hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1642997 [19/42] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/test/results/clientpositive/spark/
Date Mon, 15 Dec 2014 17:11:42 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merge_multi_expressions.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merge_multi_expressions.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merge_multi_expressions.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merge_multi_expressions.q.out Tue Dec  2 19:57:10 2014
@@ -5,97 +5,78 @@ POSTHOOK: query: explain
 select count(*) from srcpart a join srcpart b on a.key = b.key and a.hr = b.hr join srcpart c on a.hr = c.hr and a.key = c.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 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 3 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                        2 
-                      keys:
-                        0 key (type: string), hr (type: string)
-                        1 key (type: string), hr (type: string)
-                        2 key (type: string), hr (type: string)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string), hr (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), hr (type: string)
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: c
+                  alias: b
                   Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 
-                        1 
-                        2 
-                      keys:
-                        0 key (type: string), hr (type: string)
-                        1 key (type: string), hr (type: string)
-                        2 key (type: string), hr (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-      Edges:
-        Reducer 2 <- Map 1 (GROUP, 1)
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string), hr (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), hr (type: string)
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: c
                   Statistics: Num rows: 2000 Data size: 21248 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 0 to 2
-                      condition expressions:
-                        0 
-                        1 
-                        2 
-                      keys:
-                        0 key (type: string), hr (type: string)
-                        1 key (type: string), hr (type: string)
-                        2 key (type: string), hr (type: string)
-                      input vertices:
-                        1 Map 3
-                        2 Map 4
-                      Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        aggregations: count()
-                        mode: hash
-                        outputColumnNames: _col0
-                        Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                        Reduce Output Operator
-                          sort order: 
-                          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                          value expressions: _col0 (type: bigint)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string), hr (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: string), hr (type: string)
+                      Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                condition expressions:
+                  0 
+                  1 
+                  2 
+                Statistics: Num rows: 2200 Data size: 23372 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  aggregations: count()
+                  mode: hash
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    sort order: 
+                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: bigint)
+        Reducer 3 
+            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merging.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merging.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merging.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_merging.q.out Tue Dec  2 19:57:10 2014
@@ -9,13 +9,14 @@ from part p1 left outer join part p2 on
               p1.p_size > 10
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -26,73 +27,56 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (p_size > 10) (type: boolean)
                     Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {p_size}
-                        1 {p_size}
-                        2 
-                      keys:
-                        0 p_partkey (type: int)
-                        1 p_partkey (type: int)
-                        2 p_partkey (type: int)
-            Local Work:
-              Map Reduce Local Work
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: p_partkey (type: int)
+                      sort order: +
+                      Map-reduce partition columns: p_partkey (type: int)
+                      Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: p_size (type: int)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: p2
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {p_size}
-                      1 {p_size}
-                      2 
-                    keys:
-                      0 p_partkey (type: int)
-                      1 p_partkey (type: int)
-                      2 p_partkey (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                  Reduce Output Operator
+                    key expressions: p_partkey (type: int)
+                    sort order: +
+                    Map-reduce partition columns: p_partkey (type: int)
+                    Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: p_size (type: int)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: p3
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Right Outer Join1 to 2
-                    condition expressions:
-                      0 {p_size}
-                      1 {p_size}
-                      2 
-                    keys:
-                      0 p_partkey (type: int)
-                      1 p_partkey (type: int)
-                      2 p_partkey (type: int)
-                    outputColumnNames: _col5, _col17
-                    input vertices:
-                      0 Map 1
-                      1 Map 2
+                  Reduce Output Operator
+                    key expressions: p_partkey (type: int)
+                    sort order: +
+                    Map-reduce partition columns: p_partkey (type: int)
+                    Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Right Outer Join1 to 2
+                condition expressions:
+                  0 {VALUE._col4}
+                  1 {VALUE._col4}
+                  2 
+                outputColumnNames: _col5, _col17
+                Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col5 (type: int), _col17 (type: int)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col5 (type: int), _col17 (type: int)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 57 Data size: 6923 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
@@ -111,13 +95,14 @@ from part p1 left outer join part p2 on
               p1.p_size > 10 and p1.p_size > p2.p_size + 10
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-2 is a root stage
-  Stage-1 depends on stages: Stage-2
+  Stage-1 is a root stage
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-2
+  Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -128,76 +113,59 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (p_size > 10) (type: boolean)
                     Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {p_size}
-                        1 {p_size}
-                        2 
-                      keys:
-                        0 p_partkey (type: int)
-                        1 p_partkey (type: int)
-                        2 p_partkey (type: int)
-            Local Work:
-              Map Reduce Local Work
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: p_partkey (type: int)
