[04/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/fcb57100/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out -- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out index d47a04d..33d2e3d 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_mapjoin.q.out @@ -1,11 +1,15 @@ -PREHOOK: query: EXPLAIN SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint) +PREHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint) FROM alltypesorc t1 JOIN alltypesorc t2 ON t1.cint = t2.cint PREHOOK: type: QUERY -POSTHOOK: query: EXPLAIN SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint) +POSTHOOK: query: EXPLAIN VECTORIZATION EXPRESSION SELECT COUNT(t1.cint), MAX(t2.cint), MIN(t1.cint), AVG(t1.cint+t2.cint) FROM alltypesorc t1 JOIN alltypesorc t2 ON t1.cint = t2.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 @@ -24,12 +28,23 @@ STAGE PLANS: TableScan alias: t1 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: SelectColumnIsNotNull(col 2) -> boolean predicate: cint is not null (type: boolean) Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Select Operator expressions: cint (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2] Statistics: Num rows: 9173 Data size: 27396 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: @@ -37,6 +52,10 @@ STAGE PLANS: keys: 0 _col0 (type: int) 1 _col0 (type: int) +Map Join Vectorization: +className: VectorMapJoinInnerBigOnlyLongOperator +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: _col0, _col1 input vertices: 1 Map 3 @@ -44,9 +63,21 @@ STAGE PLANS: Select Operator expressions: _col0 (type: int), _col1 (type: int), (_col0 + _col1) (type: int) outputColumnNames: _col0, _col1, _col2 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [2, 2, 12] + selectExpressions: LongColAddLongColumn(col 2, col 2) -> 12:long Statistics: Num rows: 19518 Data size: 156144 Basic stats: COMPLETE Column stats: COMPLETE Group By Operator aggregations: count(_col0), max(_col1), min(_col0), avg(_col2) +Group By Vectorization: +aggregators: VectorUDAFCount(col 2) -> bigint, VectorUDAFMaxLong(col 2) -> int, VectorUDAFMinLong(col 2) -> int, VectorUDAFAvgLong(col 12) -> struct +className: VectorGroupByOperator +vectorOutput: false +native: false +projectedOutputColumns: [0, 1, 2, 3] +vectorOutputConditionsNotMet: Vector output of VectorUDAFAvgLong(col 12) -> struct output type STRUCT requires PRIMITIVE IS false mode: hash
[04/51] [partial] hive git commit: HIVE-11394: Enhance EXPLAIN display for vectorization (Matt McCline, reviewed by Gopal Vijayaraghavan)
http://git-wip-us.apache.org/repos/asf/hive/blob/f923db0b/ql/src/test/results/clientpositive/spark/vector_inner_join.q.out -- diff --git a/ql/src/test/results/clientpositive/spark/vector_inner_join.q.out b/ql/src/test/results/clientpositive/spark/vector_inner_join.q.out index 511bd79..ef19bad 100644 --- a/ql/src/test/results/clientpositive/spark/vector_inner_join.q.out +++ b/ql/src/test/results/clientpositive/spark/vector_inner_join.q.out @@ -32,12 +32,16 @@ POSTHOOK: type: QUERY POSTHOOK: Input: default@values__tmp__table__2 POSTHOOK: Output: default@orc_table_2a POSTHOOK: Lineage: orc_table_2a.c EXPRESSION [(values__tmp__table__2)values__tmp__table__2.FieldSchema(name:tmp_values_col1, type:string, comment:), ] -PREHOOK: query: explain +PREHOOK: query: explain vectorization detail select t1.a from orc_table_2a t2 join orc_table_1a t1 on t1.a = t2.c where t1.a > 2 PREHOOK: type: QUERY -POSTHOOK: query: explain +POSTHOOK: query: explain vectorization detail select t1.a from orc_table_2a t2 join orc_table_1a t1 on t1.a = t2.c where t1.a > 2 POSTHOOK: type: QUERY +PLAN VECTORIZATION: + enabled: true + enabledConditionsMet: [hive.vectorized.execution.enabled IS true] + STAGE DEPENDENCIES: Stage-2 is a root stage Stage-1 depends on stages: Stage-2 @@ -53,18 +57,45 @@ STAGE PLANS: TableScan alias: t2 Statistics: Num rows: 5 Data size: 16 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0] Filter Operator +Filter Vectorization: +className: VectorFilterOperator +native: true +predicateExpression: FilterLongColGreaterLongScalar(col 0, val 2) -> boolean predicate: (c > 2) (type: boolean) Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: c (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] Statistics: Num rows: 1 Data size: 3 Basic stats: COMPLETE Column stats: NONE Spark HashTable Sink Operator +Spark Hash Table Sink Vectorization: +className: VectorSparkHashTableSinkOperator +native: true keys: 0 _col0 (type: int) 1 _col0 (type: int) Execution mode: vectorized +Map Vectorization: +enabled: true +enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true +groupByVectorOutput: true +inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat +allNative: true +usesVectorUDFAdaptor: false +vectorized: true +rowBatchContext: +dataColumnCount: 1 +includeColumns: [0] +dataColumns: c:int +partitionColumnCount: 0 Local Work: Map Reduce Local Work @@ -77,12 +108,23 @@ STAGE PLANS: TableScan alias: t1 Statistics: Num rows: 4 Data size: 16 Basic stats: COMPLETE Column stats: NONE + TableScan Vectorization: + native: true + projectedOutputColumns: [0] Filter Operator +Filter Vectorization: +className: VectorFilterOperator +native: true +predicateExpression: FilterLongColGreaterLongScalar(col 0, val 2) -> boolean predicate: (a > 2) (type: boolean) Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: a (type: int) outputColumnNames: _col0 + Select Vectorization: + className: VectorSelectOperator + native: true + projectedOutputColumns: [0] Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: @@ -90,6 +132,14 @@ STAGE PLANS: keys: 0 _col0 (type: int)
