You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/12/13 18:44:42 UTC

svn commit: r1645338 [7/9] - in /hive/branches/spark: data/conf/spark/ itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ ql/src/test/results/clientpositive/spark/

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join25.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join25.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join25.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join25.q.out Sat Dec 13 17:44:41 2014
@@ -21,15 +21,14 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.value,
 FROM src1 x JOIN src y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -40,13 +39,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {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 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -54,34 +61,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col6
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {value}
+                        1 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join26.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join26.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join26.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join26.q.out Sat Dec 13 17:44:41 2014
@@ -102,15 +102,14 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     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 
@@ -123,13 +122,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      tag: 0
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -179,7 +183,7 @@ STAGE PLANS:
                   name: default.src1
             Truncated Path -> Alias:
               /src1 [x]
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -189,14 +193,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 1
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -246,7 +254,12 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [y]
-        Map 4 
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: z
@@ -256,14 +269,56 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 2
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      outputColumnNames: _col0, _col6, _col11
+                      input vertices:
+                        0 Map 1
+                        1 Map 2
+                      Position of Big Table: 2
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          GlobalTableId: 1
+#### A masked pattern was here ####
+                          NumFilesPerFileSink: 1
+                          Statistics: Num rows: 550 Data size: 5843 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:
+                                bucket_count -1
+                                columns key,value,val2
+                                columns.comments 
+                                columns.types string:string:string
+#### A masked pattern was here ####
+                                name default.dest_j1
+                                serialization.ddl struct dest_j1 { string key, string value, string val2}
+                                serialization.format 1
+                                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+                          TotalFiles: 1
+                          GatherStats: true
+                          MultiFileSpray: false
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -315,49 +370,6 @@ STAGE PLANS:
                   name: default.srcpart
             Truncated Path -> Alias:
               /srcpart/ds=2008-04-08/hr=11 [z]
-        Reducer 2 
-            Needs Tagging: true
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 {VALUE._col0}
-                  2 {VALUE._col0}
-                outputColumnNames: _col0, _col6, _col11
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    GlobalTableId: 1
-#### A masked pattern was here ####
-                    NumFilesPerFileSink: 1
-                    Statistics: Num rows: 550 Data size: 5843 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:
-                          bucket_count -1
-                          columns key,value,val2
-                          columns.comments 
-                          columns.types string:string:string
-#### A masked pattern was here ####
-                          name default.dest_j1
-                          serialization.ddl struct dest_j1 { string key, string value, string val2}
-                          serialization.format 1
-                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
-                    TotalFiles: 1
-                    GatherStats: true
-                    MultiFileSpray: false
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join27.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join27.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join27.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join27.q.out Sat Dec 13 17:44:41 2014
@@ -21,15 +21,14 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.value,
 FROM src1 x JOIN src y ON (x.value = y.value)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -40,13 +39,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: value is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: value (type: string)
-                      sort order: +
-                      Map-reduce partition columns: value (type: string)
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: key (type: string)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                      keys:
+                        0 value (type: string)
+                        1 value (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -54,33 +61,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: value is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: value (type: string)
-                      sort order: +
-                      Map-reduce partition columns: value (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {VALUE._col0} {KEY.reducesinkkey0}
-                  1 {KEY.reducesinkkey0}
-                outputColumnNames: _col0, _col1, _col6
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {value}
+                        1 {value}
+                      keys:
+                        0 value (type: string)
+                        1 value (type: string)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out Sat Dec 13 17:44:41 2014
@@ -19,16 +19,14 @@ INSERT OVERWRITE TABLE dest_j1
 SELECT /*+ MAPJOIN(x) */ x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -39,12 +37,23 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 
+                        1 
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -52,33 +61,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Group By Operator
-                  aggregations: count(1)
-                  keys: _col0 (type: string)
-                  mode: hash
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: _col1 (type: bigint)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        aggregations: count(1)
+                        keys: _col0 (type: string)
+                        mode: hash
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
         Reducer 3 
             Reduce Operator Tree:
               Group By Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out Sat Dec 13 17:44:41 2014
@@ -61,15 +61,14 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.cnt, y
 FROM tmp1 x JOIN tmp2 y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -80,13 +79,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: cnt (type: int)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {cnt}
+                        1 {cnt}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -94,34 +101,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: cnt (type: int)
-        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
-                Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: int), _col6 (type: int)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {cnt}
+                        1 {cnt}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: int), _col6 (type: int)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out Sat Dec 13 17:44:41 2014
@@ -21,15 +21,14 @@ SELECT /*+ MAPJOIN(X) */ x.key, x.value,
 FROM src1 x JOIN src y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -40,13 +39,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {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 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -54,34 +61,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col6
