hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From xu...@apache.org
Subject svn commit: r1641614 [39/43] - 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/smb_mapjoin_4.q.out
URL: http://svn.apache.org/viewvc/hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out?rev=1641614&r1=1641613&r2=1641614&view=diff
==============================================================================
--- hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out (original)
+++ hive/branches/spark/ql/src/test/results/clientpositive/spark/smb_mapjoin_4.q.out Tue Nov
25 13:03:18 2014
@@ -53,31 +53,16 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a join smb_bucket_2 b on a.key = b.key join
smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                  Filter Operator
-                    predicate: key is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column
stats: NONE
-                      value expressions: value (type: string)
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: c
@@ -85,13 +70,18 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 111 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: 1 Data size: 111 Basic stats: COMPLETE Column
stats: NONE
-                      value expressions: value (type: string)
-        Map 4 
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {key} {value}
+                        1 {key} {value}
+                        2 {value}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                        2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: a
@@ -99,35 +89,60 @@ STAGE PLANS:
                   Filter Operator
                     predicate: key is not null (type: boolean)
                     Statistics: Num rows: 1 Data size: 104 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: 1 Data size: 104 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
-                     Inner Join 1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
-                    Statistics: Num rows: 2 Data size: 228 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
+                    Spark HashTable Sink Operator
+                      condition expressions:
+                        0 {value}
+                        1 {key} {value}
+                        2 {key} {value}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                        2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                           Inner Join 1 to 2
+                      condition expressions:
+                        0 {key} {value}
+                        1 {key} {value}
+                        2 {key} {value}
+                      keys:
+                        0 key (type: int)
+                        1 key (type: int)
+                        2 key (type: int)
+                      outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                      input vertices:
+                        0 Map 3
+                        2 Map 2
+                      Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column
stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                        Statistics: Num rows: 2 Data size: 228 Basic stats: COMPLETE Column
stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 2 Data size: 228 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -154,14 +169,13 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key =
b.key join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -169,57 +183,73 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 3 
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: c
                   Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                     Inner Join 1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                         Inner Join 1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      1 Map 1
+                      2 Map 2
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -246,14 +276,13 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key =
b.key left outer join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -261,57 +290,73 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 3 
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: c
                   Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                     Left Outer Join1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                         Left Outer Join1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      1 Map 1
+                      2 Map 2
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -343,14 +388,13 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a left outer join smb_bucket_2 b on a.key =
b.key right outer join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -358,57 +402,73 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
         Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Left Outer Join0 to 1
-                     Right Outer Join1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 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: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
+                  Map Join Operator
+                    condition map:
+                         Left Outer Join0 to 1
+                         Right Outer Join1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      0 Map 3
+                      1 Map 1
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -544,14 +604,13 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key =
b.key join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -559,57 +618,73 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
         Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Right Outer Join0 to 1
-                     Inner Join 1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 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: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
+                  Map Join Operator
+                    condition map:
+                         Right Outer Join0 to 1
+                         Inner Join 1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      0 Map 3
+                      1 Map 1
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -638,72 +713,87 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key =
b.key left outer join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
-        Map 1 
-            Map Operator Tree:
-                TableScan
-                  alias: b
-                  Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 3 
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: c
                   Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+        Map 3 
             Map Operator Tree:
                 TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Right Outer Join0 to 1
-                     Left Outer Join1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
+                  Map Join Operator
+                    condition map:
+                         Right Outer Join0 to 1
+                         Left Outer Join1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      0 Map 3
+                      2 Map 2
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator
@@ -734,14 +824,13 @@ POSTHOOK: query: explain
 select /*+mapjoin(a,b)*/ * from smb_bucket_1 a right outer join smb_bucket_2 b on a.key =
b.key right outer join smb_bucket_3 c on b.key=c.key
 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 3 (PARTITION-LEVEL SORT, 1),
Map 4 (PARTITION-LEVEL SORT, 1)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -749,57 +838,73 @@ STAGE PLANS:
                 TableScan
                   alias: b
                   Statistics: Num rows: 1 Data size: 206 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: 1 Data size: 206 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {key} {value}
+                      1 {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+            Local Work:
+              Map Reduce Local Work
         Map 3 
             Map Operator Tree:
                 TableScan
-                  alias: c
-                  Statistics: Num rows: 2 Data size: 222 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: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Map 4 
-            Map Operator Tree:
-                TableScan
                   alias: a
                   Statistics: Num rows: 2 Data size: 208 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: 2 Data size: 208 Basic stats: COMPLETE Column stats:
NONE
-                    value expressions: value (type: string)
-        Reducer 2 
-            Reduce Operator Tree:
-              Join Operator
-                condition map:
-                     Right Outer Join0 to 1
-                     Right Outer Join1 to 2
-                condition expressions:
-                  0 {KEY.reducesinkkey0} {VALUE._col0}
-                  1 {KEY.reducesinkkey0} {VALUE._col0}
-                  2 {KEY.reducesinkkey0} {VALUE._col0}
-                outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
-                Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: int), _col1 (type: string), _col5 (type: int),
_col6 (type: string), _col10 (type: int), _col11 (type: string)
-                  outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
-                  Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column stats:
NONE
-                  File Output Operator
-                    compressed: false
+                  Spark HashTable Sink Operator
+                    condition expressions:
+                      0 {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 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: c
+                  Statistics: Num rows: 2 Data size: 222 Basic stats: COMPLETE Column stats:
NONE
+                  Map Join Operator
+                    condition map:
+                         Right Outer Join0 to 1
+                         Right Outer Join1 to 2
+                    condition expressions:
+                      0 {key} {value}
+                      1 {key} {value}
+                      2 {key} {value}
+                    keys:
+                      0 key (type: int)
+                      1 key (type: int)
+                      2 key (type: int)
+                    outputColumnNames: _col0, _col1, _col5, _col6, _col10, _col11
+                    input vertices:
+                      0 Map 3
+                      1 Map 1
                     Statistics: Num rows: 4 Data size: 457 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
+                    Select Operator
+                      expressions: _col0 (type: int), _col1 (type: string), _col5 (type:
int), _col6 (type: string), _col10 (type: int), _col11 (type: string)
+                      outputColumnNames: _col0, _col1, _col2, _col3, _col4, _col5
+                      Statistics: Num rows: 4 Data size: 457 Basic stats: COMPLETE Column
stats: NONE
+                      File Output Operator
+                        compressed: false
+                        Statistics: Num rows: 4 Data size: 457 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
+            Local Work:
+              Map Reduce Local Work
 
   Stage: Stage-0
     Fetch Operator



Mime
View raw message