You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by xu...@apache.org on 2014/10/31 03:33:09 UTC

svn commit: r1635656 [3/5] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/lib/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/java/org/apache/h...

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_14.q.out Fri Oct 31 02:33:08 2014
@@ -50,64 +50,42 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+                  Sorted Merge Bucket Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                    condition expressions:
+                      0 
+                      1 
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                    Select Operator
+                      Group By Operator
+                        aggregations: count()
+                        mode: hash
+                        outputColumnNames: _col0
+                        Reduce Output Operator
+                          sort order: 
+                          value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 
-                  1 
-                Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -156,8 +134,7 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -165,55 +142,34 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 189 Data size: 1891 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+                  Sorted Merge Bucket Map Join Operator
+                    condition map:
+                         Right Outer Join0 to 1
+                    condition expressions:
+                      0 
+                      1 
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                    Select Operator
+                      Group By Operator
+                        aggregations: count()
+                        mode: hash
+                        outputColumnNames: _col0
+                        Reduce Output Operator
+                          sort order: 
+                          value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Right Outer Join0 to 1
-                condition expressions:
-                  0 
-                  1 
-                Statistics: Num rows: 207 Data size: 2080 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 207 Data size: 2080 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_15.q.out Fri Oct 31 02:33:08 2014
@@ -48,64 +48,42 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+                  Sorted Merge Bucket Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                    condition expressions:
+                      0 
+                      1 
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                    Select Operator
+                      Group By Operator
+                        aggregations: count()
+                        mode: hash
+                        outputColumnNames: _col0
+                        Reduce Output Operator
+                          sort order: 
+                          value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 
-                  1 
-                Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -131,8 +109,7 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -140,55 +117,34 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 10 Data size: 70 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: a
-                  Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: int)
-                    sort order: +
-                    Map-reduce partition columns: key (type: int)
-                    Statistics: Num rows: 20 Data size: 160 Basic stats: COMPLETE Column stats: NONE
+                  Sorted Merge Bucket Map Join Operator
+                    condition map:
+                         Right Outer Join0 to 1
+                    condition expressions:
+                      0 
+                      1 
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                    Select Operator
+                      Group By Operator
+                        aggregations: count()
+                        mode: hash
+                        outputColumnNames: _col0
+                        Reduce Output Operator
+                          sort order: 
+                          value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Right Outer Join0 to 1
-                condition expressions:
-                  0 
-                  1 
-                Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 22 Data size: 176 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

Added: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_16.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_16.q.out?rev=1635656&view=auto
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_16.q.out (added)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_16.q.out Fri Oct 31 02:33:08 2014
@@ -0,0 +1,256 @@
+PREHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE stage_bucket_big
+(
+key BIGINT,
+value STRING
+)
+PARTITIONED BY (file_tag STRING)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@stage_bucket_big
+POSTHOOK: query: -- SORT_QUERY_RESULTS
+
+CREATE TABLE stage_bucket_big
+(
+key BIGINT,
+value STRING
+)
+PARTITIONED BY (file_tag STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@stage_bucket_big
+PREHOOK: query: CREATE TABLE bucket_big
+(
+key BIGINT,
+value STRING
+)
+PARTITIONED BY (day STRING, pri bigint)
+clustered by (key) sorted by (key) into 12 buckets
+stored as RCFile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bucket_big
+POSTHOOK: query: CREATE TABLE bucket_big
+(
+key BIGINT,
+value STRING
+)
+PARTITIONED BY (day STRING, pri bigint)
+clustered by (key) sorted by (key) into 12 buckets
+stored as RCFile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bucket_big
+PREHOOK: query: CREATE TABLE stage_bucket_small
+(
+key BIGINT,
+value string
+)
+PARTITIONED BY (file_tag STRING)
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@stage_bucket_small
+POSTHOOK: query: CREATE TABLE stage_bucket_small
+(
+key BIGINT,
+value string
+)
+PARTITIONED BY (file_tag STRING)
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@stage_bucket_small
+PREHOOK: query: CREATE TABLE bucket_small
+(
+key BIGINT,
+value string
+)
+PARTITIONED BY (pri bigint)
+clustered by (key) sorted by (key) into 12 buckets
+stored as RCFile
+PREHOOK: type: CREATETABLE
+PREHOOK: Output: database:default
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: CREATE TABLE bucket_small
+(
+key BIGINT,
+value string
+)
+PARTITIONED BY (pri bigint)
+clustered by (key) sorted by (key) into 12 buckets
+stored as RCFile
+POSTHOOK: type: CREATETABLE
+POSTHOOK: Output: database:default
+POSTHOOK: Output: default@bucket_small