+                      sort order: +
+                      Map-reduce partition columns: p_partkey (type: int)
+                      Statistics: Num rows: 8 Data size: 968 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: p_size (type: int)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: p2
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {p_size}
-                      1 {p_size}
-                      2 
-                    keys:
-                      0 p_partkey (type: int)
-                      1 p_partkey (type: int)
-                      2 p_partkey (type: int)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                  Reduce Output Operator
+                    key expressions: p_partkey (type: int)
+                    sort order: +
+                    Map-reduce partition columns: p_partkey (type: int)
+                    Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: p_size (type: int)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: p3
                   Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Right Outer Join1 to 2
-                    condition expressions:
-                      0 {p_size}
-                      1 {p_size}
-                      2 
-                    keys:
-                      0 p_partkey (type: int)
-                      1 p_partkey (type: int)
-                      2 p_partkey (type: int)
-                    outputColumnNames: _col5, _col17
-                    input vertices:
-                      0 Map 1
-                      1 Map 2
-                    Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
-                    Filter Operator
-                      predicate: (_col5 > (_col17 + 10)) (type: boolean)
+                  Reduce Output Operator
+                    key expressions: p_partkey (type: int)
+                    sort order: +
+                    Map-reduce partition columns: p_partkey (type: int)
+                    Statistics: Num rows: 26 Data size: 3147 Basic stats: COMPLETE Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Right Outer Join1 to 2
+                condition expressions:
+                  0 {VALUE._col4}
+                  1 {VALUE._col4}
+                  2 
+                outputColumnNames: _col5, _col17
+                Statistics: Num rows: 57 Data size: 6923 Basic stats: COMPLETE Column stats: NONE
+                Filter Operator
+                  predicate: (_col5 > (_col17 + 10)) (type: boolean)
+                  Statistics: Num rows: 19 Data size: 2307 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: _col5 (type: int), _col17 (type: int)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 19 Data size: 2307 Basic stats: COMPLETE Column stats: NONE
+                    File Output Operator
+                      compressed: false
                       Statistics: Num rows: 19 Data size: 2307 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col5 (type: int), _col17 (type: int)
-                        outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 19 Data size: 2307 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 19 Data size: 2307 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/join_rc.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_rc.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_rc.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_rc.q.out Tue Dec  2 19:57:10 2014
@@ -47,71 +47,64 @@ select join_rc1.key, join_rc2.value
 FROM join_rc1 JOIN join_rc2 ON join_rc1.key = join_rc2.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 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: join_rc2
+                  alias: join_rc1
                   Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: join_rc1
+                  alias: join_rc2
                   Statistics: Num rows: 500 Data size: 4812 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2406 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key}
-                        1 {value}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col6
-                      input vertices:
-                        1 Map 2
-                      Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col6 (type: string)
-                        outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 250 Data size: 2406 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}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col6
+                Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col6 (type: string)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 275 Data size: 2646 Basic stats: COMPLETE Column stats: NONE
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder.q.out Tue Dec  2 19:57:10 2014
@@ -57,13 +57,14 @@ EXPLAIN FROM T1 a JOIN src c ON c.key+1=
 SELECT a.key, a.val, c.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: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key}
-                      keys:
-                        0 UDFToDouble(key) (type: double)
-                        1 (key + 1) (type: double)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: UDFToDouble(key) (type: double)
+                      sort order: +
+                      Map-reduce partition columns: UDFToDouble(key) (type: double)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: key (type: string), val (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -96,32 +89,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key + 1) is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key}
-                      keys:
-                        0 UDFToDouble(key) (type: double)
-                        1 (key + 1) (type: double)
-                      outputColumnNames: _col0, _col1, _col5
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (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
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: (key + 1) (type: double)
+                      sort order: +
+                      Map-reduce partition columns: (key + 1) (type: double)
+                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: key (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {VALUE._col1}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (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
 
   Stage: Stage-0
     Fetch Operator
@@ -136,13 +130,14 @@ POSTHOOK: query: EXPLAIN FROM T1 a JOIN
 SELECT /*+ STREAMTABLE(a) */ a.key, a.val, c.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 
@@ -153,21 +148,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: UDFToDouble(key) is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key}
-                      keys:
-                        0 UDFToDouble(key) (type: double)
-                        1 (key + 1) (type: double)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 2 
+                    Reduce Output Operator
+                      key expressions: UDFToDouble(key) (type: double)
+                      sort order: +
+                      Map-reduce partition columns: UDFToDouble(key) (type: double)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: key (type: string), val (type: string)
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -175,32 +162,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key + 1) is not null (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key}
-                      keys:
-                        0 UDFToDouble(key) (type: double)
-                        1 (key + 1) (type: double)
-                      outputColumnNames: _col0, _col1, _col5
-                      input vertices:
-                        0 Map 1
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (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
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: (key + 1) (type: double)
+                      sort order: +
+                      Map-reduce partition columns: (key + 1) (type: double)
