hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From kgyrtk...@apache.org
Subject [15/18] hive git commit: HIVE-18108: in case basic stats are missing; rowcount estimation depends on the selected columns size (Zoltan Haindrich, reviewed by Ashutosh Chauhan)
Date Fri, 05 Jan 2018 10:49:04 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
index 010f05d..8801396 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_12.q.out
@@ -136,7 +136,7 @@ POSTHOOK: type: LOAD
 POSTHOOK: Output: default@bucket_medium@ds=2008-04-08
 Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-8:MAPRED' is a cross product
 Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-7:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
 PREHOOK: type: QUERY
 POSTHOOK: query: explain extended select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
@@ -166,7 +166,7 @@ STAGE PLANS:
   Stage: Stage-16
     Map Reduce Local Work
       Alias -> Map Local Tables:
-        $hdt$_0:c 
+        $hdt$_1:b 
           Fetch Operator
             limit: -1
             Partition Description:
@@ -177,71 +177,23 @@ STAGE PLANS:
                   partition values:
                     ds 2008-04-08
                   properties:
-                    bucket_count 4
-                    bucket_field_name key
-                    column.name.delimiter ,
-                    columns key,value
-                    columns.comments 
-                    columns.types string:string
-#### A masked pattern was here ####
-                    name default.bucket_big
-                    numFiles 4
-                    numRows 0
-                    partition_columns ds
-                    partition_columns.types string
-                    rawDataSize 0
-                    serialization.ddl struct bucket_big { string key, string value}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 5812
-#### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                
-                    input format: org.apache.hadoop.mapred.TextInputFormat
-                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                    properties:
-                      SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 4
-                      bucket_field_name key
-                      column.name.delimiter ,
-                      columns key,value
-                      columns.comments 
-                      columns.types string:string
-#### A masked pattern was here ####
-                      name default.bucket_big
-                      partition_columns ds
-                      partition_columns.types string
-                      serialization.ddl struct bucket_big { string key, string value}
-                      serialization.format 1
-                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-#### A masked pattern was here ####
-                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_big
-                  name: default.bucket_big
-                Partition
-                  base file name: ds=2008-04-09
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  partition values:
-                    ds 2008-04-09
-                  properties:
-                    bucket_count 4
+                    bucket_count 3
                     bucket_field_name key
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.bucket_big
-                    numFiles 4
+                    name default.bucket_medium
+                    numFiles 3
                     numRows 0
                     partition_columns ds
                     partition_columns.types string
                     rawDataSize 0
-                    serialization.ddl struct bucket_big { string key, string value}
+                    serialization.ddl struct bucket_medium { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 5812
+                    totalSize 170
 #### A masked pattern was here ####
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                 
@@ -249,24 +201,24 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
                       SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 4
+                      bucket_count 3
                       bucket_field_name key
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.bucket_big
+                      name default.bucket_medium
                       partition_columns ds
                       partition_columns.types string
-                      serialization.ddl struct bucket_big { string key, string value}
+                      serialization.ddl struct bucket_medium { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_big
-                  name: default.bucket_big
-        $hdt$_2:b 
+                    name: default.bucket_medium
+                  name: default.bucket_medium
+        $hdt$_2:a 
           Fetch Operator
             limit: -1
             Partition Description:
@@ -277,23 +229,23 @@ STAGE PLANS:
                   partition values:
                     ds 2008-04-08
                   properties:
-                    bucket_count 3
+                    bucket_count 2
                     bucket_field_name key
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.bucket_medium
-                    numFiles 3
+                    name default.bucket_small
+                    numFiles 2
                     numRows 0
                     partition_columns ds
                     partition_columns.types string
                     rawDataSize 0
-                    serialization.ddl struct bucket_medium { string key, string value}
+                    serialization.ddl struct bucket_small { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 170
+                    totalSize 114
 #### A masked pattern was here ####
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                 
@@ -301,56 +253,56 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
                       SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 3
+                      bucket_count 2
                       bucket_field_name key
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.bucket_medium
+                      name default.bucket_small
                       partition_columns ds
                       partition_columns.types string
-                      serialization.ddl struct bucket_medium { string key, string value}
+                      serialization.ddl struct bucket_small { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_medium
-                  name: default.bucket_medium
+                    name: default.bucket_small
+                  name: default.bucket_small
       Alias -> Map Local Operator Tree:
-        $hdt$_0:c 
+        $hdt$_1:b 
           TableScan
-            alias: c
-            Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+            alias: b
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 0
-        $hdt$_2:b 
+        $hdt$_2:a 
           TableScan
-            alias: b
-            Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+            alias: a
+            Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -362,17 +314,17 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: a
-            Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+            alias: c
+            Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -382,7 +334,7 @@ STAGE PLANS:
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 0
-                  Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
                     GlobalTableId: 0
@@ -603,7 +555,8 @@ STAGE PLANS:
               name: default.bucket_small
             name: default.bucket_small
       Truncated Path -> Alias:
-        /bucket_small/ds=2008-04-08 [$hdt$_1:a]
+        /bucket_big/ds=2008-04-08 [$hdt$_0:c]
+        /bucket_big/ds=2008-04-09 [$hdt$_0:c]
 
