hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From li...@apache.org
Subject [4/8] hive git commit: HIVE-6348: Order by/Sort by in subquery (Rui Li reviewed by Vineet Garg)
Date Fri, 30 Jun 2017 08:07:39 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/b11e43b1/ql/src/test/results/clientpositive/llap/vector_join30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/vector_join30.q.out b/ql/src/test/results/clientpositive/llap/vector_join30.q.out
index 381f13e..6b5e604 100644
--- a/ql/src/test/results/clientpositive/llap/vector_join30.q.out
+++ b/ql/src/test/results/clientpositive/llap/vector_join30.q.out
@@ -39,9 +39,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE)
-        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
-        Reducer 5 <- Map 4 (SIMPLE_EDGE)
+        Map 1 <- Map 3 (BROADCAST_EDGE)
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -67,14 +66,41 @@ STAGE PLANS:
                           native: true
                           projectedOutputColumns: [0]
                       Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Reduce Sink Vectorization:
-                            className: VectorReduceSinkObjectHashOperator
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        Map Join Vectorization:
+                            className: VectorMapJoinInnerStringOperator
                             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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                            nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+                        outputColumnNames: _col2, _col3
+                        input vertices:
+                          1 Map 3
+                        Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: sum(hash(_col2,_col3))
+                          Group By Vectorization:
+                              aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 3:int) -> bigint
+                              className: VectorGroupByOperator
+                              groupByMode: HASH
+                              vectorOutput: true
+                              native: false
+                              vectorProcessingMode: HASH
+                              projectedOutputColumns: [0]
+                          mode: hash
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            sort order: 
+                            Reduce Sink Vectorization:
+                                className: VectorReduceSinkEmptyKeyOperator
+                                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: 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:
@@ -82,10 +108,10 @@ STAGE PLANS:
                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
                 groupByVectorOutput: true
                 inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
-                allNative: true
-                usesVectorUDFAdaptor: false
+                allNative: false
+                usesVectorUDFAdaptor: true
                 vectorized: true
-        Map 4 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -109,14 +135,15 @@ STAGE PLANS:
                           projectedOutputColumns: [0, 1]
                       Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col1 (type: string)
+                        key expressions: _col0 (type: string)
                         sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
                         Reduce Sink Vectorization:
-                            className: VectorReduceSinkObjectHashOperator
+                            className: VectorReduceSinkStringOperator
                             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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: string)
+                        value expressions: _col1 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -134,59 +161,6 @@ STAGE PLANS:
                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
                 groupByVectorOutput: true
                 allNative: false
-                usesVectorUDFAdaptor: true
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Inner Join 0 to 1
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                  Map Join Vectorization:
-                      className: VectorMapJoinInnerStringOperator
-                      native: true
-                      nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
-                  outputColumnNames: _col2, _col3
-                  input vertices:
-                    1 Reducer 5
-                  Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(hash(_col2,_col3))
-                    Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint
-                        className: VectorGroupByOperator
-                        groupByMode: HASH
-                        vectorOutput: true
-                        native: false
-                        vectorProcessingMode: HASH
-                        projectedOutputColumns: [0]
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkEmptyKeyOperator
-                          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: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: false
                 usesVectorUDFAdaptor: false
                 vectorized: true
             Reduce Operator Tree:
@@ -213,34 +187,6 @@ STAGE PLANS:
                       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 5 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
 
   Stage: Stage-0
     Fetch Operator
@@ -296,9 +242,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE)
-        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
-        Reducer 5 <- Map 4 (SIMPLE_EDGE)
+        Map 1 <- Map 3 (BROADCAST_EDGE)
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -317,14 +262,41 @@ STAGE PLANS:
                         native: true
                         projectedOutputColumns: [0]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col0 (type: string)
-                      sort order: +
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                    Map Join Operator
+                      condition map:
+                           Left Outer Join 0 to 1
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                          nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+                      outputColumnNames: _col2, _col3
+                      input vertices:
+                        1 Map 3
+                      Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        aggregations: sum(hash(_col2,_col3))
+                        Group By Vectorization:
+                            aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 4:int) -> bigint
+                            className: VectorGroupByOperator
+                            groupByMode: HASH
+                            vectorOutput: true
+                            native: false
+                            vectorProcessingMode: HASH
+                            projectedOutputColumns: [0]
+                        mode: hash
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          sort order: 
+                          Reduce Sink Vectorization:
+                              className: VectorReduceSinkEmptyKeyOperator
+                              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: 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:
@@ -332,10 +304,10 @@ STAGE PLANS:
