hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject svn commit: r1670462 [16/26] - in /hive/branches/cbo: ./ ant/src/org/apache/hadoop/hive/ant/ beeline/src/java/org/apache/hive/beeline/ common/src/java/org/apache/hadoop/hive/conf/ common/src/java/org/apache/hive/common/util/ common/src/test/org/apache/...
Date Tue, 31 Mar 2015 20:14:07 GMT
Modified: hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out?rev=1670462&r1=1670461&r2=1670462&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_1_23.q.out Tue Mar 31 20:14:02 2015
@@ -189,7 +189,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
 
   Stage: Stage-7
     Conditional Operator
@@ -526,7 +526,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -784,7 +784,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
 
   Stage: Stage-7
     Conditional Operator
@@ -1192,7 +1192,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
 
   Stage: Stage-7
     Conditional Operator
@@ -1483,8 +1483,13 @@ TOK_QUERY
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-0 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-2 depends on stages: Stage-0
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
@@ -1501,17 +1506,39 @@ STAGE PLANS:
               Group By Operator
                 aggregations: count(1)
                 keys: 1 (type: int), _col1 (type: string)
-                mode: hash
+                mode: final
                 outputColumnNames: _col0, _col1, _col2
-                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: int), _col1 (type: string)
-                  sort order: ++
-                  Map-reduce partition columns: _col0 (type: int), _col1 (type: string)
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  tag: -1
-                  value expressions: _col2 (type: bigint)
-                  auto parallelism: false
+                Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int)
+                  outputColumnNames: _col0, _col1, _col2
+                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 1
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          bucket_count -1
+                          columns key1,key2,cnt
+                          columns.comments 
+                          columns.types int:int:int
+#### A masked pattern was here ####
+                          name default.outputtbl3
+                          serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl3
+                    TotalFiles: 1
+                    GatherStats: true
+                    MultiFileSpray: false
       Path -> Alias:
 #### A masked pattern was here ####
       Path -> Partition:
@@ -1564,26 +1591,53 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
-      Needs Tagging: false
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: int), KEY._col1 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2
-          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: _col0 (type: int), UDFToInteger(_col1) (type: int), UDFToInteger(_col2) (type: int)
-            outputColumnNames: _col0, _col1, _col2
-            Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+        /t1 [$hdt$_0:t1]
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+#### A masked pattern was here ####
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key1,key2,cnt
+                columns.comments 
+                columns.types int:int:int
+#### A masked pattern was here ####
+                name default.outputtbl3
+                serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl3
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+#### A masked pattern was here ####
+
+  Stage: Stage-3
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
             File Output Operator
               compressed: false
-              GlobalTableId: 1
+              GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
-              Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -1601,15 +1655,98 @@ STAGE PLANS:
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                   name: default.outputtbl3
               TotalFiles: 1
-              GatherStats: true
+              GatherStats: false
               MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              bucket_count -1
+              columns key1,key2,cnt
+              columns.comments 
+              columns.types int:int:int
+#### A masked pattern was here ####
+              name default.outputtbl3
+              serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key1,key2,cnt
+                columns.comments 
+                columns.types int:int:int
+#### A masked pattern was here ####
+                name default.outputtbl3
+                serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl3
+            name: default.outputtbl3
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-0
-    Move Operator
-      tables:
-          replace: true
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
 #### A masked pattern was here ####
-          table:
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    bucket_count -1
+                    columns key1,key2,cnt
+                    columns.comments 
+                    columns.types int:int:int
+#### A masked pattern was here ####
+                    name default.outputtbl3
+                    serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl3
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              bucket_count -1
+              columns key1,key2,cnt
+              columns.comments 
+              columns.types int:int:int
+#### A masked pattern was here ####
+              name default.outputtbl3
+              serialization.ddl struct outputtbl3 { i32 key1, i32 key2, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
               input format: org.apache.hadoop.mapred.TextInputFormat
               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
               properties:
@@ -1625,9 +1762,14 @@ STAGE PLANS:
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl3
+            name: default.outputtbl3
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-2
-    Stats-Aggr Operator
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
 
