hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From jpull...@apache.org
Subject [06/51] [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 00:39:14 GMT
http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out
index 4dd1157..58903d7 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark2.q.out
@@ -172,11 +172,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
@@ -255,11 +255,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -270,18 +270,18 @@ STAGE PLANS:
                         input vertices:
                           1 Map 2
                         Position of Big Table: 0
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column
stats: NONE
                         BucketMapJoin: true
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
                           File Output Operator
                             compressed: false
                             GlobalTableId: 1
 #### A masked pattern was here ####
                             NumFilesPerFileSink: 1
-                            Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -517,11 +517,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
@@ -600,11 +600,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -615,18 +615,18 @@ STAGE PLANS:
                         input vertices:
                           1 Map 2
                         Position of Big Table: 0
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column
stats: NONE
                         BucketMapJoin: true
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
                           File Output Operator
                             compressed: false
                             GlobalTableId: 1
 #### A masked pattern was here ####
                             NumFilesPerFileSink: 1
-                            Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
index 4133fda..60ce126 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark3.q.out
@@ -172,11 +172,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
@@ -255,11 +255,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -270,18 +270,18 @@ STAGE PLANS:
                         input vertices:
                           0 Map 1
                         Position of Big Table: 1
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column
stats: NONE
                         BucketMapJoin: true
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
                           File Output Operator
                             compressed: false
                             GlobalTableId: 1
 #### A masked pattern was here ####
                             NumFilesPerFileSink: 1
-                            Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat
@@ -517,11 +517,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 15 Data size: 1583 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 29 Data size: 3062 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
@@ -595,11 +595,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                    Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 28 Data size: 2958 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 55 Data size: 5812 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -610,17 +610,17 @@ STAGE PLANS:
                         input vertices:
                           0 Map 1
                         Position of Big Table: 1
-                        Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE Column
stats: NONE
+                        Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE Column
stats: NONE
                         Select Operator
                           expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string)
                           outputColumnNames: _col0, _col1, _col2
-                          Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                          Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
                           File Output Operator
                             compressed: false
                             GlobalTableId: 1
 #### A masked pattern was here ####
                             NumFilesPerFileSink: 1
-                            Statistics: Num rows: 30 Data size: 3253 Basic stats: COMPLETE
Column stats: NONE
+                            Statistics: Num rows: 60 Data size: 6393 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                             table:
                                 input format: org.apache.hadoop.mapred.TextInputFormat

http://git-wip-us.apache.org/repos/asf/hive/blob/d8ee05ae/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
index 64fb785..338384f 100644
--- a/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
+++ b/ql/src/test/results/clientpositive/spark/bucket_map_join_spark4.q.out
@@ -147,25 +147,25 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats:
NONE
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
-                        Position of Big Table: 1
+                        Position of Big Table: 0
             Local Work:
               Map Reduce Local Work
                 Bucket Mapjoin Context:
@@ -178,7 +178,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: tbl1
+                  base file name: tbl2
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -190,11 +190,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types int:string
 #### A masked pattern was here ####
-                    name default.tbl1
+                    name default.tbl2
                     numFiles 2
                     numRows 10
                     rawDataSize 70
-                    serialization.ddl struct tbl1 { i32 key, string value}
+                    serialization.ddl struct tbl2 { i32 key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 80
@@ -212,20 +212,20 @@ STAGE PLANS:
                       columns.comments 
                       columns.types int:string
 #### A masked pattern was here ####
-                      name default.tbl1
+                      name default.tbl2
                       numFiles 2
                       numRows 10
                       rawDataSize 70
