http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out b/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out index a8f06eb..def06a5 100644 --- a/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_join_filters.q.out @@ -122,18 +122,19 @@ STAGE PLANS: TableScan Vectorization: native: true Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), ((key > 40) and (value > 50) and (key = value)) (type: boolean) + outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true + selectExpressions: VectorUDFAdaptor(((key > 40) and (value > 50) and (key = value)))(children: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean) -> 6:boolean Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 filter predicates: 0 - 1 {(_col0 > 40)} {(_col1 > 50)} {(_col0 = _col1)} + 1 {_col2} keys: 0 1 @@ -368,18 +369,19 @@ STAGE PLANS: TableScan Vectorization: native: true Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true + selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 filter predicates: 0 - 1 {(_col0 > 40)} {(_col1 > 50)} {(_col0 = _col1)} + 1 {_col2} {_col3} {_col4} keys: 0 _col0 (type: int) 1 _col1 (type: int) @@ -397,7 +399,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int + selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) @@ -541,18 +543,19 @@ STAGE PLANS: TableScan Vectorization: native: true Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true + selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 filter predicates: 0 - 1 {(_col0 > 40)} {(_col1 > 50)} {(_col0 = _col1)} + 1 {_col2} {_col3} {_col4} keys: 0 _col0 (type: int) 1 _col0 (type: int) @@ -570,7 +573,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int + selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) @@ -714,18 +717,19 @@ STAGE PLANS: TableScan Vectorization: native: true Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true + selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 filter predicates: 0 - 1 {(_col0 > 40)} {(_col1 > 50)} {(_col0 = _col1)} + 1 {_col2} {_col3} {_col4} keys: 0 _col1 (type: int) 1 _col1 (type: int) @@ -743,7 +747,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int + selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0) @@ -886,18 +890,19 @@ STAGE PLANS: TableScan Vectorization: native: true Select Operator - expressions: key (type: int), value (type: int) - outputColumnNames: _col0, _col1 + expressions: key (type: int), value (type: int), (key > 40) (type: boolean), (value > 50) (type: boolean), (key = value) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3, _col4 Select Vectorization: className: VectorSelectOperator native: true + selectExpressions: LongColGreaterLongScalar(col 0:int, val 40) -> 3:boolean, LongColGreaterLongScalar(col 1:int, val 50) -> 4:boolean, LongColEqualLongColumn(col 0:int, col 1:int) -> 5:boolean Statistics: Num rows: 4 Data size: 32 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Right Outer Join 0 to 1 filter predicates: 0 - 1 {(_col0 > 40)} {(_col1 > 50)} {(_col0 = _col1)} + 1 {_col2} {_col3} {_col4} keys: 0 _col0 (type: int), _col1 (type: int) 1 _col0 (type: int), _col1 (type: int) @@ -915,7 +920,7 @@ STAGE PLANS: Select Vectorization: className: VectorSelectOperator native: true - selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 5:int + selectExpressions: VectorUDFAdaptor(hash(_col0,_col1,_col2,_col3)) -> 8:int Statistics: Num rows: 4 Data size: 35 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: sum(_col0)
http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out b/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out index 5ac15ef..261b470 100644 --- a/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_left_outer_join2.q.out @@ -113,24 +113,24 @@ STAGE PLANS: alias: tjoin1 Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -215,24 +215,24 @@ STAGE PLANS: alias: tjoin1 Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator @@ -320,18 +320,19 @@ STAGE PLANS: native: true vectorizationSchemaColumns: [0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [0, 1, 2, 4] + selectExpressions: LongColGreaterLongScalar(col 2:int, val 15) -> 4:boolean + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) @@ -343,12 +344,12 @@ STAGE PLANS: native: false nativeConditionsMet: hive.mapjoin.optimized.hashtable 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, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled IS false - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator @@ -381,7 +382,7 @@ STAGE PLANS: includeColumns: [0, 1, 2] dataColumns: