http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_join30.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_join30.q.out b/ql/src/test/results/clientpositive/llap/vector_join30.q.out index d7e5f58..5839815 100644 --- a/ql/src/test/results/clientpositive/llap/vector_join30.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_join30.q.out @@ -10,7 +10,7 @@ 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 +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -18,7 +18,7 @@ JOIN ON (x.key = Y.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -26,6 +26,10 @@ JOIN 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 @@ -45,44 +49,103 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: @@ -90,29 +153,60 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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 @@ -120,15 +214,30 @@ STAGE PLANS: 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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) @@ -157,7 +266,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 103231310608 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -165,7 +274,7 @@ LEFT OUTER JOIN ON (x.key = Y.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -173,6 +282,10 @@ LEFT OUTER JOIN 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 @@ -192,38 +305,89 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: @@ -231,29 +395,60 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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 @@ -261,15 +456,30 @@ STAGE PLANS: 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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) @@ -298,7 +508,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 103231310608 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x RIGHT OUTER JOIN @@ -306,7 +516,7 @@ RIGHT OUTER JOIN ON (x.key = Y.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x RIGHT OUTER JOIN @@ -314,6 +524,10 @@ RIGHT OUTER JOIN 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 @@ -333,50 +547,116 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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: @@ -384,29 +664,60 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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 @@ -438,7 +749,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 103231310608 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -449,7 +760,7 @@ JOIN ON (x.key = Z.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -460,6 +771,10 @@ JOIN 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 @@ -480,63 +795,146 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + usesVectorUDFAdaptor: false + vectorized: true Map 6 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: @@ -546,6 +944,11 @@ STAGE PLANS: 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 @@ -553,23 +956,50 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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 @@ -577,28 +1007,58 @@ STAGE PLANS: 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 @@ -632,7 +1092,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 348019368476 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -643,7 +1103,7 @@ LEFT OUTER JOIN ON (x.key = Z.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x JOIN @@ -654,6 +1114,10 @@ LEFT OUTER JOIN 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 @@ -675,59 +1139,134 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + usesVectorUDFAdaptor: false + vectorized: true Map 7 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 @@ -744,6 +1283,10 @@ STAGE PLANS: 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 @@ -753,14 +1296,30 @@ STAGE PLANS: 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 @@ -768,28 +1327,58 @@ STAGE PLANS: 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 8 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 @@ -823,7 +1412,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 348019368476 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -834,7 +1423,7 @@ LEFT OUTER JOIN ON (x.key = Z.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -845,6 +1434,10 @@ LEFT OUTER JOIN 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 @@ -866,59 +1459,134 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + usesVectorUDFAdaptor: false + vectorized: true Map 7 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 @@ -935,6 +1603,10 @@ STAGE PLANS: 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 @@ -944,14 +1616,30 @@ STAGE PLANS: 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 @@ -959,28 +1647,58 @@ STAGE PLANS: 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 8 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, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, Uniform Hash 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 @@ -1014,7 +1732,7 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@orcsrc #### A masked pattern was here #### 348019368476 -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -1025,7 +1743,7 @@ RIGHT OUTER JOIN ON (x.key = Z.key) select sum(hash(Y.key,Y.value)) PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression FROM (SELECT orcsrc.* FROM orcsrc sort by key) x LEFT OUTER JOIN @@ -1036,6 +1754,10 @@ RIGHT OUTER JOIN 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 @@ -1057,59 +1779,134 @@ STAGE PLANS: 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + usesVectorUDFAdaptor: false + vectorized: true Map 7 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: VectorReduceSinkOperator + native: false + nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, Not ACID UPDATE or DELETE IS true, No buckets IS true, No TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true + nativeConditionsNotMet: Uniform Hash IS false 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: false + 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 +
<TRUNCATED>
