hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From w...@apache.org
Subject [03/74] [abbrv] [partial] hive git commit: HIVE-16811 : Estimate statistics in absence of stats (Vineet Garg, reviewed by Ashutosh Chauhan)
Date Fri, 08 Sep 2017 06:34:55 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/8f7c5788/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
index 8d97fa4..c353280 100644
--- a/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
+++ b/ql/src/test/results/clientpositive/llap/unionDistinct_1.q.out
@@ -5684,11 +5684,11 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src_thrift
-                  Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: astring (type: string)
                     outputColumnNames: _col0
-                    Statistics: Num rows: 11 Data size: 3070 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 11 Data size: 2024 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string)
                       mode: hash
@@ -6466,35 +6466,35 @@ STAGE PLANS:
 #### A masked pattern was here ####
       Edges:
         Map 1 <- Union 2 (CONTAINS)
-        Map 4 <- Map 5 (BROADCAST_EDGE), Union 2 (CONTAINS)
         Reducer 3 <- Union 2 (SIMPLE_EDGE)
+        Reducer 5 <- Map 4 (SIMPLE_EDGE), Map 6 (SIMPLE_EDGE), Union 2 (CONTAINS)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: dst_union22_delta
-                  Statistics: Num rows: 500 Data size: 20936 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 454856 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(k0) <= 50.0) (type: boolean)
-                    Statistics: Num rows: 166 Data size: 6950 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 166 Data size: 151012 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: k1 (type: string), k2 (type: string), k3 (type: string), k4 (type: string)
                       outputColumnNames: _col0, _col1, _col2, _col3
-                      Statistics: Num rows: 166 Data size: 6950 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 166 Data size: 151012 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 348 Data size: 248973 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
                           null sort order: aaaa
                           sort order: ++++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
-                          Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 348 Data size: 248973 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -6555,50 +6555,25 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 500 Data size: 103124 Basic stats: COMPLETE Column stats: PARTIAL
+                  Statistics: Num rows: 500 Data size: 278292 Basic stats: COMPLETE Column stats: PARTIAL
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(k1) > 20.0) (type: boolean)
-                    Statistics: Num rows: 166 Data size: 30544 Basic stats: COMPLETE Column stats: PARTIAL
+                    Statistics: Num rows: 166 Data size: 89056 Basic stats: COMPLETE Column stats: PARTIAL
                     Select Operator
                       expressions: k1 (type: string), k2 (type: string), ds (type: string)
                       outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 166 Data size: 30544 Basic stats: COMPLETE Column stats: PARTIAL
-                      Map Join Operator
-                        condition map:
-                             Left Outer Join 0 to 1
-                        filter mappings:
-                          0 [1, 1]
-                        filter predicates:
-                          0 {(_col2 = '1')}
-                          1 
-                        Estimated key counts: Map 5 => 55
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1, _col4, _col5
-                        input vertices:
-                          1 Map 5
-                        Position of Big Table: 0
-                        Statistics: Num rows: 182 Data size: 33598 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string)
-                          outputColumnNames: _col0, _col1, _col2, _col3
-                          Statistics: Num rows: 182 Data size: 33598 Basic stats: COMPLETE Column stats: NONE
-                          Group By Operator
-                            keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
-                            mode: hash
-                            outputColumnNames: _col0, _col1, _col2, _col3
-                            Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE
-                            Reduce Output Operator
-                              key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
-                              null sort order: aaaa
-                              sort order: ++++
-                              Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
-                              Statistics: Num rows: 348 Data size: 40548 Basic stats: COMPLETE Column stats: NONE
-                              tag: -1
-                              auto parallelism: true
+                      Statistics: Num rows: 166 Data size: 89056 Basic stats: COMPLETE Column stats: PARTIAL
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 166 Data size: 89056 Basic stats: COMPLETE Column stats: PARTIAL
+                        tag: 0
+                        value expressions: _col1 (type: string), _col2 (type: string)
+                        auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -6653,26 +6628,26 @@ STAGE PLANS:
                   name: default.dst_union22
             Truncated Path -> Alias:
               /dst_union22/ds=1 [a]
-        Map 5 
+        Map 6 
             Map Operator Tree:
                 TableScan
                   alias: dst_union22_delta
-                  Statistics: Num rows: 500 Data size: 20936 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 367272 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: ((UDFToDouble(k0) > 50.0) and (UDFToDouble(k1) > 20.0)) (type: boolean)