rnum:int, c1:int, c2:int partitionColumnCount: 0 - scratchColumnTypeNames: [string] + scratchColumnTypeNames: [bigint, string] Map 2 Map Operator Tree: TableScan @@ -486,18 +487,19 @@ STAGE PLANS: native: true vectorizationSchemaColumns: [0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [0, 1, 2, 4] + selectExpressions: LongColGreaterLongScalar(col 2:int, val 15) -> 4:boolean + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) @@ -509,12 +511,12 @@ STAGE PLANS: native: false nativeConditionsMet: hive.mapjoin.optimized.hashtable 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, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true nativeConditionsNotMet: hive.vectorized.execution.mapjoin.native.enabled IS false - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator @@ -547,7 +549,7 @@ STAGE PLANS: includeColumns: [0, 1, 2] dataColumns: rnum:int, c1:int, c2:int partitionColumnCount: 0 - scratchColumnTypeNames: [string] + scratchColumnTypeNames: [bigint, string] Map 2 Map Operator Tree: TableScan @@ -652,44 +654,45 @@ STAGE PLANS: native: true vectorizationSchemaColumns: [0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [0, 1, 2, 4] + selectExpressions: LongColGreaterLongScalar(col 2:int, val 15) -> 4:boolean + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) Map Join Vectorization: - bigTableFilterExpressions: FilterLongColGreaterLongScalar(col 2:int, val 15) + bigTableFilterExpressions: SelectColumnIsTrue(col 4:boolean) bigTableKeyColumns: 1:int bigTableRetainColumnNums: [0, 1, 2] bigTableValueColumns: 0:int, 1:int, 2:int className: VectorMapJoinOuterLongOperator 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, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true - projectedOutput: 0:int, 1:int, 2:int, 4:char(2) - smallTableValueMapping: 4:char(2) + projectedOutput: 0:int, 1:int, 2:int, 5:char(2) + smallTableValueMapping: 5:char(2) hashTableImplementationType: OPTIMIZED - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2, 4] + projectedOutputColumnNums: [0, 1, 2, 5] Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -717,7 +720,7 @@ STAGE PLANS: includeColumns: [0, 1, 2] dataColumns: rnum:int, c1:int, c2:int partitionColumnCount: 0 - scratchColumnTypeNames: [string] + scratchColumnTypeNames: [bigint, string] Map 2 Map Operator Tree: TableScan @@ -822,44 +825,45 @@ STAGE PLANS: native: true vectorizationSchemaColumns: [0:rnum:int, 1:c1:int, 2:c2:int, 3:ROW__ID:struct<writeid:bigint,bucketid:int,rowid:bigint>] Select Operator - expressions: rnum (type: int), c1 (type: int), c2 (type: int) - outputColumnNames: _col0, _col1, _col2 + expressions: rnum (type: int), c1 (type: int), c2 (type: int), (c2 > 15) (type: boolean) + outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 3 Data size: 36 Basic stats: COMPLETE Column stats: COMPLETE + projectedOutputColumnNums: [0, 1, 2, 4] + selectExpressions: LongColGreaterLongScalar(col 2:int, val 15) -> 4:boolean + Statistics: Num rows: 3 Data size: 48 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Left Outer Join 0 to 1 filter predicates: - 0 {(_col2 > 15)} + 0 {_col3} 1 keys: 0 _col1 (type: int) 1 _col0 (type: int) Map Join Vectorization: - bigTableFilterExpressions: FilterLongColGreaterLongScalar(col 2:int, val 15) + bigTableFilterExpressions: SelectColumnIsTrue(col 4:boolean) bigTableKeyColumns: 1:int bigTableRetainColumnNums: [0, 1, 2] bigTableValueColumns: 0:int, 1:int, 2:int className: VectorMapJoinOuterLongOperator 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, Outer Join has keys IS true, Optimized Table and Supports Key Types IS true - projectedOutput: 0:int, 1:int, 2:int, 4:char(2) - smallTableValueMapping: 4:char(2) + projectedOutput: 0:int, 1:int, 2:int, 5:char(2) + smallTableValueMapping: 5:char(2) hashTableImplementationType: OPTIMIZED - outputColumnNames: _col0, _col1, _col2, _col4 + outputColumnNames: _col0, _col1, _col2, _col5 input vertices: 1 Map 2 Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col4 (type: char(2)) + expressions: _col0 (type: int), _col1 (type: int), _col2 (type: int), _col5 (type: char(2)) outputColumnNames: _col0, _col1, _col2, _col3 Select Vectorization: className: VectorSelectOperator native: true - projectedOutputColumnNums: [0, 1, 2, 4] + projectedOutputColumnNums: [0, 1, 2, 5] Statistics: Num rows: 6 Data size: 588 Basic stats: COMPLETE Column stats: COMPLETE File Output Operator compressed: false @@ -887,7 +891,7 @@ STAGE PLANS: includeColumns: [0, 1, 2] dataColumns: rnum:int, c1:int, c2:int partitionColumnCount: 0 - scratchColumnTypeNames: [string] + scratchColumnTypeNames: [bigint, string] Map 2 Map Operator Tree: TableScan http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out index aaf14ee..30b86bb 100644 --- a/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_mapjoin_reduce.q.out @@ -52,7 +52,7 @@ STAGE PLANS: className: VectorSelectOperator native: true projectedOutputColumnNums: [0, 1, 2] - Statistics: Num rows: 14 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator key expressions: _col1 (type: int) sort order: + @@ -61,7 +61,7 @@ STAGE PLANS: className: VectorReduceSinkLongOperator native: true nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true - Statistics: Num rows: 14 Data size: 224 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 14 Data size: 168 Basic stats: COMPLETE Column stats: COMPLETE value expressions: _col0 (type: int), _col2 (type: int) Execution mode: vectorized, llap LLAP IO: no inputs http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out index 895b90e..0cfd81c 100644 --- a/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_varchar_mapjoin1.q.out @@ -429,13 +429,13 @@ STAGE PLANS: predicate: c2 is not null (type: boolean) Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: c1 (type: int), c2 (type: varchar(10)) - outputColumnNames: _col0, _col1 + expressions: c1 (type: int), c2 (type: varchar(10)), CAST( c2 AS STRING) (type: string) + outputColumnNames: _col0, _col1, _col2 Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: CAST( _col1 AS STRING) (type: string) + key expressions: _col2 (type: string) sort order: + - Map-reduce partition columns: CAST( _col1 AS STRING) (type: string) + Map-reduce partition columns: _col2 (type: string) Statistics: Num rows: 3 Data size: 294 Basic stats: COMPLETE Column stats: NONE value expressions: _col0 (type: int), _col1 (type: varchar(10)) Execution mode: vectorized, llap @@ -466,17 +466,21 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 CAST( _col1 AS STRING) (type: string) + 0 _col2 (type: string) 1 _col1 (type: string) - outputColumnNames: _col0, _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col3, _col4 input vertices: 0 Map 1 Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col0 (type: int) - sort order: + + Select Operator + expressions: _col0 (type: int), _col1 (type: varchar(10)), _col3 (type: int), _col4 (type: string) + outputColumnNames: _col0, _col1, _col2, _col3 Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE - value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string) + Reduce Output Operator + key expressions: _col0 (type: int) + sort order: + + Statistics: Num rows: 3 Data size: 323 Basic stats: COMPLETE Column stats: NONE + value expressions: _col1 (type: varchar(10)), _col2 (type: int), _col3 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vector_windowing_rank.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vector_windowing_rank.q.out b/ql/src/test/results/clientpositive/llap/vector_windowing_rank.q.out index be943d5..9331132 100644 --- a/ql/src/test/results/clientpositive/llap/vector_windowing_rank.q.out +++ b/ql/src/test/results/clientpositive/llap/vector_windowing_rank.q.out @@ -1704,16 +1704,16 @@ STAGE PLANS: Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: b (type: bigint), ts (type: timestamp), dec (type: decimal(4,2)) - outputColumnNames: _col1, _col2, _col3 + outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true projectedOutputColumnNums: [3, 8, 9] Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: bigint) + key expressions: _col0 (type: bigint) sort order: + - Map-reduce partition columns: _col1 (type: bigint) + Map-reduce partition columns: _col0 (type: bigint) Reduce Sink Vectorization: className: VectorReduceSinkLongOperator keyColumns: 3:bigint @@ -1721,7 +1721,7 @@ STAGE PLANS: nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true valueColumns: 8:timestamp, 9:decimal(4,2) Statistics: Num rows: 1 Data size: 164 Basic stats: COMPLETE Column stats: NONE - value expressions: _col2 (type: timestamp), _col3 (type: decimal(4,2)) + value expressions: _col1 (type: timestamp), _col2 (type: decimal(4,2)) Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: @@ -1797,14 +1797,14 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: bigint) + 0 _col0 (type: bigint) 1 _col0 (type: bigint) - outputColumnNames: _col2, _col3 + outputColumnNames: _col1, _col2 Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col2 (type: timestamp), _col3 (type: decimal(4,2)) + key expressions: _col1 (type: timestamp), _col2 (type: decimal(4,2)) sort order: ++ - Map-reduce partition columns: _col2 (type: timestamp) + Map-reduce partition columns: _col1 (type: timestamp) Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE MergeJoin Vectorization: enabled: false @@ -1827,7 +1827,7 @@ STAGE PLANS: Reduce Operator Tree: Select Operator expressions: KEY.reducesinkkey0 (type: timestamp), KEY.reducesinkkey1 (type: decimal(4,2)) - outputColumnNames: _col2, _col3 + outputColumnNames: _col1, _col2 Select Vectorization: className: VectorSelectOperator native: true @@ -1837,18 +1837,18 @@ STAGE PLANS: Function definitions: Input definition input alias: ptf_0 - output shape: _col2: timestamp, _col3: decimal(4,2) + output shape: _col1: timestamp, _col2: decimal(4,2) type: WINDOWING Windowing table definition input alias: ptf_1 name: windowingtablefunction - order by: _col3 ASC NULLS LAST - partition by: _col2 + order by: _col2 ASC NULLS LAST + partition by: _col1 raw input shape: window functions: window function definition alias: rank_window_0 - arguments: _col3 + arguments: _col2 name: rank window function: GenericUDAFRankEvaluator window frame: ROWS PRECEDING(MAX)~FOLLOWING(MAX) @@ -1875,7 +1875,7 @@ STAGE PLANS: predicate: (rank_window_0 = 1) (type: boolean) Statistics: Num rows: 1 Data size: 180 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: _col2 (type: timestamp), _col3 (type: decimal(4,2)), 1 (type: int) + expressions: _col1 (type: timestamp), _col2 (type: decimal(4,2)), 1 (type: int) outputColumnNames: _col0, _col1, _col2 Select Vectorization: className: VectorSelectOperator http://git-wip-us.apache.org/repos/asf/hive/blob/55887646/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out ---------------------------------------------------------------------- diff --git a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out index feecc27..43ccbe9 100644 --- a/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out +++ b/ql/src/test/results/clientpositive/llap/vectorized_dynamic_partition_pruning.q.out @@ -1123,12 +1123,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -1146,7 +1146,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator - expressions: _col2 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1179,7 +1179,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1312,12 +1312,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs @@ -1338,7 +1338,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -1794,14 +1794,14 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: UDFToDouble(hr) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: @@ -1823,16 +1823,16 @@ STAGE PLANS: predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: double) + expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -1864,9 +1864,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -1968,14 +1968,14 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: (UDFToDouble(hr) * 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0D) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0D) (type: double) - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: @@ -2038,9 +2038,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0D) (type: double) + 0 _col0 (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2142,14 +2142,14 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: UDFToDouble(hr) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: UDFToDouble(_col0) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(_col0) (type: double) - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: @@ -2171,13 +2171,13 @@ STAGE PLANS: predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: double) + expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs @@ -2197,9 +2197,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + 0 _col0 (type: double) + 1 _col0 (type: double) + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2301,14 +2301,14 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: (UDFToDouble(hr) * 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: (UDFToDouble(_col0) * 2.0D) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: (UDFToDouble(_col0) * 2.0D) (type: double) - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Map-reduce partition columns: _col0 (type: double) + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs Map Vectorization: @@ -2356,9 +2356,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0D) (type: double) + 0 _col0 (type: double) 1 _col0 (type: double) - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -2473,13 +2473,13 