hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [01/15] hive git commit: HIVE-15905 : Inefficient plan for correlated subqueries (Vineet Garg via Ashutosh Chauhan)
Date Wed, 15 Feb 2017 01:26:03 GMT
Repository: hive
Updated Branches:
  refs/heads/master b14ef6d6f -> bddf5a7a9


http://git-wip-us.apache.org/repos/asf/hive/blob/bddf5a7a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
index bdfdc34..94210fd 100644
--- a/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
+++ b/ql/src/test/results/clientpositive/subquery_unqualcolumnrefs.q.out
@@ -39,95 +39,10 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain select * from src11 where src11.key1 in (select key from src where src11.value1 = value and key > '9')
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-3 is a root stage
-  Stage-2 depends on stages: Stage-3
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: src11
-            Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-            Select Operator
-              expressions: value1 (type: string)
-              outputColumnNames: value1
-              Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-              Group By Operator
-                keys: value1 (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL 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: 0 Basic stats: PARTIAL Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: src
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: (key > '9') (type: boolean)
-              Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string), value (type: string)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col0 (type: string)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col1 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col2
-          Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: string), _col2 (type: string)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              keys: _col0 (type: string), _col1 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
   Stage: Stage-1
     Map Reduce
       Map Operator Tree:
@@ -144,11 +59,25 @@ STAGE PLANS:
                 Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
                 Statistics: Num rows: 1 Data size: 0 Basic stats: PARTIAL Column stats: NONE
           TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 182 Data size: 1939 Basic stats: COMPLETE Column stats: NONE
+            alias: src
+            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+            Filter Operator
+              predicate: ((value = value) and (key > '9')) (type: boolean)
+              Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+              Select Operator
+                expressions: key (type: string), value (type: string)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string), _col1 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: string), _col1 (type: string)
+                    sort order: ++
+                    Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+                    Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
@@ -157,10 +86,10 @@ STAGE PLANS:
             0 _col0 (type: string), _col1 (type: string)
             1 _col0 (type: string), _col1 (type: string)
           outputColumnNames: _col0, _col1
-          Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
-            Statistics: Num rows: 200 Data size: 2132 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 91 Data size: 969 Basic stats: COMPLETE Column stats: NONE
             table:
                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -177,95 +106,10 @@ PREHOOK: type: QUERY
 POSTHOOK: query: explain select * from src a where a.key in (select key from src where a.value = value and key > '9')
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-3 is a root stage
-  Stage-2 depends on stages: Stage-3
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: a
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: value (type: string)
-              outputColumnNames: value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: value (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-2
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: src
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: (key > '9') (type: boolean)
-              Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string), value (type: string)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col0 (type: string)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col1 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col2
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: string), _col2 (type: string)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              keys: _col0 (type: string), _col1 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1
-              Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
   Stage: Stage-1
     Map Reduce
       Map Operator Tree:
@@ -282,11 +126,25 @@ STAGE PLANS:
                 Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
                 Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
           TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+            alias: src
+            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+            Filter Operator
+              predicate: ((value = value) and (key > '9')) (type: boolean)
+              Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+              Select Operator
+                expressions: key (type: string), value (type: string)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string), _col1 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: string), _col1 (type: string)