-                      serialization.ddl struct tbl1 { i32 key, string value}
+                      serialization.ddl struct tbl2 { i32 key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 80
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.tbl1
-                  name: default.tbl1
+                    name: default.tbl2
+                  name: default.tbl2
             Truncated Path -> Alias:
-              /tbl1 [a]
+              /tbl2 [b]
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -235,11 +235,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: value (type: string)
                       outputColumnNames: _col1
-                      Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col1 (type: string)
@@ -305,20 +305,20 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats:
NONE
+                    predicate: (key is not null and value is not null) (type: boolean)
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -327,9 +327,9 @@ STAGE PLANS:
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col3
                         input vertices:
-                          0 Map 1
-                        Position of Big Table: 1
-                        Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column
stats: NONE
+                          1 Map 2
+                        Position of Big Table: 0
+                        Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column
stats: NONE
                         BucketMapJoin: true
                         Map Join Operator
                           condition map:
@@ -341,17 +341,17 @@ STAGE PLANS:
                           input vertices:
                             1 Map 3
                           Position of Big Table: 0
-                          Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column
stats: NONE
                           Select Operator
                             expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string), _col5 (type: string)
                             outputColumnNames: _col0, _col1, _col2, _col3
-                            Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column
stats: NONE
+                            Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE
Column stats: NONE
                             File Output Operator
                               compressed: false
                               GlobalTableId: 0
 #### A masked pattern was here ####
                               NumFilesPerFileSink: 1
-                              Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE
Column stats: NONE
+                              Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                               table:
                                   input format: org.apache.hadoop.mapred.TextInputFormat
@@ -380,7 +380,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: tbl2
+                  base file name: tbl1
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -392,11 +392,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types int:string
 #### A masked pattern was here ####
-                    name default.tbl2
+                    name default.tbl1
                     numFiles 2
                     numRows 10
                     rawDataSize 70
-                    serialization.ddl struct tbl2 { i32 key, string value}
+                    serialization.ddl struct tbl1 { i32 key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 80
@@ -414,20 +414,20 @@ STAGE PLANS:
                       columns.comments 
                       columns.types int:string
 #### A masked pattern was here ####
-                      name default.tbl2
+                      name default.tbl1
                       numFiles 2
                       numRows 10
                       rawDataSize 70
-                      serialization.ddl struct tbl2 { i32 key, string value}
+                      serialization.ddl struct tbl1 { i32 key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 80
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.tbl2
-                  name: default.tbl2
+                    name: default.tbl1
+                  name: default.tbl1
             Truncated Path -> Alias:
-              /tbl2 [b]
+              /tbl1 [a]
 
   Stage: Stage-0
     Fetch Operator
@@ -592,25 +592,25 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
-                  alias: a
+                  alias: b
                   Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: (key is not null and value is not null) (type: boolean)
-                    Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column stats:
NONE
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 3 Data size: 21 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col0 (type: int)
                           1 _col0 (type: int)
-                        Position of Big Table: 1
+                        Position of Big Table: 0
             Local Work:
               Map Reduce Local Work
             Path -> Alias:
@@ -618,7 +618,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: tbl1
+                  base file name: tbl2
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -630,11 +630,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types int:string
 #### A masked pattern was here ####
-                    name default.tbl1
+                    name default.tbl2
                     numFiles 2
                     numRows 10
                     rawDataSize 70
-                    serialization.ddl struct tbl1 { i32 key, string value}
+                    serialization.ddl struct tbl2 { i32 key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 80
@@ -652,20 +652,20 @@ STAGE PLANS:
                       columns.comments 
                       columns.types int:string
 #### A masked pattern was here ####
-                      name default.tbl1
+                      name default.tbl2
                       numFiles 2
                       numRows 10
                       rawDataSize 70
-                      serialization.ddl struct tbl1 { i32 key, string value}
