (type: boolean) Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string) @@ -5409,11 +5471,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: UDFToDouble(hr) is not null (type: boolean) - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: int) outputColumnNames: _col0, _col1 - Statistics: Num rows: 1000 Data size: 94000 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 188000 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -5422,7 +5484,7 @@ STAGE PLANS: 1 _col0 (type: string), UDFToDouble(_col2) (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 1100 Data size: 103400 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 206800 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Group By Operator aggregations: count() @@ -5438,35 +5500,50 @@ STAGE PLANS: Map Operator Tree: TableScan alias: srcpart_date_hour - filterExpr: (((((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + filterExpr: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) Statistics: Num rows: 4 Data size: 1440 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (((((date = '2008-04-08') or (date = '2008-04-09')) and (UDFToDouble(hour) = 11.0)) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + predicate: (((((UDFToDouble(hour) = 11.0) and ((date = '2008-04-08') or (date = '2008-04-09'))) and hr is not null) and ds is not null) and UDFToDouble(hr) is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) sort order: ++ Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col0 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Dynamic Partitioning Event Operator Target Input: srcpart_orc Partition key expr: ds - Statistics: Num rows: 1 Data size: 360 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE Target column: ds Target Vertex: Map 1 + Select Operator + expressions: UDFToDouble(_col2) (type: double) + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Group By Operator + keys: _col0 (type: double) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Dynamic Partitioning Event Operator + Target Input: srcpart_orc + Partition key expr: UDFToDouble(hr) + Statistics: Num rows: 2 Data size: 720 Basic stats: COMPLETE Column stats: NONE + Target column: hr + Target Vertex: Map 1 Execution mode: llap Reducer 2 Execution mode: uber
http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out index 899967b..f06f311 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_nested_mapjoin.q.out @@ -14,8 +14,8 @@ STAGE PLANS: Stage: Stage-1 Tez Edges: - Map 2 <- Map 1 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) - Reducer 3 <- Map 2 (SIMPLE_EDGE) + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 @@ -24,46 +24,27 @@ STAGE PLANS: alias: v1 Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (ctinyint is not null and csmallint is not null) (type: boolean) - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: tinyint) - sort order: + - Map-reduce partition columns: _col0 (type: tinyint) - Statistics: Num rows: 3072 Data size: 660491 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: smallint), _col2 (type: double) - Execution mode: vectorized, llap - Map 2 - Map Operator Tree: - TableScan - alias: v1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Filter Operator predicate: ctinyint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: tinyint) 1 _col0 (type: tinyint) - outputColumnNames: _col1, _col2 + outputColumnNames: _col2, _col3 input vertices: - 0 Map 1 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE + 1 Map 3 + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Select Operator - expressions: _col1 (type: smallint), _col2 (type: double) + expressions: _col2 (type: smallint), _col3 (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -73,7 +54,7 @@ STAGE PLANS: outputColumnNames: _col1 input vertices: 1 Map 4 - Statistics: Num rows: 7433 Data size: 1598388 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 14867 Data size: 3196776 Basic stats: COMPLETE Column stats: NONE HybridGraceHashJoin: true Group By Operator aggregations: sum(_col1) @@ -85,6 +66,25 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: double) Execution mode: vectorized, llap + Map 3 + Map Operator Tree: + TableScan + alias: v1 + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (ctinyint is not null and csmallint is not null) (type: boolean) + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: ctinyint (type: tinyint), csmallint (type: smallint), cdouble (type: double) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: tinyint) + sort order: + + Map-reduce partition columns: _col0 (type: tinyint) + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: smallint), _col2 (type: double) + Execution mode: vectorized, llap Map 4 Map Operator Tree: TableScan @@ -92,18 +92,18 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: csmallint is not null (type: boolean) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: csmallint (type: smallint) outputColumnNames: _col0 - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: smallint) sort order: + Map-reduce partition columns: _col0 (type: smallint) - Statistics: Num rows: 6144 Data size: 1320982 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap - Reducer 3 + Reducer 2 Execution mode: vectorized, uber Reduce Operator Tree: Group By Operator http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/llap_uncompressed.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap_uncompressed.q.out b/ql/src/test/results/clientpositive/llap_uncompressed.q.out index 73e6729..a9f0901 100644 --- a/ql/src/test/results/clientpositive/llap_uncompressed.q.out +++ b/ql/src/test/results/clientpositive/llap_uncompressed.q.out @@ -84,14 +84,14 @@ STAGE PLANS: Statistics: Num rows: 12288 Data size: 2907994 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: ((cint > 10) and cbigint is not null) (type: boolean) - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ctinyint (type: tinyint), csmallint (type: smallint), cint (type: int), cbigint (type: bigint), cfloat (type: float), cdouble (type: double), cstring1 (type: string), cstring2 (type: string), ctimestamp1 (type: timestamp), ctimestamp2 (type: timestamp), cboolean1 (type: boolean), cboolean2 (type: boolean) outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7, _col8, _col9, _col10, _col11 - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 2048 Data size: 484665 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 4096 Data size: 969331 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/louter_join_ppr.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/louter_join_ppr.q.out b/ql/src/test/results/clientpositive/louter_join_ppr.q.out index cb2edde..84dce67 100644 --- a/ql/src/test/results/clientpositive/louter_join_ppr.q.out +++ b/ql/src/test/results/clientpositive/louter_join_ppr.q.out @@ -293,8 +293,8 @@ STAGE PLANS: name: default.srcpart Truncated Path -> Alias: /src [$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:b] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -974,16 +974,16 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: (((((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 15.0)) and (UDFToDouble(key) < 25.0)) and key is not null) (type: boolean) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 3 Data size: 31 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE tag: 0 value expressions: _col1 (type: string) auto parallelism: false @@ -993,17 +993,17 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) > 10.0)) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + predicate: (((((UDFToDouble(key) > 15.0) and (UDFToDouble(key) < 25.0)) and (UDFToDouble(key) < 20.0)) and (UDFToDouble(key) > 10.0)) and key is not null) (type: boolean) + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 6 Data size: 63 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 12 Data size: 127 Basic stats: COMPLETE Column stats: NONE tag: 1 value expressions: _col1 (type: string) auto parallelism: false @@ -1147,9 +1147,9 @@ STAGE PLANS: name: default.srcpart name: default.srcpart Truncated Path -> Alias: - /src [$hdt$_0:$hdt$_0:a] - /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:$hdt$_1:b] - /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:$hdt$_1:b] + /src [$hdt$_0:a] + /srcpart/ds=2008-04-08/hr=11 [$hdt$_1:b] + /srcpart/ds=2008-04-08/hr=12 [$hdt$_1:b] Needs Tagging: true Reduce Operator Tree: Join Operator @@ -1159,13 +1159,13 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 6 Data size: 69 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 13 Data size: 139 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/mapjoin_distinct.