[16/37] hive git commit: HIVE-18149: Stats: rownum estimation from datasize underestimates in most cases (Zoltan Haindrich, reviewed by Ashutosh Chauhan)

kgyrtkirk Wed, 20 Dec 2017 02:40:54 -0800

http://git-wip-us.apache.org/repos/asf/hive/blob/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
index 1d4d0bc..1d91ed9 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt17.q.out
@@ -56,73 +56,73 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
@@ -130,10 +130,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -144,10 +144,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -251,80 +251,80 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') and (val = '12')) or (key = 
'2')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') and (val = '12')) or (key = 
'2')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') or (val <> '12')) and (key <> 
'2')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') or (val <> '12')) and (key <> 
'2')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -335,10 +335,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 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/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out
index 7d459e8..d7eac4b 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt18.q.out
@@ -89,19 +89,19 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: UDFToDouble(_col0) (type: double)
                         sort order: +
                         Map-reduce partition columns: UDFToDouble(_col0) 
(type: double)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string), _col1 (type: 
string)
         Reducer 2 
             Reduce Operator Tree:

http://git-wip-us.apache.org/repos/asf/hive/blob/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
index 5e9b581..1a9fbe5 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt19.q.out
@@ -56,73 +56,73 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
@@ -130,10 +130,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -144,10 +144,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 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/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out
index 4b5fdd6..fb4ce34 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt2.q.out
@@ -56,80 +56,80 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -140,10 +140,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -192,80 +192,80 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Left Outer Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -276,10 +276,10 @@ STAGE PLANS:
                 condition map:
                      Left Outer Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -333,88 +333,88 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 7 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) and key is not null and val is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   keys: _col0 (type: string)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string)
                     sort order: +
                     Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 2 Data size: 66 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2 Data size: 660 Basic stats: 
COMPLETE Column stats: NONE
                     value expressions: _col1 (type: bigint)
         Reducer 3 
             Reduce Operator Tree:
@@ -423,10 +423,10 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -437,18 +437,18 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   keys: _col0 (type: string)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string)
                     sort order: +
                     Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 2 Data size: 66 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2 Data size: 660 Basic stats: 
COMPLETE Column stats: NONE
                     value expressions: _col1 (type: bigint)
 
   Stage: Stage-0
@@ -492,88 +492,88 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '7')) or (key = '3')) 
or (key = '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 5 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Map 7 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '7')) and (key <> 
'3')) and (key <> '8')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string), _col1 (type: 
string)
                         sort order: ++
                         Map-reduce partition columns: _col0 (type: string), 
_col1 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Left Outer Join 0 to 1
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   keys: _col0 (type: string)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string)
                     sort order: +
                     Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 2 Data size: 66 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2 Data size: 660 Basic stats: 
COMPLETE Column stats: NONE
                     value expressions: _col1 (type: bigint)
         Reducer 3 
             Reduce Operator Tree:
@@ -582,10 +582,10 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -596,18 +596,18 @@ STAGE PLANS:
                 condition map:
                      Left Outer Join 0 to 1
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 Group By Operator
                   aggregations: count()
                   keys: _col0 (type: string)
                   mode: hash
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   Reduce Output Operator
                     key expressions: _col0 (type: string)
                     sort order: +
                     Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 2 Data size: 66 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 2 Data size: 660 Basic stats: 
COMPLETE Column stats: NONE
                     value expressions: _col1 (type: bigint)
 
   Stage: Stage-0

http://git-wip-us.apache.org/repos/asf/hive/blob/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out
index 35e219d..9c0d929 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt20.q.out
@@ -56,73 +56,73 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (key = '2') (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((key <> '2') and key is not null) (type: 
boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
@@ -130,10 +130,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -144,10 +144,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 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/e26b9325/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out 
b/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out
index 705b816..3cd65b9 100644
--- a/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out
+++ b/ql/src/test/results/clientpositive/spark/skewjoinopt3.q.out
@@ -56,73 +56,73 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '8')) or (key = '3')) 
and key is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key = '2') or (key = '8')) or (key = '3')) 
and key is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '8')) and (key <> 
'3')) and key is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: ((((key <> '2') and (key <> '8')) and (key <> 
'3')) and key is not null) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
@@ -130,10 +130,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -144,10 +144,10 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -199,73 +199,73 @@ STAGE PLANS:
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((key = '2') or (key = '8')) or (key = '3')) 
(type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 3 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((key = '2') or (key = '8')) or (key = '3')) 
(type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((key <> '2') and (key <> '8')) and (key <> 
'3')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
                   alias: b
-                  Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 1 Data size: 300 Basic stats: COMPLETE 
Column stats: NONE
                   Filter Operator
                     predicate: (((key <> '2') and (key <> '8')) and (key <> 
'3')) (type: boolean)
-                    Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                    Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), val (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                      Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 1 Data size: 30 Basic stats: 
COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1 Data size: 300 Basic stats: 
COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
@@ -273,10 +273,10 @@ STAGE PLANS:
                 condition map:
                      Outer Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
@@ -287,10 +287,10 @@ STAGE PLANS:
                 condition map:
                      Outer Join 0 to 1
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 1 Data size: 33 Basic stats: COMPLETE 
Column stats: NONE
+                Statistics: Num rows: 1 Data size: 330 Basic stats: COMPLETE 
Column stats: NONE
                 File Output Operator
                   compressed: false
-                  Statistics: Num rows: 2 Data size: 66 Basic stats: COMPLETE 
Column stats: NONE
+                  Statistics: Num rows: 2 Data size: 660 Basic stats: COMPLETE 
Column stats: NONE
                   table:
                       input format: 
org.apache.hadoop.mapred.SequenceFileInputFormat
                       output format: 
org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat

[16/37] hive git commit: HIVE-18149: Stats: rownum estimation from datasize underestimates in most cases (Zoltan Haindrich, reviewed by Ashutosh Chauhan)

Reply via email to