hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1641614 [12/43] - in /hive/branches/spark: itests/src/test/resources/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/physical/ ql/src/java/org/apache/hadoop/hive/ql/optimizer/spark/ ql/src/java/org/apache/hadoop/hive/ql/parse/spark/ ql/sr...
Date Tue, 25 Nov 2014 13:03:23 GMT
Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join29.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join29.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join29.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join29.q.out Tue Nov 25 13:03:18 2014
@@ -27,69 +27,98 @@ FROM (select x.key, count(1) as cnt from
      (select y.key, count(1) as cnt from src y group by y.key) subq2 ON (subq1.key = subq2.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP, 1)
-        Reducer 5 <- Map 4 (GROUP, 1)
-        Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 5 (PARTITION-LEVEL SORT, 1)
+        Reducer 4 <- Map 3 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: y
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  alias: x
+                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: key
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count(1)
                         keys: key (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: string)
-                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: bigint)
-        Map 4 
+        Reducer 4 
+            Local Work:
+              Map Reduce Local Work
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string), _col1 (type: bigint)
+                  outputColumnNames: _col0, _col1
+                  Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {_col1}
+                      1 {_col1}
+                    keys:
+                      0 _col0 (type: string)
+                      1 _col0 (type: string)
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 2 <- Map 1 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: x
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                  alias: y
+                  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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: key
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count(1)
                         keys: key (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: string)
-                          Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: bigint)
         Reducer 2 
+            Local Work:
+              Map Reduce Local Work
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -101,52 +130,31 @@ STAGE PLANS:
                   expressions: _col0 (type: string), _col1 (type: bigint)
                   outputColumnNames: _col0, _col1
                   Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: _col1 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col3
-                Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {_col0} {_col1}
+                      1 {_col1}
+                    keys:
+                      0 _col0 (type: string)
+                      1 _col0 (type: string)
+                    outputColumnNames: _col0, _col1, _col3
+                    input vertices:
+                      0 Reducer 4
                     Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
-        Reducer 5 
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: count(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: bigint)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: _col1 (type: bigint)
+                    Select Operator
+                      expressions: _col0 (type: string), UDFToInteger(_col1) (type: int), UDFToInteger(_col3) (type: int)
+                      outputColumnNames: _col0, _col1, _col2
+                      Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.dest_j1
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join3.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join3.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join3.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join3.q.out Tue Nov 25 13:03:18 2014
@@ -19,16 +19,15 @@ FROM src src1 JOIN src src2 ON (src1.key
 INSERT OVERWRITE TABLE dest1 SELECT src1.key, src3.value
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -39,12 +38,18 @@ STAGE PLANS:
                   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: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: src3
@@ -52,13 +57,23 @@ STAGE PLANS:
                   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: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key}
+                        1 
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: src1
@@ -66,35 +81,37 @@ STAGE PLANS:
                   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: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                     Inner Join 0 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                  2 {VALUE._col0}
-                outputColumnNames: _col0, _col11
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 0 to 2
+                      condition expressions:
+                        0 {key}
+                        1 
+                        2 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                        2 key (type: string)
+                      outputColumnNames: _col0, _col11
+                      input vertices:
+                        1 Map 1
+                        2 Map 2
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: UDFToInteger(_col0) (type: int), _col11 (type: string)
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join30.q.out Tue Nov 25 13:03:18 2014
@@ -19,17 +19,39 @@ INSERT OVERWRITE TABLE dest_j1 
 SELECT /*+ MAPJOIN(x) */ x.key, count(1) FROM src1 x JOIN src y ON (x.key = y.key) group by x.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
+            Map Operator Tree:
+                TableScan
+                  alias: x
+                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 
+                        1 
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
   Stage: Stage-1
     Spark
       Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
+        Reducer 2 <- Map 1 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -40,51 +62,38 @@ STAGE PLANS:
                   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: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-        Map 4 
-            Map Operator Tree:
-                TableScan
-                  alias: x
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count(1)
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col0 (type: string)
-                      sort order: +
-                      Map-reduce partition columns: _col0 (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key}
+                        1 
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0
+                      input vertices:
+                        0 Map 3
