hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [02/16] hive git commit: HIVE-16230 : Enable CBO in presence of hints (Pengcheng Xiong via Ashutosh Chauhan)
Date Mon, 20 Mar 2017 23:33:38 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/42181575/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out b/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out
index be2ff37..9f50e9f 100644
--- a/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out
+++ b/ql/src/test/results/clientpositive/spark/smb_mapjoin_5.q.out
@@ -59,37 +59,83 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                    Sorted Merge Bucket Map Join Operator
-                      condition map:
-                           Inner Join 0 to 1
-                           Inner Join 1 to 2
-                      keys:
-                        0 key (type: int)
-                        1 key (type: int)
-                        2 key (type: int)
-                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      Select Operator
-                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                          table:
-                              input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                              output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -122,34 +168,83 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Inner Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -182,34 +277,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Left Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Left Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -247,34 +382,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Right Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Right Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -313,34 +488,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Left Outer Join0 to 1
-                         Outer Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Left Outer Join0 to 1
+                     Outer Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -384,34 +599,83 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                         Inner Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                     Inner Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -446,34 +710,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                         Left Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                     Left Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -510,34 +814,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                         Right Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                     Right Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -576,34 +920,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Right Outer Join0 to 1
-                         Outer Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                     Outer Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -644,34 +1028,83 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Outer Join 0 to 1
-                         Inner Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Right Outer Join0 to 1
+                     Inner Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -706,34 +1139,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Outer Join 0 to 1
-                         Left Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Outer Join 0 to 1
+                     Left Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -775,34 +1248,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Outer Join 0 to 1
-                         Right Outer Join1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Outer Join 0 to 1
+                     Right Outer Join1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator
@@ -841,34 +1354,74 @@ STAGE DEPENDENCIES:
 STAGE PLANS:
   Stage: Stage-1
     Spark
+      Edges:
+        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2), Map 4 (PARTITION-LEVEL SORT, 2)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: a
+                  Statistics: Num rows: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 3 
+            Map Operator Tree:
+                TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
-                  Sorted Merge Bucket Map Join Operator
-                    condition map:
-                         Outer Join 0 to 1
-                         Outer Join 1 to 2
-                    keys:
-                      0 key (type: int)
-                      1 key (type: int)
-                      2 key (type: int)
-                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                    Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
-                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
-                        table:
-                            input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                            output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Map 4 
+            Map Operator Tree:
+                TableScan
+                  alias: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                  Select Operator
+                    expressions: key (type: int), value (type: string)
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats: NONE
+                      value expressions: _col1 (type: string)
+        Reducer 2 
+            Reduce Operator Tree:
+              Join Operator
+                condition map:
+                     Outer Join 0 to 1
+                     Outer Join 1 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator


Mime
View raw message