hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1641614 [34/43] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/java/org/apache/hadoop/hive/ql/parse/spark/ ql/sr...
Date Tue, 25 Nov 2014 13:03:23 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out Tue Nov 25 13:03:18 2014
@@ -75,14 +75,13 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -93,13 +92,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: UDFToDouble(key) (type: double)
-                      sort order: +
-                      Map-reduce partition columns: UDFToDouble(key) (type: double)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: key (type: string), val (type: string)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 UDFToDouble(key) (type: double)
+                        1 UDFToDouble(key) (type: double)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -107,33 +114,32 @@ STAGE PLANS:
                   Filter Operator
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: UDFToDouble(key) (type: double)
-                      sort order: +
-                      Map-reduce partition columns: UDFToDouble(key) (type: double)
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: key (type: int), val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {VALUE._col0} {VALUE._col1}
-                  1 {VALUE._col0} {VALUE._col1}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 UDFToDouble(key) (type: double)
+                        1 UDFToDouble(key) (type: double)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 1
+                      Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 3 Data size: 13 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out Tue Nov 25 13:03:18 2014
@@ -51,116 +51,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out Tue Nov 25 13:03:18 2014
@@ -57,112 +57,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -196,112 +210,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Left Outer Join0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Left Outer Join0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -339,96 +367,112 @@ EXPLAIN
 SELECT a.key, count(1) FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
-        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
-        Reducer 4 <- Union 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 5 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 6 (NONE, 0)
+        Reducer 3 <- Union 2 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string)
+                        outputColumnNames: _col0
+                        Select Operator
+                          SELECT * : (no compute)
+                          Group By Operator
+                            aggregations: count(1)
+                            keys: _col0 (type: string)
+                            mode: hash
+                            outputColumnNames: _col0, _col1
+                            Reduce Output Operator
+                              key expressions: _col0 (type: string)
+                              sort order: +
+                              Map-reduce partition columns: _col0 (type: string)
+                              value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
         Map 6 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 8 
-            Map Operator Tree:
-                TableScan
                   alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Select Operator
-                    SELECT * : (no compute)
-                    Group By Operator
-                      aggregations: count(1)
-                      keys: _col0 (type: string)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        value expressions: _col1 (type: bigint)
-        Reducer 4 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        1 Map 5
+                      Select Operator
+                        expressions: _col0 (type: string)
+                        outputColumnNames: _col0
+                        Select Operator
+                          SELECT * : (no compute)
+                          Group By Operator
+                            aggregations: count(1)
+                            keys: _col0 (type: string)
+                            mode: hash
+                            outputColumnNames: _col0, _col1
+                            Reduce Output Operator
+                              key expressions: _col0 (type: string)
+                              sort order: +
+                              Map-reduce partition columns: _col0 (type: string)
+                              value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -447,32 +491,30 @@ STAGE PLANS:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 7 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Select Operator
-                    SELECT * : (no compute)
-                    Group By Operator
-                      aggregations: count(1)
-                      keys: _col0 (type: string)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        value expressions: _col1 (type: bigint)
-        Union 3 
-            Vertex: Union 3
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  Filter Operator
+                    predicate: ((key is not null and val is not null) and ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -499,96 +541,112 @@ POSTHOOK: query: EXPLAIN
 SELECT a.key, count(1) FROM T1 a LEFT OUTER JOIN T2 b ON a.key = b.key and a.val = b.val group by a.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
-        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
-        Reducer 4 <- Union 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 5 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 6 (NONE, 0)
+        Reducer 3 <- Union 2 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (not ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Left Outer Join0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string)
+                        outputColumnNames: _col0
+                        Select Operator
+                          SELECT * : (no compute)
+                          Group By Operator
+                            aggregations: count(1)
+                            keys: _col0 (type: string)
+                            mode: hash
+                            outputColumnNames: _col0, _col1
+                            Reduce Output Operator
+                              key expressions: _col0 (type: string)
+                              sort order: +
+                              Map-reduce partition columns: _col0 (type: string)
+                              value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
         Map 6 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Map 8 
-            Map Operator Tree:
-                TableScan
                   alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string), val (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: key (type: string), val (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Select Operator
-                    SELECT * : (no compute)
-                    Group By Operator
-                      aggregations: count(1)
-                      keys: _col0 (type: string)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        value expressions: _col1 (type: bigint)
-        Reducer 4 
+                    Map Join Operator
+                      condition map:
+                           Left Outer Join0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        1 Map 5
+                      Select Operator
+                        expressions: _col0 (type: string)
+                        outputColumnNames: _col0
+                        Select Operator
+                          SELECT * : (no compute)
+                          Group By Operator
+                            aggregations: count(1)
+                            keys: _col0 (type: string)
+                            mode: hash
+                            outputColumnNames: _col0, _col1
+                            Reduce Output Operator
+                              key expressions: _col0 (type: string)
+                              sort order: +
+                              Map-reduce partition columns: _col0 (type: string)
+                              value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -607,32 +665,30 @@ STAGE PLANS:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 7 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Select Operator
-                    SELECT * : (no compute)
-                    Group By Operator
-                      aggregations: count(1)
-                      keys: _col0 (type: string)
-                      mode: hash
-                      outputColumnNames: _col0, _col1
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        value expressions: _col1 (type: bigint)
-        Union 3 
-            Vertex: Union 3
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 5 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  Filter Operator
+                    predicate: ((((key = '2') or (key = '7')) or (key = '3')) or (key = '8')) (type: boolean)
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string), val (type: string)
+                        1 key (type: string), val (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out Tue Nov 25 13:03:18 2014
@@ -51,116 +51,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out Tue Nov 25 13:03:18 2014
@@ -51,116 +51,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message