http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_empty_where.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_empty_where.q.out b/ql/src/test/results/clientpositive/llap/vector_empty_where.q.out new file mode 100644 index 0000000..9f93f86 --- /dev/null +++ b/ql/src/test/results/clientpositive/llap/vector_empty_where.q.out @@ -0,0 +1,648 @@ +PREHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cstring1 +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cstring1 +POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 899146 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsTrue(col 13)(children: CastLongToBooleanViaLongToLong(col 12)(children: StringLength(col 6) -> 12:Long) -> 13:long) -> boolean + predicate: cstring1 (type: string) + Statistics: Num rows: 6144 Data size: 449620 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: cint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] + Statistics: Num rows: 6144 Data size: 449620 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 2 + native: false + projectedOutputColumns: [] + keys: cint (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + 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: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + 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: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col0) + Group By Vectorization: + aggregators: VectorUDAFCount(col 0) -> 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: COMPLETE + 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: COMPLETE + 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: count(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(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: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count (distinct cint) from alltypesorc where cstring1 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +POSTHOOK: query: select count (distinct cint) from alltypesorc where cstring1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +6041 +PREHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cint +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cint +POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsTrue(col 12)(children: CastLongToBooleanViaLongToLong(col 2) -> 12:long) -> boolean + predicate: cint (type: int) + Statistics: Num rows: 6144 Data size: 18348 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 2 + native: false + projectedOutputColumns: [] + keys: cint (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + 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: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + 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: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col0) + Group By Vectorization: + aggregators: VectorUDAFCount(col 0) -> 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: COMPLETE + 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: COMPLETE + 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: count(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(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: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count (distinct cint) from alltypesorc where cint +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +POSTHOOK: query: select count (distinct cint) from alltypesorc where cint +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +6082 +PREHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cfloat +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where cfloat +POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 73392 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsTrue(col 12)(children: CastDoubleToBooleanViaDoubleToLong(col 4) -> 12:long) -> boolean + predicate: cfloat (type: float) + Statistics: Num rows: 6144 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: cint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] + Statistics: Num rows: 6144 Data size: 36696 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 2 + native: false + projectedOutputColumns: [] + keys: cint (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + 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: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + 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: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col0) + Group By Vectorization: + aggregators: VectorUDAFCount(col 0) -> 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: COMPLETE + 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: COMPLETE + 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: count(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(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: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count (distinct cint) from alltypesorc where cfloat +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +POSTHOOK: query: select count (distinct cint) from alltypesorc where cfloat +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +3022 +PREHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where ctimestamp1 +PREHOOK: type: QUERY +POSTHOOK: query: explain vectorization expression +select count (distinct cint) from alltypesorc where ctimestamp1 +POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 + +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: alltypesorc + Statistics: Num rows: 12288 Data size: 528216 Basic stats: COMPLETE Column stats: COMPLETE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11] + Filter Operator + Filter Vectorization: + className: VectorFilterOperator + native: true + predicateExpression: SelectColumnIsTrue(col 12)(children: CastTimestampToBoolean(col 8) -> 12:long) -> boolean + predicate: ctimestamp1 (type: timestamp) + Statistics: Num rows: 6144 Data size: 264108 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: cint (type: int) + outputColumnNames: cint + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] + Statistics: Num rows: 6144 Data size: 264108 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 2 + native: false + projectedOutputColumns: [] + keys: cint (type: int) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Map-reduce partition columns: _col0 (type: int) + Reduce Sink Vectorization: + className: VectorReduceSinkLongOperator + 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: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + 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: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] + keys: KEY._col0 (type: int) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 2888 Data size: 8628 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(_col0) + Group By Vectorization: + aggregators: VectorUDAFCount(col 0) -> 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: COMPLETE + 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: COMPLETE + 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: count(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(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: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink + +PREHOOK: query: select count (distinct cint) from alltypesorc where ctimestamp1 +PREHOOK: type: QUERY +PREHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +POSTHOOK: query: select count (distinct cint) from alltypesorc where ctimestamp1 +POSTHOOK: type: QUERY +POSTHOOK: Input: default@alltypesorc +#### A masked pattern was here #### +3022
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out index 9ecfa56..ad312cf 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby4.q.out @@ -18,14 +18,18 @@ POSTHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 -PREHOOK: query: EXPLAIN +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION FROM srcorc INSERT OVERWRITE TABLE dest1 SELECT substr(srcorc.key,1,1) GROUP BY substr(srcorc.key,1,1) PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION FROM srcorc INSERT OVERWRITE TABLE dest1 SELECT substr(srcorc.key,1,1) GROUP BY substr(srcorc.key,1,1) POSTHOOK: type: QUERY +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 @@ -46,21 +50,55 @@ STAGE PLANS: TableScan alias: srcorc Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Select Operator expressions: substr(key, 1, 1) (type: string) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] + selectExpressions: StringSubstrColStartLen(col 0, start 0, length 1) -> 2:string 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: rand() (type: double) + 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 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: false + vectorized: true Reduce Operator Tree: Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 @@ -69,17 +107,37 @@ STAGE PLANS: 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: 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 + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out index 4c6e038..b9e7c65 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby6.q.out @@ -18,14 +18,18 @@ POSTHOOK: query: CREATE TABLE dest1(c1 STRING) STORED AS ORC POSTHOOK: type: CREATETABLE POSTHOOK: Output: database:default POSTHOOK: Output: default@dest1 -PREHOOK: query: EXPLAIN +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION FROM srcorc INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(srcorc.value,5,1) PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION FROM srcorc INSERT OVERWRITE TABLE dest1 SELECT DISTINCT substr(srcorc.value,5,1) POSTHOOK: type: QUERY +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 @@ -46,21 +50,55 @@ STAGE PLANS: TableScan alias: srcorc Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1] Select Operator expressions: substr(value, 5, 1) (type: string) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] + selectExpressions: StringSubstrColStartLen(col 1, start 4, length 1) -> 2:string 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: rand() (type: double) + 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 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: false + vectorized: true Reduce Operator Tree: Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: string) mode: partial1 outputColumnNames: _col0 @@ -69,17 +107,37 @@ STAGE PLANS: 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: 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 + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] keys: KEY._col0 (type: string) mode: final outputColumnNames: _col0 Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 250 Data size: 44000 