 PREHOOK: query: INSERT OVERWRITE TABLE outputTbl3
@@ -1790,7 +1932,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -2011,7 +2153,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -2278,7 +2420,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [$hdt$_0:$hdt$_0:$hdt$_0:t1]
+        /t1 [$hdt$_0:$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -2626,7 +2768,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:t1]
+        /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1, null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1]
 
   Stage: Stage-7
     Conditional Operator
@@ -3051,7 +3193,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:$hdt$_0:t1]
+        /t1 [null-subquery2:$hdt$_0-subquery2:$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -3247,7 +3389,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:$hdt$_0:t1]
+        /t1 [null-subquery1:$hdt$_0-subquery1:$hdt$_0:t1]
 #### A masked pattern was here ####
 
   Stage: Stage-8
@@ -4305,7 +4447,7 @@ STAGE PLANS:
               name: default.t2
             name: default.t2
       Truncated Path -> Alias:
-        /t2 [$hdt$_0:$hdt$_0:t2]
+        /t2 [$hdt$_0:t2]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator
@@ -4453,8 +4595,13 @@ TOK_QUERY
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-0 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-2 depends on stages: Stage-0
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
@@ -4471,17 +4618,44 @@ STAGE PLANS:
               Group By Operator
                 aggregations: count(1)
                 keys: _col0 (type: string), 1 (type: int), _col2 (type: string)
-                mode: hash
+                mode: final
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  sort order: +++
-                  Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  tag: -1
-                  value expressions: _col3 (type: bigint)
-                  auto parallelism: false
+                Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 1
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          COLUMN_STATS_ACCURATE true
+                          bucket_count -1
+                          columns key1,key2,key3,cnt
+                          columns.comments 
+                          columns.types int:int:string:int
+#### A masked pattern was here ####
+                          name default.outputtbl4
+                          numFiles 1
+                          numRows 6
+                          rawDataSize 48
+                          serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          totalSize 54
+#### A masked pattern was here ####
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl4
+                    TotalFiles: 1
+                    GatherStats: true
+                    MultiFileSpray: false
       Path -> Alias:
 #### A masked pattern was here ####
       Path -> Partition:
@@ -4534,26 +4708,58 @@ STAGE PLANS:
               name: default.t2
             name: default.t2
       Truncated Path -> Alias:
-        /t2 [$hdt$_0:$hdt$_0:t2]
-      Needs Tagging: false
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              GlobalTableId: 1
+        /t2 [$hdt$_0:t2]
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
-              NumFilesPerFileSink: 1
-              Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+#### A masked pattern was here ####
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+#### A masked pattern was here ####
+
+  Stage: Stage-3
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
 #### A masked pattern was here ####
+              NumFilesPerFileSink: 1
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -4576,15 +4782,118 @@ STAGE PLANS:
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                   name: default.outputtbl4
               TotalFiles: 1
-              GatherStats: true
+              GatherStats: false
               MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-0
-    Move Operator
-      tables:
-          replace: true
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
 #### A masked pattern was here ####
-          table:
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE true
+                    bucket_count -1
+                    columns key1,key2,key3,cnt
+                    columns.comments 
+                    columns.types int:int:string:int
+#### A masked pattern was here ####
+                    name default.outputtbl4
+                    numFiles 1
+                    numRows 6
+                    rawDataSize 48
+                    serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    totalSize 54
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl4
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
               input format: org.apache.hadoop.mapred.TextInputFormat
               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
               properties:
@@ -4605,9 +4914,14 @@ STAGE PLANS:
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-2
-    Stats-Aggr Operator
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
 