                 enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
                 groupByVectorOutput: true
                 inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
-                allNative: true
-                usesVectorUDFAdaptor: false
+                allNative: false
+                usesVectorUDFAdaptor: true
                 vectorized: true
-        Map 4 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -352,14 +324,15 @@ STAGE PLANS:
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                      value expressions: _col1 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -377,59 +350,6 @@ STAGE PLANS:
                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
                 groupByVectorOutput: true
                 allNative: false
-                usesVectorUDFAdaptor: true
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Left Outer Join 0 to 1
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                  Map Join Vectorization:
-                      className: VectorMapJoinOuterStringOperator
-                      native: true
-                      nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
-                  outputColumnNames: _col2, _col3
-                  input vertices:
-                    1 Reducer 5
-                  Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(hash(_col2,_col3))
-                    Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 3:int) -> bigint
-                        className: VectorGroupByOperator
-                        groupByMode: HASH
-                        vectorOutput: true
-                        native: false
-                        vectorProcessingMode: HASH
-                        projectedOutputColumns: [0]
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkEmptyKeyOperator
-                          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: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: false
                 usesVectorUDFAdaptor: false
                 vectorized: true
             Reduce Operator Tree:
@@ -456,34 +376,6 @@ STAGE PLANS:
                       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 5 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
 
   Stage: Stage-0
     Fetch Operator
@@ -539,9 +431,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 4 <- Map 3 (SIMPLE_EDGE), Reducer 2 (BROADCAST_EDGE)
-        Reducer 5 <- Reducer 4 (CUSTOM_SIMPLE_EDGE)
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+        Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -563,8 +454,9 @@ STAGE PLANS:
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
@@ -578,7 +470,7 @@ STAGE PLANS:
                 allNative: true
                 usesVectorUDFAdaptor: false
                 vectorized: true
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -594,15 +486,41 @@ STAGE PLANS:
                         native: true
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col1 (type: string)
-                      sort order: +
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                    Map Join Operator
+                      condition map:
+                           Right Outer Join 0 to 1
+                      keys:
+                        0 _col0 (type: string)
+                        1 _col0 (type: string)
+                      Map Join Vectorization:
+                          className: VectorMapJoinOuterStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                          nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+                      outputColumnNames: _col2, _col3
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        aggregations: sum(hash(_col2,_col3))
+                        Group By Vectorization:
+                            aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint
+                            className: VectorGroupByOperator
+                            groupByMode: HASH
+                            vectorOutput: true
+                            native: false
+                            vectorProcessingMode: HASH
+                            projectedOutputColumns: [0]
+                        mode: hash
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          sort order: 
+                          Reduce Sink Vectorization:
+                              className: VectorReduceSinkEmptyKeyOperator
+                              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: 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:
@@ -610,90 +528,10 @@ STAGE PLANS:
                 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
-        Reducer 2 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-        Reducer 4 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
                 allNative: false
                 usesVectorUDFAdaptor: true
                 vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Right Outer Join 0 to 1
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                  Map Join Vectorization:
-                      className: VectorMapJoinOuterStringOperator
-                      native: true
-                      nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, One MapJoin Condition IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
-                  outputColumnNames: _col2, _col3
-                  input vertices:
-                    0 Reducer 2
-                  Statistics: Num rows: 550 Data size: 96800 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(hash(_col2,_col3))
-                    Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint
-                        className: VectorGroupByOperator
-                        groupByMode: HASH
-                        vectorOutput: true
-                        native: false
-                        vectorProcessingMode: HASH
-                        projectedOutputColumns: [0]
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkEmptyKeyOperator
-                          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: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 5 
+        Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
                 enabled: true
@@ -787,10 +625,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (BROADCAST_EDGE), Reducer 6 (BROADCAST_EDGE)
-        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
-        Reducer 5 <- Map 4 (SIMPLE_EDGE)
-        Reducer 6 <- Map 4 (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 
@@ -816,14 +652,88 @@ STAGE PLANS:
                           native: true
                           projectedOutputColumns: [0]
                       Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                             Inner Join 0 to 2
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                          2 _col0 (type: string)
+                        Map Join Vectorization:
+                            className: VectorMapJoinOperator
+                            native: false
+                            nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
+                            nativeConditionsNotMet: One MapJoin Condition IS false
+                        outputColumnNames: _col2, _col3
+                        input vertices:
+                          1 Map 3
+                          2 Map 4
+                        Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: sum(hash(_col2,_col3))
