http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out index 8efe78d..c9b9e81 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin3.q.out @@ -146,14 +146,16 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) Map Join Vectorization: - bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [3] - bigTableValueColumnNums: [3] + bigTableKeyColumns: 1:int + bigTableRetainColumnNums: [3] + bigTableValueColumns: 3:decimal(8,1) bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [3] + nonOuterSmallTableKeyMapping: [] + projectedOutput: 3:decimal(8,1) + hashTableImplementationType: OPTIMIZED outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -217,10 +219,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0] + valueColumns: 0:int Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized, llap @@ -281,10 +282,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 @@ -351,14 +351,16 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) Map Join Vectorization: - bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [3] - bigTableValueColumnNums: [3] + bigTableKeyColumns: 1:int + bigTableRetainColumnNums: [3] + bigTableValueColumns: 3:decimal(8,1) bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [3] + nonOuterSmallTableKeyMapping: [] + projectedOutput: 3:decimal(8,1) + hashTableImplementationType: OPTIMIZED outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -422,10 +424,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0] + valueColumns: 0:int Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized, llap @@ -486,10 +487,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0 @@ -556,14 +556,16 @@ STAGE PLANS: 0 _col1 (type: int) 1 _col0 (type: int) Map Join Vectorization: - bigTableKeyColumnNums: [1] - bigTableRetainedColumnNums: [3] - bigTableValueColumnNums: [3] + bigTableKeyColumns: 1:int + bigTableRetainColumnNums: [3] + bigTableValueColumns: 3:decimal(8,1) bigTableValueExpressions: ConvertDecimal64ToDecimal(col 0:decimal(8,1)/DECIMAL_64) -> 3:decimal(8,1) className: VectorMapJoinInnerBigOnlyLongOperator native: true nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - projectedOutputColumnNums: [3] + nonOuterSmallTableKeyMapping: [] + projectedOutput: 3:decimal(8,1) + hashTableImplementationType: OPTIMIZED outputColumnNames: _col0 input vertices: 1 Reducer 3 @@ -627,10 +629,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0] + valueColumns: 0:int Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int) Execution mode: vectorized, llap @@ -691,10 +692,9 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE Stage: Stage-0
http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out b/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out index beaf86f..d52e212 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_ptf.q.out @@ -155,11 +155,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -410,10 +410,10 @@ STAGE PLANS: Map-reduce partition columns: p_partkey (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [1, 2, 5] + valueColumns: 1:string, 2:string, 5:int Statistics: Num rows: 26 Data size: 5902 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_name (type: string), p_mfgr (type: string), p_size (type: int) Execution mode: vectorized, llap @@ -455,10 +455,9 @@ STAGE PLANS: Map-reduce partition columns: p_partkey (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -494,6 +493,9 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 27 Data size: 6021 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: llap Reduce Vectorization: @@ -663,11 +665,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5] + partitionColumns: 2:string + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -822,11 +824,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -1074,11 +1076,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5] + partitionColumns: 2:string + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -1296,11 +1298,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5] + partitionColumns: 2:string + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -1520,11 +1522,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [0, 3, 4, 5, 6, 7, 8] + partitionColumns: 2:string + valueColumns: 0:int, 3:string, 4:string, 5:int, 6:string, 7:double, 8:string Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Execution mode: vectorized, llap @@ -1566,10 +1568,9 @@ STAGE PLANS: Map-reduce partition columns: p_partkey (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1641,6 +1642,9 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Stage: Stage-0 Fetch Operator @@ -1745,10 +1749,9 @@ STAGE PLANS: Map-reduce partition columns: p_partkey (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1781,11 +1784,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [0, 3, 4, 5, 6, 7, 8] + partitionColumns: 2:string + valueColumns: 0:int, 3:string, 4:string, 5:int, 6:string, 7:double, 8:string Statistics: Num rows: 26 Data size: 16094 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_partkey (type: int), p_brand (type: string), p_type (type: string), p_size (type: int), p_container (type: string), p_retailprice (type: double), p_comment (type: string) Execution mode: vectorized, llap @@ -1827,6 +1830,9 @@ STAGE PLANS: input format: org.apache.hadoop.mapred.SequenceFileInputFormat output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: llap Reduce Vectorization: @@ -2430,11 +2436,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -2681,11 +2687,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -3002,11 +3008,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -3224,11 +3230,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [0, 5, 7] + partitionColumns: 2:string + valueColumns: 0:int, 5:int, 7:double Statistics: Num rows: 26 Data size: 6110 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_partkey (type: int), p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -3270,10 +3276,9 @@ STAGE PLANS: Map-reduce partition columns: p_partkey (type: int) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator - keyColumnNums: [0] + keyColumns: 0:int native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [] Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: all inputs @@ -3344,6 +3349,9 @@ STAGE PLANS: Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 27 Data size: 6237 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col5 (type: int), _col7 (type: double) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 4 Execution mode: llap Reduce Vectorization: @@ -3518,11 +3526,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5] + partitionColumns: 2:string + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -3756,11 +3764,11 @@ STAGE PLANS: Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [0, 1] + keyColumns: 0:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [0] - valueColumnNums: [2] + partitionColumns: 0:string + valueColumns: 2:double Statistics: Num rows: 13 Data size: 2574 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col2 (type: double) Execution mode: vectorized, llap @@ -4019,11 +4027,11 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkObjectHashOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - partitionColumnNums: [2] - valueColumnNums: [5, 7] + partitionColumns: 2:string + valueColumns: 5:int, 7:double Statistics: Num rows: 26 Data size: 6006 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int), p_retailprice (type: double) Execution mode: vectorized, llap @@ -4536,10 +4544,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [2] + keyColumns: 2:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [1, 5] + valueColumns: 1:string, 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_name (type: string), p_size (type: int) Execution mode: vectorized, llap @@ -4885,10 +4893,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string) Reduce Sink Vectorization: className: VectorReduceSinkStringOperator - keyColumnNums: [2] + keyColumns: 2:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [1, 5] + valueColumns: 1:string, 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_name (type: string), p_size (type: int) Execution mode: vectorized, llap @@ -5231,10 +5239,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Reduce Sink Vectorization: className: VectorReduceSinkMultiKeyOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [5] + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -5553,10 +5561,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Reduce Sink Vectorization: className: VectorReduceSinkMultiKeyOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [5] + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -5917,10 +5925,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Reduce Sink Vectorization: className: VectorReduceSinkMultiKeyOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [5] + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap @@ -6250,10 +6258,10 @@ STAGE PLANS: Map-reduce partition columns: p_mfgr (type: string), p_name (type: string) Reduce Sink Vectorization: className: VectorReduceSinkMultiKeyOperator - keyColumnNums: [2, 1] + keyColumns: 2:string, 1:string native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [5] + valueColumns: 5:int Statistics: Num rows: 26 Data size: 5798 Basic stats: COMPLETE Column stats: COMPLETE value expressions: p_size (type: int) Execution mode: vectorized, llap http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out index 6421650..7142732 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_shufflejoin.q.out @@ -134,6 +134,9 @@ STAGE PLANS: sort order: Statistics: Num rows: 1 Data size: 32 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: bigint), _col1 (type: int), _col2 (type: int), _col3 (type: bigint), _col4 (type: bigint) + MergeJoin Vectorization: + enabled: false + enableConditionsNotMet: Vectorizing MergeJoin Supported IS false Reducer 3 Execution mode: vectorized, llap Reduce Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/llap/vectorized_timestamp.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_timestamp.q.out b/ql/src/test/results/clientpositive/llap/vectorized_timestamp.q.out index aa4d888..384bf61 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_timestamp.