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out index 4df25ca..3e81e47 100644 --- a/ql/src/test/results/clientpositive/mapjoin_distinct.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_distinct.q.out @@ -30,7 +30,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -44,7 +44,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -52,17 +52,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -70,7 +70,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partials outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -86,16 +86,16 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -166,7 +166,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -180,7 +180,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -188,17 +188,17 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Group By Operator keys: _col1 (type: string) mode: hash outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -206,10 +206,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -281,7 +281,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -295,7 +295,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -303,12 +303,12 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: rand() (type: double) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -316,7 +316,7 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -332,16 +332,16 @@ STAGE PLANS: key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Operator Tree: Group By Operator keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -412,7 +412,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 key (type: string) @@ -426,7 +426,7 @@ STAGE PLANS: Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -434,12 +434,12 @@ STAGE PLANS: 0 key (type: string) 1 key (type: string) outputColumnNames: _col1 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col1 (type: string) sort order: + Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE Local Work: Map Reduce Local Work Reduce Operator Tree: @@ -447,10 +447,10 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: complete outputColumnNames: _col0 - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out index 427e8b2..14c6f18 100644 --- a/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_mapjoin.q.out @@ -79,11 +79,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -97,11 +97,11 @@ STAGE PLANS: Filter Operator isSamplingPred: false predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -117,12 +117,12 @@ STAGE PLANS: GatherStats: false Filter Operator isSamplingPred: false - predicate: (key is not null and value is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + predicate: (value is not null and key is not null) (type: boolean) + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -131,7 +131,7 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0, _col1 Position of Big Table: 0 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -140,13 +140,13 @@ STAGE PLANS: 1 _col0 (type: string) outputColumnNames: _col0 Position of Big Table: 0 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false GlobalTableId: 0 #### A masked pattern was here #### NumFilesPerFileSink: 1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE #### A masked pattern was here #### table: input format: org.apache.hadoop.mapred.TextInputFormat @@ -495,11 +495,11 @@ STAGE PLANS: Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -513,11 +513,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (((value > 'val_450') and key is not null) and value is not null) (type: boolean) - Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 167 Data size: 1774 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 666 Data size: 7075 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -525,7 +525,7 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 183 Data size: 1951 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 732 Data size: 7782 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -533,10 +533,10 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0 - Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 805 Data size: 8560 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 201 Data size: 2146 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 805 Data size: 8560 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat @@ -577,11 +577,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: value is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: value (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col1 (type: string) @@ -595,11 +595,11 @@ STAGE PLANS: Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: (value is not null and key is not null) (type: boolean) - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string), ds (type: string) outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -607,7 +607,7 @@ STAGE PLANS: 0 _col1 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col2 - Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false table: @@ -630,11 +630,11 @@ STAGE PLANS: Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string) outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -651,18 +651,18 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col2 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() keys: _col2 (type: string) mode: hash outputColumnNames: _col0, _col1 - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2420 Data size: 25709 Basic stats: COMPLETE Column stats: NONE value expressions: _col1 (type: bigint) Local Work: Map Reduce Local Work @@ -672,14 +672,14 @@ STAGE PLANS: keys: KEY._col0 (type: string) mode: mergepartial outputColumnNames: _col0, _col1 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col1 (type: bigint) outputColumnNames: _col0 - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 302 Data size: 3208 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1210 Data size: 12854 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out b/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out index 50f3d9b..52a5e65 100644 --- a/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out +++ b/ql/src/test/results/clientpositive/mapjoin_memcheck.q.out @@ -47,11 +47,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE HashTable Sink Operator keys: 0 _col0 (type: string) @@ -65,11 +65,11 @@ STAGE PLANS: Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Filter Operator predicate: key is not null (type: boolean) - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 - Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 @@ -77,10 +77,10 @@ STAGE PLANS: 0 _col0 (type: string) 1 _col0 (type: string) outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false - Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.TextInputFormat output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
