hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [26/42] - 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 Mon, 15 Dec 2014 17:11:42 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_join_filter.q.out Tue Dec  2 19:57:10 2014
@@ -120,15 +120,15 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  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 
@@ -204,39 +204,7 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [src]
-        Reducer 2 
-            Local Work:
-              Map Reduce Local Work
-            Needs Tagging: false
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: min(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
-                  outputColumnNames: _col0, _col2, _col3, _col4
-                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean)
-                    Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      Position of Big Table: 0
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -246,47 +214,13 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      outputColumnNames: _col0, _col8, _col9
-                      input vertices:
-                        1 Reducer 2
-                      Position of Big Table: 0
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
-                        outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          GlobalTableId: 0
-#### A masked pattern was here ####
-                          NumFilesPerFileSink: 1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
-                                columns.types string:double:double
-                                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
-            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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      tag: 0
+                      auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -336,6 +270,67 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [a]
+        Reducer 2 
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
+                  outputColumnNames: _col0, _col2, _col3, _col4
+                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean)
+                    Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
+                      Statistics: Num rows: 21 Data size: 223 Basic stats: COMPLETE Column stats: NONE
+                      tag: 1
+                      value expressions: _col3 (type: double), _col4 (type: double)
+                      auto parallelism: false
+        Reducer 3 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {VALUE._col2} {VALUE._col3}
+                outputColumnNames: _col0, _col8, _col9
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
+                          columns.types string:double:double
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator
@@ -499,15 +494,15 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP, 3)
+        Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -583,39 +578,7 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [src]
-        Reducer 2 
-            Local Work:
-              Map Reduce Local Work
-            Needs Tagging: false
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: min(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
-                  outputColumnNames: _col0, _col2, _col3, _col4
-                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: (_col2 < 5.0) (type: boolean)
-                    Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      Position of Big Table: 0
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -625,47 +588,13 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      outputColumnNames: _col0, _col8, _col9
-                      input vertices:
-                        1 Reducer 2
-                      Position of Big Table: 0
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
-                        outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          GlobalTableId: 0
-#### A masked pattern was here ####
-                          NumFilesPerFileSink: 1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
-                                columns.types string:double:double
-                                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
-            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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      tag: 0
+                      auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -715,6 +644,67 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [a]
+        Reducer 2 
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
+                  outputColumnNames: _col0, _col2, _col3, _col4
+                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: (_col2 < 5.0) (type: boolean)
+                    Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
+                      Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+                      tag: 1
+                      value expressions: _col3 (type: double), _col4 (type: double)
+                      auto parallelism: false
+        Reducer 3 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {VALUE._col2} {VALUE._col3}
+                outputColumnNames: _col0, _col8, _col9
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
+                          columns.types string:double:double
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator
@@ -878,15 +868,15 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP, 3)
+        Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -962,39 +952,7 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [src]
-        Reducer 2 
-            Local Work:
-              Map Reduce Local Work
-            Needs Tagging: false
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: min(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
-                  outputColumnNames: _col0, _col2, _col3, _col4
-                  Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean)
-                    Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      Position of Big Table: 0
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -1004,47 +962,13 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      outputColumnNames: _col0, _col8, _col9
-                      input vertices:
-                        1 Reducer 2
-                      Position of Big Table: 0
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
-                        outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          GlobalTableId: 0
-#### A masked pattern was here ####
-                          NumFilesPerFileSink: 1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
-                                columns.types string:double:double
-                                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
-            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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      tag: 0
+                      auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -1094,6 +1018,67 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [a]
+        Reducer 2 
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
+                  outputColumnNames: _col0, _col2, _col3, _col4
+                  Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: ((_col2 < 5.0) and _col0 is not null) (type: boolean)
+                    Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
+                      Statistics: Num rows: 42 Data size: 446 Basic stats: COMPLETE Column stats: NONE
+                      tag: 1
+                      value expressions: _col3 (type: double), _col4 (type: double)
+                      auto parallelism: false
+        Reducer 3 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {VALUE._col2} {VALUE._col3}
+                outputColumnNames: _col0, _col8, _col9
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
+                          columns.types string:double:double
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator
@@ -1257,15 +1242,15 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
       Edges:
         Reducer 2 <- Map 1 (GROUP, 3)
+        Reducer 3 <- Map 4 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -1341,39 +1326,7 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [src]
-        Reducer 2 
-            Local Work:
-              Map Reduce Local Work
-            Needs Tagging: false
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: min(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
-                  outputColumnNames: _col0, _col2, _col3, _col4
-                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    isSamplingPred: false
-                    predicate: (_col2 < 5.0) (type: boolean)
-                    Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      Position of Big Table: 0
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -1383,47 +1336,13 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {_col3} {_col4}
-                      keys:
-                        0 key (type: string)
-                        1 _col0 (type: string)
-                      outputColumnNames: _col0, _col8, _col9
-                      input vertices:
-                        1 Reducer 2
-                      Position of Big Table: 0
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
-                        outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          GlobalTableId: 0
-#### A masked pattern was here ####
-                          NumFilesPerFileSink: 1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
