hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jpull...@apache.org
Subject [09/51] [partial] hive git commit: HIVE-11110: Reorder applyPreJoinOrderingTransforms, add NotNULL/FilterMerge rules, improve Filter selectivity estimation (Laljo John Pullokkaran reviewed by Jesus Camacho Rodriguez, Ashutosh Chauhan
Date Tue, 15 Dec 2015 00:39:17 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join2.q.out b/ql/src/test/results/clientpositive/spark/auto_join2.q.out
index 2424cca..10b12a9 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join2.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join2.q.out
@@ -15,14 +15,13 @@ FROM src src1 JOIN src src2 ON (src1.key = src2.key) JOIN src src3 ON (src1.key
 INSERT OVERWRITE TABLE dest_j2 SELECT src1.key, src3.value
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-4 is a root stage
-  Stage-3 depends on stages: Stage-4
+  Stage-3 is a root stage
   Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
   Stage-2 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-4
+  Stage: Stage-3
     Spark
 #### A masked pattern was here ####
       Vertices:
@@ -33,19 +32,37 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
                           1 _col0 (type: string)
             Local Work:
               Map Reduce Local Work
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: src1
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                    Select Operator
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                      Spark HashTable Sink Operator
+                        keys:
+                          0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
+                          1 UDFToDouble(_col0) (type: double)
+            Local Work:
+              Map Reduce Local Work
 
-  Stage: Stage-3
+  Stage: Stage-1
     Spark
 #### A masked pattern was here ####
       Vertices:
@@ -56,11 +73,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -70,55 +87,32 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Filter Operator
                           predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                          Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
-                          Spark HashTable Sink Operator
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                          Map Join Operator
+                            condition map:
+                                 Inner Join 0 to 1
                             keys:
                               0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
                               1 UDFToDouble(_col0) (type: double)
-            Local Work:
-              Map Reduce Local Work
-
-  Stage: Stage-1
-    Spark
-#### A masked pattern was here ####
-      Vertices:
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: src1
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
-                          1 UDFToDouble(_col0) (type: double)
-                        outputColumnNames: _col0, _col3
-                        input vertices:
-                          0 Map 1
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                        Select Operator
-                          expressions: UDFToInteger(_col0) (type: int), _col3 (type: string)
-                          outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                                name: default.dest_j2
+                            outputColumnNames: _col0, _col3
+                            input vertices:
+                              1 Map 3
+                            Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+                            Select Operator
+                              expressions: UDFToInteger(_col0) (type: int), _col3 (type: string)
+                              outputColumnNames: _col0, _col1
+                              Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+                              File Output Operator
+                                compressed: false
+                                Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
+                                table:
+                                    input format: org.apache.hadoop.mapred.TextInputFormat
+                                    output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                    serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                    name: default.dest_j2
             Local Work:
               Map Reduce Local Work
 

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join22.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join22.q.out b/ql/src/test/results/clientpositive/spark/auto_join22.q.out
index 29a9093..6e8f0f9 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join22.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join22.q.out
@@ -21,11 +21,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -39,11 +39,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -64,11 +64,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -78,7 +78,7 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1
                         input vertices:
                           1 Map 3
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Map Join Operator
                           condition map:
                                Inner Join 0 to 1
@@ -88,11 +88,11 @@ STAGE PLANS:
                           outputColumnNames: _col1
                           input vertices:
                             1 Map 4
-                          Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: hash(_col1) (type: int)
                             outputColumnNames: _col0
-                            Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                             Group By Operator
                               aggregations: sum(_col0)
                               mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join24.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join24.q.out b/ql/src/test/results/clientpositive/spark/auto_join24.q.out
index 9bc9b93..269b251 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join24.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join24.q.out
@@ -41,11 +41,11 @@ STAGE PLANS:
                   Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -66,11 +66,11 @@ STAGE PLANS:
                   Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), cnt (type: int)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 309 Data size: 1482 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -80,7 +80,7 @@ STAGE PLANS:
                         outputColumnNames: _col1
                         input vertices:
                           1 Map 3
-                        Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 339 Data size: 1630 Basic stats: COMPLETE Column stats: NONE
                         Group By Operator
                           aggregations: sum(_col1)
                           mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join26.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join26.q.out b/ql/src/test/results/clientpositive/spark/auto_join26.q.out
