FAQ
http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
index fa80956..b5e7846 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
@@ -133,11 +133,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -156,11 +156,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -170,14 +170,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -218,11 +218,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -244,17 +244,17 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        keys: key (type: int), value (type: string)
                        mode: hash
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 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: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
          Reducer 2
              Local Work:
                Map Reduce Local Work
@@ -263,11 +263,11 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int), KEY._col1 (type: string)
                  mode: mergepartial
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col0 (type: int)
                    outputColumnNames: _col0
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                    Map Join Operator
                      condition map:
                           Inner Join 0 to 1
@@ -276,7 +276,7 @@ STAGE PLANS:
                        1 _col0 (type: int)
                      input vertices:
                        1 Map 4
- Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        aggregations: count()
                        mode: hash
@@ -359,22 +359,22 @@ STAGE PLANS:
                    Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), substr(value, 5) (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                        Group By Operator
                          aggregations: sum(_col1)
                          keys: _col0 (type: int)
                          mode: hash
                          outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 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: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                            value expressions: _col1 (type: double)
          Reducer 2
              Local Work:
@@ -385,11 +385,11 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: mergepartial
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col1 (type: double), _col0 (type: int)
                    outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
                    Spark HashTable Sink Operator
                      keys:
                        0 _col1 (type: int)
@@ -406,11 +406,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -420,14 +420,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 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: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -469,11 +469,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col1 (type: int)
@@ -492,11 +492,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -517,11 +517,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -531,22 +531,22 @@ STAGE PLANS:
                          outputColumnNames: _col1, _col2
                          input vertices:
                            1 Map 3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                          Select Operator
                            expressions: _col1 (type: int), substr(_col2, 5) (type: string)
                            outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            Group By Operator
                              aggregations: sum(_col1)
                              keys: _col0 (type: int)
                              mode: hash
                              outputColumnNames: _col0, _col1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                                value expressions: _col1 (type: double)
              Local Work:
                Map Reduce Local Work
@@ -559,11 +559,11 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: mergepartial
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col1 (type: double), _col0 (type: int)
                    outputColumnNames: _col0, _col1
- Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                    Map Join Operator
                      condition map:
                           Inner Join 0 to 1
@@ -573,14 +573,14 @@ STAGE PLANS:
                      outputColumnNames: _col0, _col1, _col3
                      input vertices:
                        1 Map 4
- Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 302 Data size: 3213 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: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                        File Output Operator
                          compressed: false
- Statistics: Num rows: 150 Data size: 1600 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                          table:
                              input format: org.apache.hadoop.mapred.TextInputFormat
                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -620,11 +620,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -645,11 +645,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -659,22 +659,22 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1
                          input vertices:
                            1 Map 3
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                          Select Operator
                            expressions: _col0 (type: int), substr(_col1, 5) (type: string)
                            outputColumnNames: _col0, _col1
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                            Group By Operator
                              aggregations: sum(_col1)
                              keys: _col0 (type: int)
                              mode: hash
                              outputColumnNames: _col0, _col1
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 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: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                                value expressions: _col1 (type: double)
              Local Work:
                Map Reduce Local Work
@@ -687,11 +687,11 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: mergepartial
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
                  Select Operator
                    expressions: _col1 (type: double), _col0 (type: int)
                    outputColumnNames: _col0, _col1
- Statistics: Num rows: 66 Data size: 700 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
                    Spark HashTable Sink Operator
                      keys:
                        0 _col1 (type: int)
@@ -708,11 +708,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -722,14 +722,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -770,11 +770,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -789,11 +789,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -813,11 +813,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -830,14 +830,14 @@ STAGE PLANS:
                          input vertices:
                            1 Map 2
                            2 Map 3
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1100 Data size: 11686 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: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -876,11 +876,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -894,11 +894,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -917,11 +917,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -931,7 +931,7 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1
                          input vertices:
                            1 Map 2
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                          Map Join Operator
                            condition map:
                                 Inner Join 0 to 1
@@ -941,14 +941,14 @@ STAGE PLANS:
                            outputColumnNames: _col0, _col1, _col3
                            input vertices:
                              1 Map 3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 605 Data size: 6427 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: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                              File Output Operator
                                compressed: false
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                                table:
                                    input format: org.apache.hadoop.mapred.TextInputFormat
                                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -993,22 +993,22 @@ STAGE PLANS:
                    Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), substr(value, 5) (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                        Group By Operator
                          aggregations: sum(_col1)
                          keys: _col0 (type: int)
                          mode: hash
                          outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 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: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                            value expressions: _col1 (type: double)
          Reducer 2
              Local Work:
@@ -1019,7 +1019,7 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: mergepartial
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
                  Spark HashTable Sink Operator
                    keys:
                      0 _col0 (type: int)
@@ -1036,11 +1036,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1050,14 +1050,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1100,16 +1100,16 @@ STAGE PLANS:
                    Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), substr(value, 5) (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 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: 14 Data size: 1456 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 27 Data size: 2808 Basic stats: COMPLETE Column stats: NONE
                          value expressions: _col1 (type: string)
          Reducer 2
              Local Work:
@@ -1120,7 +1120,7 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: complete
                  outputColumnNames: _col0, _col1
- Statistics: Num rows: 7 Data size: 728 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 13 Data size: 1352 Basic stats: COMPLETE Column stats: NONE
                  Spark HashTable Sink Operator
                    keys:
                      0 _col0 (type: int)
@@ -1137,11 +1137,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1151,14 +1151,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1199,11 +1199,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: value is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col1 (type: string)
@@ -1222,11 +1222,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: value is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: value (type: string)
                        outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1236,10 +1236,10 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col2
                          input vertices:
                            0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                          File Output Operator
                            compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            table:
                                input format: org.apache.hadoop.mapred.TextInputFormat
                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1300,11 +1300,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -1323,11 +1323,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1337,14 +1337,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1372,36 +1372,18 @@ STAGE PLANS:
      Spark
  #### 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
- Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Local Work:
- Map Reduce Local Work
- Map 3
+ Map 4
              Map Operator Tree:
                  TableScan
                    alias: a
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: value is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col1 (type: string)
@@ -1411,53 +1393,78 @@ STAGE PLANS:

    Stage: Stage-1
      Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
  #### A masked pattern was here ####
        Vertices:
- Map 2
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 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: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 3
              Map Operator Tree:
                  TableScan
                    alias: a
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- 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: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1
- input vertices:
- 0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
- input vertices:
- 1 Map 3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col3 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 5312 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: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
              Local Work:
                Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe

    Stage: Stage-0
      Fetch Operator
@@ -1490,11 +1497,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string), ds (type: string)
                        outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int), _col2 (type: string)
@@ -1513,11 +1520,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string), ds (type: string)
                        outputColumnNames: _col0, _col1, _col2
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1527,14 +1534,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col4
                          input vertices:
                            0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1612,11 +1619,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1625,10 +1632,10 @@ STAGE PLANS:
                            1 _col0 (type: int)
                          input vertices:
                            1 Map 3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                          Reduce Output Operator
                            sort order:
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
              Local Work:
                Map Reduce Local Work
          Reducer 2
@@ -1733,11 +1740,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -1746,10 +1753,10 @@ STAGE PLANS:
                            1 _col0 (type: int)
                          input vertices:
                            1 Map 3
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                          Reduce Output Operator
                            sort order:
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
              Local Work:
                Map Reduce Local Work
          Reducer 2

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out
index c0169de..a54b03c 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_tez2.q.out
@@ -122,36 +122,18 @@ STAGE PLANS:
      Spark
  #### 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
- Filter Operator
- predicate: (key is not null and value is not null) (type: boolean)
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: key (type: int), value (type: string)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
- Spark HashTable Sink Operator
- keys:
- 0 _col0 (type: int)
- 1 _col0 (type: int)
- Local Work:
- Map Reduce Local Work
- Map 3
+ Map 4
              Map Operator Tree:
                  TableScan
                    alias: a
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: value is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col1 (type: string)
@@ -161,53 +143,78 @@ STAGE PLANS:

    Stage: Stage-1
      Spark
+ Edges:
+ Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 2), Map 3 (PARTITION-LEVEL SORT, 2)
  #### A masked pattern was here ####
        Vertices:
- Map 2
+ Map 1
+ Map Operator Tree:
+ TableScan
+ alias: a
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Filter Operator
+ predicate: (key is not null and value is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: key (type: int), value (type: string)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 500 Data size: 5312 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: 5312 Basic stats: COMPLETE Column stats: NONE
+ value expressions: _col1 (type: string)
+ Map 3
              Map Operator Tree:
                  TableScan
                    alias: a
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- 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: int)
- 1 _col0 (type: int)
- outputColumnNames: _col0, _col1
- input vertices:
- 0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
- Map Join Operator
- condition map:
- Inner Join 0 to 1
- keys:
- 0 _col1 (type: string)
- 1 _col1 (type: string)
- outputColumnNames: _col0, _col3
- input vertices:
- 1 Map 3
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- Select Operator
- expressions: _col0 (type: int), _col3 (type: int)
- outputColumnNames: _col0, _col1
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- File Output Operator
- compressed: false
- Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
- table:
- input format: org.apache.hadoop.mapred.TextInputFormat
- output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
- serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+ Statistics: Num rows: 500 Data size: 5312 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: 5312 Basic stats: COMPLETE Column stats: NONE
+ Reducer 2
              Local Work:
                Map Reduce Local Work
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col0 (type: int)
+ 1 _col0 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ keys:
+ 0 _col1 (type: string)
+ 1 _col1 (type: string)
+ outputColumnNames: _col0, _col3
+ input vertices:
+ 1 Map 4
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ Select Operator
+ expressions: _col0 (type: int), _col3 (type: int)
+ outputColumnNames: _col0, _col1
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ File Output Operator
+ compressed: false
+ Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+ serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe

    Stage: Stage-0
      Fetch Operator
@@ -261,12 +268,12 @@ STAGE PLANS:
                    alias: a
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
- predicate: UDFToDouble(key) is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 UDFToDouble(_col0) (type: double)
@@ -284,12 +291,12 @@ STAGE PLANS:
                    alias: b
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
- predicate: UDFToDouble(key) is not null (type: boolean)
- Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+ predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 500 Data size: 5312 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: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -299,14 +306,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1, _col3
                          input vertices:
                            0 Map 1
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -343,11 +350,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: (((key > 2) and (key > 1)) and key is not null) (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                        Spark HashTable Sink Operator
                          keys:
                            0 _col0 (type: int)
@@ -366,11 +373,11 @@ STAGE PLANS:
                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: (((key > 1) and (key > 2)) and key is not null) (type: boolean)
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -380,10 +387,10 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1
                          input vertices:
                            1 Map 2
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
                          File Output Operator
                            compressed: false
- Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
                            table:
                                input format: org.apache.hadoop.mapred.TextInputFormat
                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -574,17 +581,17 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        keys: key (type: int)
                        mode: hash
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
          Reducer 2
              Local Work:
                Map Reduce Local Work
@@ -593,7 +600,7 @@ STAGE PLANS:
                  keys: KEY._col0 (type: int)
                  mode: mergepartial
                  outputColumnNames: _col0
- Statistics: Num rows: 60 Data size: 636 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
                  Spark HashTable Sink Operator
                    keys:
                      0 _col0 (type: int)
@@ -610,11 +617,11 @@ STAGE PLANS:
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
                      predicate: key is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int)
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -624,10 +631,10 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col1
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                          File Output Operator
                            compressed: false
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                            table:
                                input format: org.apache.hadoop.mapred.TextInputFormat
                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -663,18 +670,18 @@ STAGE PLANS:
                    alias: tab
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
- predicate: UDFToDouble(value) is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ predicate: (value is not null and UDFToDouble(value) is not null) (type: boolean)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Group By Operator
                        keys: value (type: string)
                        mode: hash
                        outputColumnNames: _col0
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 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: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
          Reducer 2
              Local Work:
                Map Reduce Local Work
@@ -683,7 +690,7 @@ STAGE PLANS:
                  keys: KEY._col0 (type: string)
                  mode: mergepartial
                  outputColumnNames: _col0
- Statistics: Num rows: 60 Data size: 636 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
                  Spark HashTable Sink Operator
                    keys:
                      0 UDFToDouble(_col0) (type: double)
@@ -699,12 +706,12 @@ STAGE PLANS:
                    alias: tab
                    Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                    Filter Operator
- predicate: UDFToDouble(key) is not null (type: boolean)
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                      Select Operator
                        expressions: key (type: int), value (type: string)
                        outputColumnNames: _col0, _col1
- Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column stats: NONE
                        Map Join Operator
                          condition map:
                               Inner Join 0 to 1
@@ -714,14 +721,14 @@ STAGE PLANS:
                          outputColumnNames: _col0, _col2
                          input vertices:
                            0 Reducer 2
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                          Select Operator
                            expressions: _col0 (type: string), _col2 (type: string)
                            outputColumnNames: _col0, _col1
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                            File Output Operator
                              compressed: false
- Statistics: Num rows: 133 Data size: 1411 Basic stats: COMPLETE Column stats: NONE
+ Statistics: Num rows: 266 Data size: 2822 Basic stats: COMPLETE Column stats: NONE
                              table:
                                  input format: org.apache.hadoop.mapred.TextInputFormat
                                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucketizedhiveinputformat.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketizedhiveinputformat.q.out b/ql/src/test/results/clientpositive/spark/bucketizedhiveinputformat.q.out
index c8fc4d3..98c5802 100644
--- a/ql/src/test/results/clientpositive/spark/bucketizedhiveinputformat.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketizedhiveinputformat.q.out
@@ -22,8 +22,6 @@ POSTHOOK: query: CREATE TABLE T2(name STRING) STORED AS SEQUENCEFILE
  POSTHOOK: type: CREATETABLE
  POSTHOOK: Output: database:default
  POSTHOOK: Output: default@T2
-Warning: Shuffle Join JOIN[10][tables = [$hdt$_0, $hdt$_1]] in Work 'Reducer 2' is a cross product
-Warning: Shuffle Join JOIN[13][tables = [$hdt$_0, $hdt$_1, $hdt$_2]] in Work 'Reducer 3' is a cross product
  PREHOOK: query: INSERT OVERWRITE TABLE T2 SELECT * FROM (
  SELECT tmp1.name as name FROM (
    SELECT name, 'MMM' AS n FROM T1) tmp1

Search Discussions

Discussion Posts

Previous

Follow ups

Related Discussions

Discussion Navigation
viewthread | post
posts ‹ prev | 60 of 102 | next ›
Discussion Overview
groupcommits @
categorieshive, hadoop
postedDec 12, '15 at 6:54a
activeDec 15, '15 at 12:39a
posts102
users1
websitehive.apache.org

1 user in discussion

Jpullokk: 102 posts

People

Translate

site design / logo © 2021 Grokbase