                       Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col1 (type: bigint)
-        Reducer 3 
+                      Select Operator
+                        expressions: _col0 (type: string)
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: count(1)
+                          keys: _col0 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0, _col1
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            key expressions: _col0 (type: string)
+                            sort order: +
+                            Map-reduce partition columns: _col0 (type: string)
+                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                            value expressions: _col1 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
+        Reducer 2 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join31.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join31.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join31.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join31.q.out Tue Nov 25 13:03:18 2014
@@ -29,70 +29,99 @@ FROM (select x.key, count(1) as cnt from
 group by subq1.key
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
       Edges:
-        Reducer 2 <- Map 1 (GROUP, 1)
-        Reducer 6 <- Map 5 (GROUP, 1)
-        Reducer 3 <- Reducer 2 (PARTITION-LEVEL SORT, 1), Reducer 6 (PARTITION-LEVEL SORT, 1)
-        Reducer 4 <- Reducer 3 (GROUP, 1)
+        Reducer 5 <- Map 4 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 4 
             Map Operator Tree:
                 TableScan
-                  alias: y
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  alias: x
+                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
                     predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: key
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count(1)
                         keys: key (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: string)
-                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: bigint)
-        Map 5 
+        Reducer 5 
+            Local Work:
+              Map Reduce Local Work
+            Reduce Operator Tree:
+              Group By Operator
+                aggregations: count(VALUE._col0)
+                keys: KEY._col0 (type: string)
+                mode: mergepartial
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: string)
+                  outputColumnNames: _col0
+                  Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 
+                      1 
+                    keys:
+                      0 _col0 (type: string)
+                      1 _col0 (type: string)
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 2 <- Map 1 (GROUP, 1)
+        Reducer 3 <- Reducer 2 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: x
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                  alias: y
+                  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: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string)
                       outputColumnNames: key
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                       Group By Operator
                         aggregations: count(1)
                         keys: key (type: string)
                         mode: hash
                         outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                         Reduce Output Operator
                           key expressions: _col0 (type: string)
                           sort order: +
                           Map-reduce partition columns: _col0 (type: string)
-                          Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
                           value expressions: _col1 (type: bigint)
         Reducer 2 
+            Local Work:
+              Map Reduce Local Work
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -104,38 +133,36 @@ STAGE PLANS:
                   expressions: _col0 (type: string)
                   outputColumnNames: _col0
                   Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column stats: NONE
-        Reducer 3 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0}
-                  1 
-                outputColumnNames: _col0
-                Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count(1)
-                    keys: _col0 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0, _col1
+                  Map Join Operator
+                    condition map:
+                         Inner Join 0 to 1
+                    condition expressions:
+                      0 {_col0}
+                      1 
+                    keys:
+                      0 _col0 (type: string)
+                      1 _col0 (type: string)
+                    outputColumnNames: _col0
+                    input vertices:
+                      0 Reducer 5
                     Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col0 (type: string)
-                      sort order: +
-                      Map-reduce partition columns: _col0 (type: string)
+                    Select Operator
+                      expressions: _col0 (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col1 (type: bigint)
-        Reducer 4 
+                      Group By Operator
+                        aggregations: count(1)
+                        keys: _col0 (type: string)
+                        mode: hash
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col0 (type: string)
+                          sort order: +
+                          Map-reduce partition columns: _col0 (type: string)
+                          Statistics: Num rows: 137 Data size: 1460 Basic stats: COMPLETE Column stats: NONE
+                          value expressions: _col1 (type: bigint)
+        Reducer 3 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -155,23 +182,6 @@ STAGE PLANS:
                         output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
                         serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                         name: default.dest_j1
-        Reducer 6 
-            Reduce Operator Tree:
-              Group By Operator
-                aggregations: count(VALUE._col0)
-                keys: KEY._col0 (type: string)
-                mode: mergepartial
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string)
-                  outputColumnNames: _col0
-                  Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 6 Data size: 45 Basic stats: COMPLETE Column stats: NONE
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join32.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join32.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/join32.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/join32.q.out Tue Nov 25 13:03:18 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/join32_lessSize.q.out Tue Nov 25 13:03:18 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join33.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join33.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