   Stage: Stage-9
     Conditional Operator
@@ -667,10 +620,10 @@ STAGE PLANS:
         $hdt$_3:d 
           TableScan
             alias: d
-            Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Select Operator
-              Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               HashTable Sink Operator
                 keys:
                   0 
@@ -689,12 +642,12 @@ STAGE PLANS:
                 0 
                 1 
               Position of Big Table: 0
-              Statistics: Num rows: 255 Data size: 459327 Basic stats: PARTIAL Column stats: NONE
+              Statistics: Num rows: 1584 Data size: 1666368 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
                 aggregations: count()
                 mode: hash
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 File Output Operator
                   compressed: false
                   GlobalTableId: 0
@@ -800,7 +753,7 @@ STAGE PLANS:
             Reduce Output Operator
               null sort order: 
               sort order: 
-              Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+              Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
               tag: -1
               value expressions: _col0 (type: bigint)
               auto parallelism: false
@@ -837,13 +790,13 @@ STAGE PLANS:
           aggregations: count(VALUE._col0)
           mode: mergepartial
           outputColumnNames: _col0
-          Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+          Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
 #### A masked pattern was here ####
             NumFilesPerFileSink: 1
-            Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
             table:
                 input format: org.apache.hadoop.mapred.SequenceFileInputFormat
@@ -882,10 +835,10 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: d
-            Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Select Operator
-              Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Map Join Operator
                 condition map:
                      Inner Join 0 to 1
@@ -893,12 +846,12 @@ STAGE PLANS:
                   0 
                   1 
                 Position of Big Table: 1
-                Statistics: Num rows: 255 Data size: 459327 Basic stats: PARTIAL Column stats: NONE
+                Statistics: Num rows: 1584 Data size: 1666368 Basic stats: COMPLETE Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   mode: hash
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
                     GlobalTableId: 0
@@ -1004,19 +957,19 @@ STAGE PLANS:
             Reduce Output Operator
               null sort order: 
               sort order: 
-              Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE
               tag: 0
               auto parallelism: false
           TableScan
             alias: d
-            Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Select Operator
-              Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Reduce Output Operator
                 null sort order: 
                 sort order: 
-                Statistics: Num rows: 1 Data size: 1700 Basic stats: PARTIAL Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                 tag: 1
                 auto parallelism: false
       Path -> Alias:
@@ -1104,12 +1057,12 @@ STAGE PLANS:
           keys:
             0 
             1 
-          Statistics: Num rows: 255 Data size: 459327 Basic stats: PARTIAL Column stats: NONE
+          Statistics: Num rows: 1584 Data size: 1666368 Basic stats: COMPLETE Column stats: NONE
           Group By Operator
             aggregations: count()
             mode: hash
             outputColumnNames: _col0
-            Statistics: Num rows: 1 Data size: 8 Basic stats: PARTIAL Column stats: NONE
+            Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
             File Output Operator
               compressed: false
               GlobalTableId: 0
@@ -1232,7 +1185,7 @@ STAGE PLANS:
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     name: default.bucket_big
                   name: default.bucket_big
-        $hdt$_1:a 
+        $hdt$_2:a 
           Fetch Operator
             limit: -1
             Partition Description:
@@ -1288,35 +1241,35 @@ STAGE PLANS:
         $hdt$_0:c 
           TableScan
             alias: c
-            Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 1
-        $hdt$_1:a 
+        $hdt$_2:a 
           TableScan
             alias: a
-            Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -1329,16 +1282,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1348,7 +1301,7 @@ STAGE PLANS:
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 1
-                  Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
                     GlobalTableId: 0
@@ -1569,12 +1522,12 @@ STAGE PLANS:
               name: default.bucket_small
             name: default.bucket_small
       Truncated Path -> Alias:
-        /bucket_medium/ds=2008-04-08 [$hdt$_2:b]
+        /bucket_medium/ds=2008-04-08 [$hdt$_1:b]
 