 PREHOOK: query: INSERT OVERWRITE TABLE outputTbl4
@@ -4696,8 +5010,13 @@ TOK_QUERY
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-0 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-2 depends on stages: Stage-0
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
@@ -4714,17 +5033,39 @@ STAGE PLANS:
               Group By Operator
                 aggregations: count(1)
                 keys: _col0 (type: string), 1 (type: int), _col2 (type: string), 2 (type: int)
-                mode: hash
+                mode: final
                 outputColumnNames: _col0, _col1, _col2, _col3, _col4
-                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int)
-                  sort order: ++++
-                  Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string), _col3 (type: int)
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  tag: -1
-                  value expressions: _col4 (type: bigint)
-                  auto parallelism: false
+                Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), UDFToInteger(_col4) (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3, _col4
+                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 1
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          bucket_count -1
+                          columns key1,key2,key3,key4,cnt
+                          columns.comments 
+                          columns.types int:int:string:int:int
+#### A masked pattern was here ####
+                          name default.outputtbl5
+                          serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl5
+                    TotalFiles: 1
+                    GatherStats: true
+                    MultiFileSpray: false
       Path -> Alias:
 #### A masked pattern was here ####
       Path -> Partition:
@@ -4777,45 +5118,16 @@ STAGE PLANS:
               name: default.t2
             name: default.t2
       Truncated Path -> Alias:
-        /t2 [$hdt$_0:$hdt$_0:t2]
-      Needs Tagging: false
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string), KEY._col3 (type: int)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3, _col4
-          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), _col3 (type: int), UDFToInteger(_col4) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3, _col4
-            Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-            File Output Operator
-              compressed: false
-              GlobalTableId: 1
-#### A masked pattern was here ####
-              NumFilesPerFileSink: 1
-              Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
-              table:
-                  input format: org.apache.hadoop.mapred.TextInputFormat
-                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                  properties:
-                    bucket_count -1
-                    columns key1,key2,key3,key4,cnt
-                    columns.comments 
-                    columns.types int:int:string:int:int
-#### A masked pattern was here ####
-                    name default.outputtbl5
-                    serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
-                    serialization.format 1
-                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        /t2 [$hdt$_0:t2]
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
-                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-                  name: default.outputtbl5
-              TotalFiles: 1
-              GatherStats: true
-              MultiFileSpray: false
 
   Stage: Stage-0
     Move Operator
@@ -4843,21 +5155,165 @@ STAGE PLANS:
     Stats-Aggr Operator
 #### A masked pattern was here ####
 
