Repository: hive Updated Branches: refs/heads/master 6dd01360a -> ae1eb15d4
http://git-wip-us.apache.org/repos/asf/hive/blob/ae1eb15d/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out index 70cdd7a..1f60366 100644 --- a/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/vector_groupby_mapjoin.q.out @@ -1,4 +1,6 @@ -Warning: Map Join MAPJOIN[42][bigTable=?] in task 'Stage-8:MAPRED' is a cross product +Warning: Map Join MAPJOIN[53][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[43][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: explain vectorization expression select * from src @@ -23,13 +25,17 @@ PLAN VECTORIZATION: STAGE DEPENDENCIES: Stage-4 is a root stage - Stage-10 depends on stages: Stage-4 - Stage-8 depends on stages: Stage-10 - Stage-7 depends on stages: Stage-5, Stage-8 , consists of Stage-9, Stage-2 - Stage-9 has a backup stage: Stage-2 - Stage-6 depends on stages: Stage-9 - Stage-3 depends on stages: Stage-2, Stage-6 + Stage-10 depends on stages: Stage-4 , consists of Stage-13, Stage-1 + Stage-13 has a backup stage: Stage-1 + Stage-9 depends on stages: Stage-13 + Stage-8 depends on stages: Stage-1, Stage-5, Stage-9 , consists of Stage-11, Stage-12, Stage-2 + Stage-11 has a backup stage: Stage-2 + Stage-6 depends on stages: Stage-11 + Stage-3 depends on stages: Stage-2, Stage-6, Stage-7 + Stage-12 has a backup stage: Stage-2 + Stage-7 depends on stages: Stage-12 Stage-2 + Stage-1 Stage-5 is a root stage Stage-0 depends on stages: Stage-3 @@ -51,26 +57,27 @@ STAGE PLANS: projectedOutputColumnNums: [0] Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator - aggregations: count(), count(key) Group By Vectorization: - aggregators: VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0:string) -> bigint className: VectorGroupByOperator groupByMode: HASH + keyExpressions: col 0:string native: false vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1] + projectedOutputColumnNums: [] + keys: key (type: string) mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0 + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - sort order: + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint), _col1 (type: bigint) + Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized Map Vectorization: enabled: true @@ -87,95 +94,107 @@ STAGE PLANS: enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Reduce Operator Tree: Group By Operator - aggregations: count(VALUE._col0), count(VALUE._col1) + keys: KEY._col0 (type: string) mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: _col0 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-10 + Conditional Operator + + Stage: Stage-13 Map Reduce Local Work Alias -> Map Local Tables: - $hdt$_0:src + $hdt$_0:$INTNAME Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $hdt$_0:src + $hdt$_0:$INTNAME + TableScan + HashTable Sink Operator + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + + Stage: Stage-9 + Map Reduce + Map Operator Tree: TableScan alias: src Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true Select Operator expressions: key (type: string), value (type: string) outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE - HashTable Sink Operator + Map Join Operator + condition map: + Left Outer Join 0 to 1 keys: - 0 - 1 - - Stage: Stage-8 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 - 1 - Map Join Vectorization: - bigTableValueExpressions: col 0:bigint, col 1:bigint - className: VectorMapJoinOperator - native: false - nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - outputColumnNames: _col0, _col1, _col2, _col3 - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator + 0 _col0 (type: string) + 1 _col0 (type: string) + Map Join Vectorization: + bigTableKeyExpressions: col 0:string + bigTableValueExpressions: col 0:string, col 1:string + className: VectorMapJoinOperator native: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true + nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Execution mode: vectorized Map Vectorization: enabled: true enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [] - featureSupportInUse: [] - inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat + inputFormatFeatureSupport: [DECIMAL_64] + featureSupportInUse: [DECIMAL_64] + inputFileFormats: org.apache.hadoop.mapred.TextInputFormat allNative: false usesVectorUDFAdaptor: false vectorized: true Local Work: Map Reduce Local Work - Stage: Stage-7 + Stage: Stage-8 Conditional Operator - Stage: Stage-9 + Stage: Stage-11 Map Reduce Local Work Alias -> Map Local Tables: - $INTNAME1 + $hdt$_0:$INTNAME1 Fetch Operator limit: -1 Alias -> Map Local Operator Tree: - $INTNAME1 + $hdt$_0:$INTNAME1 TableScan HashTable Sink Operator keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 + 1 Stage: Stage-6 Map Reduce @@ -185,43 +204,50 @@ STAGE PLANS: native: true Map Join Operator condition map: - Left Outer Join 0 to 1 + Inner Join 0 to 1 keys: - 0 _col0 (type: string) - 1 _col0 (type: string) + 0 + 1 Map Join Vectorization: - bigTableKeyExpressions: col 0:string - bigTableValueExpressions: col 0:string, col 1:string, col 2:bigint, col 3:bigint + bigTableValueExpressions: col 0:string, col 1:string, col 2:boolean className: VectorMapJoinOperator native: false - nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true + nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - outputColumnNames: _col0, _col1, _col2, _col3, _col5 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE - Filter Operator - Filter Vectorization: - className: VectorFilterOperator + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Select Vectorization: + className: VectorSelectOperator native: true - predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 2:bigint, val 0), FilterExprAndExpr(children: SelectColumnIsNull(col 4:boolean), SelectColumnIsNotNull(col 0:string), FilterLongColGreaterEqualLongColumn(col 3:bigint, col 2:bigint))) - predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator + projectedOutputColumnNums: [0, 1, 3, 4, 2] + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Filter Operator + Filter Vectorization: + className: VectorFilterOperator native: true - projectedOutputColumnNums: [0, 1] + predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 0), FilterExprAndExpr(children: SelectColumnIsNull(col 