hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From vg...@apache.org
Subject [43/51] [partial] hive git commit: HIVE-16811 : Estimate statistics in absence of stats (Vineet Garg, reviewed by Ashutosh Chauhan)
Date Sat, 02 Sep 2017 05:09:15 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out
index 649afb5..f763566 100644
--- a/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out
+++ b/ql/src/test/results/clientpositive/llap/bucket_map_join_tez1.q.out
@@ -125,64 +125,71 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 45994 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 43713 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col0 (type: int)
-                          1 _col0 (type: int)
-                        outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          0 Map 1
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 550 Data size: 10243 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
+                      Statistics: Num rows: 475 Data size: 90060 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: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col3
+                Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 522 Data size: 99066 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
@@ -217,39 +224,39 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: tab_part
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: key (type: int), value (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
-                        Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 3316 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 2 
@@ -259,11 +266,11 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 237 Data size: 44935 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: int)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 237 Data size: 44935 Basic stats: COMPLETE Column stats: NONE
                   Map Join Operator
                     condition map:
                          Inner Join 0 to 1
@@ -272,7 +279,7 @@ STAGE PLANS:
                       1 _col0 (type: int)
                     input vertices:
                       1 Map 4
-                    Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 260 Data size: 49428 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       mode: hash
@@ -346,91 +353,95 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE)
-        Reducer 3 <- Map 2 (CUSTOM_SIMPLE_EDGE)
+        Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: int)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-            Execution mode: llap
-            LLAP IO: no inputs
-        Map 2 
-            Map Operator Tree:
-                TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
-                        outputColumnNames: _col0
+                        outputColumnNames: _col1
                         input vertices:
-                          0 Map 1
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                        Map Join Operator
-                          condition map:
-                               Inner Join 0 to 1
-                          keys:
-                            0 _col0 (type: int)
-                            1 _col0 (type: int)
-                          input vertices:
-                            1 Map 4
-                          Statistics: Num rows: 605 Data size: 11267 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: 
+                          1 Map 3
+                        Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col1 (type: int)
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+                          Map Join Operator
+                            condition map:
+                                 Inner Join 0 to 1
+                            keys:
+                              0 _col0 (type: int)
+                              1 _col0 (type: int)
+                            input vertices:
+                              1 Map 4
+                            Statistics: Num rows: 574 Data size: 2186 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
-                              value expressions: _col0 (type: bigint)
+                              Reduce Output Operator
+                                sort order: 
+                                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
+                                value expressions: _col0 (type: bigint)
+            Execution mode: llap
+            LLAP IO: no inputs
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 230 Data size: 878 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: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: d
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 1808 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: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Reducer 3 
+        Reducer 2 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -498,91 +509,95 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 3 <- Map 1 (CUSTOM_EDGE), Map 2 (CUSTOM_EDGE)
-        Reducer 4 <- Map 3 (CUSTOM_SIMPLE_EDGE)
+        Map 1 <- Map 3 (CUSTOM_EDGE), Map 4 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (CUSTOM_SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: d
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 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: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: int)
+                          1 _col0 (type: int)
+                        outputColumnNames: _col1
+                        input vertices:
+                          1 Map 3
+                        Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col1 (type: int)
+                          outputColumnNames: _col0
+                          Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
+                          Map Join Operator
+                            condition map:
+                                 Inner Join 0 to 1
+                            keys:
+                              0 _col0 (type: int)
+                              1 _col0 (type: int)
+                            input vertices:
+                              1 Map 4
+                            Statistics: Num rows: 574 Data size: 2186 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)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 878 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  alias: d
+                  Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col0 (type: int)
-                          1 _col0 (type: int)
-                        outputColumnNames: _col0
-                        input vertices:
-                          0 Map 2
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                        Map Join Operator
-                          condition map:
-                               Inner Join 0 to 1
-                          keys:
-                            0 _col0 (type: int)
-                            1 _col0 (type: int)
-                          input vertices:
-                            0 Map 1
-                          Statistics: Num rows: 605 Data size: 11267 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)
+                      Statistics: Num rows: 475 Data size: 1808 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: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Reducer 4 
+        Reducer 2 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -654,25 +669,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcbucket_mapjoin
-                  Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 27 Data size: 7884 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), substr(value, 5) (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: sum(_col1)
                         keys: _col0 (type: int)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 26 Data size: 7592 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: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: double)
             Execution mode: llap
             LLAP IO: no inputs
@@ -680,14 +695,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 45994 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -697,14 +712,14 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1, _col3
                         input vertices:
                           0 Reducer 2
-                        Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 253 Data size: 48084 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 253 Data size: 48084 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 253 Data size: 48084 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -719,16 +734,16 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col1 (type: double), _col0 (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col1 (type: int)
                     sort order: +
                     Map-reduce partition columns: _col1 (type: int)
-                    Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: NONE
                     value expressions: _col0 (type: double)
 