-                    Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 40399 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: k1 (type: string), k3 (type: string), k4 (type: string)
                       outputColumnNames: _col0, _col1, _col2
-                      Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 55 Data size: 40399 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         null sort order: a
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 55 Data size: 2302 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 55 Data size: 40399 Basic stats: COMPLETE Column stats: NONE
                         tag: 1
                         value expressions: _col1 (type: string), _col2 (type: string)
                         auto parallelism: true
@@ -6738,14 +6713,14 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: string), KEY._col2 (type: string), KEY._col3 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 174 Data size: 20274 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 174 Data size: 124486 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 1
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
                   Static Partition Specification: ds=2/
-                  Statistics: Num rows: 174 Data size: 20274 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 174 Data size: 124486 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.TextInputFormat
@@ -6769,6 +6744,41 @@ STAGE PLANS:
                   TotalFiles: 1
                   GatherStats: true
                   MultiFileSpray: false
+        Reducer 5 
+            Execution mode: llap
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Left Outer Join 0 to 1
+                filter mappings:
+                  0 [1, 1]
+                filter predicates:
+                  0 {(VALUE._col1 = '1')}
+                  1 
+                keys:
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0, _col1, _col4, _col5
+                Position of Big Table: 0
+                Statistics: Num rows: 182 Data size: 97961 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: string), _col4 (type: string), _col5 (type: string)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 182 Data size: 97961 Basic stats: COMPLETE Column stats: NONE
+                  Group By Operator
+                    keys: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+                    mode: hash
+                    outputColumnNames: _col0, _col1, _col2, _col3
+                    Statistics: Num rows: 348 Data size: 248973 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+                      null sort order: aaaa
+                      sort order: ++++
+                      Map-reduce partition columns: _col0 (type: string), _col1 (type: string), _col2 (type: string), _col3 (type: string)
+                      Statistics: Num rows: 348 Data size: 248973 Basic stats: COMPLETE Column stats: NONE
+                      tag: -1
+                      auto parallelism: true
         Union 2 
             Vertex: Union 2
 
@@ -7697,27 +7707,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src2
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -7777,24 +7787,24 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src5
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       keys: key (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         null sort order: a
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                         tag: -1
                         value expressions: _col1 (type: bigint)
                         auto parallelism: true
@@ -7855,27 +7865,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src3
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -7935,27 +7945,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src4
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -8020,18 +8030,18 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 51 Data size: 244 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 51 Data size: 8958 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Reducer 3 
@@ -8042,18 +8052,18 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Reducer 5 
@@ -8064,18 +8074,18 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 154 Data size: 738 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 154 Data size: 27838 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Reducer 7 
@@ -8086,13 +8096,13 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 77 Data size: 369 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 77 Data size: 13919 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
-                  Statistics: Num rows: 77 Data size: 369 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 77 Data size: 13919 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -8189,36 +8199,36 @@ STAGE PLANS:
       Edges:
         Map 1 <- Union 2 (CONTAINS)
         Map 6 <- Union 2 (CONTAINS)
-        Map 7 <- Map 8 (BROADCAST_EDGE), Union 4 (CONTAINS)
         Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS)
         Reducer 5 <- Union 4 (SIMPLE_EDGE)
+        Reducer 8 <- Map 7 (SIMPLE_EDGE), Map 9 (SIMPLE_EDGE), Union 4 (CONTAINS)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: src2
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -8278,27 +8288,27 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: src3
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -8358,45 +8368,24 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        Estimated key counts: Map 8 => 103
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col2
-                        input vertices:
-                          1 Map 8
-                        Position of Big Table: 0
-                        Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: _col0 (type: string), _col2 (type: bigint)
-                          outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
-                          Group By Operator
-                            keys: _col0 (type: string), _col1 (type: bigint)
-                            mode: hash
-                            outputColumnNames: _col0, _col1