+                    sort order: ++
+                    Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+                    Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
@@ -329,46 +187,11 @@ where b.key in
         )
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-4 is a root stage
-  Stage-2 depends on stages: Stage-4
-  Stage-3 depends on stages: Stage-2
-  Stage-1 depends on stages: Stage-3
+  Stage-2 is a root stage
+  Stage-1 depends on stages: Stage-2
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-4
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: b
-            Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: value (type: string)
-              outputColumnNames: value
-              Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: value (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
   Stage: Stage-2
     Map Reduce
       Map Operator Tree:
@@ -376,65 +199,29 @@ STAGE PLANS:
             alias: src
             Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
-              predicate: (key > '9') (type: boolean)
-              Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: key (type: string), value (type: string)
+              predicate: ((value = value) and (key > '9')) (type: boolean)
+              Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+              Group By Operator
+                keys: key (type: string), value (type: string)
+                mode: hash
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 83 Data size: 881 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                  value expressions: _col0 (type: string)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col1 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col0, _col2
-          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            keys: _col0 (type: string), _col2 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string), _col1 (type: string)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  key expressions: _col0 (type: string), _col1 (type: string)
+                  sort order: ++
+                  Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+                  Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Group By Operator
           keys: KEY._col0 (type: string), KEY._col1 (type: string)
           mode: mergepartial
           outputColumnNames: _col0, _col1
-          Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
           Group By Operator
             keys: _col0 (type: string), _col1 (type: string)
             mode: hash
             outputColumnNames: _col0, _col1
-            Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
             File Output Operator
               compressed: false
               table:
@@ -462,7 +249,7 @@ STAGE PLANS:
               key expressions: _col0 (type: string), _col1 (type: string)
               sort order: ++
               Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Join Operator
           condition map:
@@ -506,17 +293,11 @@ where b.p_name not in
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
   Stage-3 is a root stage
-  Stage-4 depends on stages: Stage-3, Stage-6
-  Stage-5 depends on stages: Stage-4
-  Stage-1 depends on stages: Stage-5
-  Stage-2 depends on stages: Stage-1, Stage-10
-  Stage-6 is a root stage
-  Stage-7 is a root stage
-  Stage-8 depends on stages: Stage-7, Stage-11
-  Stage-9 depends on stages: Stage-8
-  Stage-10 depends on stages: Stage-9, Stage-12
-  Stage-11 is a root stage
-  Stage-12 is a root stage
+  Stage-4 depends on stages: Stage-3
+  Stage-1 depends on stages: Stage-4
+  Stage-2 depends on stages: Stage-1, Stage-6
+  Stage-5 is a root stage
+  Stage-6 depends on stages: Stage-5
   Stage-0 depends on stages: Stage-2
 
 STAGE PLANS:
@@ -526,18 +307,21 @@ STAGE PLANS:
           TableScan
             alias: part
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              TopN Hash Memory Usage: 0.1
-              value expressions: p_name (type: string)
+            Filter Operator
+              predicate: (p_mfgr = p_mfgr) (type: boolean)
+              Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+              Reduce Output Operator
+                key expressions: p_mfgr (type: string), p_size (type: int)
+                sort order: ++
+                Map-reduce partition columns: p_mfgr (type: string)
+                Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+                TopN Hash Memory Usage: 0.1
+                value expressions: p_name (type: string)
       Reduce Operator Tree:
         Select Operator
           expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
           outputColumnNames: _col1, _col2, _col5
-          Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           PTF Operator
             Function definitions:
                 Input definition
@@ -558,20 +342,26 @@ STAGE PLANS:
                         window function: GenericUDAFRankEvaluator
                         window frame: PRECEDING(MAX)~FOLLOWING(MAX)
                         isPivotResult: true
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: (rank_window_0 <= 2) (type: boolean)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: _col2 (type: string), _col1 (type: string)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-                File Output Operator
-                  compressed: false
-                  table:
-                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                      serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+                outputColumnNames: _col1, _col0