index 71f4338..d750586 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join26.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join26.q.out
@@ -36,11 +36,11 @@ STAGE PLANS:
                   Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -61,11 +61,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -75,18 +75,18 @@ STAGE PLANS:
                         outputColumnNames: _col0
                         input vertices:
                           0 Map 1
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Group By Operator
                           aggregations: count(1)
                           keys: _col0 (type: string)
                           mode: hash
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                           Reduce Output Operator
                             key expressions: _col0 (type: string)
                             sort order: +
                             Map-reduce partition columns: _col0 (type: string)
-                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                             value expressions: _col1 (type: bigint)
             Local Work:
               Map Reduce Local Work
@@ -97,14 +97,14 @@ STAGE PLANS:
                 keys: KEY._col0 (type: string)
                 mode: mergepartial
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: UDFToInteger(_col0) (type: int), UDFToInteger(_col1) (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 137 Data size: 1455 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join3.q.out b/ql/src/test/results/clientpositive/spark/auto_join3.q.out
index 54e24f3..0347f2c 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join3.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join3.q.out
@@ -32,11 +32,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -51,11 +51,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -75,11 +75,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -92,14 +92,14 @@ STAGE PLANS:
                         input vertices:
                           1 Map 2
                           2 Map 3
-                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: UDFToInteger(_col0) (type: int), _col3 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join30.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join30.q.out b/ql/src/test/results/clientpositive/spark/auto_join30.q.out
index 4b67445..5cb05ab 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join30.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join30.q.out
@@ -33,15 +33,15 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: string)
                         sort order: +
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
         Reducer 5 
             Local Work:
@@ -50,7 +50,7 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                 Spark HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -70,15 +70,15 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Local Work:
               Map Reduce Local Work
@@ -86,7 +86,7 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -96,7 +96,7 @@ STAGE PLANS:
                   outputColumnNames: _col2, _col3
                   input vertices:
                     1 Reducer 5
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: sum(hash(_col2,_col3))
                     mode: hash
@@ -472,15 +472,15 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: string)
                         sort order: +
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
         Reducer 5 
             Local Work:
@@ -489,7 +489,7 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: string), KEY.reducesinkkey0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                 Spark HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -502,7 +502,7 @@ STAGE PLANS:
               Select Operator
                 expressions: VALUE._col0 (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                 Spark HashTable Sink Operator
                   keys:
                     0 _col0 (type: string)
@@ -523,15 +523,15 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Local Work:
               Map Reduce Local Work
@@ -539,7 +539,7 @@ STAGE PLANS:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string)
                 outputColumnNames: _col0
-                Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                 Map Join Operator
                   condition map:
                        Inner Join 0 to 1
@@ -552,7 +552,7 @@ STAGE PLANS:
                   input vertices:
                     1 Reducer 5
                     2 Reducer 7
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 1100 Data size: 11686 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: sum(hash(_col2,_col3))
                     mode: hash

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join8.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join8.q.out b/ql/src/test/results/clientpositive/spark/auto_join8.q.out
index 21374ff..7c4ed3a 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join8.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join8.q.out
@@ -76,12 +76,12 @@ STAGE PLANS:
                   alias: src1
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) and key is not null) (type: boolean)
-                    Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+                    predicate: ((UDFToDouble(key) > 10.0) and (UDFToDouble(key) < 20.0)) (type: boolean)
+                    Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 28 Data size: 297 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Left Outer Join0 to 1
@@ -91,17 +91,17 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1, _col2, _col3
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 30 Data size: 326 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
                         Filter Operator
                           predicate: _col2 is null (type: boolean)
-                          Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
                           Select Operator
                             expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), null (type: int), _col3 (type: string)
                             outputColumnNames: _col0, _col1, _col2, _col3
-                            Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
                             File Output Operator
                               compressed: false
-                              Statistics: Num rows: 15 Data size: 163 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 30 Data size: 321 Basic stats: COMPLETE Column stats: NONE
                               table:
                                   input format: org.apache.hadoop.mapred.TextInputFormat
                                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join9.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join9.q.out b/ql/src/test/results/clientpositive/spark/auto_join9.q.out
index 568891b..b2ed51c 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join9.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join9.q.out