-                            Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE
-                            Reduce Output Operator
-                              key expressions: _col0 (type: string), _col1 (type: bigint)
-                              null sort order: aa
-                              sort order: ++
-                              Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                              Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE
-                              tag: -1
-                              auto parallelism: true
+                      Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
+                        auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -8450,26 +8439,26 @@ STAGE PLANS:
                   name: default.src4
             Truncated Path -> Alias:
               /src4 [a]
-        Map 8 
+        Map 9 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         null sort order: a
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                         tag: 1
                         value expressions: _col1 (type: bigint)
                         auto parallelism: true
@@ -8534,18 +8523,18 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 216 Data size: 1037 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Reducer 5 
@@ -8556,13 +8545,13 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 108 Data size: 518 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 108 Data size: 19391 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
-                  Statistics: Num rows: 108 Data size: 518 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 108 Data size: 19391 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -8579,6 +8568,36 @@ STAGE PLANS:
                   TotalFiles: 1
                   GatherStats: false
                   MultiFileSpray: false
+        Reducer 8 
+            Execution mode: llap
+            Needs Tagging: false
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0, _col2
+                Position of Big Table: 1
+                Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col2 (type: bigint)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
+                  Group By Operator
+                    keys: _col0 (type: string), _col1 (type: bigint)
+                    mode: hash
+                    outputColumnNames: _col0, _col1
+                    Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
+                    Reduce Output Operator
+                      key expressions: _col0 (type: string), _col1 (type: bigint)
+                      null sort order: aa
+                      sort order: ++
+                      Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
+                      Statistics: Num rows: 216 Data size: 38782 Basic stats: COMPLETE Column stats: NONE
+                      tag: -1
+                      auto parallelism: true
         Union 2 
             Vertex: Union 2
         Union 4 
@@ -8651,37 +8670,37 @@ STAGE PLANS:
       Edges:
         Map 1 <- Union 2 (CONTAINS)
         Map 6 <- Union 2 (CONTAINS)
-        Map 7 <- Map 9 (BROADCAST_EDGE)
         Reducer 3 <- Union 2 (SIMPLE_EDGE), Union 4 (CONTAINS)
         Reducer 5 <- Union 4 (SIMPLE_EDGE)
-        Reducer 8 <- Map 7 (SIMPLE_EDGE), Union 4 (CONTAINS)
+        Reducer 8 <- Map 10 (SIMPLE_EDGE), Map 7 (SIMPLE_EDGE)
+        Reducer 9 <- Reducer 8 (SIMPLE_EDGE), Union 4 (CONTAINS)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: src2
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), count (type: bigint)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: bigint)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: bigint)
                           null sort order: aa
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           auto parallelism: true
             Execution mode: llap
@@ -8737,33 +8756,28 @@ STAGE PLANS:
                   name: default.src2
             Truncated Path -> Alias:
               /src2 [src2]
-        Map 6 
+        Map 10 
             Map Operator Tree:
                 TableScan
-                  alias: src3
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  alias: b
+                  Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string), count (type: bigint)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
-                      Group By Operator
-                        keys: _col0 (type: string), _col1 (type: bigint)
-                        mode: hash
-                        outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
-                        Reduce Output Operator
-                          key expressions: _col0 (type: string), _col1 (type: bigint)
-                          null sort order: aa
-                          sort order: ++
-                          Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                          Statistics: Num rows: 206 Data size: 988 Basic stats: COMPLETE Column stats: NONE
-                          tag: -1
-                          auto parallelism: true
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        null sort order: a
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+                        tag: 1
+                        auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -8771,7 +8785,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: src3
+                  base file name: src5
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -8782,11 +8796,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types string:bigint
 #### A masked pattern was here ####
-                    name default.src3
+                    name default.src5
                     numFiles 1
                     numRows 309
                     rawDataSize 1482
-                    serialization.ddl struct src3 { string key, i64 count}
+                    serialization.ddl struct src5 { string key, i64 count}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 1791
@@ -8803,61 +8817,47 @@ STAGE PLANS:
