hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [21/31] - 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/skewjoinopt10.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt10.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt10.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt10.q.out Tue Dec  2 19:57:10 2014
@@ -49,14 +49,16 @@ explain 
 select * from (select a.key as key, b.value as array_val from T1 a join array_valued_T1 b on a.key=b.key) i lateral view explode (array_val) c as val
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 3), Map 7 (PARTITION-LEVEL SORT, 3)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -67,140 +69,40 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (key = '8')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 3 <- Map 2 (NONE, 0), Map 4 (NONE, 0)
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (key = '8')) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col6
-                      input vertices:
-                        0 Map 1
-                      Select Operator
-                        expressions: _col0 (type: string), _col6 (type: array<string>)
-                        outputColumnNames: _col0, _col1
-                        Lateral View Forward
-                          Select Operator
-                            SELECT * : (no compute)
-                            expressions: _col0 (type: string), _col1 (type: array<string>)
-                            outputColumnNames: org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc, org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc
-                            Lateral View Join Operator
-                              outputColumnNames: _col0, _col1, _col2
-                              Select Operator
-                                expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
-                                outputColumnNames: _col0, _col1, _col2
-                                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
-                          Select Operator
-                            expressions: _col1 (type: array<string>)
-                            outputColumnNames: _col0
-                            UDTF Operator
-                              function name: explode
-                              Lateral View Join Operator
-                                outputColumnNames: _col0, _col1, _col2
-                                Select Operator
-                                  expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
-                                  outputColumnNames: _col0, _col1, _col2
-                                  File Output Operator
-                                    compressed: false
-                                    table:
-                                        input format: org.apache.hadoop.mapred.TextInputFormat
-                                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
-        Map 4 
+                    Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: array<string>)
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: b
+                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '8'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col6
-                      input vertices:
-                        0 Map 5
-                      Select Operator
-                        expressions: _col0 (type: string), _col6 (type: array<string>)
-                        outputColumnNames: _col0, _col1
-                        Lateral View Forward
-                          Select Operator
-                            SELECT * : (no compute)
-                            expressions: _col0 (type: string), _col1 (type: array<string>)
-                            outputColumnNames: org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc, org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc
-                            Lateral View Join Operator
-                              outputColumnNames: _col0, _col1, _col2
-                              Select Operator
-                                expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
-                                outputColumnNames: _col0, _col1, _col2
-                                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
-                          Select Operator
-                            expressions: _col1 (type: array<string>)
-                            outputColumnNames: _col0
-                            UDTF Operator
-                              function name: explode
-                              Lateral View Join Operator
-                                outputColumnNames: _col0, _col1, _col2
-                                Select Operator
-                                  expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
-                                  outputColumnNames: _col0, _col1, _col2
-                                  File Output Operator
-                                    compressed: false
-                                    table:
-                                        input format: org.apache.hadoop.mapred.TextInputFormat
-                                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
-        Union 3 
-            Vertex: Union 3
-
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 5 
+                    Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 2 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: array<string>)
+        Map 7 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -208,15 +110,101 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (not (key = '8'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 {value}
-                      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
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col6 (type: array<string>)
+                  outputColumnNames: _col0, _col1
+                  Lateral View Forward
+                    Select Operator
+                      SELECT * : (no compute)
+                      expressions: _col0 (type: string), _col1 (type: array<string>)
+                      outputColumnNames: org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc, org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc
+                      Lateral View Join Operator
+                        outputColumnNames: _col0, _col1, _col2
+                        Select Operator
+                          expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
+                          outputColumnNames: _col0, _col1, _col2
+                          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
+                    Select Operator
+                      expressions: _col1 (type: array<string>)
+                      outputColumnNames: _col0
+                      UDTF Operator
+                        function name: explode
+                        Lateral View Join Operator
+                          outputColumnNames: _col0, _col1, _col2
+                          Select Operator
+                            expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