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_timestamp.q.out @@ -155,10 +155,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0, 1] + valueColumns: 0:timestamp, 1:timestamp Statistics: Num rows: 1 Data size: 80 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: timestamp), _col1 (type: timestamp) Execution mode: vectorized, llap @@ -381,10 +380,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0, 1] + valueColumns: 0:double, 1:bigint Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: bigint) Execution mode: vectorized, llap @@ -522,10 +520,9 @@ STAGE PLANS: sort order: Reduce Sink Vectorization: className: VectorReduceSinkEmptyKeyOperator - keyColumnNums: [] native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - valueColumnNums: [0, 1, 2] + valueColumns: 0:double, 1:double, 2:bigint Statistics: Num rows: 1 Data size: 24 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: double), _col1 (type: double), _col2 (type: bigint) Execution mode: vectorized, llap http://git-wip-us.apache.org/repos/asf/hive/blob/a37827ec/ql/src/test/results/clientpositive/mapjoin2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/mapjoin2.q.out b/ql/src/test/results/clientpositive/mapjoin2.q.out index 6b85e13..2288b4b 100644 --- a/ql/src/test/results/clientpositive/mapjoin2.q.out +++ b/ql/src/test/results/clientpositive/mapjoin2.q.out @@ -27,6 +27,85 @@ POSTHOOK: Output: default@tbl_n1 POSTHOOK: Lineage: tbl_n1.n SCRIPT [] POSTHOOK: Lineage: tbl_n1.t SCRIPT [] Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select a.n, a.t, isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a left outer join (select * from tbl_n1 where 1 = 2) b on a.n = b.n +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.n, a.t, isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a left outer join (select * from tbl_n1 where 1 = 2) b on a.n = b.n +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_1:tbl_n1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_1:tbl_n1 + TableScan + alias: tbl_n1 + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: n (type: bigint), t (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: tbl_n1 + filterExpr: (n = 1L) (type: boolean) + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (n = 1L) (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 1L (type: bigint), _col0 (type: string), _col1 is null (type: boolean), _col2 is null (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select a.n, a.t, isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a left outer join (select * from tbl_n1 where 1 = 2) b on a.n = b.n PREHOOK: type: QUERY PREHOOK: Input: default@tbl_n1 @@ -37,6 +116,91 @@ POSTHOOK: Input: default@tbl_n1 #### A masked pattern was here #### 1 one true true Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select isnull(a.n), isnull(a.t), b.n, b.t from (select * from tbl_n1 where 2 = 1) a right outer join (select * from tbl_n1 where n = 2) b on a.n = b.n +PREHOOK: type: QUERY +POSTHOOK: query: explain +select isnull(a.n), isnull(a.t), b.n, b.t from (select * from tbl_n1 where 2 = 1) a right outer join (select * from tbl_n1 where n = 2) b on a.n = b.n +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:tbl_n1 + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:tbl_n1 + TableScan + alias: tbl_n1 + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: false (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: n (type: bigint), t (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + HashTable Sink Operator + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: tbl_n1 + filterExpr: (n = 2L) (type: boolean) + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (n = 2L) (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: t (type: string) + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 is null (type: boolean), _col1 is null (type: boolean), 2L (type: bigint), _col2 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[13][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select isnull(a.n), isnull(a.t), b.n, b.t from (select * from tbl_n1 where 2 = 1) a right outer join (select * from tbl_n1 where n = 2) b on a.n = b.n PREHOOK: type: QUERY PREHOOK: Input: default@tbl_n1 @@ -47,6 +211,81 @@ POSTHOOK: Input: default@tbl_n1 #### A masked pattern was here #### true true 2 two Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product +PREHOOK: query: explain +select isnull(a.n), isnull(a.t), isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a full outer join (select * from tbl_n1 where n = 2) b on a.n = b.n +PREHOOK: type: QUERY +POSTHOOK: query: explain +select isnull(a.n), isnull(a.t), isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a full outer join (select * from tbl_n1 where n = 2) b on a.n = b.n +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: tbl_n1 + filterExpr: (n = 1L) (type: boolean) + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (n = 1L) (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 1L (type: bigint), t (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: string) + TableScan + alias: tbl_n1 + filterExpr: (n = 2L) (type: boolean) + Statistics: Num rows: 2 Data size: 10 