                       columns.comments 
                       columns.types string:bigint
 #### A masked pattern was here ####
-                      name default.src3
+                      name default.src5
                       numFiles 1
                       numRows 309
                       rawDataSize 1482
-                      serialization.ddl struct src3 { string key, i64 count}
+                      serialization.ddl struct src5 { string key, i64 count}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 1791
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.src3
-                  name: default.src3
+                    name: default.src5
+                  name: default.src5
             Truncated Path -> Alias:
-              /src3 [src3]
-        Map 7 
+              /src5 [b]
+        Map 6 
             Map Operator Tree:
                 TableScan
-                  alias: a
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  alias: src3
+                  Statistics: Num rows: 309 Data size: 56640 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        Estimated key counts: Map 9 => 103
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0
-                        input vertices:
-                          1 Map 9
-                        Position of Big Table: 0
-                        Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
-                        Group By Operator
-                          aggregations: count()
-                          keys: _col0 (type: string)
-                          mode: hash
-                          outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
-                          Reduce Output Operator
-                            key expressions: _col0 (type: string)
-                            null sort order: a
-                            sort order: +
-                            Map-reduce partition columns: _col0 (type: string)
-                            Statistics: Num rows: 113 Data size: 543 Basic stats: COMPLETE Column stats: NONE
-                            tag: -1
-                            value expressions: _col1 (type: bigint)
-                            auto parallelism: true
+                      expressions: key (type: string), count (type: bigint)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
+                      Group By Operator
+                        keys: _col0 (type: string), _col1 (type: bigint)
+                        mode: hash
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col0 (type: string), _col1 (type: bigint)
+                          null sort order: aa
+                          sort order: ++
+                          Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
+                          Statistics: Num rows: 206 Data size: 37760 Basic stats: COMPLETE Column stats: NONE
+                          tag: -1
+                          auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
             Path -> Alias:
@@ -8865,7 +8865,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: src4
+                  base file name: src3
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -8876,11 +8876,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types string:bigint
 #### A masked pattern was here ####
-                    name default.src4
+                    name default.src3
                     numFiles 1
                     numRows 309
                     rawDataSize 1482
-                    serialization.ddl struct src4 { string key, i64 count}
+                    serialization.ddl struct src3 { string key, i64 count}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 1791
@@ -8897,41 +8897,41 @@ STAGE PLANS:
                       columns.comments 
                       columns.types string:bigint
 #### A masked pattern was here ####
-                      name default.src4
+                      name default.src3
                       numFiles 1
                       numRows 309
                       rawDataSize 1482
-                      serialization.ddl struct src4 { string key, i64 count}
+                      serialization.ddl struct src3 { string key, i64 count}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 1791
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.src4
-                  name: default.src4
+                    name: default.src3
+                  name: default.src3
             Truncated Path -> Alias:
-              /src4 [a]
-        Map 9 
+              /src3 [src3]
+        Map 7 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
+                  alias: a
+                  Statistics: Num rows: 309 Data size: 54280 Basic stats: COMPLETE Column stats: NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
                     predicate: (UDFToDouble(key) < 10.0) (type: boolean)
-                    Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         null sort order: a
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
-                        tag: 1
+                        Statistics: Num rows: 103 Data size: 18093 Basic stats: COMPLETE Column stats: NONE
+                        tag: 0
                         auto parallelism: true
             Execution mode: llap
             LLAP IO: no inputs
@@ -8940,7 +8940,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: src5
+                  base file name: src4
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -8951,11 +8951,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types string:bigint
 #### A masked pattern was here ####
-                    name default.src5
+                    name default.src4
                     numFiles 1
                     numRows 309
                     rawDataSize 1482
-                    serialization.ddl struct src5 { string key, i64 count}
+                    serialization.ddl struct src4 { string key, i64 count}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 1791
@@ -8972,20 +8972,20 @@ STAGE PLANS:
                       columns.comments 