-PREHOOK: query: INSERT OVERWRITE TABLE outputTbl5
-SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2
-PREHOOK: type: QUERY
-PREHOOK: Input: default@t2
-PREHOOK: Output: default@outputtbl5
-POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl5
-SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2
-POSTHOOK: type: QUERY
-POSTHOOK: Input: default@t2
-POSTHOOK: Output: default@outputtbl5
-POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.null, ]
-POSTHOOK: Lineage: outputtbl5.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ]
-POSTHOOK: Lineage: outputtbl5.key2 SIMPLE []
-POSTHOOK: Lineage: outputtbl5.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ]
-POSTHOOK: Lineage: outputtbl5.key4 SIMPLE []
+  Stage: Stage-3
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+#### A masked pattern was here ####
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    bucket_count -1
+                    columns key1,key2,key3,key4,cnt
+                    columns.comments 
+                    columns.types int:int:string:int:int
+#### A masked pattern was here ####
+                    name default.outputtbl5
+                    serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl5
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              bucket_count -1
+              columns key1,key2,key3,key4,cnt
+              columns.comments 
+              columns.types int:int:string:int:int
+#### A masked pattern was here ####
+              name default.outputtbl5
+              serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key1,key2,key3,key4,cnt
+                columns.comments 
+                columns.types int:int:string:int:int
+#### A masked pattern was here ####
+                name default.outputtbl5
+                serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl5
+            name: default.outputtbl5
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+#### A masked pattern was here ####
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    bucket_count -1
+                    columns key1,key2,key3,key4,cnt
+                    columns.comments 
+                    columns.types int:int:string:int:int
+#### A masked pattern was here ####
+                    name default.outputtbl5
+                    serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl5
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              bucket_count -1
+              columns key1,key2,key3,key4,cnt
+              columns.comments 
+              columns.types int:int:string:int:int
+#### A masked pattern was here ####
+              name default.outputtbl5
+              serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                bucket_count -1
+                columns key1,key2,key3,key4,cnt
+                columns.comments 
+                columns.types int:int:string:int:int
+#### A masked pattern was here ####
+                name default.outputtbl5
+                serialization.ddl struct outputtbl5 { i32 key1, i32 key2, string key3, i32 key4, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl5
+            name: default.outputtbl5
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
+PREHOOK: query: INSERT OVERWRITE TABLE outputTbl5
+SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2
+PREHOOK: type: QUERY
+PREHOOK: Input: default@t2
+PREHOOK: Output: default@outputtbl5
+POSTHOOK: query: INSERT OVERWRITE TABLE outputTbl5
+SELECT key, 1, val, 2, count(1) FROM T2 GROUP BY key, 1, val, 2
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@t2
+POSTHOOK: Output: default@outputtbl5
+POSTHOOK: Lineage: outputtbl5.cnt EXPRESSION [(t2)t2.null, ]
+POSTHOOK: Lineage: outputtbl5.key1 EXPRESSION [(t2)t2.FieldSchema(name:key, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl5.key2 SIMPLE []
+POSTHOOK: Lineage: outputtbl5.key3 SIMPLE [(t2)t2.FieldSchema(name:val, type:string, comment:null), ]
+POSTHOOK: Lineage: outputtbl5.key4 SIMPLE []
 PREHOOK: query: SELECT * FROM outputTbl5 
 ORDER BY key1, key2, key3, key4
 PREHOOK: type: QUERY
@@ -4943,8 +5399,13 @@ TOK_QUERY
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-0 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-2 depends on stages: Stage-0
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
@@ -4961,17 +5422,44 @@ STAGE PLANS:
               Group By Operator
                 aggregations: count(1)
                 keys: _col0 (type: string), 1 (type: int), _col2 (type: string)
-                mode: hash
+                mode: final
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  sort order: +++
-                  Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  tag: -1
-                  value expressions: _col3 (type: bigint)
-                  auto parallelism: false
+                Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 1
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          COLUMN_STATS_ACCURATE true
+                          bucket_count -1
+                          columns key1,key2,key3,cnt
+                          columns.comments 
+                          columns.types int:int:string:int
+#### A masked pattern was here ####
+                          name default.outputtbl4
+                          numFiles 1
+                          numRows 6
+                          rawDataSize 48
+                          serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          totalSize 54
+#### A masked pattern was here ####
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl4
+                    TotalFiles: 1
+                    GatherStats: true
+                    MultiFileSpray: false
       Path -> Alias:
 #### A masked pattern was here ####
       Path -> Partition:
@@ -5024,26 +5512,142 @@ STAGE PLANS:
               name: default.t2
             name: default.t2
       Truncated Path -> Alias:
-        /t2 [$hdt$_0:$hdt$_0:$hdt$_0:t2]
-      Needs Tagging: false
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+        /t2 [$hdt$_0:t2]
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+#### A masked pattern was here ####
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+#### A masked pattern was here ####
+
+  Stage: Stage-3
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
+#### A masked pattern was here ####
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE true
+                    bucket_count -1
+                    columns key1,key2,key3,cnt
+                    columns.comments 
+                    columns.types int:int:string:int
+#### A masked pattern was here ####
+                    name default.outputtbl4
+                    numFiles 1
+                    numRows 6
+                    rawDataSize 48
+                    serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    totalSize 54
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl4
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
+
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
             File Output Operator
               compressed: false
-              GlobalTableId: 1
+              GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
-              Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -5066,15 +5670,34 @@ STAGE PLANS:
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                   name: default.outputtbl4
               TotalFiles: 1
-              GatherStats: true
+              GatherStats: false
               MultiFileSpray: false
-
-  Stage: Stage-0
-    Move Operator
-      tables:
-          replace: true
+      Path -> Alias:
 #### A masked pattern was here ####
-          table:
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
               input format: org.apache.hadoop.mapred.TextInputFormat
               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
               properties:
@@ -5095,9 +5718,14 @@ STAGE PLANS:
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-2
-    Stats-Aggr Operator
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
 