   Stage: Stage-18
     Map Reduce Local Work
       Alias -> Map Local Tables:
-        $hdt$_1:a 
+        $hdt$_0:c 
           Fetch Operator
             limit: -1
             Partition Description:
@@ -1585,23 +1538,23 @@ STAGE PLANS:
                   partition values:
                     ds 2008-04-08
                   properties:
-                    bucket_count 2
+                    bucket_count 4
                     bucket_field_name key
                     column.name.delimiter ,
                     columns key,value
                     columns.comments 
                     columns.types string:string
 #### A masked pattern was here ####
-                    name default.bucket_small
-                    numFiles 2
+                    name default.bucket_big
+                    numFiles 4
                     numRows 0
                     partition_columns ds
                     partition_columns.types string
                     rawDataSize 0
-                    serialization.ddl struct bucket_small { string key, string value}
+                    serialization.ddl struct bucket_big { string key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    totalSize 114
+                    totalSize 5812
 #### A masked pattern was here ####
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                 
@@ -1609,24 +1562,72 @@ STAGE PLANS:
                     output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                     properties:
                       SORTBUCKETCOLSPREFIX TRUE
-                      bucket_count 2
+                      bucket_count 4
                       bucket_field_name key
                       column.name.delimiter ,
                       columns key,value
                       columns.comments 
                       columns.types string:string
 #### A masked pattern was here ####
-                      name default.bucket_small
+                      name default.bucket_big
                       partition_columns ds
                       partition_columns.types string
-                      serialization.ddl struct bucket_small { string key, string value}
+                      serialization.ddl struct bucket_big { string key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.bucket_small
-                  name: default.bucket_small
-        $hdt$_2:b 
+                    name: default.bucket_big
+                  name: default.bucket_big
+                Partition
+                  base file name: ds=2008-04-09
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  partition values:
+                    ds 2008-04-09
+                  properties:
+                    bucket_count 4
+                    bucket_field_name key
+                    column.name.delimiter ,
+                    columns key,value
+                    columns.comments 
+                    columns.types string:string
+#### A masked pattern was here ####
+                    name default.bucket_big
+                    numFiles 4
+                    numRows 0
+                    partition_columns ds
+                    partition_columns.types string
+                    rawDataSize 0
+                    serialization.ddl struct bucket_big { string key, string value}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    totalSize 5812
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                
+                    input format: org.apache.hadoop.mapred.TextInputFormat
+                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                    properties:
+                      SORTBUCKETCOLSPREFIX TRUE
+                      bucket_count 4
+                      bucket_field_name key
+                      column.name.delimiter ,
+                      columns key,value
+                      columns.comments 
+                      columns.types string:string
+#### A masked pattern was here ####
+                      name default.bucket_big
+                      partition_columns ds
+                      partition_columns.types string
+                      serialization.ddl struct bucket_big { string key, string value}
+                      serialization.format 1
+                      serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    name: default.bucket_big
+                  name: default.bucket_big
+        $hdt$_1:b 
           Fetch Operator
             limit: -1
             Partition Description:
@@ -1679,38 +1680,38 @@ STAGE PLANS:
                     name: default.bucket_medium
                   name: default.bucket_medium
       Alias -> Map Local Operator Tree:
-        $hdt$_1:a 
+        $hdt$_0:c 
           TableScan
-            alias: a
-            Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+            alias: c
+            Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 2
-        $hdt$_2:b 
+        $hdt$_1:b 
           TableScan
             alias: b
-            Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -1722,17 +1723,17 @@ STAGE PLANS:
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: c
-            Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+            alias: a
+            Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1742,7 +1743,7 @@ STAGE PLANS:
                     1 _col0 (type: string)
                     2 _col0 (type: string)
                   Position of Big Table: 2
-                  Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
                     GlobalTableId: 0
@@ -1963,70 +1964,69 @@ STAGE PLANS:
               name: default.bucket_small
             name: default.bucket_small
       Truncated Path -> Alias:
-        /bucket_big/ds=2008-04-08 [$hdt$_0:c]
-        /bucket_big/ds=2008-04-09 [$hdt$_0:c]
+        /bucket_small/ds=2008-04-08 [$hdt$_2:a]
 
