hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jpull...@apache.org
Subject [04/51] [partial] hive git commit: HIVE-11110: Reorder applyPreJoinOrderingTransforms, add NotNULL/FilterMerge rules, improve Filter selectivity estimation (Laljo John Pullokkaran reviewed by Jesus Camacho Rodriguez, Ashutosh Chauhan)
Date Sat, 12 Dec 2015 06:54:53 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
index b2b93fb..eb1109d 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin1.q.out
@@ -553,7 +553,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -632,7 +632,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -643,18 +643,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -946,7 +946,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -1020,7 +1020,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1031,18 +1031,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out
index d7d7d40..fb0c851 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin10.q.out
@@ -210,7 +210,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 869 Data size: 3477 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -334,7 +334,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 869 Data size: 3477 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1737 Data size: 6950 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -344,7 +344,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 955 Data size: 3824 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1910 Data size: 7645 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
                         mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out
index dfdff5c..c761cc5 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin11.q.out
@@ -220,7 +220,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1070 Data size: 4281 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -349,7 +349,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1070 Data size: 4281 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -359,7 +359,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2354 Data size: 9418 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()
@@ -629,7 +629,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1070 Data size: 4281 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int), part (type: string)
@@ -758,7 +758,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1070 Data size: 4281 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2140 Data size: 8562 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -768,7 +768,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 1177 Data size: 4709 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 2354 Data size: 9418 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin12.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin12.q.out
index 07f3c15..b1cf619 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin12.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin12.q.out
@@ -179,7 +179,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -259,7 +259,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -269,7 +269,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()
@@ -481,7 +481,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -556,7 +556,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -566,7 +566,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
                         mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin13.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin13.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin13.q.out
index 1d6e64c..efb7198 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin13.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin13.q.out
@@ -138,7 +138,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -214,7 +214,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1000 Data size: 10624 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -224,7 +224,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      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
                       Group By Operator
                         aggregations: count()
                         mode: hash
@@ -473,7 +473,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -554,7 +554,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -564,7 +564,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      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
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()
@@ -770,7 +770,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -851,7 +851,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -861,7 +861,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      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
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()
@@ -1069,7 +1069,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -1150,7 +1150,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     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
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1160,7 +1160,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      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
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin2.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin2.q.out
index d82480e..b833522 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin2.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin2.q.out
@@ -177,7 +177,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -256,7 +256,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -267,18 +267,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -579,7 +579,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -658,7 +658,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -669,18 +669,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1003,7 +1003,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 58 Data size: 6124 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -1130,7 +1130,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1141,18 +1141,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin3.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin3.q.out
index 39552c1..7b3e66f 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin3.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin3.q.out
@@ -208,7 +208,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -287,7 +287,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -298,18 +298,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -617,7 +617,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -696,7 +696,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -707,18 +707,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col7 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin4.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin4.q.out
index ad2762d..72e8258 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin4.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin4.q.out
@@ -194,7 +194,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -268,7 +268,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -279,18 +279,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -567,7 +567,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -641,7 +641,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -652,18 +652,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 14 Data size: 1512 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 28 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin5.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin5.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin5.q.out
index f7c3d4d..05f2512 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin5.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin5.q.out
@@ -244,7 +244,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -318,7 +318,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 110 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -329,18 +329,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 121 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 121 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 121 Data size: 12786 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -682,7 +682,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -756,7 +756,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 58 Data size: 6124 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -767,18 +767,18 @@ STAGE PLANS:
                       input vertices:
                         0 Map 1
                       Position of Big Table: 1
-                      Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out
index 84f68a3..3d5fb96 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin7.q.out
@@ -158,7 +158,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -240,7 +240,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -251,16 +251,16 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col8 (type: string)
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: int), _col1 (type: string)
                           sort order: ++
-                          Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                           tag: -1
                           TopN: 1
                           TopN Hash Memory Usage: 0.1
@@ -331,7 +331,7 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: int), KEY.reducesinkkey1 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 1
                   Statistics: Num rows: 1 Data size: 4 Basic stats: COMPLETE Column stats: NONE

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin8.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin8.q.out
index d6c42b5..c1a5e29 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin8.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin8.q.out
@@ -144,7 +144,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -225,7 +225,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -235,7 +235,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()
@@ -455,7 +455,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -536,7 +536,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -546,7 +546,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Group By Operator
                         aggregations: count()

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin9.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin9.q.out
index e65e689..8fb3978 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin9.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin9.q.out
@@ -152,7 +152,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 525 Data size: 2100 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1050 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -228,7 +228,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -238,7 +238,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 577 Data size: 2310 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1155 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
                         mode: hash
@@ -485,7 +485,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -561,7 +561,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 344 Data size: 1377 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 687 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -571,7 +571,7 @@ STAGE PLANS:
                       input vertices:
                         1 Map 3
                       Position of Big Table: 0
-                      Statistics: Num rows: 378 Data size: 1514 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 755 Data size: 3025 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count()
                         mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative.q.out
index 031c46c..b6b96a3 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative.q.out
@@ -152,7 +152,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 20 Data size: 2100 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 40 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -226,7 +226,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -237,17 +237,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 22 Data size: 2310 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 44 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 22 Data size: 2310 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 44 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 22 Data size: 2310 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 44 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative2.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative2.q.out
index 4a8f46d..1ee2775 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative2.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative2.q.out
@@ -154,7 +154,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 58 Data size: 6124 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: int)
@@ -281,7 +281,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 1375 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 26 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -292,18 +292,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: int), _col1 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2
-                        Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 1
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 31 Data size: 3368 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 63 Data size: 6736 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/08f73adc/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative3.q.out b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative3.q.out
index 3671564..3f9f8a5 100644
--- a/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative3.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucketmapjoin_negative3.q.out
@@ -213,7 +213,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -289,7 +289,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -300,18 +300,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -460,7 +460,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -536,7 +536,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -547,18 +547,18 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       BucketMapJoin: true
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -704,7 +704,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 11 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 (key + key) (type: double)
@@ -775,7 +775,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key + key) is not null (type: boolean)
-                    Statistics: Num rows: 11 Data size: 2200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -786,17 +786,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 12 Data size: 2420 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 12 Data size: 2420 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 12 Data size: 2420 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -940,7 +940,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -1011,7 +1011,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1022,17 +1022,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1176,7 +1176,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -1247,7 +1247,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1258,17 +1258,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1412,7 +1412,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -1483,7 +1483,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1494,17 +1494,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1648,7 +1648,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -1719,7 +1719,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1730,17 +1730,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -1884,7 +1884,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -1955,7 +1955,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -1966,17 +1966,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
@@ -2120,7 +2120,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Spark HashTable Sink Operator
                       keys:
                         0 key (type: string), value (type: string)
@@ -2191,7 +2191,7 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 6 Data size: 1200 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 21 Data size: 4200 Basic stats: COMPLETE Column stats: NONE
                     Map Join Operator
                       condition map:
                            Inner Join 0 to 1
@@ -2202,17 +2202,17 @@ STAGE PLANS:
                       input vertices:
                         1 Map 2
                       Position of Big Table: 0
-                      Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                       Select Operator
                         expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
                         outputColumnNames: _col0, _col1, _col2, _col3
-                        Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
                           GlobalTableId: 0
 #### A masked pattern was here ####
                           NumFilesPerFileSink: 1
-                          Statistics: Num rows: 6 Data size: 1320 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 23 Data size: 4620 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat


Mime
View raw message