+                      serialization.ddl struct tbl2 { i32 key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 80
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.tbl1
-                  name: default.tbl1
+                    name: default.tbl2
+                  name: default.tbl2
             Truncated Path -> Alias:
-              /tbl1 [a]
+              /tbl2 [b]
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -675,11 +675,11 @@ STAGE PLANS:
                   Filter Operator
                     isSamplingPred: false
                     predicate: value is not null (type: boolean)
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: value (type: string)
                       outputColumnNames: _col1
-                      Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Spark HashTable Sink Operator
                         keys:
                           0 _col1 (type: string)
@@ -745,20 +745,20 @@ STAGE PLANS:
     Spark
 #### A masked pattern was here ####
       Vertices:
-        Map 2 
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
+                  alias: a
                   Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                   GatherStats: false
                   Filter Operator
                     isSamplingPred: false
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column stats:
NONE
+                    predicate: (key is not null and value is not null) (type: boolean)
+                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats:
NONE
                     Select Operator
                       expressions: key (type: int), value (type: string)
                       outputColumnNames: _col0, _col1
-                      Statistics: Num rows: 5 Data size: 35 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column
stats: NONE
                       Map Join Operator
                         condition map:
                              Inner Join 0 to 1
@@ -767,9 +767,9 @@ STAGE PLANS:
                           1 _col0 (type: int)
                         outputColumnNames: _col0, _col1, _col3
                         input vertices:
-                          0 Map 1
-                        Position of Big Table: 1
-                        Statistics: Num rows: 5 Data size: 38 Basic stats: COMPLETE Column
stats: NONE
+                          1 Map 2
+                        Position of Big Table: 0
+                        Statistics: Num rows: 11 Data size: 77 Basic stats: COMPLETE Column
stats: NONE
                         Map Join Operator
                           condition map:
                                Inner Join 0 to 1
@@ -780,17 +780,17 @@ STAGE PLANS:
                           input vertices:
                             1 Map 3
                           Position of Big Table: 0
-                          Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column
stats: NONE
+                          Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE Column
stats: NONE
                           Select Operator
                             expressions: _col0 (type: int), _col1 (type: string), _col3 (type:
string), _col5 (type: string)
                             outputColumnNames: _col0, _col1, _col2, _col3
-                            Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE Column
stats: NONE
+                            Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE
Column stats: NONE
                             File Output Operator
                               compressed: false
                               GlobalTableId: 0
 #### A masked pattern was here ####
                               NumFilesPerFileSink: 1
-                              Statistics: Num rows: 5 Data size: 41 Basic stats: COMPLETE
Column stats: NONE
+                              Statistics: Num rows: 12 Data size: 84 Basic stats: COMPLETE
Column stats: NONE
 #### A masked pattern was here ####
                               table:
                                   input format: org.apache.hadoop.mapred.TextInputFormat
@@ -814,7 +814,7 @@ STAGE PLANS:
             Path -> Partition:
 #### A masked pattern was here ####
                 Partition
-                  base file name: tbl2
+                  base file name: tbl1
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                   properties:
@@ -826,11 +826,11 @@ STAGE PLANS:
                     columns.comments 
                     columns.types int:string
 #### A masked pattern was here ####
-                    name default.tbl2
+                    name default.tbl1
                     numFiles 2
                     numRows 10
                     rawDataSize 70
-                    serialization.ddl struct tbl2 { i32 key, string value}
+                    serialization.ddl struct tbl1 { i32 key, string value}
                     serialization.format 1
                     serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                     totalSize 80
@@ -848,20 +848,20 @@ STAGE PLANS:
                       columns.comments 
                       columns.types int:string
 #### A masked pattern was here ####
-                      name default.tbl2
+                      name default.tbl1
                       numFiles 2
                       numRows 10
                       rawDataSize 70
-                      serialization.ddl struct tbl2 { i32 key, string value}
+                      serialization.ddl struct tbl1 { i32 key, string value}
                       serialization.format 1
                       serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                       totalSize 80
 #### A masked pattern was here ####
                     serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                    name: default.tbl2
-                  name: default.tbl2
+                    name: default.tbl1
+                  name: default.tbl1
             Truncated Path -> Alias:
-              /tbl2 [b]
+              /tbl1 [a]
 
   Stage: Stage-0
     Fetch Operator


Mime
View raw message