hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [24/31] - 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/skewjoinopt6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt6.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt6.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt6.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') or (key = '8')) 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 {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') or (key = '8')) 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)
-                        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') or (key = '8')) 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)
-                        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') or (key = '8')) 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 {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

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt7.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt7.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt7.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt7.q.out Tue Dec  2 19:57:10 2014
@@ -67,135 +67,61 @@ EXPLAIN
 SELECT a.*, b.*, c.* FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c on a.key = c.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), Map 5 (PARTITION-LEVEL SORT, 1)
+        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1), Map 9 (PARTITION-LEVEL SORT, 1)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (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') or (key = '8')) 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 {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 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)
         Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+                  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
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 2 <- Map 1 (NONE, 0), Map 7 (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 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: c
+                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 3
-                        2 Map 4
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        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 7 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Filter Operator
-                    predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 5
-                        2 Map 6
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        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 5 
+                    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 6 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -203,18 +129,13 @@ STAGE PLANS:
                   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
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 6 
+                    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 8 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -222,17 +143,68 @@ STAGE PLANS:
                   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
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 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)
+        Map 9 
+            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 (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)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  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 7 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  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/skewjoinopt8.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt8.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt8.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt8.q.out Tue Dec  2 19:57:10 2014
@@ -65,135 +65,61 @@ EXPLAIN
 SELECT a.*, b.*, c.* FROM T1 a JOIN T2 b ON a.key = b.key JOIN T3 c on a.key = c.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), Map 5 (PARTITION-LEVEL SORT, 1)
+        Reducer 7 <- Map 6 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1), Map 9 (PARTITION-LEVEL SORT, 1)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 7 (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 = '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} {val}
-                        1 {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 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)
         Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((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} {val}
-                        1 {key} {val}
-                        2 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 2 <- Map 1 (NONE, 0), Map 7 (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 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: c
+                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = '3') or (key = '8'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 3
-                        2 Map 4
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        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 7 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Filter Operator
-                    predicate: (key is not null and (not ((key = '3') or (key = '8')))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      input vertices:
-                        1 Map 5
-                        2 Map 6
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        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 5 
+                    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 6 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -201,18 +127,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (not ((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} {val}
-                        1 {val}
-                        2 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 6 
+                    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 8 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -220,17 +141,68 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (not ((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} {val}
-                        1 {key} {val}
-                        2 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 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)
+        Map 9 
+            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 (not ((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)
+                      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
+                     Inner Join 0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  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 7 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                  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/skewjoinopt9.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt9.q.out Tue Dec  2 19:57:10 2014
@@ -195,37 +195,15 @@ select key, count(1) as cnt from T1 grou
 join T2 b on subq1.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 3 
-            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 (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {_col0} {_col1}
-                        1 {val}
-                      keys:
-                        0 _col0 (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP, 3)
+        Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -248,9 +226,21 @@ STAGE PLANS:
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
                         value expressions: _col1 (type: bigint)
+        Map 4 
+            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 (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 
-            Local Work:
-              Map Reduce Local Work
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -258,30 +248,33 @@ STAGE PLANS:
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
                 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 {_col0} {_col1}
-                    1 {key} {val}
-                  keys:
-                    0 _col0 (type: string)
-                    1 key (type: string)
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  value expressions: _col1 (type: bigint)
+        Reducer 3 
+            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, _col2, _col3
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string)
                   outputColumnNames: _col0, _col1, _col2, _col3
-                  input vertices:
-                    1 Map 3
                   Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Select Operator
-                    expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string)
-                    outputColumnNames: _col0, _col1, _col2, _col3
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE 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
+                    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/smb_mapjoin9.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin9.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin9.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin9.q.out Tue Dec  2 19:57:10 2014
@@ -106,26 +106,54 @@ TOK_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 
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
-            Local Work:
-              Map Reduce Local Work
+        Map 3 
+        Reducer 2 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col6, _col7
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Select Operator
+                  expressions: _col6 (type: int), _col7 (type: string), '2010-10-15' (type: string), _col0 (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          columns _col0,_col1,_col2,_col3
+                          columns.types int:string:string:int
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator
@@ -239,26 +267,54 @@ TOK_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 
-            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 
-            Local Work:
-              Map Reduce Local Work
+        Map 3 
+        Reducer 2 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col6, _col7
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Select Operator
+                  expressions: _col6 (type: int), _col7 (type: string), '2010-10-15' (type: string), _col0 (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          columns _col0,_col1,_col2,_col3
+                          columns.types int:string:string:int
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator
@@ -317,74 +373,67 @@ hive_test_smb_bucket2 b
 ON a.key = b.key WHERE a.ds = '2010-10-15' and b.ds='2010-10-15' and  b.key IS NOT NULL
 POSTHOOK: type: CREATETABLE_AS_SELECT
 STAGE DEPENDENCIES:
-  Stage-3 is a root stage
-  Stage-1 depends on stages: Stage-3
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
-  Stage-4 depends on stages: Stage-0
-  Stage-2 depends on stages: Stage-4
+  Stage-3 depends on stages: Stage-0
+  Stage-2 depends on stages: Stage-3
 
 STAGE PLANS:
-  Stage: Stage-3
+  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 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col6, _col7
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col6 (type: int), _col7 (type: string), '2010-10-15' (type: string), _col0 (type: int)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 275 Data size: 2921 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
-                              name: default.smb_mapjoin9_results
-            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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col6, _col7
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col6 (type: int), _col7 (type: string), '2010-10-15' (type: string), _col0 (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 275 Data size: 2921 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
+                        name: default.smb_mapjoin9_results
 
   Stage: Stage-0
     Move Operator
@@ -392,7 +441,7 @@ STAGE PLANS:
           hdfs directory: true
 #### A masked pattern was here ####
 
-  Stage: Stage-4
+  Stage: Stage-3
       Create Table Operator:
         Create Table
           columns: k1 int, value string, ds string, k2 int

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_1.q.out Tue Dec  2 19:57:10 2014
@@ -57,13 +57,14 @@ explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_2 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
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -74,21 +75,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### 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: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -96,32 +89,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 114 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: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (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
+                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 114 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
@@ -146,32 +140,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_2 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            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 
@@ -179,32 +155,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 206 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: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 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
+                    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
@@ -234,13 +222,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_2 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
+  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 
@@ -248,51 +237,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (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
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 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
+                    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
@@ -407,13 +389,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_2 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
+  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 
@@ -424,21 +407,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### 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: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -446,32 +421,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 114 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: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (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
+                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 114 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
@@ -496,32 +472,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            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 
@@ -529,32 +487,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 206 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: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 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
+                    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
@@ -584,13 +554,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 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
+  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 
@@ -598,51 +569,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (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
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 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
+                    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



Mime
View raw message