+                Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  aggregations: count(), count(_col0)
+                  keys: _col1 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-4
     Map Reduce
@@ -581,49 +371,7 @@ STAGE PLANS:
               key expressions: _col0 (type: string)
               sort order: +
               Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: string)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1, _col2
-          Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col2 (type: string), _col1 (type: string)
-            outputColumnNames: _col2, _col1
-            Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-            Group By Operator
-              aggregations: count(), count(_col1)
-              keys: _col2 (type: string)
-              mode: hash
-              outputColumnNames: _col0, _col1, _col2
-              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-5
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col1 (type: bigint), _col2 (type: bigint)
       Reduce Operator Tree:
         Group By Operator
@@ -631,7 +379,7 @@ STAGE PLANS:
           keys: KEY._col0 (type: string)
           mode: mergepartial
           outputColumnNames: _col0, _col1, _col2
-          Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
             table:
@@ -660,7 +408,7 @@ STAGE PLANS:
               key expressions: _col0 (type: string)
               sort order: +
               Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col1 (type: bigint), _col2 (type: bigint)
       Reduce Operator Tree:
         Join Operator
@@ -690,10 +438,10 @@ STAGE PLANS:
               value expressions: _col2 (type: int), _col4 (type: bigint), _col5 (type: bigint)
           TableScan
             Reduce Output Operator
-              key expressions: _col3 (type: string), _col1 (type: string)
+              key expressions: _col0 (type: string), _col1 (type: string)
               sort order: ++
-              Map-reduce partition columns: _col3 (type: string), _col1 (type: string)
-              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+              Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+              Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
               value expressions: _col2 (type: boolean)
       Reduce Operator Tree:
         Join Operator
@@ -701,11 +449,11 @@ STAGE PLANS:
                Left Outer Join0 to 1
           keys:
             0 _col0 (type: string), _col1 (type: string)
-            1 _col3 (type: string), _col1 (type: string)
+            1 _col0 (type: string), _col1 (type: string)
           outputColumnNames: _col0, _col1, _col2, _col4, _col5, _col8
           Statistics: Num rows: 30 Data size: 3807 Basic stats: COMPLETE Column stats: NONE
           Filter Operator
-            predicate: CASE WHEN ((_col4 = 0)) THEN (true) WHEN (_col4 is null) THEN (true) WHEN (_col8 is not null) THEN (false) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (false) ELSE (true) END (type: boolean)
+            predicate: (not CASE WHEN ((_col4 = 0)) THEN (false) WHEN (_col4 is null) THEN (false) WHEN (_col8 is not null) THEN (true) WHEN (_col0 is null) THEN (null) WHEN ((_col5 < _col4)) THEN (true) ELSE (false) END) (type: boolean)
             Statistics: Num rows: 15 Data size: 1903 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: _col1 (type: string), _col0 (type: string), _col2 (type: int)
@@ -719,57 +467,27 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
-  Stage: Stage-6
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: b
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: p_mfgr (type: string)
-              outputColumnNames: p_mfgr
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: p_mfgr (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-7
+  Stage: Stage-5
     Map Reduce
       Map Operator Tree:
           TableScan
             alias: part
             Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Reduce Output Operator
-              key expressions: p_mfgr (type: string), p_size (type: int)
-              sort order: ++
-              Map-reduce partition columns: p_mfgr (type: string)
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              TopN Hash Memory Usage: 0.1
-              value expressions: p_name (type: string)
+            Filter Operator
+              predicate: (p_mfgr = p_mfgr) (type: boolean)
+              Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+              Reduce Output Operator
+                key expressions: p_mfgr (type: string), p_size (type: int)
+                sort order: ++
+                Map-reduce partition columns: p_mfgr (type: string)
+                Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
+                TopN Hash Memory Usage: 0.1
+                value expressions: p_name (type: string)
       Reduce Operator Tree:
         Select Operator
           expressions: VALUE._col1 (type: string), KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: int)
           outputColumnNames: _col1, _col2, _col5
-          Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
           PTF Operator
             Function definitions:
                 Input definition
@@ -790,59 +508,27 @@ STAGE PLANS:
                         window function: GenericUDAFRankEvaluator
                         window frame: PRECEDING(MAX)~FOLLOWING(MAX)
                         isPivotResult: true
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: (rank_window_0 <= 2) (type: boolean)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
               Select Operator
-                expressions: _col2 (type: string), _col1 (type: string)