@@ -32,11 +32,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -55,11 +55,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -69,14 +69,14 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col4
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Select Operator
                           expressions: UDFToInteger(_col0) (type: int), _col4 (type: string)
                           outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                           File Output Operator
                             compressed: false
-                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
                                 output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
index 6466c39..250c1ef 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_reordering_values.q.out
@@ -471,16 +471,16 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: userid is not null (type: boolean)
-                    Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: userid (type: int)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: int)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: int)
-                        Statistics: Num rows: 50 Data size: 144 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 100 Data size: 288 Basic stats: COMPLETE Column stats: NONE
                         tag: 1
                         auto parallelism: false
             Path -> Alias:
@@ -599,11 +599,11 @@ STAGE PLANS:
                   0 _col3 (type: int)
                   1 _col0 (type: int)
                 outputColumnNames: _col4, _col5
-                Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col4 (type: string), _col5 (type: int)
                   outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 55 Data size: 158 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 110 Data size: 316 Basic stats: COMPLETE Column stats: NONE
                   Limit
                     Number of rows: 5
                     Statistics: Num rows: 5 Data size: 10 Basic stats: COMPLETE Column stats: NONE

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out
index 71fe68e..e826380 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_stats.q.out
@@ -48,12 +48,12 @@ STAGE PLANS:
                   alias: smalltable
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+                    Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
@@ -74,16 +74,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -91,16 +91,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Local Work:
               Map Reduce Local Work
@@ -112,10 +112,10 @@ STAGE PLANS:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
                   predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                  Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   Map Join Operator
                     condition map:
                          Inner Join 0 to 1
@@ -125,10 +125,10 @@ STAGE PLANS:
                     outputColumnNames: _col0, _col1, _col2
                     input vertices:
                       1 Map 4
-                    Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                     File Output Operator
                       compressed: false
-                      Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                       table:
                           input format: org.apache.hadoop.mapred.TextInputFormat
                           output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -196,12 +196,12 @@ STAGE PLANS:
                   alias: smalltable
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+                    Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
@@ -214,7 +214,7 @@ STAGE PLANS:
                   alias: smalltable2
                   Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
@@ -240,16 +240,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -257,16 +257,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Local Work:
               Map Reduce Local Work
@@ -278,10 +278,10 @@ STAGE PLANS:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Filter Operator
                   predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                  Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   Map Join Operator
                     condition map:
                          Inner Join 0 to 1
@@ -291,10 +291,10 @@ STAGE PLANS:
                     outputColumnNames: _col0, _col1, _col2
                     input vertices:
                       1 Map 4
-                    Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                     Filter Operator
                       predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                      Statistics: Num rows: 76 Data size: 810 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -304,10 +304,10 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1, _col2
                         input vertices:
                           1 Map 5
-                        Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE
                         File Output Operator
                           compressed: false
-                          Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE
                           table:
                               input format: org.apache.hadoop.mapred.TextInputFormat
                               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out
index 7a6bf9b..4062faf 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_stats2.q.out
@@ -41,11 +41,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -58,7 +58,7 @@ STAGE PLANS:
                   alias: smalltable
                   Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
@@ -82,11 +82,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -96,10 +96,10 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Filter Operator
                           predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                          Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                           Map Join Operator
                             condition map:
                                  Inner Join 0 to 1
@@ -109,10 +109,10 @@ STAGE PLANS:
                             outputColumnNames: _col0, _col1, _col2
                             input vertices:
                               1 Map 3
-                            Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                             File Output Operator
                               compressed: false
-                              Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                               table:
                                   input format: org.apache.hadoop.mapred.TextInputFormat
                                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -183,11 +183,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: string)
@@ -200,12 +200,12 @@ STAGE PLANS:
                   alias: smalltable
                   Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
-                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
