hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From hashut...@apache.org
Subject [1/9] hive git commit: HIVE-11171 : Join reordering algorithm might introduce projects between joins (Jesus Camacho Rodriguez via Ashutosh Chauhan)
Date Tue, 07 Jul 2015 16:21:38 GMT
Repository: hive
Updated Branches:
  refs/heads/master 7b98e37a8 -> b963769d4


http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out
index 2a41aae..01ccae7 100644
--- a/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out
+++ b/ql/src/test/results/clientpositive/tez/limit_pushdown.q.out
@@ -887,9 +887,9 @@ STAGE PLANS:
     Tez
       Edges:
         Reducer 2 <- Map 1 (SIMPLE_EDGE)
-        Reducer 3 <- Reducer 2 (SIMPLE_EDGE)
-        Reducer 4 <- Reducer 3 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
-        Reducer 6 <- Map 5 (SIMPLE_EDGE)
+        Reducer 3 <- Reducer 2 (SIMPLE_EDGE), Reducer 6 (SIMPLE_EDGE)
+        Reducer 5 <- Map 4 (SIMPLE_EDGE)
+        Reducer 6 <- Reducer 5 (SIMPLE_EDGE)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -914,7 +914,7 @@ STAGE PLANS:
                         Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
                         TopN Hash Memory Usage: 0.3
                         value expressions: _col1 (type: bigint)
-        Map 5 
+        Map 4 
             Map Operator Tree:
                 TableScan
                   alias: src
@@ -945,32 +945,18 @@ STAGE PLANS:
                 outputColumnNames: _col0, _col1
                 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats:
NONE
                 Limit
-                  Number of rows: 3
-                  Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
-                  Reduce Output Operator
-                    sort order: 
-                    Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
-                    TopN Hash Memory Usage: 0.3
-                    value expressions: _col0 (type: string), _col1 (type: bigint)
-        Reducer 3 
-            Reduce Operator Tree:
-              Select Operator
-                expressions: VALUE._col0 (type: string), VALUE._col1 (type: bigint)
-                outputColumnNames: _col0, _col1
-                Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
-                Limit
-                  Number of rows: 3
-                  Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
+                  Number of rows: 2
+                  Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats:
NONE
                   Filter Operator
                     predicate: _col0 is not null (type: boolean)
-                    Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: string)
-                      Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: bigint)
-        Reducer 4 
+        Reducer 3 
             Reduce Operator Tree:
               Merge Join Operator
                 condition map:
@@ -978,23 +964,19 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col0, _col1, _col3
+                outputColumnNames: _col0, _col1, _col2, _col3
                 Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col0 (type: string), _col3 (type: bigint), _col0 (type: string),
_col1 (type: bigint)
-                  outputColumnNames: _col0, _col1, _col2, _col3
+                Limit
+                  Number of rows: 4
                   Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats:
NONE
-                  Limit
-                    Number of rows: 4
+                  File Output Operator
+                    compressed: false
                     Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column stats:
NONE
-                    File Output Operator
-                      compressed: false
-                      Statistics: Num rows: 2 Data size: 22 Basic stats: COMPLETE Column
stats: NONE
-                      table:
-                          input format: org.apache.hadoop.mapred.TextInputFormat
-                          output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                          serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 6 
+                    table:
+                        input format: org.apache.hadoop.mapred.TextInputFormat
+                        output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                        serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Reducer 5 
             Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
@@ -1003,16 +985,30 @@ STAGE PLANS:
                 outputColumnNames: _col0, _col1
                 Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column stats:
NONE
                 Limit
-                  Number of rows: 2
-                  Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats:
NONE
+                  Number of rows: 3
+                  Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
+                  Reduce Output Operator
+                    sort order: 
+                    Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
+                    TopN Hash Memory Usage: 0.3
+                    value expressions: _col0 (type: string), _col1 (type: bigint)
+        Reducer 6 
+            Reduce Operator Tree:
+              Select Operator
+                expressions: VALUE._col0 (type: string), VALUE._col1 (type: bigint)
+                outputColumnNames: _col0, _col1
+                Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
+                Limit
+                  Number of rows: 3
+                  Statistics: Num rows: 3 Data size: 30 Basic stats: COMPLETE Column stats:
NONE
                   Filter Operator
                     predicate: _col0 is not null (type: boolean)
-                    Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column stats:
NONE
+                    Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column stats:
NONE
                     Reduce Output Operator
                       key expressions: _col0 (type: string)
                       sort order: +
                       Map-reduce partition columns: _col0 (type: string)
-                      Statistics: Num rows: 1 Data size: 10 Basic stats: COMPLETE Column
stats: NONE
+                      Statistics: Num rows: 2 Data size: 20 Basic stats: COMPLETE Column
stats: NONE
                       value expressions: _col1 (type: bigint)
 