Files hive/branches/spark/ql/src/test/results/clientpositive/spark/join33.q.out (original) and hive/branches/spark/ql/src/test/results/clientpositive/spark/join33.q.out Tue Nov 25 13:03:18 2014 differ

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join36.q.out Tue Nov 25 13:03:18 2014
@@ -61,16 +61,15 @@ SELECT /*+ MAPJOIN(x) */ x.key, x.cnt, y
 FROM tmp1 x JOIN tmp2 y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -81,13 +80,21 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 155 Data size: 743 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: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: cnt (type: int)
-        Map 3 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {cnt}
+                        1 {cnt}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: x
@@ -95,34 +102,33 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 155 Data size: 743 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: 155 Data size: 743 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: cnt (type: int)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col6
-                Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: int), _col6 (type: int)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {cnt}
+                        1 {cnt}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        1 Map 1
+                      Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: int), _col6 (type: int)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 170 Data size: 817 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join37.q.out Tue Nov 25 13:03:18 2014
@@ -21,16 +21,37 @@ SELECT /*+ MAPJOIN(X) */ x.key, x.value,
 FROM src1 x JOIN src y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
+  Stage: Stage-4
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: x
+                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {value}
+                        1 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+            Local Work:
+              Map Reduce Local Work
+
   Stage: Stage-1
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -41,48 +62,33 @@ STAGE PLANS:
                   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: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Map 3 
-            Map Operator Tree:
-                TableScan
-                  alias: x
-                  Statistics: Num rows: 25 Data size: 191 Basic stats: COMPLETE Column stats: NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: key (type: string)
-                      sort order: +
-                      Map-reduce partition columns: key (type: string)
-                      Statistics: Num rows: 13 Data size: 99 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col6
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {key} {value}
+                        1 {value}
+                      keys:
+                        0 key (type: string)
+                        1 key (type: string)
+                      outputColumnNames: _col0, _col1, _col6
+                      input vertices:
+                        0 Map 2
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                      Select Operator
+                        expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), _col6 (type: string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                              name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join38.q.out Tue Nov 25 13:03:18 2014
@@ -49,15 +49,13 @@ where b.col11 = 111
 group by a.value, b.col5
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-3 is a root stage
+  Stage-1 depends on stages: Stage-3
   Stage-0 depends on stages: Stage-1
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-3
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 4 (PARTITION-LEVEL SORT, 1)
-        Reducer 3 <- Reducer 2 (GROUP, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -68,12 +66,23 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (col11 = 111) (type: boolean)
                     Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: '111' (type: string)
-                      sort order: +
-                      Statistics: Num rows: 1 Data size: 63 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: col5 (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {value}
+                        1 {col5}
+                      keys:
+                        0 '111' (type: string)
+                        1 '111' (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+      Edges:
+        Reducer 3 <- Map 2 (GROUP, 1)
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -81,37 +90,37 @@ STAGE PLANS:
                   Filter Operator
                     predicate: (key = 111) (type: boolean)
                     Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: '111' (type: string)
-                      sort order: +
-                      Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Inner Join 0 to 1
-                condition expressions:
-                  0 {VALUE._col0}
-                  1 {VALUE._col5}
-                outputColumnNames: _col1, _col10
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col1 (type: string), _col10 (type: string)
-                  outputColumnNames: _col1, _col10
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                  Group By Operator
-                    aggregations: count(1)
-                    keys: _col1 (type: string), _col10 (type: string)
-                    mode: hash
-                    outputColumnNames: _col0, _col1, _col2
-                    Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                    Reduce Output Operator
-                      key expressions: _col0 (type: string), _col1 (type: string)
-                      sort order: ++
-                      Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      condition expressions:
+                        0 {value}
+                        1 {col5}
+                      keys:
+                        0 '111' (type: string)
+                        1 '111' (type: string)
+                      outputColumnNames: _col1, _col10
+                      input vertices:
+                        1 Map 1
                       Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
-                      value expressions: _col2 (type: bigint)
+                      Select Operator
+                        expressions: _col1 (type: string), _col10 (type: string)
+                        outputColumnNames: _col1, _col10
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                        Group By Operator
+                          aggregations: count(1)
+                          keys: _col1 (type: string), _col10 (type: string)