+                          Group By Vectorization:
+                              aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint
+                              className: VectorGroupByOperator
+                              groupByMode: HASH
+                              vectorOutput: true
+                              native: false
+                              vectorProcessingMode: HASH
+                              projectedOutputColumns: [0]
+                          mode: hash
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            sort order: 
+                            Reduce Sink Vectorization:
+                                className: VectorReduceSinkEmptyKeyOperator
+                                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: 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:
+                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: true
+                vectorized: true
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: orcsrc
+                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1]
+                  Filter Operator
+                    Filter Vectorization:
+                        className: VectorFilterOperator
+                        native: true
+                        predicateExpression: SelectColumnIsNotNull(col 0) -> boolean
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Select Vectorization:
+                          className: VectorSelectOperator
+                          native: true
+                          projectedOutputColumns: [0, 1]
+                      Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
                         Reduce Sink Vectorization:
-                            className: VectorReduceSinkObjectHashOperator
+                            className: VectorReduceSinkStringOperator
                             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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -850,31 +760,22 @@ STAGE PLANS:
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
                       Select Vectorization:
                           className: VectorSelectOperator
                           native: true
-                          projectedOutputColumns: [0, 1]
+                          projectedOutputColumns: [0]
                       Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
-                        key expressions: _col1 (type: string)
-                        sort order: +
-                        Reduce Sink Vectorization:
-                            className: VectorReduceSinkObjectHashOperator
-                            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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: string)
-                      Reduce Output Operator
-                        key expressions: _col1 (type: string)
+                        key expressions: _col0 (type: string)
                         sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
                         Reduce Sink Vectorization:
-                            className: VectorReduceSinkObjectHashOperator
+                            className: VectorReduceSinkStringOperator
                             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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col0 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -892,63 +793,6 @@ STAGE PLANS:
                 enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
                 groupByVectorOutput: true
                 allNative: false
-                usesVectorUDFAdaptor: true
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Inner Join 0 to 1
-                       Inner Join 0 to 2
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                    2 _col0 (type: string)
-                  Map Join Vectorization:
-                      className: VectorMapJoinOperator
-                      native: false
-                      nativeConditionsMet: hive.mapjoin.optimized.hashtable IS true, hive.vectorized.execution.mapjoin.native.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No nullsafe IS true, Small table vectorizes IS true, Optimized Table and Supports Key Types IS true
-                      nativeConditionsNotMet: One MapJoin Condition IS false
-                  outputColumnNames: _col2, _col3
-                  input vertices:
-                    1 Reducer 5
-                    2 Reducer 6
-                  Statistics: Num rows: 1100 Data size: 193600 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: sum(hash(_col2,_col3))
-                    Group By Vectorization:
-                        aggregators: VectorUDAFSumLong(VectorUDFAdaptor(hash(_col2,_col3)) -> 2:int) -> bigint
-                        className: VectorGroupByOperator
-                        groupByMode: HASH
-                        vectorOutput: true
-                        native: false
-                        vectorProcessingMode: HASH
-                        projectedOutputColumns: [0]
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Reduce Sink Vectorization:
-                          className: VectorReduceSinkEmptyKeyOperator
-                          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: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: false
                 usesVectorUDFAdaptor: false
                 vectorized: true
             Reduce Operator Tree:
@@ -975,61 +819,6 @@ STAGE PLANS:
                       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 5 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
-        Reducer 6 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -1097,11 +886,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
-        Reducer 6 <- Map 5 (SIMPLE_EDGE)
-        Reducer 7 <- Map 5 (SIMPLE_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -1123,8 +909,9 @@ STAGE PLANS:
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
@@ -1138,7 +925,7 @@ STAGE PLANS:
                 allNative: true
                 usesVectorUDFAdaptor: false
                 vectorized: true
-        Map 5 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -1155,23 +942,50 @@ STAGE PLANS:
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                      value expressions: _col1 (type: string)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: orcsrc
+                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1]
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: _col0
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0]
+                    Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -1183,33 +997,6 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
         Reducer 2 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Merge Join Operator
@@ -1237,7 +1024,7 @@ STAGE PLANS:
                     sort order: 
                     Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
                 enabled: true
@@ -1270,61 +1057,6 @@ STAGE PLANS:
                       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 6 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
-        Reducer 7 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -1392,11 +1124,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
-        Reducer 6 <- Map 5 (SIMPLE_EDGE)
-        Reducer 7 <- Map 5 (SIMPLE_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -1418,8 +1147,9 @@ STAGE PLANS:
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