 PREHOOK: query: INSERT OVERWRITE TABLE outputTbl4
@@ -5229,8 +5857,13 @@ TOK_QUERY
 
 STAGE DEPENDENCIES:
   Stage-1 is a root stage
-  Stage-0 depends on stages: Stage-1
+  Stage-7 depends on stages: Stage-1 , consists of Stage-4, Stage-3, Stage-5
+  Stage-4
+  Stage-0 depends on stages: Stage-4, Stage-3, Stage-6
   Stage-2 depends on stages: Stage-0
+  Stage-3
+  Stage-5
+  Stage-6 depends on stages: Stage-5
 
 STAGE PLANS:
   Stage: Stage-1
@@ -5246,19 +5879,45 @@ STAGE PLANS:
               Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
               Group By Operator
                 aggregations: count(1)
-                bucketGroup: true
                 keys: _col0 (type: string), 2 (type: int), _col2 (type: string)
-                mode: hash
+                mode: final
                 outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                Reduce Output Operator
-                  key expressions: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  sort order: +++
-                  Map-reduce partition columns: _col0 (type: string), _col1 (type: int), _col2 (type: string)
-                  Statistics: Num rows: 6 Data size: 24 Basic stats: COMPLETE Column stats: NONE
-                  tag: -1
-                  value expressions: _col3 (type: bigint)
-                  auto parallelism: false
+                Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                Select Operator
+                  expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
+                  outputColumnNames: _col0, _col1, _col2, _col3
+                  Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+                  File Output Operator
+                    compressed: false
+                    GlobalTableId: 1
+#### A masked pattern was here ####
+                    NumFilesPerFileSink: 1
+                    Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+#### A masked pattern was here ####
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        properties:
+                          COLUMN_STATS_ACCURATE true
+                          bucket_count -1
+                          columns key1,key2,key3,cnt
+                          columns.comments 
+                          columns.types int:int:string:int
+#### A masked pattern was here ####
+                          name default.outputtbl4
+                          numFiles 1
+                          numRows 6
+                          rawDataSize 48
+                          serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                          serialization.format 1
+                          serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          totalSize 54
+#### A masked pattern was here ####
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                        name: default.outputtbl4
+                    TotalFiles: 1
+                    GatherStats: true
+                    MultiFileSpray: false
       Path -> Alias:
 #### A masked pattern was here ####
       Path -> Partition:
@@ -5311,26 +5970,58 @@ STAGE PLANS:
               name: default.t2
             name: default.t2
       Truncated Path -> Alias:
-        /t2 [$hdt$_0:$hdt$_0:$hdt$_0:t2]
-      Needs Tagging: false
-      Reduce Operator Tree:
-        Group By Operator
-          aggregations: count(VALUE._col0)
-          keys: KEY._col0 (type: string), KEY._col1 (type: int), KEY._col2 (type: string)
-          mode: mergepartial
-          outputColumnNames: _col0, _col1, _col2, _col3
-          Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-          Select Operator
-            expressions: UDFToInteger(_col0) (type: int), _col1 (type: int), _col2 (type: string), UDFToInteger(_col3) (type: int)
-            outputColumnNames: _col0, _col1, _col2, _col3
-            Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
+        /t2 [$hdt$_0:t2]
+
+  Stage: Stage-7
+    Conditional Operator
+
+  Stage: Stage-4
+    Move Operator
+      files:
+          hdfs directory: true
+#### A masked pattern was here ####
+
+  Stage: Stage-0
+    Move Operator
+      tables:
+          replace: true
+#### A masked pattern was here ####
+          table:
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+
+  Stage: Stage-2
+    Stats-Aggr Operator
+#### A masked pattern was here ####
+
+  Stage: Stage-3
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
             File Output Operator
               compressed: false
-              GlobalTableId: 1
+              GlobalTableId: 0
 #### A masked pattern was here ####
               NumFilesPerFileSink: 1
-              Statistics: Num rows: 3 Data size: 12 Basic stats: COMPLETE Column stats: NONE
-#### A masked pattern was here ####
               table:
                   input format: org.apache.hadoop.mapred.TextInputFormat
                   output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
@@ -5353,15 +6044,118 @@ STAGE PLANS:
                   serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