+                expressions: _col1 (type: string), _col2 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-                File Output Operator
-                  compressed: false
-                  table:
-                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                      serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+                Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  keys: _col0 (type: string), _col1 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-8
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: string)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1, _col2
-          Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-          Group By Operator
-            keys: _col1 (type: string), _col2 (type: string)
-            mode: hash
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-9
+  Stage: Stage-6
     Map Reduce
       Map Operator Tree:
           TableScan
@@ -850,121 +536,26 @@ STAGE PLANS:
               key expressions: _col0 (type: string), _col1 (type: string)
               sort order: ++
               Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-              Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 484 Basic stats: COMPLETE Column stats: NONE
       Reduce Operator Tree:
         Group By Operator
           keys: KEY._col0 (type: string), KEY._col1 (type: string)
           mode: mergepartial
           outputColumnNames: _col0, _col1
-          Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
-            outputColumnNames: _col0, _col1, _col2
-            Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-10
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 7 Data size: 865 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col1 (type: string), _col2 (type: boolean)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: string)
-              sort order: +
-              Map-reduce partition columns: _col0 (type: string)
-              Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Inner Join 0 to 1
-          keys:
-            0 _col0 (type: string)
-            1 _col0 (type: string)
-          outputColumnNames: _col1, _col2, _col3
-          Statistics: Num rows: 14 Data size: 1730 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-11
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: b
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-            Select Operator
-              expressions: p_mfgr (type: string)
-              outputColumnNames: p_mfgr
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: p_mfgr (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-12
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: b
-            Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 2 Data size: 242 Basic stats: COMPLETE Column stats: NONE
+          Filter Operator
+            predicate: (_col0 = _col0) (type: boolean)
+            Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
             Select Operator
-              expressions: p_name (type: string)
-              outputColumnNames: p_name
-              Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                keys: p_name (type: string)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 26 Data size: 3147 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: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Group By Operator
-          keys: KEY._col0 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 13 Data size: 1573 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+              expressions: _col0 (type: string), _col1 (type: string), true (type: boolean)
+              outputColumnNames: _col0, _col1, _col2
+              Statistics: Num rows: 1 Data size: 121 Basic stats: COMPLETE Column stats: NONE
+              File Output Operator
+                compressed: false
+                table:
+                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
   Stage: Stage-0
     Fetch Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/bddf5a7a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out
index 5ea9a65..a2f59d5 100644
--- a/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out
+++ b/ql/src/test/results/clientpositive/vector_mapjoin_reduce.q.out
@@ -205,18 +205,9 @@ PLAN VECTORIZATION:
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-16 depends on stages: Stage-1
-  Stage-12 depends on stages: Stage-16
-  Stage-11 depends on stages: Stage-12, Stage-13 , consists of Stage-15, Stage-3
-  Stage-15 has a backup stage: Stage-3
-  Stage-10 depends on stages: Stage-15
-  Stage-3
-  Stage-6 is a root stage
-  Stage-18 depends on stages: Stage-6
-  Stage-8 depends on stages: Stage-18
-  Stage-17 depends on stages: Stage-8
-  Stage-13 depends on stages: Stage-17
-  Stage-0 depends on stages: Stage-10, Stage-3
+  Stage-8 depends on stages: Stage-1
+  Stage-6 depends on stages: Stage-8
+  Stage-0 depends on stages: Stage-6
 
 STAGE PLANS:
   Stage: Stage-1
@@ -267,12 +258,15 @@ STAGE PLANS:
                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
                 serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
 
-  Stage: Stage-16
+  Stage: Stage-8
     Map Reduce Local Work
       Alias -> Map Local Tables:
         $hdt$_1:li 
           Fetch Operator
             limit: -1
+        $hdt$_2:lineitem 
+          Fetch Operator
+            limit: -1
       Alias -> Map Local Operator Tree:
         $hdt$_1:li 
           TableScan
@@ -289,264 +283,32 @@ STAGE PLANS:
                   keys:
                     0 _col0 (type: int)
                     1 _col1 (type: int)
-
-  Stage: Stage-12
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Map Join Operator