   Stage: Stage-1
     Map Reduce
       Map Operator Tree:
           TableScan
-            alias: a
-            Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+            alias: c
+            Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string)
                   null sort order: a
                   sort order: +
                   Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 1 Data size: 114 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 240 Data size: 116240 Basic stats: COMPLETE Column stats: NONE
                   tag: 0
                   auto parallelism: false
           TableScan
             alias: b
-            Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string)
                   null sort order: a
                   sort order: +
                   Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 1 Data size: 170 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 3 Data size: 1700 Basic stats: COMPLETE Column stats: NONE
                   tag: 1
                   auto parallelism: false
           TableScan
-            alias: c
-            Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+            alias: a
+            Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string)
                   null sort order: a
                   sort order: +
                   Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 116 Data size: 11624 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 1140 Basic stats: COMPLETE Column stats: NONE
                   tag: 2
                   auto parallelism: false
       Path -> Alias:
@@ -2231,8 +2231,8 @@ STAGE PLANS:
       Truncated Path -> Alias:
         /bucket_big/ds=2008-04-08 [$hdt$_0:c]
         /bucket_big/ds=2008-04-09 [$hdt$_0:c]
-        /bucket_medium/ds=2008-04-08 [$hdt$_2:b]
-        /bucket_small/ds=2008-04-08 [$hdt$_1:a]
+        /bucket_medium/ds=2008-04-08 [$hdt$_1:b]
+        /bucket_small/ds=2008-04-08 [$hdt$_2:a]
       Needs Tagging: true
       Reduce Operator Tree:
         Join Operator
@@ -2243,7 +2243,7 @@ STAGE PLANS:
             0 _col0 (type: string)
             1 _col0 (type: string)
             2 _col0 (type: string)
-          Statistics: Num rows: 255 Data size: 25572 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 528 Data size: 255728 Basic stats: COMPLETE Column stats: NONE
           File Output Operator
             compressed: false
             GlobalTableId: 0
@@ -2271,7 +2271,7 @@ STAGE PLANS:
 
 Warning: Map Join MAPJOIN[32][bigTable=?] in task 'Stage-8:MAPRED' is a cross product
 Warning: Map Join MAPJOIN[31][bigTable=?] in task 'Stage-7:MAPRED' is a cross product
-Warning: Shuffle Join JOIN[17][tables = [$hdt$_1, $hdt$_2, $hdt$_0, $hdt$_3]] in Stage 'Stage-2:MAPRED' is a cross product
+Warning: Shuffle Join JOIN[17][tables = [$hdt$_0, $hdt$_1, $hdt$_2, $hdt$_3]] in Stage 'Stage-2:MAPRED' is a cross product
 PREHOOK: query: select count(*) FROM bucket_small a JOIN bucket_medium b ON a.key = b.key JOIN bucket_big c ON c.key = b.key JOIN bucket_medium d ON c.key = b.key
 PREHOOK: type: QUERY
 PREHOOK: Input: default@bucket_big

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
index 4c31a69..ed85c3b 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_2.q.out
@@ -95,16 +95,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -353,16 +353,16 @@ STAGE PLANS:
         $hdt$_1:b 
           TableScan
             alias: b
-            Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -374,16 +374,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -690,16 +690,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -711,16 +711,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 2 Data size: 226 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 4 Data size: 2260 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -924,16 +924,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out
index caa3017..fe46bb5 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_3.q.out
@@ -95,16 +95,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -242,16 +242,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -497,16 +497,16 @@ STAGE PLANS:
         $hdt$_1:b 
           TableScan
             alias: b
-            Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -518,16 +518,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -784,16 +784,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -805,16 +805,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 4 Data size: 2280 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1018,16 +1018,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 58 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 120 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
index 21a1175..91f2f13 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_4.q.out
@@ -111,16 +111,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -258,16 +258,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -513,16 +513,16 @@ STAGE PLANS:
         $hdt$_1:b 
           TableScan
             alias: b
-            Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -534,16 +534,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -800,16 +800,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -821,16 +821,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1034,16 +1034,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 27 Data size: 2750 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 56 Data size: 27500 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
index a4cdbec..c099242 100644
--- a/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
+++ b/ql/src/test/results/clientpositive/auto_sortmerge_join_7.q.out
@@ -128,16 +128,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -327,16 +327,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -634,16 +634,16 @@ STAGE PLANS:
         $hdt$_1:b 
           TableScan
             alias: b
-            Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -655,16 +655,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1019,16 +1019,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -1040,16 +1040,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 4 Data size: 452 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 8 Data size: 4520 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -1302,16 +1302,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: a
-            Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             Filter Operator
               isSamplingPred: false
               predicate: key is not null (type: boolean)
-              Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 54 Data size: 5500 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 112 Data size: 55000 Basic stats: COMPLETE Column stats: NONE
                 Sorted Merge Bucket Map Join Operator
                   condition map:
                        Inner Join 0 to 1