                       columns.types string:bigint
 #### A masked pattern was here ####
-                      name default.src5
+                      name default.src4
                       numFiles 1
                       numRows 309
                       rawDataSize 1482
-                      serialization.ddl struct src5 { string key, i64 count}
+                      serialization.ddl struct src4 { string key, i64 count}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 1791
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.src5
-                  name: default.src5
+                    name: default.src4
+                  name: default.src4
             Truncated Path -> Alias:
-              /src5 [b]
+              /src4 [a]
         Reducer 3 
             Execution mode: llap
             Needs Tagging: false
@@ -8994,18 +8994,18 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 103 Data size: 494 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 103 Data size: 18880 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Reducer 5 
@@ -9016,13 +9016,13 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: bigint)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 79 Data size: 379 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 79 Data size: 14280 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
 #### A masked pattern was here ####
                   NumFilesPerFileSink: 1
-                  Statistics: Num rows: 79 Data size: 379 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 79 Data size: 14280 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                   table:
                       input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -9043,23 +9043,51 @@ STAGE PLANS:
             Execution mode: llap
             Needs Tagging: false
             Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col0
+                Position of Big Table: 0
+                Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
+                Group By Operator
+                  aggregations: count()
+                  keys: _col0 (type: string)
+                  mode: hash
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
+                  Reduce Output Operator
+                    key expressions: _col0 (type: string)
+                    null sort order: a
+                    sort order: +
+                    Map-reduce partition columns: _col0 (type: string)
+                    Statistics: Num rows: 113 Data size: 19902 Basic stats: COMPLETE Column stats: NONE
+                    tag: -1
+                    value expressions: _col1 (type: bigint)
+                    auto parallelism: true
+        Reducer 9 
+            Execution mode: llap
+            Needs Tagging: false
+            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 56 Data size: 269 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 9862 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string), _col1 (type: bigint)
                     null sort order: aa
                     sort order: ++
                     Map-reduce partition columns: _col0 (type: string), _col1 (type: bigint)
-                    Statistics: Num rows: 159 Data size: 763 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 159 Data size: 28742 Basic stats: COMPLETE Column stats: NONE
                     tag: -1
                     auto parallelism: true
         Union 2 
@@ -9209,42 +9237,42 @@ STAGE PLANS:
             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: 180480 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string), value (type: string)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string), _col1 (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1000 Data size: 360960 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1000 Data size: 360960 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Map 7 
             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: 180480 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string), value (type: string)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string), _col1 (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1000 Data size: 360960 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1000 Data size: 18624 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1000 Data size: 360960 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 3 
@@ -9280,20 +9308,20 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 500 Data size: 9312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 180480 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     keys: _col0 (type: string)
                     mode: complete
                     outputColumnNames: _col0
-                    Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: _col0 (type: string), _col0 (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 4656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 90240 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: string)
                         mode: hash
@@ -10647,109 +10675,117 @@ STAGE PLANS:
     Tez
 #### A masked pattern was here ####
       Edges:
-        Map 2 <- Union 3 (CONTAINS)
-        Map 5 <- Union 3 (CONTAINS)
-        Reducer 4 <- Map 1 (BROADCAST_EDGE), Union 3 (SIMPLE_EDGE)
+        Map 3 <- Union 4 (CONTAINS)
+        Map 6 <- Union 4 (CONTAINS)
+        Reducer 2 <- Map 1 (SIMPLE_EDGE), Reducer 5 (SIMPLE_EDGE)
+        Reducer 5 <- Union 4 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (UDFToDouble(key) = 97.0) (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 43792 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 250 Data size: 43792 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Map 2 
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: dim_pho
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (UDFToDouble(key) = 97.0) (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: string)
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                          Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Map 5 
+        Map 6 