-              condition map:
-                   Inner Join 0 to 1
-              keys:
-                0 _col0 (type: int)
-                1 _col1 (type: int)
-              outputColumnNames: _col0, _col1, _col3, _col4
-              Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
-              File Output Operator
-                compressed: false
-                table:
-                    input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                    serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-      Map Vectorization:
-          enabled: false
-          enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
-          inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
-      Local Work:
-        Map Reduce Local Work
-
-  Stage: Stage-11
-    Conditional Operator
-
-  Stage: Stage-15
-    Map Reduce Local Work
-      Alias -> Map Local Tables:
-        $INTNAME1 
-          Fetch Operator
-            limit: -1
-      Alias -> Map Local Operator Tree:
-        $INTNAME1 
-          TableScan
-            HashTable Sink Operator
-              keys:
-                0 _col1 (type: int), _col4 (type: int)
-                1 _col0 (type: int), _col1 (type: int)
-
-  Stage: Stage-10
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Map Join Operator
-              condition map:
-                   Left Semi Join 0 to 1
-              keys:
-                0 _col1 (type: int), _col4 (type: int)
-                1 _col0 (type: int), _col1 (type: int)
-              outputColumnNames: _col0, _col3
-              Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: _col0 (type: int), _col3 (type: int)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-                File Output Operator
-                  compressed: false
-                  Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-                  table:
-                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-      Map Vectorization:
-          enabled: false
-          enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
-          inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
-      Local Work:
-        Map Reduce Local Work
-
-  Stage: Stage-3
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Reduce Output Operator
-              key expressions: _col1 (type: int), _col4 (type: int)
-              sort order: ++
-              Map-reduce partition columns: _col1 (type: int), _col4 (type: int)
-              Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
-              value expressions: _col0 (type: int), _col3 (type: int)
-          TableScan
-            Reduce Output Operator
-              key expressions: _col0 (type: int), _col1 (type: int)
-              sort order: ++
-              Map-reduce partition columns: _col0 (type: int), _col1 (type: int)
-              Statistics: Num rows: 60 Data size: 7258 Basic stats: COMPLETE Column stats: NONE
-      Reduce Operator Tree:
-        Join Operator
-          condition map:
-               Left Semi Join 0 to 1
-          keys:
-            0 _col1 (type: int), _col4 (type: int)
-            1 _col0 (type: int), _col1 (type: int)
-          outputColumnNames: _col0, _col3
-          Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: int), _col3 (type: int)
-            outputColumnNames: _col0, _col1
-            Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              Statistics: Num rows: 66 Data size: 7983 Basic stats: COMPLETE Column stats: NONE
-              table:
-                  input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-
-  Stage: Stage-6
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            alias: lineitem
-            Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: l_partkey is not null (type: boolean)
-              Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                Group By Vectorization:
-                    vectorOutput: false
-                    native: false
-                    projectedOutputColumns: null
-                keys: l_partkey (type: int)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: int)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: int)
-                  Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-      Map Vectorization:
-          enabled: false
-          enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
-          inputFileFormats: org.apache.hadoop.mapred.TextInputFormat
-      Reduce Vectorization:
-          enabled: false
-          enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
-          enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
-      Reduce Operator Tree:
-        Group By Operator
-          Group By Vectorization:
-              vectorOutput: false
-              native: false
-              projectedOutputColumns: null
-          keys: KEY._col0 (type: int)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-18
-    Map Reduce Local Work
-      Alias -> Map Local Tables:
-        $hdt$_2:$hdt$_3:$hdt$_4:li 
-          Fetch Operator
-            limit: -1
-      Alias -> Map Local Operator Tree:
-        $hdt$_2:$hdt$_3:$hdt$_4:li 
-          TableScan
-            alias: li
-            Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-            Filter Operator
-              predicate: l_partkey is not null (type: boolean)
-              Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: l_partkey (type: int), l_linenumber (type: int)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
-                HashTable Sink Operator
-                  keys:
-                    0 _col0 (type: int)
-                    1 _col0 (type: int)
-
-  Stage: Stage-8