+                          mode: hash
+                          outputColumnNames: _col0, _col1, _col2
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                          Reduce Output Operator
+                            key expressions: _col0 (type: string), _col1 (type: string)
+                            sort order: ++
+                            Map-reduce partition columns: _col0 (type: string), _col1 (type: string)
+                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats: NONE
+                            value expressions: _col2 (type: bigint)
+            Local Work:
+              Map Reduce Local Work
         Reducer 3 
             Reduce Operator Tree:
               Group By Operator

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join39.q.out Tue Nov 25 13:03:18 2014
@@ -21,30 +21,18 @@ SELECT /*+ MAPJOIN(y) */ x.key, x.value,
 FROM src x left outer JOIN (select * from src where key <= 100) y ON (x.key = y.key)
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: x
-                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                  Reduce Output Operator
-                    key expressions: key (type: string)
-                    sort order: +
-                    Map-reduce partition columns: key (type: string)
-                    Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
-                    value expressions: value (type: string)
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: src
@@ -56,34 +44,52 @@ STAGE PLANS:
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 166 Data size: 1763 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6
-                Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
+                      Spark HashTable Sink Operator
+                        condition expressions:
+                          0 {key} {value}
+                          1 {_col1}
+                        keys:
+                          0 key (type: string)
+                          1 _col0 (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: x
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                    condition expressions:
+                      0 {key} {value}
+                      1 {_col0} {_col1}
+                    keys:
+                      0 key (type: string)
+                      1 _col0 (type: string)
+                    outputColumnNames: _col0, _col1, _col5, _col6
+                    input vertices:
+                      1 Map 2
                     Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest_j1
+                    Select Operator
+                      expressions: _col0 (type: string), _col1 (type: string), _col5 (type: string), _col6 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3
+                      Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column stats: NONE
+                        table:
+                            input format: org.apache.hadoop.mapred.TextInputFormat
+                            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                            name: default.dest_j1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-2
     Dependency Collection

Modified: hive/branches/spark/ql/src/test/results/clientpositive/spark/join4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/join4.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/join4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/join4.q.out Tue Nov 25 13:03:18 2014
@@ -41,76 +41,82 @@ FROM (
 INSERT OVERWRITE TABLE dest1 SELECT c.c1, c.c2, c.c3, c.c4
 POSTHOOK: type: QUERY
 STAGE DEPENDENCIES:
-  Stage-1 is a root stage
+  Stage-4 is a root stage
+  Stage-1 depends on stages: Stage-4
   Stage-2 depends on stages: Stage-1
   Stage-0 depends on stages: Stage-2
   Stage-3 depends on stages: Stage-0
 
 STAGE PLANS:
-  Stage: Stage-1
+  Stage: Stage-4
     Spark
-      Edges:
-        Reducer 2 <- Map 1 (PARTITION-LEVEL SORT, 1), Map 3 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
+        Map 2 
             Map Operator Tree:
                 TableScan
-                  alias: src1
+                  alias: src2
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((key > 10) and (key < 20)) (type: boolean)
+                    predicate: ((key > 15) and (key < 25)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-        Map 3 
+                      Spark HashTable Sink Operator
+                        condition expressions:
+                          0 {_col0} {_col1}
+                          1 {_col1}
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
             Map Operator Tree:
                 TableScan
-                  alias: src2
+                  alias: src1
                   Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column stats: NONE
                   Filter Operator
-                    predicate: ((key > 15) and (key < 25)) (type: boolean)
+                    predicate: ((key > 10) and (key < 20)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
                     Select Operator
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column stats: NONE
-                        value expressions: _col1 (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                Select Operator
-                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3
-                  Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
-                    table:
-                        input format: org.apache.hadoop.mapred.TextInputFormat
-                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                        name: default.dest1
+                      Map Join Operator
+                        condition map:
+                             Left Outer Join0 to 1
+                        condition expressions:
+                          0 {_col0} {_col1}
+                          1 {_col0} {_col1}
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        input vertices:
+                          1 Map 2
+                        Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                        Select Operator
+                          expressions: UDFToInteger(_col0) (type: int), _col1 (type: string), UDFToInteger(_col2) (type: int), _col3 (type: string)
+                          outputColumnNames: _col0, _col1, _col2, _col3
+                          Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                          File Output Operator
+                            compressed: false
+                            Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats: NONE
+                            table:
+                                input format: org.apache.hadoop.mapred.TextInputFormat
+                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                                name: default.dest1
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-2
     Dependency Collection



Mime
View raw message