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out b/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out
index 7626a73..b891507 100644
--- a/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out
+++ b/ql/src/test/results/clientpositive/avro_schema_evolution_native.q.out
@@ -248,11 +248,11 @@ STAGE PLANS:
       Processor Tree:
         TableScan
           alias: episodes_partitioned
-          Statistics: Num rows: 3 Data size: 889 Basic stats: COMPLETE Column stats: NONE
+          Statistics: Num rows: 3 Data size: 8890 Basic stats: COMPLETE Column stats: NONE
           Select Operator
             expressions: title (type: string), air_date (type: string), doctor (type: int), value (type: int), doctor_pt (type: int)
             outputColumnNames: _col0, _col1, _col2, _col3, _col4
-            Statistics: Num rows: 3 Data size: 889 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 3 Data size: 8890 Basic stats: COMPLETE Column stats: NONE
             ListSink
 
 PREHOOK: query: SELECT * FROM episodes_partitioned WHERE doctor_pt > 6
@@ -337,14 +337,14 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: episodes_partitioned
-            Statistics: Num rows: 3 Data size: 889 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 3 Data size: 8890 Basic stats: COMPLETE Column stats: NONE
             Select Operator
               expressions: title (type: string), air_date (type: string), doctor (type: int), value (type: int), doctor_pt (type: int)
               outputColumnNames: _col0, _col1, _col2, _col3, _col4
-              Statistics: Num rows: 3 Data size: 889 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 3 Data size: 8890 Basic stats: COMPLETE Column stats: NONE
               File Output Operator
                 compressed: false
-                Statistics: Num rows: 3 Data size: 889 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 3 Data size: 8890 Basic stats: COMPLETE Column stats: NONE
                 table:
                     input format: org.apache.hadoop.mapred.SequenceFileInputFormat
                     output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out
index 379906e..6f1ba4f 100644
--- a/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out
+++ b/ql/src/test/results/clientpositive/beeline/smb_mapjoin_10.q.out
@@ -78,10 +78,10 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 13 Data size: 4140 Basic stats: COMPLETE Column stats: NONE
             Filter Operator
               predicate: (pageid is not null and postid is not null and type is not null and userid is not null) (type: boolean)
-              Statistics: Num rows: 3 Data size: 414 Basic stats: COMPLETE Column stats: NONE
+              Statistics: Num rows: 13 Data size: 4140 Basic stats: COMPLETE Column stats: NONE
               Sorted Merge Bucket Map Join Operator
                 condition map:
                      Inner Join 0 to 1

http://git-wip-us.apache.org/repos/asf/hive/blob/d0fa7d55/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out
index 3545f86..35f05d5 100644
--- a/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out
+++ b/ql/src/test/results/clientpositive/bucket_map_join_spark1.q.out
@@ -182,16 +182,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             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: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: int), value (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: int)
@@ -203,16 +203,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             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: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: int), value (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -221,17 +221,17 @@ STAGE PLANS:
                     1 _col0 (type: int)
                   outputColumnNames: _col0, _col1, _col3
                   Position of Big Table: 1
-                  Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string)
                     outputColumnNames: _col0, _col1, _col2
-                    Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 163 Data size: 63932 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: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                       table:
                           input format: org.apache.hadoop.mapred.TextInputFormat
@@ -261,7 +261,7 @@ STAGE PLANS:
                     Select Operator
                       expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                       outputColumnNames: key, value1, value2
-                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll')
                         mode: hash
@@ -619,16 +619,16 @@ STAGE PLANS:
         $hdt$_0:a 
           TableScan
             alias: a
-            Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             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: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: int), value (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 HashTable Sink Operator
                   keys:
                     0 _col0 (type: int)
@@ -640,16 +640,16 @@ STAGE PLANS:
       Map Operator Tree:
           TableScan
             alias: b
-            Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+            Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
             GatherStats: false
             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: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
               Select Operator
                 expressions: key (type: int), value (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 149 Data size: 58120 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -658,17 +658,17 @@ STAGE PLANS:
                     1 _col0 (type: int)
                   outputColumnNames: _col0, _col1, _col3
                   Position of Big Table: 1
-                  Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
                   Select Operator
                     expressions: UDFToString(_col0) (type: string), _col1 (type: string), _col3 (type: string)
                     outputColumnNames: _col0, _col1, _col2
-                    Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 163 Data size: 63932 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: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
 #### A masked pattern was here ####
                       table:
                           input format: org.apache.hadoop.mapred.TextInputFormat
@@ -698,7 +698,7 @@ STAGE PLANS:
                     Select Operator
                       expressions: _col0 (type: string), _col1 (type: string), _col2 (type: string)
                       outputColumnNames: key, value1, value2
-                      Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 163 Data size: 63932 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: compute_stats(key, 'hll'), compute_stats(value1, 'hll'), compute_stats(value2, 'hll')
                         mode: hash


Mime
View raw message