                   name: default.outputtbl4
               TotalFiles: 1
-              GatherStats: true
+              GatherStats: false
               MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
+              input format: org.apache.hadoop.mapred.TextInputFormat
+              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+              properties:
+                COLUMN_STATS_ACCURATE true
+                bucket_count -1
+                columns key1,key2,key3,cnt
+                columns.comments 
+                columns.types int:int:string:int
+#### A masked pattern was here ####
+                name default.outputtbl4
+                numFiles 1
+                numRows 6
+                rawDataSize 48
+                serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                serialization.format 1
+                serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                totalSize 54
+#### A masked pattern was here ####
+              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-0
-    Move Operator
-      tables:
-          replace: true
+  Stage: Stage-5
+    Map Reduce
+      Map Operator Tree:
+          TableScan
+            GatherStats: false
+            File Output Operator
+              compressed: false
+              GlobalTableId: 0
 #### A masked pattern was here ####
-          table:
+              NumFilesPerFileSink: 1
+              table:
+                  input format: org.apache.hadoop.mapred.TextInputFormat
+                  output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                  properties:
+                    COLUMN_STATS_ACCURATE true
+                    bucket_count -1
+                    columns key1,key2,key3,cnt
+                    columns.comments 
+                    columns.types int:int:string:int
+#### A masked pattern was here ####
+                    name default.outputtbl4
+                    numFiles 1
+                    numRows 6
+                    rawDataSize 48
+                    serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+                    serialization.format 1
+                    serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                    totalSize 54
+#### A masked pattern was here ####
+                  serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                  name: default.outputtbl4
+              TotalFiles: 1
+              GatherStats: false
+              MultiFileSpray: false
+      Path -> Alias:
+#### A masked pattern was here ####
+      Path -> Partition:
+#### A masked pattern was here ####
+          Partition
+            base file name: -ext-10001
+            input format: org.apache.hadoop.mapred.TextInputFormat
+            output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+            properties:
+              COLUMN_STATS_ACCURATE true
+              bucket_count -1
+              columns key1,key2,key3,cnt
+              columns.comments 
+              columns.types int:int:string:int
+#### A masked pattern was here ####
+              name default.outputtbl4
+              numFiles 1
+              numRows 6
+              rawDataSize 48
+              serialization.ddl struct outputtbl4 { i32 key1, i32 key2, string key3, i32 cnt}
+              serialization.format 1
+              serialization.lib org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+              totalSize 54
+#### A masked pattern was here ####
+            serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+          
               input format: org.apache.hadoop.mapred.TextInputFormat
               output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
               properties:
@@ -5382,9 +6176,14 @@ STAGE PLANS:
 #### A masked pattern was here ####
               serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
               name: default.outputtbl4
+            name: default.outputtbl4
+      Truncated Path -> Alias:
+#### A masked pattern was here ####
 
-  Stage: Stage-2
-    Stats-Aggr Operator
+  Stage: Stage-6
+    Move Operator
+      files:
+          hdfs directory: true
 #### A masked pattern was here ####
 
 PREHOOK: query: INSERT OVERWRITE TABLE outputTbl4

Modified: hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_6.q.out
URL: http://svn.apache.org/viewvc/hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_6.q.out?rev=1670462&r1=1670461&r2=1670462&view=diff
==============================================================================
--- hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_6.q.out (original)
+++ hive/branches/cbo/ql/src/test/results/clientpositive/groupby_sort_6.q.out Tue Mar 31 20:14:02 2015
@@ -425,7 +425,7 @@ STAGE PLANS:
               name: default.t1
             name: default.t1
       Truncated Path -> Alias:
-        /t1/ds=2 [$hdt$_0:$hdt$_0:t1]
+        /t1/ds=2 [$hdt$_0:t1]
       Needs Tagging: false
       Reduce Operator Tree:
         Group By Operator



Mime
View raw message