+                            outputColumnNames: _col0, _col1, _col2
+                            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}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col6 (type: array<string>)
+                  outputColumnNames: _col0, _col1
+                  Lateral View Forward
+                    Select Operator
+                      SELECT * : (no compute)
+                      expressions: _col0 (type: string), _col1 (type: array<string>)
+                      outputColumnNames: org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc, org.apache.hadoop.hive.ql.plan.ExprNodeColumnDesc
+                      Lateral View Join Operator
+                        outputColumnNames: _col0, _col1, _col2
+                        Select Operator
+                          expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
+                          outputColumnNames: _col0, _col1, _col2
+                          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
+                    Select Operator
+                      expressions: _col1 (type: array<string>)
+                      outputColumnNames: _col0
+                      UDTF Operator
+                        function name: explode
+                        Lateral View Join Operator
+                          outputColumnNames: _col0, _col1, _col2
+                          Select Operator
+                            expressions: _col0 (type: string), _col1 (type: array<string>), _col2 (type: string)
+                            outputColumnNames: _col0, _col1, _col2
+                            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/skewjoinopt11.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt11.q.out Tue Dec  2 19:57:10 2014
@@ -59,178 +59,77 @@ select * from	
 ) subq1
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3, Stage-4, Stage-5
-  Stage-3 depends on stages: Stage-2
-  Stage-4 depends on stages: Stage-2, Stage-3
-  Stage-5 depends on stages: Stage-2, Stage-3, Stage-4
+  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 and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
-        Union 2 <- Map 1 (NONE, 0), Map 4 (NONE, 0), Map 7 (NONE, 0), Map 9 (NONE, 0)
+        Reducer 12 <- Map 11 (PARTITION-LEVEL SORT, 1), Map 13 (PARTITION-LEVEL SORT, 1)
+        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)
+        Reducer 9 <- Map 10 (PARTITION-LEVEL SORT, 1), Map 8 (PARTITION-LEVEL SORT, 1)
+        Union 3 <- Reducer 12 (NONE, 0), Reducer 2 (NONE, 0), Reducer 6 (NONE, 0), Reducer 9 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             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 (key = '2')) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col6
-                      input vertices:
-                        1 Map 3
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          File Output Operator
-                            compressed: false
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
-        Map 4 
+                    Statistics: Num rows: 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 10 
             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 (key = '2')) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col6
-                      input vertices:
-                        1 Map 5
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          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 
+                    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 11 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col6
-                      input vertices:
-                        1 Map 6
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          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 9 
+                    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 13 
             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'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col6
-                      input vertices:
-                        1 Map 8
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          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 4 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -238,42 +137,40 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-4
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        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 5 
+            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 (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 Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
-                    predicate: (key is not null and (not (key = '2'))) (type: boolean)
+                    predicate: (key is not null and (key = '2')) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-5
-    Spark
-#### A masked pattern was here ####
-      Vertices:
+                    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
@@ -282,15 +179,98 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (not (key = '2'))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
+        Reducer 12 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+                    outputColumnNames: _col0, _col1, _col2
+                    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 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+                    outputColumnNames: _col0, _col1, _col2
+                    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 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+                    outputColumnNames: _col0, _col1, _col2
+                    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 9 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
+                    outputColumnNames: _col0, _col1, _col2
+                    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/skewjoinopt12.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt12.q.out Tue Dec  2 19:57:10 2014
@@ -49,122 +49,108 @@ EXPLAIN
 SELECT a.*, b.* FROM T1 a JOIN T2 b ON a.key = b.key and a.val = b.val
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 6 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 
-                      keys:
-                        0 key (type: string), val (type: string)
-                        1 key (type: string), val (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Union 2 <- Map 1 (NONE, 0), Map 5 (NONE, 0)
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string), val (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), val (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13')))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: string), val (type: string)
-                        1 key (type: string), val (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 3
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        File Output Operator
-                          compressed: false
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: string), val (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), val (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
         Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: string), val (type: string)
-                        1 key (type: string), val (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 4
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        File Output Operator
-                          compressed: false
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
-        Union 2 
-            Vertex: Union 2
-
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 4 
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: string), val (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), val (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (not ((((key = '2') and (val = '12')) or ((key = '8') and (val = '18'))) or ((key = '3') and (val = '13'))))) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 
-                      keys:
-                        0 key (type: string), val (type: string)
-                        1 key (type: string), val (type: string)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string), val (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), val (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Reducer 6 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+                  1 {KEY.reducesinkkey0} {KEY.reducesinkkey1}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  File Output Operator
+                    compressed: false
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt13.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt13.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt13.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt13.q.out Tue Dec  2 19:57:10 2014
@@ -75,16 +75,32 @@ T1 a join T2 b on a.key = b.key 
 join T3 c on a.val = c.val
 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 4 (PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Reducer 2 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  Filter Operator
+                    predicate: (key is not null and val is not null) (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 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -92,16 +108,13 @@ STAGE PLANS:
                   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 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 3 
+                    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: c
@@ -109,67 +122,49 @@ STAGE PLANS:
                   Filter Operator
                     predicate: val 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} {_col5} {_col6}
-                        1 {key}
-                      keys:
-                        0 _col1 (type: string)
-                        1 val (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: (key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
+                    Reduce Output Operator
+                      key expressions: val (type: string)
+                      sort order: +
+                      Map-reduce partition columns: val (type: string)
                       Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        condition expressions:
-                          0 {_col0} {_col1} {_col5} {_col6}
-                          1 {key} {val}
-                        keys:
-                          0 _col1 (type: string)
-                          1 val (type: string)
-                        outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                        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: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                          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
-            Local Work:
-              Map Reduce Local Work
+                      value expressions: key (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: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+        Reducer 3 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4} {VALUE._col5}
+                  1 {VALUE._col0} {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                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
+                  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/skewjoinopt14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/skewjoinopt14.q.out Tue Dec  2 19:57:10 2014
@@ -79,69 +79,50 @@ T1 a join T2 b on a.key = b.key 
 join T3 c on a.val = c.val
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2, Stage-3
-  Stage-3 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        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 and (key = '2')) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 1), Union 2 (PARTITION-LEVEL SORT, 1)
-        Union 2 <- Map 1 (NONE, 0), Map 7 (NONE, 0)
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
+        Reducer 4 <- Map 6 (PARTITION-LEVEL SORT, 1), Union 3 (PARTITION-LEVEL SORT, 1)
+        Reducer 8 <- Map 7 (PARTITION-LEVEL SORT, 1), Map 9 (PARTITION-LEVEL SORT, 1)
+        Union 3 <- Reducer 2 (NONE, 0), Reducer 8 (NONE, 0)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: ((key is not null and val is not null) and (key = '2')) (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
-                      Reduce Output Operator
-                        key expressions: _col1 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col1 (type: string)
-                        value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
-            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: 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)
+        Map 6 
+            Map Operator Tree:
+                TableScan
                   alias: c
                   Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
@@ -156,29 +137,46 @@ STAGE PLANS:
         Map 7 
             Map Operator Tree:
                 TableScan
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  Filter Operator
+                    predicate: (key is not null and (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 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 val is not null) and (not (key = '2'))) (type: boolean)
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 6
-                      Reduce Output Operator
-                        key expressions: _col1 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col1 (type: string)
-                        value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Reducer 3 
+                    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
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+        Reducer 4 
             Reduce Operator Tree:
               Join Operator
                 condition map:
@@ -199,30 +197,22 @@ STAGE PLANS:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 2 
-            Vertex: Union 2
-
-  Stage: Stage-3
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 6 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: (key is not null and (not (key = '2'))) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
+        Reducer 8 
+            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
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message