hive-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From vik...@apache.org
Subject svn commit: r1665371 - in /hive/trunk/ql/src: java/org/apache/hadoop/hive/ql/optimizer/ test/queries/clientpositive/ test/results/clientpositive/spark/ test/results/clientpositive/tez/
Date Mon, 09 Mar 2015 22:02:43 GMT
Author: vikram
Date: Mon Mar  9 22:02:43 2015
New Revision: 1665371

URL: http://svn.apache.org/r1665371
Log:
HIVE-9836: Hive on tez: fails when virtual columns are present in the join conditions (for
e.g. partition columns) (Vikram Dixit, reviewed by Gunther Hagleitner)

Modified:
    hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConvertJoinMapJoin.java
    hive/trunk/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
    hive/trunk/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
    hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out

Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConvertJoinMapJoin.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConvertJoinMapJoin.java?rev=1665371&r1=1665370&r2=1665371&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConvertJoinMapJoin.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/ConvertJoinMapJoin.java Mon
Mar  9 22:02:43 2015
@@ -484,6 +484,11 @@ public class ConvertJoinMapJoin implemen
         int colCount = 0;
         // parent op is guaranteed to have a single list because it is a reduce sink
         for (String colName : parentColNames.get(0)) {
+          if (listBucketCols.size() <= colCount) {
+            // can happen with virtual columns. RS would add the column to its output columns
+            // but it would not exist in the grandparent output columns or exprMap.
+            return false;
+          }
           // all columns need to be at least a subset of the parentOfParent's bucket cols
           ExprNodeDesc exprNodeDesc = colExprMap.get(colName);
           if (exprNodeDesc instanceof ExprNodeColumnDesc) {

Modified: hive/trunk/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q?rev=1665371&r1=1665370&r2=1665371&view=diff
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q (original)
+++ hive/trunk/ql/src/test/queries/clientpositive/bucket_map_join_tez1.q Mon Mar  9 22:02:43
2015
@@ -82,4 +82,6 @@ from tab1 a join tab_part b on a.key = b
 
 explain select a.key, b.key from tab_part a join tab_part c on a.key = c.key join tab_part
b on a.value = b.value;
 
-
+explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key and a.ds = b.ds;

Modified: hive/trunk/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out?rev=1665371&r1=1665370&r2=1665371&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/spark/bucket_map_join_tez1.q.out Mon Mar
 9 22:02:43 2015
@@ -1218,3 +1218,78 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key and a.ds = b.ds
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key and a.ds = b.ds
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-2 is a root stage
+  Stage-1 depends on stages: Stage-2
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-2
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column
stats: NONE
+                    Spark HashTable Sink Operator
+                      keys:
+                        0 key (type: int), ds (type: string)
+                        1 key (type: int), ds (type: string)
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-1
+    Spark
+#### A masked pattern was here ####
+      Vertices:
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int), ds (type: string)
+                        1 key (type: int), ds (type: string)
+                      outputColumnNames: _col0, _col1, _col7
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: string), _col7 (type:
string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE
Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+            Local Work:
+              Map Reduce Local Work
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+

Modified: hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out?rev=1665371&r1=1665370&r2=1665371&view=diff
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out (original)
+++ hive/trunk/ql/src/test/results/clientpositive/tez/bucket_map_join_tez1.q.out Mon Mar 
9 22:02:43 2015
@@ -1127,3 +1127,87 @@ STAGE PLANS:
       Processor Tree:
         ListSink
 
+PREHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key and a.ds = b.ds
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+select a.key, a.value, b.value
+from tab a join tab_part b on a.key = b.key and a.ds = b.ds
+POSTHOOK: type: QUERY
+STAGE DEPENDENCIES:
+  Stage-1 is a root stage
+  Stage-0 depends on stages: Stage-1
+
+STAGE PLANS:
+  Stage: Stage-1
+    Tez
+      Edges:
+        Map 2 <- Map 1 (BROADCAST_EDGE)
+#### A masked pattern was here ####
+      Vertices:
+        Map 1 
+            Map Operator Tree:
+                TableScan
+                  alias: a
+                  Statistics: Num rows: 242 Data size: 2566 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column
stats: NONE
+                    Reduce Output Operator
+                      key expressions: key (type: int), ds (type: string)
+                      sort order: ++
+                      Map-reduce partition columns: key (type: int), ds (type: string)
+                      Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column
stats: NONE
+                      value expressions: value (type: string)
+                    Select Operator
+                      expressions: ds (type: string)
+                      outputColumnNames: _col0
+                      Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column
stats: NONE
+                      Group By Operator
+                        keys: _col0 (type: string)
+                        mode: hash
+                        outputColumnNames: _col0
+                        Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE Column
stats: NONE
+                        Dynamic Partitioning Event Operator
+                          Target Input: b
+                          Partition key expr: ds
+                          Statistics: Num rows: 121 Data size: 1283 Basic stats: COMPLETE
Column stats: NONE
+                          Target column: ds
+                          Target Vertex: Map 2
+        Map 2 
+            Map Operator Tree:
+                TableScan
+                  alias: b
+                  Statistics: Num rows: 500 Data size: 5312 Basic stats: COMPLETE Column
stats: NONE
+                  Filter Operator
+                    predicate: key is not null (type: boolean)
+                    Statistics: Num rows: 250 Data size: 2656 Basic stats: COMPLETE Column
stats: NONE
+                    Map Join Operator
+                      condition map:
+                           Inner Join 0 to 1
+                      keys:
+                        0 key (type: int), ds (type: string)
+                        1 key (type: int), ds (type: string)
+                      outputColumnNames: _col0, _col1, _col7
+                      input vertices:
+                        0 Map 1
+                      Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                      Select Operator
+                        expressions: _col0 (type: int), _col1 (type: string), _col7 (type:
string)
+                        outputColumnNames: _col0, _col1, _col2
+                        Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE Column
stats: NONE
+                        File Output Operator
+                          compressed: false
+                          Statistics: Num rows: 275 Data size: 2921 Basic stats: COMPLETE
Column stats: NONE
+                          table:
+                              input format: org.apache.hadoop.mapred.TextInputFormat
+                              output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+                              serde: org.apache.hadoop.hive.serde2.lazy.LazySimpleSerDe
+
+  Stage: Stage-0
+    Fetch Operator
+      limit: -1
+      Processor Tree:
+        ListSink
+



Mime
View raw message