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out index 742cebc..80a5696 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_3.q.out @@ -101,12 +101,16 @@ POSTHOOK: Lineage: vectortab2korc.si SIMPLE [(vectortab2k)vectortab2k.FieldSchem POSTHOOK: Lineage: vectortab2korc.t SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:t, type:tinyint, comment:null), ] POSTHOOK: Lineage: vectortab2korc.ts SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:ts, type:timestamp, comment:null), ] POSTHOOK: Lineage: vectortab2korc.ts2 SIMPLE [(vectortab2k)vectortab2k.FieldSchema(name:ts2, type:timestamp, comment:null), ] -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select s, t, max(b) from vectortab2korc group by s, t PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select s, t, max(b) from vectortab2korc group by s, t 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 @@ -124,12 +128,26 @@ STAGE PLANS: TableScan alias: vectortab2korc Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12] Select Operator expressions: t (type: tinyint), s (type: string), b (type: bigint) outputColumnNames: t, s, b + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 8, 3] Statistics: Num rows: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: max(b) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 3) -> bigint + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0, col 8 + native: false + projectedOutputColumns: [0] keys: t (type: tinyint), s (type: string) mode: hash outputColumnNames: _col0, _col1, _col2 @@ -138,15 +156,41 @@ STAGE PLANS: key expressions: _col0 (type: tinyint), _col1 (type: string) sort order: ++ Map-reduce partition columns: _col0 (type: tinyint), _col1 (type: string) + Reduce Sink Vectorization: + className: VectorReduceSinkMultiKeyOperator + 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: 2000 Data size: 918712 Basic stats: COMPLETE Column stats: NONE value expressions: _col2 (type: bigint) 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: false + vectorized: true Reduce Operator Tree: Group By Operator aggregations: max(VALUE._col0) + Group By Vectorization: + aggregators: VectorUDAFMaxLong(col 2) -> bigint + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0, col 1 + native: false + projectedOutputColumns: [0] keys: KEY._col0 (type: tinyint), KEY._col1 (type: string) mode: mergepartial outputColumnNames: _col0, _col1, _col2 @@ -154,9 +198,16 @@ STAGE PLANS: Select Operator expressions: _col1 (type: string), _col0 (type: tinyint), _col2 (type: bigint) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [1, 0, 2] Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE File Output Operator compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false Statistics: Num rows: 1000 Data size: 459356 Basic stats: COMPLETE Column stats: NONE table: input format: org.apache.hadoop.mapred.SequenceFileInputFormat http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out index a0a3393..249f1f3 100644 --- a/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_groupby_mapjoin.q.out @@ -1,74 +1,241 @@ Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product -PREHOOK: query: explain +PREHOOK: query: explain vectorization expression select * from src where not key in (select key from src) order by key PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization expression select * from src where not key in (select key from src) order by key POSTHOOK: type: QUERY -Plan optimized by CBO. +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] -Vertex dependency in root stage -Map 1 <- Reducer 4 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) -Reducer 2 <- Map 1 (SIMPLE_EDGE) -Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) -Reducer 6 <- Map 5 (SIMPLE_EDGE) +STAGE DEPENDENCIES: + Stage-1 is a root stage + Stage-0 depends on stages: Stage-1 -Stage-0 - Fetch Operator - limit:-1 - Stage-1 - Reducer 2 vectorized, llap - File Output Operator [FS_37] - Select Operator [SEL_36] (rows=500 width=178) - Output:["_col0","_col1"] - <-Map 1 [SIMPLE_EDGE] llap - SHUFFLE [RS_22] - Select Operator [SEL_21] (rows=500 width=178) - Output:["_col0","_col1"] - Filter Operator [FIL_20] (rows=500 width=198) - predicate:((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) - Map Join Operator [MAPJOIN_28] (rows=500 width=198) - Conds:MAPJOIN_27._col0=RS_35._col0(Left Outer),Output:["_col0","_col1","_col2","_col3","_col5"] - <-Reducer 6 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_35] - PartitionCols:_col0 - Select Operator [SEL_34] (rows=205 width=91) - Output:["_col0","_col1"] - Group By Operator [GBY_33] (rows=205 width=87) - Output:["_col0"],keys:KEY._col0 - <-Map 5 [SIMPLE_EDGE] llap - SHUFFLE [RS_11] - PartitionCols:_col0 - Group By Operator [GBY_10] (rows=205 width=87) - Output:["_col0"],keys:key - TableScan [TS_8] (rows=500 width=87) - default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Map Join Operator [MAPJOIN_27] (rows=500 width=194) - Conds:(Inner),Output:["_col0","_col1","_col2","_col3"] - <-Reducer 4 [BROADCAST_EDGE] vectorized, llap - BROADCAST [RS_32] - Group By Operator [GBY_31] (rows=1 width=16) - Output:["_col0","_col1"],aggregations:["count(VALUE._col0)","count(VALUE._col1)"] - <-Map 3 [CUSTOM_SIMPLE_EDGE] llap - PARTITION_ONLY_SHUFFLE [RS_5] - Group By Operator [GBY_4] (rows=1 width=16) - Output:["_col0","_col1"],aggregations:["count()","count(key)"] - Select Operator [SEL_3] (rows=500 width=87) - Output:["key"] - TableScan [TS_2] (rows=500 width=87) - default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key"] - <-Select Operator [SEL_1] (rows=500 width=178) - Output:["_col0","_col1"] - TableScan [TS_0] (rows=500 width=178) - default@src,src,Tbl:COMPLETE,Col:COMPLETE,Output:["key","value"] +STAGE PLANS: + Stage: Stage-1 + Tez +#### A masked pattern was here #### + Edges: + Map 1 <- Reducer 4 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (SIMPLE_EDGE) + Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) + Reducer 6 <- Map 5 (SIMPLE_EDGE) +#### A masked pattern was here #### + Vertices: + Map 1 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string), value (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 + 1 + outputColumnNames: _col0, _col1, _col2, _col3 + input vertices: + 1 Reducer 4 + Statistics: Num rows: 500 Data size: 97000 Basic stats: COMPLETE Column stats: COMPLETE + Map Join Operator + condition map: + Left Outer Join0 to 1 + keys: + 0 _col0 (type: string) + 1 _col0 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3, _col5 + input vertices: + 1 Reducer 6 + Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE + Filter Operator + predicate: ((_col2 = 0) or (_col5 is null and _col0 is not null and (_col3 >= _col2))) (type: boolean) + Statistics: Num rows: 500 Data size: 99000 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), _col1 (type: string) + outputColumnNames: _col0, _col1 + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: string) + Execution mode: llap + LLAP IO: no inputs + Map Vectorization: + enabled: false + enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + Map 3 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: key (type: string) + outputColumnNames: key + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + aggregations: count(), count(key) + Group By Vectorization: + vectorOutput: false + native: false + projectedOutputColumns: null + mode: hash + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + Execution mode: llap + LLAP IO: no inputs + Map Vectorization: + enabled: false + enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + Map 5 + Map Operator Tree: + TableScan + alias: src + Statistics: Num rows: 500 Data size: 43500 Basic stats: COMPLETE Column stats: COMPLETE + Group By Operator + Group By Vectorization: + vectorOutput: false + native: false + projectedOutputColumns: null + keys: key (type: string) + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Execution mode: llap + LLAP IO: no inputs + Map Vectorization: + enabled: false + enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false + inputFileFormats: org.apache.hadoop.mapred.TextInputFormat + 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: false + vectorized: true + Reduce Operator Tree: + Select Operator + expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: string) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + File Output Operator + compressed: false + File Sink Vectorization: + className: VectorFileSinkOperator + native: false + Statistics: Num rows: 500 Data size: 89000 Basic stats: COMPLETE Column stats: COMPLETE + table: + input format: org.apache.hadoop.mapred.SequenceFileInputFormat + output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat + serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe + 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: count(VALUE._col0), count(VALUE._col1) + Group By Vectorization: + aggregators: VectorUDAFCountMerge(col 0) -> bigint, VectorUDAFCountMerge(col 1) -> bigint + className: VectorGroupByOperator + vectorOutput: true + native: false + projectedOutputColumns: [0, 1] + mode: mergepartial + outputColumnNames: _col0, _col1 + Statistics: Num rows: 1 Data size: 16 Basic stats: COMPLETE Column stats: COMPLETE + 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: 16 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col0 (type: bigint), _col1 (type: bigint) + 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: false + usesVectorUDFAdaptor: false + vectorized: true + Reduce Operator Tree: + Group By Operator + Group By Vectorization: + className: VectorGroupByOperator + vectorOutput: true + keyExpressions: col 0 + native: false + projectedOutputColumns: [] + keys: KEY._col0 (type: string) + mode: mergepartial + outputColumnNames: _col0 + Statistics: Num rows: 205 Data size: 17835 Basic stats: COMPLETE Column stats: COMPLETE + Select Operator + expressions: _col0 (type: string), true (type: boolean) + outputColumnNames: _col0, _col1 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0, 1] + selectExpressions: ConstantVectorExpression(val 1) -> 1:long + Statistics: Num rows: 205 Data size: 18655 Basic stats: COMPLETE Column stats: COMPLETE + 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: 205 Data size: 18655 Basic stats: COMPLETE Column stats: COMPLETE + value expressions: _col1 (type: boolean) + + Stage: Stage-0 + Fetch Operator + limit: -1 + Processor Tree: + ListSink Warning: Map Join MAPJOIN[27][bigTable=?] in task 'Map 1' is a cross product PREHOOK: query: select *