   Stage: Stage-0

http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/tez/mrr.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/mrr.q.out b/ql/src/test/results/clientpositive/tez/mrr.q.out
index d42f9b0..efbd02d 100644
--- a/ql/src/test/results/clientpositive/tez/mrr.q.out
+++ b/ql/src/test/results/clientpositive/tez/mrr.q.out
@@ -1679,7 +1679,7 @@ STAGE PLANS:
   Stage: Stage-1
     Tez
       Edges:
-        Map 1 <- Reducer 4 (BROADCAST_EDGE)
+        Map 3 <- Reducer 2 (BROADCAST_EDGE)
         Reducer 2 <- Map 1 (SIMPLE_EDGE)
         Reducer 4 <- Map 3 (SIMPLE_EDGE)
 #### A masked pattern was here ####
@@ -1696,26 +1696,18 @@ STAGE PLANS:
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1, _col3
-                        input vertices:
-                          1 Reducer 4
-                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
-                        HybridGraceHashJoin: true
-                        Select Operator
-                          expressions: _col0 (type: string), _col3 (type: bigint), _col1
(type: string)
-                          outputColumnNames: _col0, _col1, _col3
-                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE
Column stats: NONE
-                          Reduce Output Operator
-                            key expressions: _col0 (type: string)
-                            sort order: +
-                            Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE
Column stats: NONE
-                            value expressions: _col1 (type: bigint), _col3 (type: string)
+                      Group By Operator
+                        aggregations: count(_col1)
+                        keys: _col0 (type: string)
+                        mode: hash
+                        outputColumnNames: _col0, _col1
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                        Reduce Output Operator
+                          key expressions: _col0 (type: string)
+                          sort order: +
+                          Map-reduce partition columns: _col0 (type: string)
+                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE
Column stats: NONE
+                          value expressions: _col1 (type: bigint)
         Map 3 
             Map Operator Tree:
                 TableScan
@@ -1728,33 +1720,24 @@ STAGE PLANS:
                       expressions: key (type: string), value (type: string)
                       outputColumnNames: _col0, _col1
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-                      Group By Operator
-                        aggregations: count(_col1)
-                        keys: _col0 (type: string)
-                        mode: hash
-                        outputColumnNames: _col0, _col1
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        outputColumnNames: _col0, _col1, _col2, _col3
+                        input vertices:
+                          0 Reducer 2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                        HybridGraceHashJoin: true
                         Reduce Output Operator
                           key expressions: _col0 (type: string)
                           sort order: +
-                          Map-reduce partition columns: _col0 (type: string)
-                          Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE
Column stats: NONE
-                          value expressions: _col1 (type: bigint)
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE
Column stats: NONE
+                          value expressions: _col1 (type: bigint), _col2 (type: string),
_col3 (type: string)
         Reducer 2 
             Reduce Operator Tree:
-              Select Operator
-                expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint),
KEY.reducesinkkey0 (type: string), VALUE._col1 (type: string)
-                outputColumnNames: _col0, _col1, _col2, _col3
-                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats:
NONE
-                File Output Operator
-                  compressed: false
-                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
-                  table:
-                      input format: org.apache.hadoop.mapred.TextInputFormat
-                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Reducer 4 
-            Reduce Operator Tree:
               Group By Operator
                 aggregations: count(VALUE._col0)
                 keys: KEY._col0 (type: string)
@@ -1767,6 +1750,19 @@ STAGE PLANS:
                   Map-reduce partition columns: _col0 (type: string)
                   Statistics: Num rows: 125 Data size: 1328 Basic stats: COMPLETE Column
stats: NONE
                   value expressions: _col1 (type: bigint)
+        Reducer 4 
+            Reduce Operator Tree:
+              Select Operator
+                expressions: KEY.reducesinkkey0 (type: string), VALUE._col0 (type: bigint),
VALUE._col1 (type: string), VALUE._col2 (type: string)
+                outputColumnNames: _col0, _col1, _col2, _col3
+                Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column stats:
NONE
+                File Output Operator
+                  compressed: false
+                  Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                  table:
+                      input format: org.apache.hadoop.mapred.TextInputFormat
+                      output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                      serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
 