-    Map Reduce
-      Map Operator Tree:
-          TableScan
-            Map Join Operator
-              condition map:
-                   Inner Join 0 to 1
-              keys:
-                0 _col0 (type: int)
-                1 _col0 (type: int)
-              outputColumnNames: _col2
-              Statistics: Num rows: 110 Data size: 13198 Basic stats: COMPLETE Column stats: NONE
-              Group By Operator
-                Group By Vectorization:
-                    vectorOutput: false
-                    native: false
-                    projectedOutputColumns: null
-                keys: _col2 (type: int)
-                mode: hash
-                outputColumnNames: _col0
-                Statistics: Num rows: 110 Data size: 13198 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: int)
-                  sort order: +
-                  Map-reduce partition columns: _col0 (type: int)
-                  Statistics: Num rows: 110 Data size: 13198 Basic stats: COMPLETE Column stats: NONE
-      Map Vectorization:
-          enabled: false
-          enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false
-          inputFileFormats: org.apache.hadoop.mapred.SequenceFileInputFormat
-      Local Work:
-        Map Reduce Local Work
-      Reduce Vectorization:
-          enabled: false
-          enableConditionsMet: hive.vectorized.execution.reduce.enabled IS true
-          enableConditionsNotMet: hive.execution.engine mr IN [tez, spark] IS false
-      Reduce Operator Tree:
-        Group By Operator
-          Group By Vectorization:
-              vectorOutput: false
-              native: false
-              projectedOutputColumns: null
-          keys: KEY._col0 (type: int)
-          mode: mergepartial
-          outputColumnNames: _col0
-          Statistics: Num rows: 55 Data size: 6599 Basic stats: COMPLETE Column stats: NONE
-          File Output Operator
-            compressed: false
-            table:
-                input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
-
-  Stage: Stage-17
-    Map Reduce Local Work
-      Alias -> Map Local Tables:
-        $hdt$_2:$hdt$_2:lineitem 
-          Fetch Operator
-            limit: -1
-      Alias -> Map Local Operator Tree:
-        $hdt$_2:$hdt$_2:lineitem 
+        $hdt$_2:lineitem 
           TableScan
             alias: lineitem
             Statistics: Num rows: 100 Data size: 11999 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
-              predicate: (l_shipmode = 'AIR') (type: boolean)
-              Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
+              predicate: ((l_shipmode = 'AIR') and (l_linenumber = l_linenumber)) (type: boolean)
+              Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: l_orderkey (type: int), l_linenumber (type: int)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 50 Data size: 5999 Basic stats: COMPLETE Column stats: NONE
-                HashTable Sink Operator
-                  keys:
-                    0 _col1 (type: int)
-                    1 _col0 (type: int)
+                Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  Group By Vectorization:
+                      vectorOutput: false
+                      native: false
+                      projectedOutputColumns: null
+                  keys: _col0 (type: int), _col1 (type: int)
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 25 Data size: 2999 Basic stats: COMPLETE Column stats: NONE
+                  HashTable Sink Operator
+                    keys:
+                      0 _col1 (type: int), _col4 (type: int)
+                      1 _col0 (type: int), _col1 (type: int)
 
-  Stage: Stage-13
+  Stage: Stage-6
     Map Reduce
       Map Operator Tree:
           TableScan
@@ -554,29 +316,29 @@ STAGE PLANS:
               condition map:
                    Inner Join 0 to 1
               keys:
-                0 _col1 (type: int)
-                1 _col0 (type: int)
-              outputColumnNames: _col0, _col3
-              Statistics: Num rows: 60 Data size: 7258 Basic stats: COMPLETE Column stats: NONE
-              Select Operator
-                expressions: _col0 (type: int), _col3 (type: int)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 60 Data size: 7258 Basic stats: COMPLETE Column stats: NONE
-                Group By Operator
-                  Group By Vectorization:
-                      vectorOutput: false
-                      native: false
-                      projectedOutputColumns: null
-                  keys: _col0 (type: int), _col1 (type: int)
-                  mode: hash
+                0 _col0 (type: int)
+                1 _col1 (type: int)
+              outputColumnNames: _col0, _col1, _col3, _col4
+              Statistics: Num rows: 55 Data size: 6598 Basic stats: COMPLETE Column stats: NONE
+              Map Join Operator
+                condition map:
+                     Left Semi Join 0 to 1
+                keys:
+                  0 _col1 (type: int), _col4 (type: int)
+                  1 _col0 (type: int), _col1 (type: int)
+                outputColumnNames: _col0, _col3
+                Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col3 (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 60 Data size: 7258 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
+                    Statistics: Num rows: 60 Data size: 7257 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazybinary.LazyBinarySerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
       Map Vectorization:
           enabled: false
           enabledConditionsNotMet: hive.vectorized.use.vector.serde.deserialize IS false


Mime
View raw message