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {value}
+                        1 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out Sat Dec 13 17:44:41 2014
@@ -58,14 +58,14 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 126 Basic stats: COMPLETE Column stats: NONE
+                  alias: a
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (col11 = 111) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (key = 111) (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       condition expressions:
                         0 {value}
@@ -79,17 +79,17 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP, 3)
+        Reducer 3 <- Map 2 (GROUP, 3)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 126 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (key = 111) (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (col11 = 111) (type: boolean)
+                    Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -101,7 +101,7 @@ STAGE PLANS:
                         1 '111' (type: string)
                       outputColumnNames: _col1, _col10
                       input vertices:
-                        1 Map 3
+                        0 Map 1
                       Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count(1)
@@ -117,7 +117,7 @@ STAGE PLANS:
                           value expressions: _col2 (type: bigint)
             Local Work:
               Map Reduce Local Work
-        Reducer 2 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out Sat Dec 13 17:44:41 2014
@@ -21,15 +21,14 @@ SELECT /*+ MAPJOIN(y) */ x.key, x.value,
 FROM src x left outer JOIN (select * from src where key <= 100) y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -44,45 +43,52 @@ STAGE PLANS:
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-        Map 3 
+                      Spark HashTable Sink Operator
+                        condition expressions:
+                          0 {key} {value}
+                          1 {_col1}
+                        keys:
+                          0 key (type: string)
+                          1 _col0 (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: x
                   Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 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: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                    condition expressions:
+                      0 {key} {value}
+                      1 {_col0} {_col1}
+                    keys:
+                      0 key (type: string)
+                      1 _col0 (type: string)
+                    outputColumnNames: _col0, _col1, _col5, _col6
+                    input vertices:
+                      1 Map 1
                     Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Move Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join40.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join40.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join40.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join40.q.out Sat Dec 13 17:44:41 2014
@@ -3093,14 +3093,13 @@ SELECT /*+ MAPJOIN(y) */ x.key, x.value,
 FROM src x left outer JOIN (select * from src where key <= 100) y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-2 is a root stage
+  Stage-1 depends on stages: Stage-2
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-2
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -3115,44 +3114,51 @@ STAGE PLANS:
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 166 Data size: 1763 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: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-        Map 3 
+                      Spark HashTable Sink Operator
+                        condition expressions:
+                          0 {key} {value}
+                          1 {_col1}
+                        keys:
+                          0 key (type: string)
+                          1 _col0 (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: x
                   Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 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: 550 Data size: 5843 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: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                    condition expressions:
+                      0 {key} {value}
+                      1 {_col0} {_col1}
+                    keys:
+                      0 key (type: string)
+                      1 _col0 (type: string)
+                    outputColumnNames: _col0, _col1, _col5, _col6
+                    input vertices:
+                      1 Map 1
                     Statistics: Num rows: 550 Data size: 5843 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
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 550 Data size: 5843 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
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out?rev=1645338&r1=1645337&r2=1645338&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_map_ppr.q.out Sat Dec 13 17:44:41 2014
@@ -104,15 +104,14 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     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 
@@ -125,13 +124,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      tag: 0
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -181,7 +185,7 @@ STAGE PLANS:
                   name: default.src1
             Truncated Path -> Alias:
               /src1 [x]
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -191,14 +195,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 1
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -248,7 +256,12 @@ STAGE PLANS:
                   name: default.src
             Truncated Path -> Alias:
               /src [y]
-        Map 4 
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: z
@@ -258,14 +271,56 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 2
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      outputColumnNames: _col0, _col6, _col11
+                      input vertices:
+                        0 Map 1
+                        1 Map 2
+                      Position of Big Table: 2
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          GlobalTableId: 1
+#### A masked pattern was here ####
+                          NumFilesPerFileSink: 1
+                          Statistics: Num rows: 550 Data size: 5843 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:
+                                bucket_count -1
+                                columns key,value,val2
+                                columns.comments 
+                                columns.types string:string:string
+#### A masked pattern was here ####
+                                name default.dest_j1
+                                serialization.ddl struct dest_j1 { string key, string value, string val2}
+                                serialization.format 1
+                                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+                          TotalFiles: 1
+                          GatherStats: true
+                          MultiFileSpray: false
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -317,49 +372,6 @@ STAGE PLANS:
                   name: default.srcpart
             Truncated Path -> Alias:
               /srcpart/ds=2008-04-08/hr=11 [z]
-        Reducer 2 
-            Needs Tagging: true
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 {VALUE._col0}
-                  2 {VALUE._col0}
-                outputColumnNames: _col0, _col6, _col11
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    GlobalTableId: 1
-#### A masked pattern was here ####
-                    NumFilesPerFileSink: 1
-                    Statistics: Num rows: 550 Data size: 5843 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:
-                          bucket_count -1
-                          columns key,value,val2
-                          columns.comments 
-                          columns.types string:string:string
-#### A masked pattern was here ####
-                          name default.dest_j1
-                          serialization.ddl struct dest_j1 { string key, string value, string val2}
-                          serialization.format 1
-                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
-                    TotalFiles: 1
-                    GatherStats: true
-                    MultiFileSpray: false
 