+                    Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 (UDFToDouble(_col0) + UDFToDouble(_col1)) (type: double)
@@ -218,7 +218,7 @@ STAGE PLANS:
                   alias: smalltable2
                   Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: UDFToDouble(key) is not null (type: boolean)
+                    predicate: (key is not null and UDFToDouble(key) is not null) (type: boolean)
                     Statistics: Num rows: 1 Data size: 30 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
@@ -242,11 +242,11 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -256,10 +256,10 @@ STAGE PLANS:
                         outputColumnNames: _col0, _col1
                         input vertices:
                           1 Map 2
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                         Filter Operator
                           predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                          Statistics: Num rows: 138 Data size: 1465 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                           Map Join Operator
                             condition map:
                                  Inner Join 0 to 1
@@ -269,10 +269,10 @@ STAGE PLANS:
                             outputColumnNames: _col0, _col1, _col2
                             input vertices:
                               1 Map 3
-                            Statistics: Num rows: 151 Data size: 1611 Basic stats: COMPLETE Column stats: NONE
+                            Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                             Filter Operator
                               predicate: (UDFToDouble(_col0) + UDFToDouble(_col1)) is not null (type: boolean)
-                              Statistics: Num rows: 76 Data size: 810 Basic stats: COMPLETE Column stats: NONE
+                              Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                               Map Join Operator
                                 condition map:
                                      Inner Join 0 to 1
@@ -282,10 +282,10 @@ STAGE PLANS:
                                 outputColumnNames: _col0, _col1, _col2
                                 input vertices:
                                   1 Map 4
-                                Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE
+                                Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE
                                 File Output Operator
                                   compressed: false
-                                  Statistics: Num rows: 83 Data size: 891 Basic stats: COMPLETE Column stats: NONE
+                                  Statistics: Num rows: 665 Data size: 7069 Basic stats: COMPLETE Column stats: NONE
                                   table:
                                       input format: org.apache.hadoop.mapred.TextInputFormat
                                       output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
index 932fdcc..659c305 100644
--- a/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
+++ b/ql/src/test/results/clientpositive/spark/auto_join_without_localtask.q.out
@@ -23,16 +23,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 4 
             Map Operator Tree:
@@ -41,16 +41,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -60,18 +60,18 @@ STAGE PLANS:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string), _col1 (type: string)
                   sort order: ++
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   TopN Hash Memory Usage: 0.1
         Reducer 3 
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 40
                   Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE
@@ -163,17 +163,17 @@ STAGE PLANS:
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: (value is not null and key is not null) (type: boolean)
-                    Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (key is not null and value is not null) (type: boolean)
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col1 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col1 (type: string)
-                        Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col0 (type: string)
         Map 5 
             Map Operator Tree:
@@ -182,16 +182,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: value (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Map 6 
             Map Operator Tree:
                 TableScan
@@ -199,16 +199,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -218,12 +218,12 @@ STAGE PLANS:
                   0 _col1 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string)
                   sort order: +
                   Map-reduce partition columns: _col0 (type: string)
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   value expressions: _col1 (type: string)
         Reducer 3 
             Reduce Operator Tree:
@@ -234,18 +234,18 @@ STAGE PLANS:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string), _col1 (type: string)
                   sort order: ++
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                   TopN Hash Memory Usage: 0.1
         Reducer 4 
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 605 Data size: 6427 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 40
                   Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE
@@ -337,17 +337,17 @@ STAGE PLANS:
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((UDFToDouble(key) > 100.0) and value is not null) (type: boolean)
-                    Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                    predicate: (((UDFToDouble(key) > 100.0) and value is not null) and key is not null) (type: boolean)
+                    Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 166 Data size: 1763 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: 83 Data size: 881 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
                         value expressions: _col1 (type: string)
         Map 5 
             Map Operator Tree:
@@ -373,16 +373,16 @@ STAGE PLANS:
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: value (type: string)
                       outputColumnNames: _col0
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -408,18 +408,18 @@ STAGE PLANS:
                   0 _col1 (type: string)
                   1 _col0 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Reduce Output Operator
                   key expressions: _col0 (type: string), _col1 (type: string)
                   sort order: ++
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                   TopN Hash Memory Usage: 0.1
         Reducer 4 
             Reduce Operator Tree:
               Select Operator
                 expressions: KEY.reducesinkkey0 (type: string), KEY.reducesinkkey1 (type: string)
                 outputColumnNames: _col0, _col1
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
                 Limit
                   Number of rows: 40
                   Statistics: Num rows: 40 Data size: 400 Basic stats: COMPLETE Column stats: NONE


Mime
View raw message