             Map Operator Tree:
                 TableScan
                   alias: jackson_sev_add
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (UDFToDouble(key) = 97.0) (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         keys: _col0 (type: string), _col1 (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string), _col1 (type: string)
                           sort order: ++
                           Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
-                          Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 500 Data size: 175168 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
-        Reducer 4 
+        Reducer 2 
+            Execution mode: llap
+            Reduce Operator Tree:
+              Merge Join Operator
+                condition map:
+                     Inner Join 0 to 1
+                keys:
+                  0 _col0 (type: string)
+                  1 _col0 (type: string)
+                outputColumnNames: _col1, _col2
+                Statistics: Num rows: 275 Data size: 48171 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col1 (type: string), _col2 (type: string)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 275 Data size: 48171 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    Statistics: Num rows: 275 Data size: 48171 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
+        Reducer 5 
             Execution mode: llap
             Reduce Operator Tree:
               Group By Operator
                 keys: KEY._col0 (type: string), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                Map Join Operator
-                  condition map:
-                       Inner Join 0 to 1
-                  keys:
-                    0 _col0 (type: string)
-                    1 _col0 (type: string)
-                  outputColumnNames: _col1, _col2
-                  input vertices:
-                    0 Map 1
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  Select Operator
-                    expressions: _col1 (type: string), _col2 (type: string)
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.SequenceFileInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Union 3 
-            Vertex: Union 3
+                Statistics: Num rows: 250 Data size: 87584 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: 250 Data size: 87584 Basic stats: COMPLETE Column stats: NONE
+                  value expressions: _col1 (type: string)
+        Union 4 
+            Vertex: Union 4
 
   Stage: Stage-0
     Fetch Operator
@@ -12014,42 +12050,42 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: t1
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string), value (type: string)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string), _col1 (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: t2
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string), value (type: string)
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       keys: _col0 (type: string), _col1 (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 20 Data size: 140 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 20 Data size: 7360 Basic stats: COMPLETE Column stats: NONE
             Execution mode: llap
             LLAP IO: no inputs
         Reducer 3 
@@ -12059,24 +12095,24 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string), KEY._col1 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count(1)
                     keys: _col0 (type: string)
                     mode: complete
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                       File Output Operator
                         compressed: false
-                        Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                         table:
                             input format: org.apache.hadoop.mapred.TextInputFormat
                             output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -12085,18 +12121,18 @@ STAGE PLANS:
                 Select Operator
                   expressions: _col1 (type: string)
                   outputColumnNames: _col1
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count(1)
                     keys: _col1 (type: string)
                     mode: hash
                     outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 3680 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10 Data size: 3680 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col1 (type: bigint)
         Reducer 4 
             Execution mode: llap
@@ -12106,14 +12142,14 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: string), UDFToInteger(_col1) (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 5 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -12274,22 +12310,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: t1
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string)
                     outputColumnNames: key
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       keys: key (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -12297,22 +12333,22 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: t2
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: key (type: string)
                     outputColumnNames: key
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                     Group By Operator
                       aggregations: count()
                       keys: key (type: string)
                       mode: hash
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 10 Data size: 1840 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: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 10 Data size: 1840 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: bigint)
             Execution mode: llap
             LLAP IO: no inputs
@@ -12324,17 +12360,17 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 5 Data size: 920 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   keys: _col0 (type: string), _col1 (type: bigint)
                   mode: hash
     

<TRUNCATED>

Mime
View raw message