+                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: key (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {VALUE._col1}
+                  1 {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (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
 
   Stage: Stage-0
     Fetch Operator
@@ -251,98 +239,85 @@ POSTHOOK: query: EXPLAIN FROM T1 a
 SELECT a.key, b.key, a.val, c.val
 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, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {val}
-                      1 
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                  Reduce Output Operator
+                    key expressions: key (type: string)
+                    sort order: +
+                    Map-reduce partition columns: key (type: string)
+                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                    value expressions: val (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {val}
-                      1 {key}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5
-                    input vertices:
-                      1 Map 2
-                    Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {_col0} {_col5}
-                        1 {val}
-                      keys:
-                        0 _col1 (type: string)
-                        1 val (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                  Reduce Output Operator
+                    key expressions: key (type: string)
+                    sort order: +
+                    Map-reduce partition columns: key (type: string)
+                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: c
                   Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {_col0} {_col1} {_col5}
-                      1 {val}
-                    keys:
-                      0 _col1 (type: string)
-                      1 val (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col11
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: val (type: string)
+                    sort order: +
+                    Map-reduce partition columns: val (type: string)
+                    Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5
+                Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+                  value expressions: _col0 (type: string), _col5 (type: string)
+        Reducer 3 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4}
+                  1 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col11
+                Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL 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
@@ -361,98 +336,85 @@ POSTHOOK: query: EXPLAIN FROM T1 a
 SELECT /*+ STREAMTABLE(a) */ a.key, b.key, a.val, c.val
 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, 3), Map 4 (PARTITION-LEVEL SORT, 3)
+        Reducer 3 <- Map 5 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Spark HashTable Sink Operator
-                    condition expressions:
-                      0 {key} {val}
-                      1 
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-2
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                  Reduce Output Operator
+                    key expressions: key (type: string)
+                    sort order: +
+                    Map-reduce partition columns: key (type: string)
+                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                    value expressions: val (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                    condition expressions:
-                      0 {key} {val}
-                      1 {key}
-                    keys:
-                      0 key (type: string)
-                      1 key (type: string)
-                    outputColumnNames: _col0, _col1, _col5
-                    input vertices:
-                      1 Map 2
-                    Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {_col0} {_col5}
-                        1 {val}
-                      keys:
-                        0 _col1 (type: string)
-                        1 val (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
+                  Reduce Output Operator
+                    key expressions: key (type: string)
+                    sort order: +
+                    Map-reduce partition columns: key (type: string)
+                    Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: c
                   Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                    condition expressions:
-                      0 {_col0} {_col1} {_col5}
-                      1 {val}
-                    keys:
-                      0 _col1 (type: string)
-                      1 val (type: string)
-                    outputColumnNames: _col0, _col1, _col5, _col11
-                    input vertices:
-                      0 Map 1
+                  Reduce Output Operator
+                    key expressions: val (type: string)
+                    sort order: +
+                    Map-reduce partition columns: val (type: string)
+                    Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5
+                Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  Statistics: Num rows: 0 Data size: 33 Basic stats: PARTIAL Column stats: NONE
+                  value expressions: _col0 (type: string), _col5 (type: string)
+        Reducer 3 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4}
+                  1 {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col11
+                Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: string), _col5 (type: string), _col1 (type: string), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 0 Data size: 36 Basic stats: PARTIAL 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/join_reorder2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder2.q.out?rev=1642997&r1=1642996&r2=1642997&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder2.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join_reorder2.q.out Tue Dec  2 19:57:10 2014
@@ -75,125 +75,97 @@ FROM T1 a JOIN T2 b ON a.key = b.key
           JOIN T4 d ON c.key = d.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), Map 4 (PARTITION-LEVEL SORT, 1), Map 5 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                        2 {key} {val}
-                        3 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                        3 key (type: string)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {val}
-                        3 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                        3 key (type: string)
-            Local Work:
-              Map Reduce Local Work
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: d
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  alias: c
+                  Statistics: Num rows: 0 Data size: 20 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                        3 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                        3 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 5 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: d
                   Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 1 to 2
-                           Inner Join 2 to 3
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                        2 {key} {val}
-                        3 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                        2 key (type: string)
-                        3 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
-                      input vertices:
-                        1 Map 2
-                        2 Map 3
-                        3 Map 4
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
