Repository: hive Updated Branches: refs/heads/master aef22bf4e -> 7fc723678
http://git-wip-us.apache.org/repos/asf/hive/blob/7fc72367/ql/src/test/results/clientpositive/llap/vector_join30.q.out.orig ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_join30.q.out.orig b/ql/src/test/results/clientpositive/llap/vector_join30.q.out.orig deleted file mode 100644 index 6b544f3..0000000 --- a/ql/src/test/results/clientpositive/llap/vector_join30.q.out.orig +++ /dev/null @@ -1,2220 +0,0 @@ -PREHOOK: query: CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src -PREHOOK: type: CREATETABLE_AS_SELECT -PREHOOK: Input: default@src -PREHOOK: Output: database:default -PREHOOK: Output: default@orcsrc -POSTHOOK: query: CREATE TABLE orcsrc STORED AS ORC AS SELECT * FROM src -POSTHOOK: type: CREATETABLE_AS_SELECT -POSTHOOK: Input: default@src -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), ] -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0) -> boolean - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 4 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0) -> boolean - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: true - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Map Join Vectorization: - className: VectorMapJoinInnerStringOperator - 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 - outputColumnNames: _col2, _col3 - input vertices: - 1 Reducer 5 - Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkEmptyKeyOperator - 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 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - Reducer 5 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -103231310608 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 4 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: true - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Left Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Map Join Vectorization: - className: VectorMapJoinOuterStringOperator - 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 - outputColumnNames: _col2, _col3 - input vertices: - 1 Reducer 5 - Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 3:int) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkEmptyKeyOperator - 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 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - Reducer 5 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -103231310608 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 2 (BROADCAST_EDGE) - Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 3 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reducer 4 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: true - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Right Outer Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - Map Join Vectorization: - className: VectorMapJoinOuterStringOperator - 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 - outputColumnNames: _col2, _col3 - input vertices: - 0 Reducer 2 - Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkEmptyKeyOperator - 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 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 5 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -103231310608 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) - Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) - Reducer 5 <- Map 4 (SIMPLE_EDGE) - Reducer 6 <- Map 4 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0) -> boolean - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 4 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Filter Operator - Filter Vectorization: - className: VectorFilterOperator - native: true - predicateExpression: SelectColumnIsNotNull(col 0) -> boolean - predicate: key is not null (type: boolean) - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: true - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - Inner Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - Map Join Vectorization: - className: VectorMapJoinOperator - native: false - nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true - nativeConditionsNotMet: One MapJoin Condition IS false - outputColumnNames: _col2, _col3 - input vertices: - 1 Reducer 5 - 2 Reducer 6 - Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Reduce Sink Vectorization: - className: VectorReduceSinkEmptyKeyOperator - 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 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) - Reducer 3 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - Reducer 5 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 6 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -348019368476 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 7 <- Map 5 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 5 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Inner Join 0 to 1 - Left Outer Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - vectorOutput: false - native: false - projectedOutputColumns: null - 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 - value expressions: _col0 (type: bigint) - Reducer 4 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - Reducer 6 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 7 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -348019368476 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 7 <- Map 5 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 5 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reducer 3 - Execution mode: llap - Reduce Operator Tree: - Merge Join Operator - condition map: - Left Outer Join 0 to 1 - Left Outer Join 0 to 2 - keys: - 0 _col0 (type: string) - 1 _col0 (type: string) - 2 _col0 (type: string) - outputColumnNames: _col2, _col3 - Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(hash(_col2,_col3)) - Group By Vectorization: - vectorOutput: false - native: false - projectedOutputColumns: null - 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 - value expressions: _col0 (type: bigint) - Reducer 4 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 0) -> bigint - className: VectorGroupByOperator - vectorOutput: true - native: false - projectedOutputColumns: [0] - mode: mergepartial - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - File Sink Vectorization: - className: VectorFileSinkOperator - native: false - Statistics: Num rows: 1 Data size: 8 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 - Reducer 6 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1, 0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string) - Reducer 7 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true - groupByVectorOutput: true - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Map-reduce partition columns: _col0 (type: string) - Reduce Sink Vectorization: - className: VectorReduceSinkStringOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - - Stage: Stage-0 - Fetch Operator - limit: -1 - Processor Tree: - ListSink - -PREHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -PREHOOK: Input: default@orcsrc -#### A masked pattern was here #### -POSTHOOK: query: FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@orcsrc -#### A masked pattern was here #### -348019368476 -PREHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization expression -FROM -(SELECT orcsrc.* FROM orcsrc sort by key) x -LEFT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Y -ON (x.key = Y.key) -RIGHT OUTER JOIN -(SELECT orcsrc.* FROM orcsrc sort by value) Z -ON (x.key = Z.key) -select sum(hash(Y.key,Y.value)) -POSTHOOK: type: QUERY -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-0 depends on stages: Stage-1 - -STAGE PLANS: - Stage: Stage-1 - Tez -#### A masked pattern was here #### - Edges: - Reducer 2 <- Map 1 (SIMPLE_EDGE) - Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE) - Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE) - Reducer 6 <- Map 5 (SIMPLE_EDGE) - Reducer 7 <- Map 5 (SIMPLE_EDGE) -#### A masked pattern was here #### - Vertices: - Map 1 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string) - outputColumnNames: _col0 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Map 5 - Map Operator Tree: - TableScan - alias: orcsrc - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedOutputColumns: [0, 1] - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Select Operator - expressions: key (type: string), value (type: string) - outputColumnNames: _col0, _col1 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumns: [0, 1] - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Reduce Sink Vectorization: - className: VectorReduceSinkObjectHashOperator - 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 - Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string) - Execution mode: vectorized, llap - LLAP IO: all inputs - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true - groupByVectorOutput: true - inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true - usesVectorUDFAdaptor: false - vectorized: true - Reducer 2 - Execution mode: vectorized, llap - Reduce Vectorization: - enabled: true - enableCondi <TRUNCATED>