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: (n = 2L) (type: boolean) + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: 2L (type: bigint), t (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 5 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: string) + Reduce Operator Tree: + Join Operator + condition map: + Full Outer Join 0 to 1 + filter predicates: + 0 + 1 {false} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 is null (type: boolean), _col1 is null (type: boolean), _col2 is null (type: boolean), _col3 is null (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 11 Basic stats: COMPLETE Column stats: NONE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Shuffle Join JOIN[8][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select isnull(a.n), isnull(a.t), isnull(b.n), isnull(b.t) from (select * from tbl_n1 where n = 1) a full outer join (select * from tbl_n1 where n = 2) b on a.n = b.n PREHOOK: type: QUERY PREHOOK: Input: default@tbl_n1 @@ -58,6 +297,74 @@ POSTHOOK: Input: default@tbl_n1 false false true true true true false false Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:_dummy_table + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:_dummy_table + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 11 (type: int), 1 (type: int), 1 (type: int), 0 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: _dummy_database@_dummy_table @@ -68,6 +375,77 @@ POSTHOOK: Input: _dummy_database@_dummy_table #### A masked pattern was here #### 11 1 1 0 0 Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a left outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a left outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_1:_dummy_table + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_1:_dummy_table + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 1 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col1, _col2 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 11 (type: int), 1 (type: int), _col1 (type: int), 0 (type: int), _col2 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a left outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: _dummy_database@_dummy_table @@ -78,6 +456,83 @@ POSTHOOK: Input: _dummy_database@_dummy_table #### A masked pattern was here #### 11 1 1 0 0 Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a right outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a right outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:_dummy_table + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:_dummy_table + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 11 (type: int), 1 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + HashTable Sink Operator + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), 1 (type: int), _col2 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product PREHOOK: query: select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a right outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key PREHOOK: type: QUERY PREHOOK: Input: _dummy_database@_dummy_table @@ -87,6 +542,83 @@ POSTHOOK: type: QUERY POSTHOOK: Input: _dummy_database@_dummy_table #### A masked pattern was here #### 11 1 1 0 0 +Warning: Map Join MAPJOIN[9][bigTable=?] in task 'Stage-3:MAPRED' is a cross product +PREHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a right outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +PREHOOK: type: QUERY +POSTHOOK: query: explain +select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a right outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key +POSTHOOK: type: QUERY +STAGE DEPENDENCIES: + Stage-4 is a root stage + Stage-3 depends on stages: Stage-4 + Stage-0 depends on stages: Stage-3 + +STAGE PLANS: + Stage: Stage-4 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:_dummy_table + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:_dummy_table + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: 11 (type: int), 1 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + HashTable Sink Operator + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + + Stage: Stage-3 + Map Reduce + Map Operator Tree: + TableScan + alias: _dummy_table + Row Limit Per Split: 1 + Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Right Outer Join 0 to 1 + filter predicates: + 0 + 1 {true} + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2 + Statistics: Num rows: 1 Data size: 12 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: int), _col1 (type: int), 1 (type: int), _col2 (type: int), 0 (type: int) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + Statistics: Num rows: 1 Data size: 20 Basic stats: COMPLETE Column stats: COMPLETE + 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 + Local Work: + Map Reduce Local Work + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + Warning: Shuffle Join JOIN[6][tables = [$hdt$_0, $hdt$_1]] in Stage 'Stage-1:MAPRED' is a cross product PREHOOK: query: select a.key, a.a_one, b.b_one, a.a_zero, b.b_zero from ( SELECT 11 key, 0 confuse_you, 1 a_one, 0 a_zero ) a full outer join ( SELECT 11 key, 0 confuse_you, 1 b_one, 0 b_zero ) b on a.key = b.key PREHOOK: type: QUERY