hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [22/31] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/test/results/clientpositive/spark/
Date Tue, 02 Dec 2014 19:57:14 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt15.q.out Tue Dec  2 19:57:10 2014
@@ -87,122 +87,112 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 3), Map 7 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
                     Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            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 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 3
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        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
+                    Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val (type: string)
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 4
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        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-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
                     Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE 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: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  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: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  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
 
   Stage: Stage-0
     Fetch Operator
@@ -239,14 +229,16 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 3), Map 7 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -257,88 +249,41 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key = 2) or (key = 3)) (type: boolean)
                     Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 3 <- Map 2 (NONE, 0), Map 4 (NONE, 0)
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key = 2) or (key = 3)) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        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 4 
+                    Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (not ((key = 2) or (key = 3))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 5
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        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 3 
-            Vertex: Union 3
-
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 5 
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 7 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -346,15 +291,50 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (not ((key = 2) or (key = 3))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      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:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  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:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  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
 
   Stage: Stage-0
     Fetch Operator
@@ -393,94 +373,87 @@ EXPLAIN
 SELECT count(1) FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3)
+        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 3), Map 8 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
+        Reducer 4 <- Union 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 4 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
                     Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            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 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = 2) or (key = 3))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      input vertices:
-                        1 Map 4
-                      Group By Operator
-                        aggregations: count(1)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Reduce Output Operator
-                          sort order: 
-                          value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
+                    Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
         Map 6 
             Map Operator Tree:
                 TableScan
+                  alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
+                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+        Map 8 
+            Map Operator Tree:
+                TableScan
                   alias: a
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      input vertices:
-                        1 Map 5
-                      Group By Operator
-                        aggregations: count(1)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Reduce Output Operator
-                          sort order: 
-                          value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
-        Reducer 3 
+                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Group By Operator
+                  aggregations: count(1)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Reduce Output Operator
+                    sort order: 
+                    value expressions: _col0 (type: bigint)
+        Reducer 4 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -498,30 +471,23 @@ 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
-        Union 2 
-            Vertex: Union 2
-
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 5 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: (key is not null and (not ((key = 2) or (key = 3)))) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
+        Reducer 7 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Group By Operator
+                  aggregations: count(1)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Reduce Output Operator
+                    sort order: 
+                    value expressions: _col0 (type: bigint)
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-0
     Fetch Operator
@@ -547,14 +513,17 @@ POSTHOOK: query: EXPLAIN
 SELECT count(1) FROM T1 a RIGHT OUTER JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 5 (PARTITION-LEVEL SORT, 3)
+        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 3), Map 8 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (NONE, 0)
+        Reducer 4 <- Union 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -565,75 +534,65 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key = 2) or (key = 3)) (type: boolean)
                     Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 3 <- Map 2 (NONE, 0), Map 5 (NONE, 0)
-        Reducer 4 <- Union 3 (GROUP, 1)
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key = 2) or (key = 3)) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      input vertices:
-                        0 Map 1
-                      Group By Operator
-                        aggregations: count(1)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Reduce Output Operator
-                          sort order: 
-                          value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
-        Map 5 
+                    Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+        Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (not ((key = 2) or (key = 3))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      input vertices:
-                        0 Map 6
-                      Group By Operator
-                        aggregations: count(1)
-                        mode: hash
-                        outputColumnNames: _col0
-                        Reduce Output Operator
-                          sort order: 
-                          value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Map 8 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (not ((key = 2) 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: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Group By Operator
+                  aggregations: count(1)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Reduce Output Operator
+                    sort order: 
+                    value expressions: _col0 (type: bigint)
         Reducer 4 
             Reduce Operator Tree:
               Group By Operator
@@ -652,31 +611,24 @@ 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:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Group By Operator
+                  aggregations: count(1)
+                  mode: hash
+                  outputColumnNames: _col0
+                  Reduce Output Operator
+                    sort order: 
+                    value expressions: _col0 (type: bigint)
         Union 3 
             Vertex: Union 3
 
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 6 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: (not ((key = 2) or (key = 3))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-0
     Fetch Operator
       limit: -1

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt16.q.out Tue Dec  2 19:57:10 2014
@@ -49,122 +49,108 @@ 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-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     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 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  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') and (val = '12')) or (key = '3'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    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 
+                    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 
             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') and (val = '12')) or (key = '3'))) (type: boolean)
-                    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
-                        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
+                    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 
             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') and (val = '12')) or (key = '3')))) (type: boolean)
-                    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
-                        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-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    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 Operator Tree:
                 TableScan
-                  alias: b
+                  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 (not (((key = '2') and (val = '12')) or (key = '3')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    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
+                    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
+                  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
+                  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
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out Tue Dec  2 19:57:10 2014
@@ -53,122 +53,112 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     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 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   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
-                    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 
+                    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 
             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)
-                    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
-                        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
+                    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 5 
             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)
-                    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
-                        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-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    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 Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   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
-                    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
+                    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
+                  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
+                  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
 
   Stage: Stage-0
     Fetch Operator
@@ -261,122 +251,108 @@ 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-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 3), Map 7 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  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') and (val = '12')) or (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    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 
+                    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 
             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') and (val = '12')) or (key = '2'))) (type: boolean)
-                    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
-                        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
+                    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 
             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') and (val = '12')) or (key = '2')))) (type: boolean)
-                    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
-                        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-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    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 Operator Tree:
                 TableScan
-                  alias: b
+                  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 (not (((key = '2') and (val = '12')) or (key = '2')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    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
+                    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
+                  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
+                  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
 
   Stage: Stage-0
     Fetch Operator

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=1642997&r1=1642996&r2=1642997&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 Dec  2 19:57:10 2014
@@ -75,35 +75,14 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    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
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -114,32 +93,47 @@ 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
-                    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 2
-                      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
+                    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)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  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)
+        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
 
   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=1642997&r1=1642996&r2=1642997&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 Dec  2 19:57:10 2014
@@ -51,122 +51,112 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     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 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   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
-                    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 
+                    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 
             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)
-                    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
-                        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
+                    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 5 
             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)
-                    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
-                        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-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    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 Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   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
-                    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
+                    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
+                  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
+                  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
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message