2:boolean), SelectColumnIsNotNull(col 0:string), FilterLongColGreaterEqualLongColumn(col 4:bigint, col 3:bigint))) + predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Execution mode: vectorized Map Vectorization: enabled: true @@ -278,16 +304,141 @@ STAGE PLANS: output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + Stage: Stage-12 + Map Reduce Local Work + Alias -> Map Local Tables: + $hdt$_0:$INTNAME + Fetch Operator + limit: -1 + Alias -> Map Local Operator Tree: + $hdt$_0:$INTNAME + TableScan + HashTable Sink Operator + keys: + 0 + 1 + + Stage: Stage-7 + Map Reduce + Map Operator Tree: + TableScan + TableScan Vectorization: + native: true + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + Map Join Vectorization: + bigTableValueExpressions: col 0:bigint, col 1:bigint + className: VectorMapJoinOperator + native: false + nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true + nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1, 3, 4, 2] + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: FilterExprOrExpr(children: FilterLongColEqualLongScalar(col 3:bigint, val 0), FilterExprAndExpr(children: SelectColumnIsNull(col 2:boolean), SelectColumnIsNotNull(col 0:string), FilterLongColGreaterEqualLongColumn(col 4:bigint, col 3:bigint))) + predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumnNums: [0, 1] + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + Execution mode: vectorized + Map Vectorization: + enabled: true + enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true + inputFormatFeatureSupport: [] + featureSupportInUse: [] + inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat + allNative: false + usesVectorUDFAdaptor: false + vectorized: true + Local Work: + Map Reduce Local Work + Stage: Stage-2 Map Reduce Map Operator Tree: TableScan Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 500 Data size: 13812 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint), _col3 (type: bigint) + sort order: + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: string), _col1 (type: string), _col3 (type: boolean) + TableScan + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Reduce Operator Tree: + Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col3, _col4, _col5 + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string), _col4 (type: bigint), _col5 (type: bigint), _col3 (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE + Filter Operator + predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + + Stage: Stage-1 + Map Reduce + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 5312 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 + 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 + value expressions: _col1 (type: string) TableScan Reduce Output Operator key expressions: _col0 (type: string) @@ -302,21 +453,14 @@ STAGE PLANS: keys: 0 _col0 (type: string) 1 _col0 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3, _col5 - Statistics: Num rows: 550 Data size: 15193 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: ((_col2 = 0L) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), _col1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 366 Data size: 10110 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: _col0, _col1, _col3 + Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-5 Map Reduce @@ -335,27 +479,26 @@ STAGE PLANS: projectedOutputColumnNums: [0] Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE Group By Operator + aggregations: count(), count(key) Group By Vectorization: + aggregators: VectorUDAFCountStar(*) -> bigint, VectorUDAFCount(col 0:string) -> bigint className: VectorGroupByOperator groupByMode: HASH - keyExpressions: col 0:string native: false vectorProcessingMode: HASH - projectedOutputColumnNums: [] - keys: key (type: string) + projectedOutputColumnNums: [0, 1] mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) + sort order: Reduce Sink Vectorization: className: VectorReduceSinkOperator native: false nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true nativeConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint), _col1 (type: bigint) Execution mode: vectorized Map Vectorization: enabled: true @@ -372,20 +515,16 @@ STAGE PLANS: enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false Reduce Operator Tree: Group By Operator - keys: KEY._col0 (type: string) + aggregations: count(VALUE._col0), count(VALUE._col1) mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col0 (type: string), true (type: boolean) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - table: - input format: org.apache.hadoop.mapred.SequenceFileInputFormat - output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat - serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: NONE + File Output Operator + compressed: false + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe Stage: Stage-0 Fetch Operator @@ -393,7 +532,9 @@ STAGE PLANS: Processor Tree: ListSink -Warning: Map Join MAPJOIN[42][bigTable=?] in task 'Stage-8:MAPRED' is a cross product +Warning: Map Join MAPJOIN[53][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[43][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from src where not key in @@ -422,7 +563,9 @@ POSTHOOK: Output: database:default POSTHOOK: Output: default@orcsrc POSTHOOK: Lineage: orcsrc.key SIMPLE [(src)src.FieldSchema(name:key, type:string, comment:default), ] POSTHOOK: Lineage: orcsrc.value SIMPLE [(src)src.FieldSchema(name:value, type:string, comment:default), ] -Warning: Map Join MAPJOIN[42][bigTable=?] in task 'Stage-8:MAPRED' is a cross product +Warning: Map Join MAPJOIN[53][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[43][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from orcsrc where not key in @@ -439,7 +582,9 @@ order by key POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### -Warning: Map Join MAPJOIN[42][bigTable=?] in task 'Stage-8:MAPRED' is a cross product +Warning: Map Join MAPJOIN[53][bigTable=?] in task 'Stage-7:MAPRED' is a cross product +Warning: Map Join MAPJOIN[43][bigTable=?] in task 'Stage-6:MAPRED' is a cross product +Warning: Shuffle Join JOIN[19][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Stage 'Stage-2:MAPRED' is a cross product PREHOOK: query: select * from orcsrc where not key in