   Stage: Stage-0
@@ -756,22 +771,77 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 3 (CUSTOM_EDGE)
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (CUSTOM_SIMPLE_EDGE)
+        Map 1 <- Reducer 4 (CUSTOM_EDGE)
+        Map 3 <- Map 2 (CUSTOM_EDGE)
+        Reducer 4 <- Map 3 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: b
+                  Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: int)
+                          1 _col1 (type: int)
+                        outputColumnNames: _col0, _col1, _col2
+                        input vertices:
+                          1 Reducer 4
+                        Statistics: Num rows: 287 Data size: 1093 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col0 (type: int), _col2 (type: double), _col1 (type: string)
+                          outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 287 Data size: 1093 Basic stats: COMPLETE Column stats: NONE
+                          File Output Operator
+                            compressed: false
+                            Statistics: Num rows: 287 Data size: 1093 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
+            Execution mode: llap
+            LLAP IO: no inputs
+        Map 2 
+            Map Operator Tree:
+                TableScan
                   alias: tab_part
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 1904 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 1808 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: 475 Data size: 1808 Basic stats: COMPLETE Column stats: NONE
+            Execution mode: llap
+            LLAP IO: no inputs
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: tab
+                  Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -780,53 +850,27 @@ STAGE PLANS:
                           1 _col0 (type: int)
                         outputColumnNames: _col1, _col2
                         input vertices:
-                          1 Map 3
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                          0 Map 2
+                        Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col1 (type: int), substr(_col2, 5) (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
                           Group By Operator
                             aggregations: sum(_col1)
                             keys: _col0 (type: int)
                             mode: hash
                             outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 522 Data size: 1988 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: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 522 Data size: 1988 Basic stats: COMPLETE Column stats: NONE
                               value expressions: _col1 (type: double)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: tab
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: int), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-                      Reduce Output Operator
-                        key expressions: _col0 (type: int)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-            Execution mode: llap
-            LLAP IO: no inputs
-        Reducer 2 
+        Reducer 4 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -834,32 +878,17 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 261 Data size: 994 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col1 (type: double), _col0 (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 275 Data size: 5121 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Inner Join 0 to 1
-                    keys:
-                      0 _col1 (type: int)
-                      1 _col0 (type: int)
-                    outputColumnNames: _col0, _col1, _col3
-                    input vertices:
-                      1 Map 3
-                    Statistics: Num rows: 302 Data size: 5633 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
-                      outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 302 Data size: 5633 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 302 Data size: 5633 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
+                  Statistics: Num rows: 261 Data size: 994 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col1 (type: int)
+                    sort order: +
+                    Map-reduce partition columns: _col1 (type: int)
+                    Statistics: Num rows: 261 Data size: 994 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: double)
 
   Stage: Stage-0
     Fetch Operator
@@ -886,22 +915,58 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 3 (CUSTOM_EDGE)
-        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 4 (CUSTOM_SIMPLE_EDGE)
+        Map 1 <- Reducer 3 (CUSTOM_EDGE)
+        Map 2 <- Map 4 (CUSTOM_EDGE)
+        Reducer 3 <- Map 2 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: int)
+                          1 _col1 (type: int)
+                        outputColumnNames: _col1, _col2, _col3
+                        input vertices:
+                          1 Reducer 3
+                        Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: _col3 (type: int), _col2 (type: double), _col1 (type: string)
+                          outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE
+                          File Output Operator
+                            compressed: false
+                            Statistics: Num rows: 522 Data size: 93514 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
+            Execution mode: llap
+            LLAP IO: no inputs
+        Map 2 
+            Map Operator Tree:
+                TableScan
                   alias: x
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -910,66 +975,46 @@ STAGE PLANS:
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1
                         input vertices:
-                          1 Map 3
-                        Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                          1 Map 4
+                        Statistics: Num rows: 253 Data size: 45401 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col0 (type: int), substr(_col1, 5) (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 253 Data size: 45401 Basic stats: COMPLETE Column stats: NONE
                           Group By Operator
                             aggregations: sum(_col1)
                             keys: _col0 (type: int)
                             mode: hash
                             outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 253 Data size: 45401 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: 266 Data size: 4952 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 253 Data size: 45401 Basic stats: COMPLETE Column stats: NONE
                               value expressions: _col1 (type: double)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: y
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 878 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: int), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 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: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-            Execution mode: llap
-            LLAP IO: no inputs
-        Reducer 2 
+        Reducer 3 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
@@ -977,32 +1022,17 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 133 Data size: 2476 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 126 Data size: 22610 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col1 (type: double), _col0 (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 133 Data size: 2476 Basic stats: COMPLETE Column stats: NONE
-                  Map Join Operator
-                    condition map:
-                         Inner Join 0 to 1
-                    keys:
-                      0 _col1 (type: int)
-                      1 _col0 (type: int)
-                    outputColumnNames: _col0, _col1, _col3
-                    input vertices:
-                      1 Map 4
-                    Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: _col1 (type: int), _col0 (type: double), _col3 (type: string)
-                      outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                      File Output Operator
-                        compressed: false
-                        Statistics: Num rows: 550 Data size: 10243 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
+                  Statistics: Num rows: 126 Data size: 22610 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col1 (type: int)
+                    sort order: +
+                    Map-reduce partition columns: _col1 (type: int)
+                    Statistics: Num rows: 126 Data size: 22610 Basic stats: COMPLETE Column stats: NONE
+                    value expressions: _col0 (type: double)
 