   Stage: Stage-0
     Move Operator
@@ -657,15 +669,14 @@ TOK_QUERY
 
 
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     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 
@@ -678,14 +689,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: UDFToDouble(key) (type: double)
-                      sort order: +
-                      Map-reduce partition columns: UDFToDouble(key) (type: double)
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      tag: 0
-                      value expressions: key (type: string)
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 UDFToDouble(key) (type: double)
+                        1 UDFToDouble(key) (type: double)
+                        2 UDFToDouble(key) (type: double)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -735,7 +750,7 @@ STAGE PLANS:
                   name: default.src1_copy
             Truncated Path -> Alias:
               /src1_copy [x]
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: y
@@ -745,14 +760,18 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: UDFToDouble(key) (type: double)
-                      sort order: +
-                      Map-reduce partition columns: UDFToDouble(key) (type: double)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 1
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 UDFToDouble(key) (type: double)
+                        1 UDFToDouble(key) (type: double)
+                        2 UDFToDouble(key) (type: double)
+                      Position of Big Table: 2
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -802,7 +821,12 @@ STAGE PLANS:
                   name: default.src_copy
             Truncated Path -> Alias:
               /src_copy [y]
-        Map 4 
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: z
@@ -812,14 +836,61 @@ STAGE PLANS:
                     isSamplingPred: false
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: UDFToDouble(key) (type: double)
-                      sort order: +
-                      Map-reduce partition columns: UDFToDouble(key) (type: double)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      tag: 2
-                      value expressions: value (type: string)
-                      auto parallelism: false
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 {key}
+                        1 {value}
+                        2 {value}
+                      keys:
+                        0 UDFToDouble(key) (type: double)
+                        1 UDFToDouble(key) (type: double)
+                        2 UDFToDouble(key) (type: double)
+                      outputColumnNames: _col0, _col6, _col11
+                      input vertices:
+                        0 Map 1
+                        1 Map 2
+                      Position of Big Table: 2
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          GlobalTableId: 1
+#### A masked pattern was here ####
+                          NumFilesPerFileSink: 1
+                          Statistics: Num rows: 550 Data size: 5843 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:
+                                COLUMN_STATS_ACCURATE true
+                                bucket_count -1
+                                columns key,value,val2
+                                columns.comments 
+                                columns.types string:string:string
+#### A masked pattern was here ####
+                                name default.dest_j1
+                                numFiles 1
+                                numRows 107
+                                rawDataSize 2018
+                                serialization.ddl struct dest_j1 { string key, string value, string val2}
+                                serialization.format 1
+                                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                totalSize 2125
+#### A masked pattern was here ####
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+                          TotalFiles: 1
+                          GatherStats: true
+                          MultiFileSpray: false
+            Local Work:
+              Map Reduce Local Work
             Path -> Alias:
 #### A masked pattern was here ####
             Path -> Partition:
@@ -871,54 +942,6 @@ STAGE PLANS:
                   name: default.srcpart
             Truncated Path -> Alias:
               /srcpart/ds=2008-04-08/hr=11 [z]
-        Reducer 2 
-            Needs Tagging: true
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 {VALUE._col0}
-                  1 {VALUE._col1}
-                  2 {VALUE._col1}
-                outputColumnNames: _col0, _col6, _col11
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col11 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    GlobalTableId: 1
-#### A masked pattern was here ####
-                    NumFilesPerFileSink: 1
-                    Statistics: Num rows: 550 Data size: 5843 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:
-                          COLUMN_STATS_ACCURATE true
-                          bucket_count -1
-                          columns key,value,val2
-                          columns.comments 
-                          columns.types string:string:string
-#### A masked pattern was here ####
-                          name default.dest_j1
-                          numFiles 1
-                          numRows 107
-                          rawDataSize 2018
-                          serialization.ddl struct dest_j1 { string key, string value, string val2}
-                          serialization.format 1
-                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                          totalSize 2125
-#### A masked pattern was here ####
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
-                    TotalFiles: 1
-                    GatherStats: true
-                    MultiFileSpray: false
 
   Stage: Stage-0
     Move Operator