-                                columns.types string:double:double
-                                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
-            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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      tag: 0
+                      auto parallelism: false
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -1473,6 +1392,67 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [a]
+        Reducer 2 
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: min(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), (_col1 + 1) (type: double), (_col1 + 2) (type: double), (_col1 + 3) (type: double)
+                  outputColumnNames: _col0, _col2, _col3, _col4
+                  Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    isSamplingPred: false
+                    predicate: (_col2 < 5.0) (type: boolean)
+                    Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string)
+                      sort order: +
+                      Map-reduce partition columns: _col0 (type: string)
+                      Statistics: Num rows: 41 Data size: 435 Basic stats: COMPLETE Column stats: NONE
+                      tag: 1
+                      value expressions: _col3 (type: double), _col4 (type: double)
+                      auto parallelism: false
+        Reducer 3 
+            Needs Tagging: true
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {VALUE._col2} {VALUE._col3}
+                outputColumnNames: _col0, _col8, _col9
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col8 (type: double), _col9 (type: double)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 0
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE 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
+                          columns.types string:double:double
+                          escape.delim \
+                          hive.serialization.extend.nesting.levels true
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    TotalFiles: 1
+                    GatherStats: false
+                    MultiFileSpray: false
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join1.q.out Tue Dec  2 19:57:10 2014
@@ -21,74 +21,68 @@ EXPLAIN
  WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key > 10) and (key < 20)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key > 10) and (key < 20)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Left Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: ((((_col0 > 10) and (_col0 < 20)) and (_col5 > 15)) and (_col5 < 25)) (type: boolean)
-                        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)
-                          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
-            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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: ((((_col0 > 10) and (_col0 < 20)) and (_col5 > 15)) and (_col5 < 25)) (type: boolean)
+                  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)
+                    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
@@ -141,74 +135,68 @@ POSTHOOK: query: EXPLAIN
  WHERE a.key > 10 AND a.key < 20 AND b.key > 15 AND b.key < 25
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key > 10) and (key < 20)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: ((key > 10) and (key < 20)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Left Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: ((_col5 > 15) and (_col5 < 25)) (type: boolean)
-                        Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3
-                          Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: ((_col5 > 15) and (_col5 < 25)) (type: boolean)
+                  Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                    outputColumnNames: _col0, _col1, _col2, _col3
+                    Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join2.q.out Tue Dec  2 19:57:10 2014
@@ -21,13 +21,14 @@ EXPLAIN
  WHERE a.key > '10' AND a.key < '20' AND b.key > '15' AND b.key < '25'
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -38,21 +39,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key > '15') and (key < '25')) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -60,35 +53,36 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key > '15') and (key < '25')) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: ((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) (type: boolean)
-                        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)
-                          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
-            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: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: ((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) (type: boolean)
+                  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)
+                    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
@@ -261,13 +255,14 @@ POSTHOOK: query: EXPLAIN
  WHERE a.key > '10' AND a.key < '20' AND b.key > '15' AND b.key < '25'
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -278,21 +273,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key > '15') and (key < '25')) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -300,35 +287,36 @@ STAGE PLANS:
                   Filter Operator
                     predicate: ((key > '15') and (key < '25')) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Right Outer Join0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean)
-                        Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3
-                          Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: ((_col0 > '10') and (_col0 < '20')) (type: boolean)
+                  Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                    outputColumnNames: _col0, _col1, _col2, _col3
+                    Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 6 Data size: 64 Basic stats: COMPLETE Column stats: NONE
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/ppd_outer_join4.q.out Tue Dec  2 19:57:10 2014
@@ -27,13 +27,14 @@ EXPLAIN
  WHERE a.key > '10' AND a.key < '20' AND b.key > '15' AND b.key < '25' AND sqrt(c.key) <> 13
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -44,18 +45,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -63,23 +59,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -87,39 +73,37 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Left Outer Join0 to 1
-                           Right Outer Join0 to 2
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10
-                      input vertices:
-                        0 Map 1
-                        1 Map 2
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: (((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) and (sqrt(_col10) <> 13)) (type: boolean)
-                        Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3, _col4
-                          Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Right Outer Join0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10
+                Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: (((((_col0 > '10') and (_col0 < '20')) and (_col5 > '15')) and (_col5 < '25')) and (sqrt(_col10) <> 13)) (type: boolean)
+                  Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string)
+                    outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                    Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -408,13 +392,14 @@ POSTHOOK: query: EXPLAIN
  WHERE a.key > '10' AND a.key < '20' AND b.key > '15' AND b.key < '25' AND sqrt(c.key) <> 13
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3), Map 4 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -425,18 +410,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -444,23 +424,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -468,39 +438,37 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (sqrt(key) <> 13) (type: boolean)
                     Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Left Outer Join0 to 1
-                           Right Outer Join0 to 2
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                        2 {key}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10
-                      input vertices:
-                        0 Map 1
-                        1 Map 2
-                      Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
-                      Filter Operator
-                        predicate: ((((_col5 > '15') and (_col5 < '25')) and (_col0 > '10')) and (_col0 < '20')) (type: boolean)
-                        Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3, _col4
-                          Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Right Outer Join0 to 2
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10
+                Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: ((((_col5 > '15') and (_col5 < '25')) and (_col0 > '10')) and (_col0 < '20')) (type: boolean)
+                  Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string)
+                    outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                    Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 13 Data size: 138 Basic stats: COMPLETE Column stats: NONE
+                      table:
+                          input format: org.apache.hadoop.mapred.TextInputFormat
+                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message