   Stage: Stage-0
     Fetch Operator
@@ -1027,86 +1057,92 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 1 <- Map 2 (CUSTOM_EDGE), Map 3 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE), Map 4 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                             Inner Join 0 to 2
-                        keys:
-                          0 _col0 (type: int)
-                          1 _col0 (type: int)
-                          2 _col0 (type: int)
-                        outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          1 Map 2
-                          2 Map 3
-                        Statistics: Num rows: 1100 Data size: 20486 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 1100 Data size: 20486 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 1100 Data size: 20486 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
+                      Statistics: Num rows: 475 Data size: 85013 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: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  alias: c
+                  Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: int), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: int)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 230 Data size: 878 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
+                        Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Map 3 
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: int)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      expressions: key (type: int), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 230 Data size: 41274 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                     Inner Join 0 to 2
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                  2 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col4
+                Statistics: Num rows: 1045 Data size: 187028 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col4 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 1045 Data size: 187028 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 1045 Data size: 187028 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
@@ -1138,14 +1174,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: x
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 89488 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 85013 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -1155,7 +1191,7 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 522 Data size: 93514 Basic stats: COMPLETE Column stats: NONE
                         Map Join Operator
                           condition map:
                                Inner Join 0 to 1
@@ -1165,14 +1201,14 @@ STAGE PLANS:
                           outputColumnNames: _col0, _col1, _col3
                           input vertices:
                             1 Map 3
-                          Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 574 Data size: 102865 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
                             outputColumnNames: _col0, _col1, _col2
-                            Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 574 Data size: 102865 Basic stats: COMPLETE Column stats: NONE
                             File Output Operator
                               compressed: false
-                              Statistics: Num rows: 605 Data size: 11267 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 574 Data size: 102865 Basic stats: COMPLETE Column stats: NONE
                               table:
                                   input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                   output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1183,38 +1219,38 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: y
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 924 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 878 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 878 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: c
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 3490 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 3316 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: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 3316 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
@@ -1252,25 +1288,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcbucket_mapjoin
-                  Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 27 Data size: 7884 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), substr(value, 5) (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: sum(_col1)
                         keys: _col0 (type: int)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 26 Data size: 7592 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: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: double)
             Execution mode: llap
             LLAP IO: no inputs
@@ -1278,14 +1314,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -1295,14 +1331,14 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1, _col3
                         input vertices:
                           0 Reducer 2
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1317,12 +1353,12 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 13 Data size: 3796 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: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: NONE
                   value expressions: _col1 (type: double)
 
   Stage: Stage-0
@@ -1358,19 +1394,19 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: srcbucket_mapjoin
-                  Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 27 Data size: 7884 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), substr(value, 5) (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 26 Data size: 7592 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: 27 Data size: 3024 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 26 Data size: 7592 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
@@ -1378,14 +1414,14 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -1395,14 +1431,14 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1, _col3
                         input vertices:
                           0 Reducer 2
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: double), _col3 (type: string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -1417,12 +1453,12 @@ STAGE PLANS:
                 keys: KEY._col0 (type: int)
                 mode: complete
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 13 Data size: 3796 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: 13 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 13 Data size: 3796 Basic stats: COMPLETE Column stats: NONE
                   value expressions: _col1 (type: double)
 
   Stage: Stage-0
@@ -1448,60 +1484,66 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (BROADCAST_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 45994 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col1 (type: string)
-                        Statistics: Num rows: 242 Data size: 4502 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 43713 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: int)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 92896 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 88251 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: value (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col1 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1, _col2
-                        input vertices:
-                          0 Map 1
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                        File Output Operator
-                          compressed: false
-                          Statistics: Num rows: 550 Data size: 10243 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
+                      Statistics: Num rows: 475 Data size: 88251 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 475 Data size: 88251 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col1 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0, _col1, _col2
+                Statistics: Num rows: 522 Data size: 97076 Basic stats: COMPLETE Column stats: NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 522 Data size: 97076 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
@@ -1548,64 +1590,71 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Map 1 (CUSTOM_EDGE)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Map 3 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 242 Data size: 43428 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 230 Data size: 41274 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: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 230 Data size: 41274 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 94800 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col0 (type: int)
-                          1 _col0 (type: int)
-                        outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          0 Map 1
-                        Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
-                          outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 550 Data size: 10243 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 550 Data size: 10243 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
+                      Statistics: Num rows: 475 Data size: 90060 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: 475 Data size: 90060 Basic stats: COMPLETE Column stats: NONE
+                        value expressions: _col1 (type: string)
             Execution mode: llap
             LLAP IO: no inputs
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: int)
+                  1 _col0 (type: int)
+                outputColumnNames: _col0, _col1, _col3
+                Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), _col1 (type: string), _col3 (type: string)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 522 Data size: 99066 Basic stats: COMPLETE Column stats: NONE
+                    table:
+   

<TRUNCATED>

Mime
View raw message