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: CAST( (UDFToDouble(hr) * 2.0D) AS STRING) (type: string) outputColumnNames: _col0 Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: CAST( (UDFToDouble(_col0) * 2.0D) AS STRING) (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: CAST( (UDFToDouble(_col0) * 2.0D) AS STRING) (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE Execution mode: vectorized, llap LLAP IO: no inputs @@ -2502,16 +2502,16 @@ STAGE PLANS: predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: double) + expressions: CAST( hr AS STRING) (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: CAST( _col0 AS STRING) (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: CAST( _col0 AS STRING) (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: CAST( _col0 AS STRING) (type: string) + expressions: _col0 (type: string) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -2543,8 +2543,8 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 CAST( (UDFToDouble(_col0) * 2.0D) AS STRING) (type: string) - 1 CAST( _col0 AS STRING) (type: string) + 0 _col0 (type: string) + 1 _col0 (type: string) Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -2848,12 +2848,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator sort order: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: string), _col2 (type: string) + value expressions: _col0 (type: string), _col1 (type: string) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -2874,8 +2874,8 @@ STAGE PLANS: keys: 0 1 - outputColumnNames: _col0, _col1, _col2, _col4 - residual filter predicates: {((_col0 = _col2) or (_col1 = _col4))} + outputColumnNames: _col0, _col1, _col2, _col3 + residual filter predicates: {((_col0 = _col2) or (_col1 = _col3))} Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE Select Operator Statistics: Num rows: 4000 Data size: 4420000 Basic stats: COMPLETE Column stats: NONE @@ -3010,12 +3010,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -3033,7 +3033,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator - expressions: _col2 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -3066,7 +3066,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() @@ -3863,21 +3863,21 @@ STAGE PLANS: Map 1 Map Operator Tree: TableScan - alias: srcpart_hour_n2 - filterExpr: (UDFToDouble(hr) = 13.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE + alias: srcpart_date_n8 + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(hr) = 13.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) + expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3903,11 +3903,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) + value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: unknown Map Vectorization: @@ -3920,21 +3920,21 @@ STAGE PLANS: Map 6 Map Operator Tree: TableScan - alias: srcpart_date_n8 - filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + alias: srcpart_hour_n2 + filterExpr: (UDFToDouble(hr) = 13.0D) (type: boolean) + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(hr) = 13.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) + expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator key expressions: _col0 (type: string) sort order: + Map-reduce partition columns: _col0 (type: string) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -3954,14 +3954,14 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + 1 _col0 (type: string) + outputColumnNames: _col2 + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col2 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + Map-reduce partition columns: _col2 (type: string) + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE MergeJoin Vectorization: enabled: false enableConditionsNotMet: Vectorizing MergeJoin Supported IS false @@ -3972,9 +3972,9 @@ STAGE PLANS: condition map: Inner Join 0 to 1 keys: - 0 _col1 (type: string) + 0 _col2 (type: string) 1 _col0 (type: string) - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 889 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -5393,7 +5393,7 @@ STAGE PLANS: Inner Join 0 to 1 keys: 0 _col0 (type: string), _col1 (type: string) - 1 _col0 (type: string), _col2 (type: string) + 1 _col0 (type: string), _col1 (type: string) input vertices: 1 Map 3 Statistics: Num rows: 2200 Data size: 809600 Basic stats: COMPLETE Column stats: NONE @@ -5428,12 +5428,12 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), _col2 (type: string) + key expressions: _col0 (type: string), _col1 (type: string) sort order: ++ - Map-reduce partition columns: _col0 (type: string), _col2 (type: string) + Map-reduce partition columns: _col0 (type: string), _col1 (type: string) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -5451,7 +5451,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator - expressions: _col2 (type: string) + expressions: _col1 (type: string) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -5741,18 +5741,18 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: UDFToDouble(hr) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 UDFToDouble(_col0) (type: double) - 1 UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + 0 _col0 (type: double) + 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -5783,16 +5783,16 @@ STAGE PLANS: predicate: ((UDFToDouble(hour) = 11.0D) and hr is not null) (type: boolean) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: double) + expressions: UDFToDouble(UDFToInteger((hr / 2.0D))) (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + key expressions: _col0 (type: double) sort order: + - Map-reduce partition columns: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + Map-reduce partition columns: _col0 (type: double) Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: UDFToDouble(UDFToInteger((_col0 / 2.0D))) (type: double) + expressions: _col0 (type: double) outputColumnNames: _col0 Statistics: Num rows: 1 Data size: 192 Basic stats: COMPLETE Column stats: NONE Group By Operator @@ -5906,18 +5906,18 @@ STAGE PLANS: filterExpr: hr is not null (type: boolean) Statistics: Num rows: 2000 Data size: 389248 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: hr (type: string) + expressions: (UDFToDouble(hr) * 2.0D) (type: double) outputColumnNames: _col0 - Statistics: Num rows: 2000 Data size: 368000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 16000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 (UDFToDouble(_col0) * 2.0D) (type: double) + 0 _col0 (type: double) 1 _col0 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 404800 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 17600 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -6852,39 +6852,51 @@ STAGE PLANS: Tez #### A masked pattern was here #### Edges: - Map 1 <- Map 2 (BROADCAST_EDGE) - Map 3 <- Map 1 (BROADCAST_EDGE) - Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE) + Map 1 <- Map 3 (BROADCAST_EDGE), Map 4 (BROADCAST_EDGE) + Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE) #### A masked pattern was here #### Vertices: Map 1 Map Operator Tree: TableScan - alias: srcpart_hour_n2 - filterExpr: (UDFToDouble(hr) = 13.0D) (type: boolean) - Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE + alias: srcpart_date_n8 + filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: (UDFToDouble(hr) = 13.0D) (type: boolean) - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: hr (type: string) + expressions: ds (type: string) outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE Map Join Operator condition map: Inner Join 0 to 1 keys: 0 _col0 (type: string) - 1 _col1 (type: string) - outputColumnNames: _col1 + 1 _col0 (type: string) + outputColumnNames: _col2 input vertices: - 1 Map 2 - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - key expressions: _col1 (type: string) - sort order: + - Map-reduce partition columns: _col1 (type: string) - Statistics: Num rows: 1 Data size: 202 Basic stats: COMPLETE Column stats: NONE + 1 Map 3 + Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE + Map Join Operator + condition map: + Inner Join 0 to 1 + keys: + 0 _col2 (type: string) + 1 _col0 (type: string) + input vertices: + 1 Map 4 + Statistics: Num rows: 2 Data size: 889 Basic stats: COMPLETE Column stats: NONE + Group By Operator + aggregations: count() + mode: hash + outputColumnNames: _col0 + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + sort order: + Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE + value expressions: _col0 (type: bigint) Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -6893,10 +6905,10 @@ STAGE PLANS: inputFormatFeatureSupport: [DECIMAL_64] featureSupportInUse: [DECIMAL_64] inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: true + allNative: false usesVectorUDFAdaptor: false vectorized: true - Map 2 + Map 3 Map Operator Tree: TableScan alias: srcpart @@ -6910,11 +6922,11 @@ STAGE PLANS: outputColumnNames: _col0, _col1 Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE Reduce Output Operator - key expressions: _col1 (type: string) + key expressions: _col0 (type: string) sort order: + - Map-reduce partition columns: _col1 (type: string) + Map-reduce partition columns: _col0 (type: string) Statistics: Num rows: 1 Data size: 368 Basic stats: COMPLETE Column stats: COMPLETE - value expressions: _col0 (type: string) + value expressions: _col1 (type: string) Execution mode: vectorized, llap LLAP IO: unknown Map Vectorization: @@ -6924,37 +6936,24 @@ STAGE PLANS: allNative: true usesVectorUDFAdaptor: false vectorized: true - Map 3 + Map 4 Map Operator Tree: TableScan - alias: srcpart_date_n8 - filterExpr: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + alias: srcpart_hour_n2 + filterExpr: (UDFToDouble(hr) = 13.0D) (type: boolean) + Statistics: Num rows: 2 Data size: 368 Basic stats: COMPLETE Column stats: NONE Filter Operator - predicate: ((date = '2008-04-08') and ds is not null) (type: boolean) - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE + predicate: (UDFToDouble(hr) = 13.0D) (type: boolean) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string) + expressions: hr (type: string) outputColumnNames: _col0 - Statistics: Num rows: 2 Data size: 736 Basic stats: COMPLETE Column stats: NONE - Map Join Operator - condition map: - Inner Join 0 to 1 - keys: - 0 _col1 (type: string) - 1 _col0 (type: string) - input vertices: - 0 Map 1 - Statistics: Num rows: 2 Data size: 809 Basic stats: COMPLETE Column stats: NONE - Group By Operator - aggregations: count() - mode: hash - outputColumnNames: _col0 - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - Reduce Output Operator - sort order: - Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE - value expressions: _col0 (type: bigint) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE + Reduce Output Operator + key expressions: _col0 (type: string) + sort order: + + Map-reduce partition columns: _col0 (type: string) + Statistics: Num rows: 1 Data size: 184 Basic stats: COMPLETE Column stats: NONE Execution mode: vectorized, llap LLAP IO: all inputs Map Vectorization: @@ -6963,10 +6962,10 @@ STAGE PLANS: inputFormatFeatureSupport: [DECIMAL_64] featureSupportInUse: [DECIMAL_64] inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat - allNative: false + allNative: true usesVectorUDFAdaptor: false vectorized: true - Reducer 4 + Reducer 2 Execution mode: vectorized, llap Reduce Vectorization: enabled: true @@ -7351,18 +7350,18 @@ STAGE PLANS: alias: srcpart_orc_n0 Statistics: Num rows: 2000 Data size: 564000 Basic stats: COMPLETE Column stats: COMPLETE Select Operator - expressions: ds (type: string), hr (type: int) + expressions: ds (type: string), UDFToDouble(hr) (type: double) outputColumnNames: _col0, _col1 - Statistics: Num rows: 2000 Data size: 376000 Basic stats: COMPLETE Column stats: COMPLETE + Statistics: Num rows: 2000 Data size: 384000 Basic stats: COMPLETE Column stats: COMPLETE Map Join Operator condition map: Inner Join 0 to 1 keys: - 0 _col0 (type: string), UDFToDouble(_col1) (type: double) - 1 _col0 (type: string), UDFToDouble(_col2) (type: double) + 0 _col0 (type: string), _col1 (type: double) + 1 _col0 (type: string), _col1 (type: double) input vertices: 1 Map 3 - Statistics: Num rows: 2200 Data size: 413600 Basic stats: COMPLETE Column stats: NONE + Statistics: Num rows: 2200 Data size: 422400 Basic stats: COMPLETE Column stats: NONE Group By Operator aggregations: count() mode: hash @@ -7384,13 +7383,13 @@ STAGE PLANS: predicate: ((UDFToDouble(hour) = 11.0D) and (date) IN ('2008-04-08', '2008-04-09') and ds is not null and hr is not null) (type: boolean) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator - expressions: ds (type: string), hr (type: string) - outputColumnNames: _col0, _col2 + expressions: ds (type: string), UDFToDouble(hr) (type: double) + outputColumnNames: _col0, _col1 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Reduce Output Operator - key expressions: _col0 (type: string), UDFToDouble(_col2) (type: double) + key expressions: _col0 (type: string), _col1 (type: double) sort order: ++ - Map-reduce partition columns: _col0 (type: string), UDFToDouble(_col2) (type: double) + Map-reduce partition columns: _col0 (type: string), _col1 (type: double) Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Select Operator expressions: _col0 (type: string) @@ -7408,7 +7407,7 @@ STAGE PLANS: Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Target Vertex: Map 1 Select Operator - expressions: UDFToDouble(_col2) (type: double) + expressions: _col1 (type: double) outputColumnNames: _col0 Statistics: Num rows: 2 Data size: 1472 Basic stats: COMPLETE Column stats: NONE Group By Operator