                       Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.TextInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                      value expressions: val (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 1 to 2
+                     Inner Join 2 to 3
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                  2 {KEY.reducesinkkey0} {VALUE._col0}
+                  3 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -235,16 +207,33 @@ FROM T1 a JOIN T2 b ON a.key = b.key
           JOIN T4 d ON a.key + 1 = d.key + 1
 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 5 (PARTITION-LEVEL SORT, 3)
+        Reducer 3 <- Map 6 (PARTITION-LEVEL SORT, 3), Reducer 2 (PARTITION-LEVEL SORT, 3)
+        Reducer 4 <- Map 7 (PARTITION-LEVEL SORT, 3), Reducer 3 (PARTITION-LEVEL SORT, 3)
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
+                  Filter Operator
+                    predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean)
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 5 
             Map Operator Tree:
                 TableScan
                   alias: b
@@ -252,16 +241,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and (key + 1) is not null) (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {key} {val}
-                        1 {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 3 
+                    Reduce Output Operator
+                      key expressions: key (type: string)
+                      sort order: +
+                      Map-reduce partition columns: key (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: val (type: string)
+        Map 6 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -269,16 +255,13 @@ STAGE PLANS:
                   Filter Operator
                     predicate: val is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {_col0} {_col1} {_col5} {_col6}
-                        1 {key}
-                      keys:
-                        0 _col1 (type: string)
-                        1 val (type: string)
-            Local Work:
-              Map Reduce Local Work
-        Map 4 
+                    Reduce Output Operator
+                      key expressions: val (type: string)
+                      sort order: +
+                      Map-reduce partition columns: val (type: string)
+                      Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                      value expressions: key (type: string)
+        Map 7 
             Map Operator Tree:
                 TableScan
                   alias: d
@@ -286,80 +269,65 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key + 1) is not null (type: boolean)
                     Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Spark HashTable Sink Operator
-                      condition expressions:
-                        0 {_col0} {_col1} {_col5} {_col6} {_col10} {_col11}
-                        1 {key} {val}
-                      keys:
-                        0 (_col0 + 1) (type: double)
-                        1 (key + 1) (type: double)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 0 Data size: 30 Basic stats: PARTIAL Column stats: NONE
-                  Filter Operator
-                    predicate: ((key is not null and val is not null) and (key + 1) is not null) (type: boolean)
-                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                    Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                      condition expressions:
-                        0 {key} {val}
-                        1 {key} {val}
-                      keys:
-                        0 key (type: string)
-                        1 key (type: string)
-                      outputColumnNames: _col0, _col1, _col5, _col6
-                      input vertices:
-                        1 Map 2
+                    Reduce Output Operator
+                      key expressions: (key + 1) (type: double)
+                      sort order: +
+                      Map-reduce partition columns: (key + 1) (type: double)
                       Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        condition expressions:
-                          0 {_col0} {_col1} {_col5} {_col6}
-                          1 {key} {val}
-                        keys:
-                          0 _col1 (type: string)
-                          1 val (type: string)
-                        outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                        input vertices:
-                          1 Map 3
-                        Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                        Map Join Operator
-                          condition map:
-                               Inner Join 0 to 1
-                          condition expressions:
-                            0 {_col0} {_col1} {_col5} {_col6} {_col10} {_col11}
-                            1 {key} {val}
-                          keys:
-                            0 (_col0 + 1) (type: double)
-                            1 (key + 1) (type: double)
-                          outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
-                          input vertices:
-                            1 Map 4
-                          Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                          Select Operator
-                            expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
-                            outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
-                            Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                            File Output Operator
-                              compressed: false
-                              Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
-                              table:
-                                  input format: org.apache.hadoop.mapred.TextInputFormat
-                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-            Local Work:
-              Map Reduce Local Work
+                      value expressions: key (type: string), val (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {KEY.reducesinkkey0} {VALUE._col0}
+                  1 {KEY.reducesinkkey0} {VALUE._col0}
+                outputColumnNames: _col0, _col1, _col5, _col6
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Reduce Output Operator
+                  key expressions: _col1 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col1 (type: string)
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  value expressions: _col0 (type: string), _col5 (type: string), _col6 (type: string)
+        Reducer 3 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {KEY.reducesinkkey0} {VALUE._col4} {VALUE._col5}
+                  1 {VALUE._col0} {KEY.reducesinkkey0}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Reduce Output Operator
+                  key expressions: (_col0 + 1) (type: double)
+                  sort order: +
+                  Map-reduce partition columns: (_col0 + 1) (type: double)
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  value expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string)
+        Reducer 4 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                condition expressions:
+                  0 {VALUE._col0} {VALUE._col1} {VALUE._col5} {VALUE._col6} {VALUE._col10} {VALUE._col11}
+                  1 {VALUE._col0} {VALUE._col1}
+                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11, _col15, _col16
+                Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string), _col10 (type: string), _col11 (type: string), _col15 (type: string), _col16 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5, _col6, _col7
+                  Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 0 Data size: 0 Basic stats: NONE Column stats: NONE
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message