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' overwrite into table stage_bucket_small partition (file_tag='1')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@stage_bucket_small
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' overwrite into table stage_bucket_small partition (file_tag='1')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@stage_bucket_small
+POSTHOOK: Output: default@stage_bucket_small@file_tag=1
+PREHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' overwrite into table stage_bucket_small partition (file_tag='2')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@stage_bucket_small
+POSTHOOK: query: load data local inpath '../../data/files/srcsortbucket1outof4.txt' overwrite into table stage_bucket_small partition (file_tag='2')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@stage_bucket_small
+POSTHOOK: Output: default@stage_bucket_small@file_tag=2
+PREHOOK: query: insert overwrite table bucket_small partition(pri) 
+select 
+key, 
+value, 
+file_tag as pri 
+from 
+stage_bucket_small 
+where file_tag between 1 and 2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@stage_bucket_small
+PREHOOK: Input: default@stage_bucket_small@file_tag=1
+PREHOOK: Input: default@stage_bucket_small@file_tag=2
+PREHOOK: Output: default@bucket_small
+POSTHOOK: query: insert overwrite table bucket_small partition(pri) 
+select 
+key, 
+value, 
+file_tag as pri 
+from 
+stage_bucket_small 
+where file_tag between 1 and 2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@stage_bucket_small
+POSTHOOK: Input: default@stage_bucket_small@file_tag=1
+POSTHOOK: Input: default@stage_bucket_small@file_tag=2
+POSTHOOK: Output: default@bucket_small@pri=1
+POSTHOOK: Output: default@bucket_small@pri=2
+POSTHOOK: Lineage: bucket_small PARTITION(pri=1).key SIMPLE [(stage_bucket_small)stage_bucket_small.FieldSchema(name:key, type:bigint, comment:null), ]
+POSTHOOK: Lineage: bucket_small PARTITION(pri=1).value SIMPLE [(stage_bucket_small)stage_bucket_small.FieldSchema(name:value, type:string, comment:null), ]
+POSTHOOK: Lineage: bucket_small PARTITION(pri=2).key SIMPLE [(stage_bucket_small)stage_bucket_small.FieldSchema(name:key, type:bigint, comment:null), ]
+POSTHOOK: Lineage: bucket_small PARTITION(pri=2).value SIMPLE [(stage_bucket_small)stage_bucket_small.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' overwrite into table stage_bucket_big partition (file_tag='1')
+PREHOOK: type: LOAD
+#### A masked pattern was here ####
+PREHOOK: Output: default@stage_bucket_big
+POSTHOOK: query: load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' overwrite into table stage_bucket_big partition (file_tag='1')
+POSTHOOK: type: LOAD
+#### A masked pattern was here ####
+POSTHOOK: Output: default@stage_bucket_big
+POSTHOOK: Output: default@stage_bucket_big@file_tag=1
+PREHOOK: query: insert overwrite table bucket_big partition(day,pri) 
+select 
+key, 
+value, 
+'day1' as day, 
+1 as pri 
+from 
+stage_bucket_big 
+where 
+file_tag='1'
+PREHOOK: type: QUERY
+PREHOOK: Input: default@stage_bucket_big
+PREHOOK: Input: default@stage_bucket_big@file_tag=1
+PREHOOK: Output: default@bucket_big
+POSTHOOK: query: insert overwrite table bucket_big partition(day,pri) 
+select 
+key, 
+value, 
+'day1' as day, 
+1 as pri 
+from 
+stage_bucket_big 
+where 
+file_tag='1'
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@stage_bucket_big
+POSTHOOK: Input: default@stage_bucket_big@file_tag=1
+POSTHOOK: Output: default@bucket_big@day=day1/pri=1
+POSTHOOK: Lineage: bucket_big PARTITION(day=day1,pri=1).key SIMPLE [(stage_bucket_big)stage_bucket_big.FieldSchema(name:key, type:bigint, comment:null), ]
+POSTHOOK: Lineage: bucket_big PARTITION(day=day1,pri=1).value SIMPLE [(stage_bucket_big)stage_bucket_big.FieldSchema(name:value, type:string, comment:null), ]
+PREHOOK: query: select 
+a.key , 
+a.value , 
+b.value , 
+'day1' as day, 
+1 as pri 
+from 
+( 
+select 
+key, 
+value 
+from bucket_big where day='day1'
+) a 
+left outer join 
+( 
+select 
+key, 
+value
+from bucket_small 
+where pri between 1 and 2
+) b 
+on 
+(a.key = b.key)
+PREHOOK: type: QUERY
+PREHOOK: Input: default@bucket_big
+PREHOOK: Input: default@bucket_big@day=day1/pri=1
+PREHOOK: Input: default@bucket_small
+PREHOOK: Input: default@bucket_small@pri=1
+PREHOOK: Input: default@bucket_small@pri=2
+#### A masked pattern was here ####
+POSTHOOK: query: select 
+a.key , 
+a.value , 
+b.value , 
+'day1' as day, 
+1 as pri 
+from 
+( 
+select 
+key, 
+value 
+from bucket_big where day='day1'
+) a 
+left outer join 
+( 
+select 
+key, 
+value
+from bucket_small 
+where pri between 1 and 2
+) b 
+on 
+(a.key = b.key)
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@bucket_big
+POSTHOOK: Input: default@bucket_big@day=day1/pri=1
+POSTHOOK: Input: default@bucket_small
+POSTHOOK: Input: default@bucket_small@pri=1
+POSTHOOK: Input: default@bucket_small@pri=2
+#### A masked pattern was here ####
+0	val_0	val_0	day1	1
+0	val_0	val_0	day1	1
+0	val_0	val_0	day1	1
+0	val_0	val_0	day1	1
+0	val_0	val_0	day1	1
+0	val_0	val_0	day1	1
+103	val_103	val_103	day1	1
+103	val_103	val_103	day1	1
+103	val_103	val_103	day1	1
+103	val_103	val_103	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+169	val_169	val_169	day1	1
+172	val_172	val_172	day1	1
+172	val_172	val_172	day1	1
+172	val_172	val_172	day1	1
+172	val_172	val_172	day1	1
+374	val_374	val_374	day1	1
+374	val_374	val_374	day1	1

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_2.q.out Fri Oct 31 02:33:08 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_3.q.out Fri Oct 31 02:33:08 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_4.q.out Fri Oct 31 02:33:08 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_5.q.out Fri Oct 31 02:33:08 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_6.q.out Fri Oct 31 02:33:08 2014
@@ -96,27 +96,13 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: c
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
@@ -127,7 +113,7 @@ STAGE PLANS:
                       sort order: +
                       Map-reduce partition columns: value (type: string)
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 6 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -135,61 +121,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -232,9 +204,8 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Reducer 5 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
         Reducer 3 <- Reducer 2 (GROUP, 1)
-        Reducer 5 <- Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -253,30 +224,25 @@ STAGE PLANS:
         Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 6 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
@@ -285,17 +251,13 @@ STAGE PLANS:
                 condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
         Reducer 3 
             Reduce Operator Tree:
@@ -303,33 +265,15 @@ STAGE PLANS:
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 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
-        Reducer 5 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-0
     Fetch Operator
@@ -368,39 +312,33 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Map 6 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 6 
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: h
@@ -419,49 +357,27 @@ STAGE PLANS:
                 condition map:
                      Inner Join 0 to 1
                 condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -617,85 +533,48 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: c
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 
+                        1 
+                        2 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                        2 key (type: int)
+                      Select Operator
+                        Group By Operator
+                          aggregations: count()
+                          mode: hash
+                          outputColumnNames: _col0
+                          Reduce Output Operator
+                            sort order: 
+                            value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 
-                  1 
-                  2 
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -734,27 +613,13 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: c
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
@@ -765,7 +630,7 @@ STAGE PLANS:
                       sort order: +
                       Map-reduce partition columns: value (type: string)
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 6 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -773,61 +638,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -866,27 +717,13 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: c
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
@@ -897,7 +734,7 @@ STAGE PLANS:
                       sort order: +
                       Map-reduce partition columns: value (type: string)
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 6 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -905,61 +742,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1115,85 +938,48 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1), Map 5 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: c
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 
+                        1 
+                        2 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                        2 key (type: int)
+                      Select Operator
+                        Group By Operator
+                          aggregations: count()
+                          mode: hash
+                          outputColumnNames: _col0
+                          Reduce Output Operator
+                            sort order: 
+                            value expressions: _col0 (type: bigint)
         Reducer 2 
             Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 
-                  1 
-                  2 
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count()
-                    mode: hash
-                    outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col0 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1232,27 +1018,13 @@ STAGE PLANS:
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 6 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Map 5 (GROUP PARTITION-LEVEL SORT, 1), Reducer 2 (GROUP PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP PARTITION-LEVEL SORT, 1), Map 4 (GROUP PARTITION-LEVEL SORT, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: b
-                  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
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 5 
-            Map Operator Tree:
-                TableScan
                   alias: c
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
@@ -1263,7 +1035,7 @@ STAGE PLANS:
                       sort order: +
                       Map-reduce partition columns: value (type: string)
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 6 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -1271,61 +1043,47 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key is not null and value is not null) (type: boolean)
                     Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: int)
-                      sort order: +
-                      Map-reduce partition columns: key (type: int)
-                      Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
+                    Sorted Merge Bucket Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col1
+                      Reduce Output Operator
+                        key expressions: _col1 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Join Operator
                 condition map:
                      Inner Join 0 to 1
                 condition expressions:
-                  0 {VALUE._col0}
-                  1 
-                outputColumnNames: _col1
-                Statistics: Num rows: 275 Data size: 2921 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: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
                   0 
                   1 
-                Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
-                  Statistics: Num rows: 302 Data size: 3213 Basic stats: COMPLETE Column stats: NONE
                   Group By Operator
                     aggregations: count()
                     mode: hash
                     outputColumnNames: _col0
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     Reduce Output Operator
                       sort order: 
-                      Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                       value expressions: _col0 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 mode: mergepartial
                 outputColumnNames: _col0
-                Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                 Select Operator
                   expressions: _col0 (type: bigint)
                   outputColumnNames: _col0
-                  Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                   File Output Operator
                     compressed: false
-                    Statistics: Num rows: 1 Data size: 8 Basic stats: COMPLETE Column stats: NONE
                     table:
                         input format: org.apache.hadoop.mapred.TextInputFormat
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_7.q.out Fri Oct 31 02:33:08 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out?rev=1635656&r1=1635655&r2=1635656&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/auto_sortmerge_join_8.q.out Fri Oct 31 02:33:08 2014 differ