@@ -1433,7 +1163,7 @@ STAGE PLANS:
                 allNative: true
                 usesVectorUDFAdaptor: false
                 vectorized: true
-        Map 5 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -1450,23 +1180,50 @@ STAGE PLANS:
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                      value expressions: _col1 (type: string)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: orcsrc
+                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1]
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: _col0
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0]
+                    Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -1478,33 +1235,6 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
         Reducer 2 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Merge Join Operator
@@ -1532,7 +1262,7 @@ STAGE PLANS:
                     sort order: 
                     Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
                 enabled: true
@@ -1565,61 +1295,6 @@ STAGE PLANS:
                       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 6 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
-        Reducer 7 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -1687,11 +1362,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
-        Reducer 6 <- Map 5 (SIMPLE_EDGE)
-        Reducer 7 <- Map 5 (SIMPLE_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -1713,8 +1385,9 @@ STAGE PLANS:
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
@@ -1728,7 +1401,7 @@ STAGE PLANS:
                 allNative: true
                 usesVectorUDFAdaptor: false
                 vectorized: true
-        Map 5 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -1745,31 +1418,50 @@ STAGE PLANS:
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                      value expressions: _col1 (type: string)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: orcsrc
+                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1]
                   Select Operator
-                    expressions: key (type: string), value (type: string)
-                    outputColumnNames: _col0, _col1
+                    expressions: key (type: string)
+                    outputColumnNames: _col0
                     Select Vectorization:
                         className: VectorSelectOperator
                         native: true
-                        projectedOutputColumns: [0, 1]
+                        projectedOutputColumns: [0]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -1781,33 +1473,6 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
         Reducer 2 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Merge Join Operator
@@ -1835,7 +1500,7 @@ STAGE PLANS:
                     sort order: 
                     Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Execution mode: vectorized, llap
             Reduce Vectorization:
                 enabled: true
@@ -1868,61 +1533,6 @@ STAGE PLANS:
                       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 6 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0, _col1
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1, 0]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col1 (type: string)
-        Reducer 7 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorization:
-                    className: VectorSelectOperator
-                    native: true
-                    projectedOutputColumns: [1]
-                Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: string)
-                  Reduce Sink Vectorization:
-                      className: VectorReduceSinkStringOperator
-                      native: true
-                      nativeConditionsMet: hive.vectorized.execution.reducesink.new.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true, No PTF TopN IS true, No DISTINCT columns IS true, BinarySortableSerDe for keys IS true, LazyBinarySerDe for values IS true
-                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -1990,11 +1600,8 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE), Reducer 7 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (CUSTOM_SIMPLE_EDGE)
-        Reducer 6 <- Map 5 (SIMPLE_EDGE)
-        Reducer 7 <- Map 5 (SIMPLE_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE), Map 5 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -2016,8 +1623,9 @@ STAGE PLANS:
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
@@ -2031,7 +1639,7 @@ STAGE PLANS:
                 allNative: true
                 usesVectorUDFAdaptor: false
                 vectorized: true
-        Map 5 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: orcsrc
@@ -2048,23 +1656,50 @@ STAGE PLANS:
                         projectedOutputColumns: [0, 1]
                     Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
+                      value expressions: _col1 (type: string)
+            Execution mode: vectorized, llap
+            LLAP IO: all inputs
+            Map Vectorization:
+                enabled: true
+                enabledConditionsMet: hive.vectorized.use.vectorized.input.format IS true
+                groupByVectorOutput: true
+                inputFileFormats: org.apache.hadoop.hive.ql.io.orc.OrcInputFormat
+                allNative: true
+                usesVectorUDFAdaptor: false
+                vectorized: true
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: orcsrc
+                  Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
+                  TableScan Vectorization:
+                      native: true
+                      projectedOutputColumns: [0, 1]
+                  Select Operator
+                    expressions: key (type: string)
+                    outputColumnNames: _col0
+                    Select Vectorization:
+                        className: VectorSelectOperator
+                        native: true
+                        projectedOutputColumns: [0]
+                    Statistics: Num rows: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
-                      key expressions: _col1 (type: string)
+                      key expressions: _col0 (type: string)
                       sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
                       Reduce Sink Vectorization:
-                          className: VectorReduceSinkObjectHashOperator
+                          className: VectorReduceSinkStringOperator
                           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: 500 Data size: 88000 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: string)
             Execution mode: vectorized, llap
             LLAP IO: all inputs
             Map Vectorization:
@@ -2076,33 +1711,6 @@ STAGE PLANS:
                 usesVectorUDFAdaptor: false
                 vectorized: true
         Reducer 2 
-            Execution mode: vectorized, llap
-            Reduce Vectorization:
-                enabled: true
-                enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true, hive.execution.engine tez IN [tez, spark] IS true
-                groupByVectorOutput: true
-                allNative: true
-                usesVectorUDFAdaptor: false
-                vectorized: true
-            Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string)
-                outputColumnNames: _col0
-                Select Vectorizat

<TRUNCATED>

Mime
View raw message