   Stage: Stage-0
     Fetch Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/tez/skewjoin.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/skewjoin.q.out b/ql/src/test/results/clientpositive/tez/skewjoin.q.out
index ec368f9..7d0a8e5 100644
--- a/ql/src/test/results/clientpositive/tez/skewjoin.q.out
+++ b/ql/src/test/results/clientpositive/tez/skewjoin.q.out
@@ -858,15 +858,14 @@ STAGE PLANS:
                     predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) <
80.0)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
-                      expressions: key (type: string), value (type: string)
-                      outputColumnNames: _col0, _col1
+                      expressions: key (type: string)
+                      outputColumnNames: _col0
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
-                        value expressions: _col1 (type: string)
         Map 6 
             Map Operator Tree:
                 TableScan
@@ -876,14 +875,15 @@ STAGE PLANS:
                     predicate: ((UDFToDouble(key) < 100.0) and (UDFToDouble(key) <
80.0)) (type: boolean)
                     Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
                     Select Operator
-                      expressions: key (type: string)
-                      outputColumnNames: _col0
+                      expressions: key (type: string), value (type: string)
+                      outputColumnNames: _col0, _col1
                       Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
                       Reduce Output Operator
                         key expressions: _col0 (type: string)
                         sort order: +
                         Map-reduce partition columns: _col0 (type: string)
                         Statistics: Num rows: 55 Data size: 584 Basic stats: COMPLETE Column
stats: NONE
+                        value expressions: _col1 (type: string)
         Reducer 2 
             Reduce Operator Tree:
               Merge Join Operator
@@ -929,18 +929,14 @@ STAGE PLANS:
                 keys:
                   0 _col0 (type: string)
                   1 _col0 (type: string)
-                outputColumnNames: _col1, _col2
+                outputColumnNames: _col0, _col2
                 Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats:
NONE
-                Select Operator
-                  expressions: _col2 (type: string), _col1 (type: string)
-                  outputColumnNames: _col0, _col2
+                Reduce Output Operator
+                  key expressions: _col0 (type: string)
+                  sort order: +
+                  Map-reduce partition columns: _col0 (type: string)
                   Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column stats:
NONE
-                  Reduce Output Operator
-                    key expressions: _col0 (type: string)
-                    sort order: +
-                    Map-reduce partition columns: _col0 (type: string)
-                    Statistics: Num rows: 60 Data size: 642 Basic stats: COMPLETE Column
stats: NONE
-                    value expressions: _col2 (type: string)
+                  value expressions: _col2 (type: string)
 
   Stage: Stage-0
     Fetch Operator

http://git-wip-us.apache.org/repos/asf/hive/blob/b963769d/ql/src/test/results/clientpositive/tez/tez_union.q.out
----------------------------------------------------------------------
diff --git a/ql/src/test/results/clientpositive/tez/tez_union.q.out b/ql/src/test/results/clientpositive/tez/tez_union.q.out
index 4012b90..5a7d0d6 100644
--- a/ql/src/test/results/clientpositive/tez/tez_union.q.out
+++ b/ql/src/test/results/clientpositive/tez/tez_union.q.out
@@ -330,8 +330,8 @@ STAGE PLANS:
   Stage: Stage-1
     Tez
       Edges:
-        Map 1 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS)
-        Map 3 <- Map 4 (BROADCAST_EDGE), Union 2 (CONTAINS)
+        Map 2 <- Map 1 (BROADCAST_EDGE), Union 3 (CONTAINS)
+        Map 4 <- Map 1 (BROADCAST_EDGE), Union 3 (CONTAINS)
 #### A masked pattern was here ####
       Vertices:
         Map 1 
@@ -346,29 +346,17 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-                      Map Join Operator
-                        condition map:
-                             Inner Join 0 to 1
-                        keys:
-                          0 _col0 (type: string)
-                          1 _col0 (type: string)
-                        outputColumnNames: _col0, _col1
-                        input vertices:
-                          1 Map 4
-                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column
stats: NONE
-                        HybridGraceHashJoin: true
-                        Select Operator
-                          expressions: _col1 (type: string), _col0 (type: string)
-                          outputColumnNames: _col0, _col1
-                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE
Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE
Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
-        Map 3 
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                      Reduce Output Operator
+                        key expressions: _col0 (type: string)
+                        sort order: +
+                        Map-reduce partition columns: _col0 (type: string)
+                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+        Map 2 
             Map Operator Tree:
                 TableScan
                   alias: s1
@@ -388,20 +376,16 @@ STAGE PLANS:
                           1 _col0 (type: string)
                         outputColumnNames: _col0, _col1
                         input vertices:
-                          1 Map 4
+                          0 Map 1
                         Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column
stats: NONE
                         HybridGraceHashJoin: true
-                        Select Operator
-                          expressions: _col1 (type: string), _col0 (type: string)
-                          outputColumnNames: _col0, _col1
+                        File Output Operator
+                          compressed: false
                           Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE
Column stats: NONE
-                          File Output Operator
-                            compressed: false
-                            Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE
Column stats: NONE
-                            table:
-                                input format: org.apache.hadoop.mapred.TextInputFormat
-                                output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
-                                serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+                          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
         Map 4 
             Map Operator Tree:
                 TableScan
@@ -414,18 +398,26 @@ STAGE PLANS:
                       expressions: key (type: string)
                       outputColumnNames: _col0
                       Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-                      Reduce Output Operator
-                        key expressions: _col0 (type: string)
-                        sort order: +
-                        Map-reduce partition columns: _col0 (type: string)
-                        Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
-        Union 2 
-            Vertex: Union 2
+                      Map Join Operator
+                        condition map:
+                             Inner Join 0 to 1
+                        keys:
+                          0 _col0 (type: string)
+                          1 _col0 (type: string)
+                        outputColumnNames: _col0, _col1
+                        input vertices:
+                          0 Map 1
+                        Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE Column
stats: NONE
+                        HybridGraceHashJoin: true
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 550 Data size: 5843 Basic stats: COMPLETE
Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+        Union 3 
+            Vertex: Union 3
 
   Stage: Stage-0
     Fetch Operator


Mime
View raw message