hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [26/31] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/test/results/clientpositive/spark/
Date Tue, 02 Dec 2014 19:57:14 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_2.q.out Tue Dec  2 19:57:10 2014
@@ -57,13 +57,14 @@ explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -74,21 +75,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -96,32 +89,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -148,32 +142,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -181,32 +157,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -236,13 +224,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -250,51 +239,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -411,13 +393,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -428,21 +411,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -450,32 +425,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -502,32 +478,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a left outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -535,32 +493,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -590,13 +560,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_1 a right outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -604,51 +575,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_25.q.out Tue Dec  2 19:57:10 2014
@@ -53,39 +53,31 @@ POSTHOOK: query: explain 
 select * from (select a.key from smb_bucket_1 a join smb_bucket_2 b on (a.key = b.key) where a.key = 5) t1 left outer join (select c.key from smb_bucket_2 c join smb_bucket_3 d on (c.key = d.key) where c.key=5) t2 on (t1.key=t2.key) where t2.key=5
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-3 is a root stage
-  Stage-2 depends on stages: Stage-3
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-3
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
+        Reducer 6 <- Map 5 (PARTITION-LEVEL SORT, 1), Map 7 (PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                  alias: a
+                  Statistics: Num rows: 52 Data size: 208 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key = 5) (type: boolean)
-                    Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 5 (type: int)
-                        1 5 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: 5 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -93,106 +85,94 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key = 5) (type: boolean)
                     Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 5 (type: int)
-                        1 5 (type: int)
-            Local Work:
-              Map Reduce Local Work
-        Map 4 
+                    Reduce Output Operator
+                      key expressions: 5 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: d
-                  Statistics: Num rows: 55 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  alias: c
+                  Statistics: Num rows: 51 Data size: 206 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key = 5) (type: boolean)
-                    Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 5 (type: int)
-                        1 5 (type: int)
-                      input vertices:
-                        0 Map 3
-                      Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: 5 (type: int)
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
-                        Spark HashTable Sink Operator
-                          condition expressions:
-                            0 {_col0}
-                            1 
-                          keys:
-                            0 _col0 (type: int)
-                            1 _col0 (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: 5 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 25 Data size: 100 Basic stats: COMPLETE Column stats: NONE
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 52 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  alias: d
+                  Statistics: Num rows: 55 Data size: 222 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key = 5) (type: boolean)
-                    Statistics: Num rows: 26 Data size: 104 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 
-                        1 
-                      keys:
-                        0 5 (type: int)
-                        1 5 (type: int)
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: 5 (type: int)
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
-                        Map Join Operator
-                          condition map:
-                               Left Outer Join0 to 1
-                          condition expressions:
-                            0 {_col0}
-                            1 {_col0}
-                          keys:
-                            0 _col0 (type: int)
-                            1 _col0 (type: int)
-                          outputColumnNames: _col0, _col1
-                          input vertices:
-                            1 Map 4
-                          Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
-                          Filter Operator
-                            predicate: (_col1 = 5) (type: boolean)
-                            Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
-                            Select Operator
-                              expressions: _col0 (type: int), 5 (type: int)
-                              outputColumnNames: _col0, _col1
-                              Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
-                              File Output Operator
-                                compressed: false
-                                Statistics: Num rows: 15 Data size: 62 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
+                    Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: 5 (type: int)
+                      sort order: +
+                      Statistics: Num rows: 27 Data size: 108 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: 5 (type: int)
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: int)
+                    sort order: +
+                    Map-reduce partition columns: _col0 (type: int)
+                    Statistics: Num rows: 28 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+        Reducer 3 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0}
+                  1 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 31 Data size: 129 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: (_col1 = 5) (type: boolean)
+                  Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col0 (type: int), 5 (type: int)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 15 Data size: 62 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
+                      Statistics: Num rows: 15 Data size: 62 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
+        Reducer 6 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 
+                  1 
+                Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: 5 (type: int)
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: int)
+                    sort order: +
+                    Map-reduce partition columns: _col0 (type: int)
+                    Statistics: Num rows: 29 Data size: 118 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_3.q.out Tue Dec  2 19:57:10 2014
@@ -61,35 +61,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_2 a join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -100,32 +79,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 226 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
@@ -152,32 +146,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_2 a left outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -185,32 +161,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -239,13 +227,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(a)*/ * from smb_bucket_2 a right outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -253,51 +242,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -413,35 +395,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_2 a join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {value}
-                        1 {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -452,32 +413,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {value}
-                        1 {key} {value}
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int)
+                      sort order: +
+                      Map-reduce partition columns: key (type: int)
+                      Statistics: Num rows: 1 Data size: 111 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 1 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1 Data size: 226 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
@@ -504,32 +480,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_2 a left outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {value}
-                      1 {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -537,32 +495,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -591,13 +561,14 @@ POSTHOOK: query: explain
 select /*+mapjoin(b)*/ * from smb_bucket_2 a right outer join smb_bucket_3 b on a.key = b.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 3), Map 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -605,51 +576,44 @@ STAGE PLANS:
                 TableScan
                   alias: a
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
                   Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {value}
-                      1 {key} {value}
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: key (type: int)
+                    sort order: +
+                    Map-reduce partition columns: key (type: int)
+                    Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: value (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 2 Data size: 244 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.TextInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message