hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1641614 [35/43] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/java/org/apache/hadoop/hive/ql/parse/spark/ ql/sr...
Date Tue, 25 Nov 2014 13:03:23 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt4.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt4.q.out Tue Nov 25 13:03:18 2014
@@ -47,116 +47,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -191,116 +201,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T2 a JOIN T1 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt5.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt5.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt5.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt5.q.out Tue Nov 25 13:03:18 2014
@@ -49,116 +49,126 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
-        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not ((key = '2') or (key = '3')))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 3
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 7 
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {val}
+                        1 {key} {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col5, _col6
+                      input vertices:
+                        1 Map 4
+                      Select Operator
+                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 2 
+            Vertex: Union 2
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and ((key = '2') or (key = '3'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {val}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator

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

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=1641614&r1=1641613&r2=1641614&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 Nov 25 13:03:18 2014
@@ -67,16 +67,14 @@ 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-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), 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 1 
@@ -87,128 +85,158 @@ 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
-                    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)
+                    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
         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 (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 5 
+                    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
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 3 <- Map 2 (NONE, 0), Map 7 (NONE, 0)
+#### 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
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (not (((key = '2') or (key = '8')) or (key = '3')))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 6 
+                    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 4
+                        2 Map 1
+                      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
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and (((key = '2') or (key = '8')) or (key = '3'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      value expressions: val (type: string)
-        Map 8 
+                    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
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 3 
+            Vertex: Union 3
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 5 
             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
-                    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 
+                    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 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  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)
                     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
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 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
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {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-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=1641614&r1=1641613&r2=1641614&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 Nov 25 13:03:18 2014
@@ -65,16 +65,14 @@ 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-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3, Stage-4
+  Stage-4 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1), 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 1 
@@ -85,128 +83,158 @@ 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
-                    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)
+                    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
         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 (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)
-        Map 5 
+                    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
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Union 3 <- Map 2 (NONE, 0), Map 7 (NONE, 0)
+#### 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
+                  alias: a
                   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)
-        Map 6 
+                    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 4
+                        2 Map 1
+                      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
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: a
                   Filter Operator
                     predicate: (key is not null and ((key = '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)
-        Map 8 
+                    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
+                        Select Operator
+                          SELECT * : (no compute)
+                          File Output Operator
+                            compressed: false
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+        Union 3 
+            Vertex: Union 3
+
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 5 
             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
-                    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 
+                    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 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  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)
                     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
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 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
-                  Select Operator
-                    SELECT * : (no compute)
-                    File Output Operator
-                      compressed: false
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {val}
+                        1 {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-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=1641614&r1=1641613&r2=1641614&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 Nov 25 13:03:18 2014
@@ -195,15 +195,37 @@ select key, count(1) as cnt from T1 grou
 join T2 b on subq1.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
+  Stage: Stage-3
+    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, 1)
-        Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -230,21 +252,9 @@ 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)
@@ -256,33 +266,30 @@ STAGE PLANS:
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
                   Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
+                  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)
+                    outputColumnNames: _col0, _col1, _col2, _col3
+                    input vertices:
+                      1 Map 3
                     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
-                  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
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: bigint), _col2 (type: string), _col3 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3
+                      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
 
   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=1641614&r1=1641613&r2=1641614&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 Nov 25 13:03:18 2014
@@ -113,47 +113,11 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
+        Map 2 <- Map 1 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
-        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
+        Map 2 
 
   Stage: Stage-0
     Fetch Operator
@@ -274,47 +238,11 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
+        Map 2 <- Map 1 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
-        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
+        Map 2 
 
   Stage: Stage-0
     Fetch Operator
@@ -373,17 +301,16 @@ 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-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
-  Stage-4 depends on stages: Stage-2, Stage-0
-  Stage-3 depends on stages: Stage-4
+  Stage-5 depends on stages: Stage-2, Stage-0
+  Stage-3 depends on stages: Stage-5
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -394,13 +321,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 3 
+                    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 2 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -408,38 +343,38 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        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
+                    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 1
+                      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
 
   Stage: Stage-2
     Dependency Collection
 
-  Stage: Stage-4
+  Stage: Stage-5
       Create Table Operator:
         Create Table
           columns: k1 int, value string, ds string, k2 int



Mime
View raw message