http://git-wip-us.apache.org/repos/asf/hive/blob/afa9ffee/ql/src/test/results/clientpositive/vector_windowing_gby.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vector_windowing_gby.q.out b/ql/src/test/results/clientpositive/vector_windowing_gby.q.out deleted file mode 100644 index 7585f26..0000000 --- a/ql/src/test/results/clientpositive/vector_windowing_gby.q.out +++ /dev/null @@ -1,245 +0,0 @@ -PREHOOK: query: explain vectorization detail - select rank() over (order by return_ratio) as return_rank from - (select sum(wr.cint)/sum(ws.c_int) as return_ratio - from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 - group by ws.c_boolean ) in_web -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail - select rank() over (order by return_ratio) as return_rank from - (select sum(wr.cint)/sum(ws.c_int) as return_ratio - from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 - group by ws.c_boolean ) in_web -POSTHOOK: type: QUERY -Explain -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string), c_int (type: int), c_boolean (type: boolean) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 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: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: boolean) - TableScan - alias: wr - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cstring1 is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cint (type: int), cstring1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Map Vectorization: - enabled: false - enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3), sum(_col1) - keys: _col2 (type: boolean) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 2906160 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-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2] - projectedColumns: [_col0:boolean, _col1:bigint, _col2:bigint] - Reduce Output Operator - key expressions: _col0 (type: boolean) - sort order: + - Map-reduce partition columns: _col0 (type: boolean) - 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: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - 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 - rowBatchContext: - dataColumnCount: 3 - includeColumns: [0, 1, 2] - dataColumns: _col0:boolean, _col1:bigint, _col2:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col2 (type: bigint) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 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-3 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1] - projectedColumns: [_col1:bigint, _col2:bigint] - Reduce Output Operator - key expressions: 0 (type: int), (UDFToDouble(_col1) / UDFToDouble(_col2)) (type: double) - sort order: ++ - Map-reduce partition columns: 0 (type: int) - 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: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - 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 - rowBatchContext: - dataColumnCount: 2 - includeColumns: [0, 1] - dataColumns: _col1:bigint, _col2:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, double, double, double, bigint] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col1: bigint, _col2: bigint - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (UDFToDouble(_col1) / UDFToDouble(_col2)) ASC NULLS FIRST - partition by: 0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: (UDFToDouble(_col1) / UDFToDouble(_col2)) - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: rank_window_0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6758 Data size: 1453080 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: select rank() over (order by return_ratio) as return_rank from - (select sum(wr.cint)/sum(ws.c_int) as return_ratio - from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 - group by ws.c_boolean ) in_web -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -PREHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -POSTHOOK: query: select rank() over (order by return_ratio) as return_rank from - (select sum(wr.cint)/sum(ws.c_int) as return_ratio - from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 - group by ws.c_boolean ) in_web -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -POSTHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -return_rank
http://git-wip-us.apache.org/repos/asf/hive/blob/afa9ffee/ql/src/test/results/clientpositive/vector_windowing_gby2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/vector_windowing_gby2.q.out b/ql/src/test/results/clientpositive/vector_windowing_gby2.q.out deleted file mode 100644 index ba3f374..0000000 --- a/ql/src/test/results/clientpositive/vector_windowing_gby2.q.out +++ /dev/null @@ -1,1007 +0,0 @@ -PREHOOK: query: explain vectorization detail -select rank() over (order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by ws.key -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail -select rank() over (order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by ws.key -POSTHOOK: type: QUERY -Explain -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3, 4] - projectedColumns: [key:string, value:string, c_int:int, c_float:float, c_boolean:boolean] - Select Operator - expressions: key (type: string), c_int (type: int) - outputColumnNames: key, c_int - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 2] - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(c_int) - Group By Vectorization: - aggregators: VectorUDAFSumLong(col 2:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0] - keys: key (type: string) - mode: hash - outputColumnNames: _col0, _col1 - Statistics: Num rows: 20 Data size: 262 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: 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: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - rowBatchContext: - dataColumnCount: 5 - includeColumns: [0, 2] - dataColumns: key:string, value:string, c_int:int, c_float:float, c_boolean:boolean - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0) - keys: KEY._col0 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint) - outputColumnNames: _col1 - Statistics: Num rows: 10 Data size: 131 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-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0] - projectedColumns: [_col1:bigint] - Reduce Output Operator - key expressions: 0 (type: int), _col1 (type: bigint) - sort order: ++ - Map-reduce partition columns: 0 (type: int) - 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: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - 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 - rowBatchContext: - dataColumnCount: 1 - includeColumns: [0] - dataColumns: _col1:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, bigint] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col1 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col1: bigint - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col1 ASC NULLS FIRST - partition by: 0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col1 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: rank_window_0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 131 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: select rank() over (order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by ws.key -PREHOOK: type: QUERY -PREHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -POSTHOOK: query: select rank() over (order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by ws.key -POSTHOOK: type: QUERY -POSTHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -return_rank -1 -2 -2 -2 -5 -5 -7 -PREHOOK: query: explain vectorization detail -select avg(cast(ws.key as int)) over (partition by min(ws.value) order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by cast(ws.key as int) -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail -select avg(cast(ws.key as int)) over (partition by min(ws.value) order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by cast(ws.key as int) -POSTHOOK: type: QUERY -Explain -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-0 depends on stages: Stage-2 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3, 4] - projectedColumns: [key:string, value:string, c_int:int, c_float:float, c_boolean:boolean] - Select Operator - expressions: UDFToInteger(key) (type: int), value (type: string), c_int (type: int) - outputColumnNames: _col0, _col1, _col2 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [5, 1, 2] - selectExpressions: CastStringToLong(col 0:string) -> 5:int - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: min(_col1), sum(_col2) - Group By Vectorization: - aggregators: VectorUDAFMinString(col 1:string) -> string, VectorUDAFSumLong(col 2:int) -> bigint - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 5:int - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1] - keys: _col0 (type: int) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + - Map-reduce partition columns: _col0 (type: int) - 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: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col2 (type: bigint) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - rowBatchContext: - dataColumnCount: 5 - includeColumns: [0, 1, 2] - dataColumns: key:string, value:string, c_int:int, c_float:float, c_boolean:boolean - partitionColumnCount: 0 - scratchColumnTypeNames: [bigint] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: min(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: int) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 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-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2] - projectedColumns: [_col0:int, _col1:string, _col2:bigint] - Reduce Output Operator - key expressions: _col1 (type: string), _col2 (type: bigint) - sort order: ++ - Map-reduce partition columns: _col1 (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: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - 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 - rowBatchContext: - dataColumnCount: 3 - includeColumns: [0, 1, 2] - dataColumns: _col0:int, _col1:string, _col2:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: bigint) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: string, _col2: bigint - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col2 ASC NULLS FIRST - partition by: _col1 - raw input shape: - window functions: - window function definition - alias: avg_window_0 - arguments: _col0 - name: avg - window function: GenericUDAFAverageEvaluatorDouble - window frame: RANGE PRECEDING(MAX)~CURRENT - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: avg_window_0 (type: double) - outputColumnNames: _col0 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 131 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: select avg(cast(ws.key as int)) over (partition by min(ws.value) order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by cast(ws.key as int) -PREHOOK: type: QUERY -PREHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -POSTHOOK: query: select avg(cast(ws.key as int)) over (partition by min(ws.value) order by sum(ws.c_int)) as return_rank -from cbo_t3 ws -group by cast(ws.key as int) -POSTHOOK: type: QUERY -POSTHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -return_rank -NULL -1.0 -2.0 -3.0 -PREHOOK: query: explain vectorization detail -select rank () over(partition by key order by sum(c_int - c_float) desc) , -dense_rank () over(partition by lower(value) order by sum(c_float/c_int) asc), -percent_rank () over(partition by max(c_int) order by sum((c_float/c_int) - c_int) asc) -from cbo_t3 -group by key, value -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail -select rank () over(partition by key order by sum(c_int - c_float) desc) , -dense_rank () over(partition by lower(value) order by sum(c_float/c_int) asc), -percent_rank () over(partition by max(c_int) order by sum((c_float/c_int) - c_int) asc) -from cbo_t3 -group by key, value -POSTHOOK: type: QUERY -Explain -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-4 depends on stages: Stage-3 - Stage-0 depends on stages: Stage-4 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: cbo_t3 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3, 4] - projectedColumns: [key:string, value:string, c_int:int, c_float:float, c_boolean:boolean] - Select Operator - expressions: key (type: string), value (type: string), (UDFToFloat(c_int) - c_float) (type: float), (UDFToDouble(c_float) / UDFToDouble(c_int)) (type: double), c_int (type: int), ((UDFToDouble(c_float) / UDFToDouble(c_int)) - UDFToDouble(c_int)) (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Select Vectorization: - className: VectorSelectOperator - native: true - projectedOutputColumnNums: [0, 1, 6, 7, 2, 9] - selectExpressions: DoubleColSubtractDoubleColumn(col 5:float, col 3:float)(children: CastLongToFloatViaLongToDouble(col 2:int) -> 5:float) -> 6:float, DoubleColDivideDoubleColumn(col 3:double, col 5:double)(children: col 3:float, CastLongToDouble(col 2:int) -> 5:double) -> 7:double, DoubleColSubtractDoubleColumn(col 8:double, col 5:double)(children: DoubleColDivideDoubleColumn(col 3:double, col 5:double)(children: col 3:float, CastLongToDouble(col 2:int) -> 5:double) -> 8:double, CastLongToDouble(col 2:int) -> 5:double) -> 9:double - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col2), sum(_col3), max(_col4), sum(_col5) - Group By Vectorization: - aggregators: VectorUDAFSumDouble(col 6:float) -> double, VectorUDAFSumDouble(col 7:double) -> double, VectorUDAFMaxLong(col 2:int) -> int, VectorUDAFSumDouble(col 9:double) -> double - className: VectorGroupByOperator - groupByMode: HASH - keyExpressions: col 0:string, col 1:string - native: false - vectorProcessingMode: HASH - projectedOutputColumnNums: [0, 1, 2, 3] - keys: _col0 (type: string), _col1 (type: string) - mode: hash - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: string), _col1 (type: string) - sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col1 (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: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: double), _col3 (type: double), _col4 (type: int), _col5 (type: double) - Execution mode: vectorized - Map Vectorization: - enabled: true - enabledConditionsMet: hive.vectorized.use.vector.serde.deserialize IS true - inputFormatFeatureSupport: [DECIMAL_64] - featureSupportInUse: [DECIMAL_64] - inputFileFormats: org.apache.hadoop.mapred.TextInputFormat - allNative: false - usesVectorUDFAdaptor: false - vectorized: true - rowBatchContext: - dataColumnCount: 5 - includeColumns: [0, 1, 2, 3] - dataColumns: key:string, value:string, c_int:int, c_float:float, c_boolean:boolean - partitionColumnCount: 0 - scratchColumnTypeNames: [double, double, double, double, double] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1), max(VALUE._col2), sum(VALUE._col3) - keys: KEY._col0 (type: string), KEY._col1 (type: string) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 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-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3, 4, 5] - projectedColumns: [_col0:string, _col1:string, _col2:double, _col3:double, _col4:int, _col5:double] - Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: double) - 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: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: string), _col3 (type: double), _col4 (type: int), _col5 (type: double) - 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 - rowBatchContext: - dataColumnCount: 6 - includeColumns: [0, 1, 2, 3, 4, 5] - dataColumns: _col0:string, _col1:string, _col2:double, _col3:double, _col4:int, _col5:double - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string), KEY.reducesinkkey1 (type: double), VALUE._col1 (type: double), VALUE._col2 (type: int), VALUE._col3 (type: double) - outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: string, _col1: string, _col2: double, _col3: double, _col4: int, _col5: double - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col2 DESC NULLS LAST - partition by: _col0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: _col2 - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: rank_window_0 (type: int), _col1 (type: string), _col3 (type: double), _col4 (type: int), _col5 (type: double) - outputColumnNames: rank_window_0, _col1, _col3, _col4, _col5 - Statistics: Num rows: 10 Data size: 131 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-3 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3, 4] - projectedColumns: [rank_window_0:int, _col1:string, _col3:double, _col4:int, _col5:double] - Reduce Output Operator - key expressions: lower(_col1) (type: string), _col3 (type: double) - sort order: ++ - Map-reduce partition columns: lower(_col1) (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: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - value expressions: rank_window_0 (type: int), _col1 (type: string), _col4 (type: int), _col5 (type: double) - 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 - rowBatchContext: - dataColumnCount: 5 - includeColumns: [0, 1, 2, 3, 4] - dataColumns: rank_window_0:int, _col1:string, _col3:double, _col4:int, _col5:double - partitionColumnCount: 0 - scratchColumnTypeNames: [string, string] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col2 (type: string), KEY.reducesinkkey1 (type: double), VALUE._col4 (type: int), VALUE._col5 (type: double) - outputColumnNames: _col0, _col2, _col4, _col5, _col6 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col2: string, _col4: double, _col5: int, _col6: double - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col4 ASC NULLS FIRST - partition by: lower(_col2) - raw input shape: - window functions: - window function definition - alias: dense_rank_window_1 - arguments: _col4 - name: dense_rank - window function: GenericUDAFDenseRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: dense_rank_window_1 (type: int), _col0 (type: int), _col5 (type: int), _col6 (type: double) - outputColumnNames: dense_rank_window_1, _col0, _col5, _col6 - Statistics: Num rows: 10 Data size: 131 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-4 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2, 3] - projectedColumns: [dense_rank_window_1:int, _col0:int, _col5:int, _col6:double] - Reduce Output Operator - key expressions: _col5 (type: int), _col6 (type: double) - sort order: ++ - Map-reduce partition columns: _col5 (type: int) - 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: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - value expressions: dense_rank_window_1 (type: int), _col0 (type: int) - 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 - rowBatchContext: - dataColumnCount: 4 - includeColumns: [0, 1, 2, 3] - dataColumns: dense_rank_window_1:int, _col0:int, _col5:int, _col6:double - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col0 (type: int), VALUE._col1 (type: int), KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: double) - outputColumnNames: _col0, _col1, _col6, _col7 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col0: int, _col1: int, _col6: int, _col7: double - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: _col7 ASC NULLS FIRST - partition by: _col6 - raw input shape: - window functions: - window function definition - alias: percent_rank_window_2 - arguments: _col7 - name: percent_rank - window function: GenericUDAFPercentRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: int), _col0 (type: int), percent_rank_window_2 (type: double) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 10 Data size: 131 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 10 Data size: 131 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: select rank () over(partition by key order by sum(c_int - c_float) desc) , -dense_rank () over(partition by lower(value) order by sum(c_float/c_int) asc), -percent_rank () over(partition by max(c_int) order by sum((c_float/c_int) - c_int) asc) -from cbo_t3 -group by key, value -PREHOOK: type: QUERY -PREHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -POSTHOOK: query: select rank () over(partition by key order by sum(c_int - c_float) desc) , -dense_rank () over(partition by lower(value) order by sum(c_float/c_int) asc), -percent_rank () over(partition by max(c_int) order by sum((c_float/c_int) - c_int) asc) -from cbo_t3 -group by key, value -POSTHOOK: type: QUERY -POSTHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -_c0 _c1 _c2 -1 1 0.0 -1 1 0.0 -1 1 0.0 -1 1 0.0 -1 1 0.0 -1 1 0.0 -1 1 0.0 -PREHOOK: query: explain vectorization detail -select rank() over (order by sum(wr.cint)/sum(ws.c_int)) as return_rank -from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 -group by ws.c_boolean -PREHOOK: type: QUERY -POSTHOOK: query: explain vectorization detail -select rank() over (order by sum(wr.cint)/sum(ws.c_int)) as return_rank -from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 -group by ws.c_boolean -POSTHOOK: type: QUERY -Explain -PLAN VECTORIZATION: - enabled: true - enabledConditionsMet: [hive.vectorized.execution.enabled IS true] - -STAGE DEPENDENCIES: - Stage-1 is a root stage - Stage-2 depends on stages: Stage-1 - Stage-3 depends on stages: Stage-2 - Stage-0 depends on stages: Stage-3 - -STAGE PLANS: - Stage: Stage-1 - Map Reduce - Map Operator Tree: - TableScan - alias: ws - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: value is not null (type: boolean) - Statistics: Num rows: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: value (type: string), c_int (type: int), c_boolean (type: boolean) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 20 Data size: 262 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: 20 Data size: 262 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: int), _col2 (type: boolean) - TableScan - alias: wr - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Filter Operator - predicate: cstring1 is not null (type: boolean) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: cint (type: int), cstring1 (type: string) - outputColumnNames: _col0, _col1 - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 12288 Data size: 2641964 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: int) - Map Vectorization: - enabled: false - enabledConditionsNotMet: Vectorized map work only works with 1 TableScanOperator IS false - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1, _col2, _col3 - Statistics: Num rows: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: sum(_col3), sum(_col1) - keys: _col2 (type: boolean) - mode: hash - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 13516 Data size: 2906160 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-2 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1, 2] - projectedColumns: [_col0:boolean, _col1:bigint, _col2:bigint] - Reduce Output Operator - key expressions: _col0 (type: boolean) - sort order: + - Map-reduce partition columns: _col0 (type: boolean) - 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: 13516 Data size: 2906160 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - 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 - rowBatchContext: - dataColumnCount: 3 - includeColumns: [0, 1, 2] - dataColumns: _col0:boolean, _col1:bigint, _col2:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Group By Operator - aggregations: sum(VALUE._col0), sum(VALUE._col1) - keys: KEY._col0 (type: boolean) - mode: mergepartial - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: _col1 (type: bigint), _col2 (type: bigint) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 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-3 - Map Reduce - Map Operator Tree: - TableScan - TableScan Vectorization: - native: true - projectedColumnNums: [0, 1] - projectedColumns: [_col1:bigint, _col2:bigint] - Reduce Output Operator - key expressions: 0 (type: int), (UDFToDouble(_col1) / UDFToDouble(_col2)) (type: double) - sort order: ++ - Map-reduce partition columns: 0 (type: int) - 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: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: bigint), _col2 (type: bigint) - 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 - rowBatchContext: - dataColumnCount: 2 - includeColumns: [0, 1] - dataColumns: _col1:bigint, _col2:bigint - partitionColumnCount: 0 - scratchColumnTypeNames: [bigint, double, double, double, bigint] - Reduce Vectorization: - enabled: false - enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true - enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false - Reduce Operator Tree: - Select Operator - expressions: VALUE._col1 (type: bigint), VALUE._col2 (type: bigint) - outputColumnNames: _col1, _col2 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - PTF Operator - Function definitions: - Input definition - input alias: ptf_0 - output shape: _col1: bigint, _col2: bigint - type: WINDOWING - Windowing table definition - input alias: ptf_1 - name: windowingtablefunction - order by: (UDFToDouble(_col1) / UDFToDouble(_col2)) ASC NULLS FIRST - partition by: 0 - raw input shape: - window functions: - window function definition - alias: rank_window_0 - arguments: (UDFToDouble(_col1) / UDFToDouble(_col2)) - name: rank - window function: GenericUDAFRankEvaluator - window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) - isPivotResult: true - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - Select Operator - expressions: rank_window_0 (type: int) - outputColumnNames: _col0 - Statistics: Num rows: 6758 Data size: 1453080 Basic stats: COMPLETE Column stats: NONE - File Output Operator - compressed: false - Statistics: Num rows: 6758 Data size: 1453080 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: select rank() over (order by sum(wr.cint)/sum(ws.c_int)) as return_rank -from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 -group by ws.c_boolean -PREHOOK: type: QUERY -PREHOOK: Input: default@alltypesorc -PREHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -POSTHOOK: query: select rank() over (order by sum(wr.cint)/sum(ws.c_int)) as return_rank -from cbo_t3 ws join alltypesorc wr on ws.value = wr.cstring1 -group by ws.c_boolean -POSTHOOK: type: QUERY -POSTHOOK: Input: default@alltypesorc -POSTHOOK: Input: default@cbo_t3 -#### A masked pattern was here #### -return_rank