You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@hive.apache.org by na...@apache.org on 2011/03/24 06:05:09 UTC
svn commit: r1084847 - in /hive/trunk/ql/src:
java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java
java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java
test/queries/clientpositive/auto_join27.q
test/results/clientpositive/auto_join27.q.out
Author: namit
Date: Thu Mar 24 05:05:09 2011
New Revision: 1084847
URL: http://svn.apache.org/viewvc?rev=1084847&view=rev
Log:
HIVE-1965 Auto convert mapjoin should not throw exception if the top
operator is union operator (Yongqiang He via namit)
[Title]
Summary:
Trac Bug: #
Blame Rev:
Reviewed By:
Test Plan:
Revert Plan:
Database Impact:
Memcache Impact:
Other Notes:
EImportant:
- begin *PUBLIC* platform impact section -
Bugzilla: #
- end platform impact -
Added:
hive/trunk/ql/src/test/queries/clientpositive/auto_join27.q
hive/trunk/ql/src/test/results/clientpositive/auto_join27.q.out
Modified:
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java
hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java?rev=1084847&r1=1084846&r2=1084847&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/lib/DefaultGraphWalker.java Thu Mar 24 05:05:09 2011
@@ -121,11 +121,9 @@ public class DefaultGraphWalker implemen
if ((nd.getChildren() == null)
|| getDispatchedList().containsAll(nd.getChildren())) {
// all children are done or no need to walk the children
- if (getDispatchedList().contains(nd)) {
- // sanity check
- assert false;
+ if (!getDispatchedList().contains(nd)) {
+ dispatch(nd, opStack);
}
- dispatch(nd, opStack);
opStack.pop();
return;
}
Modified: hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java?rev=1084847&r1=1084846&r2=1084847&view=diff
==============================================================================
--- hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java (original)
+++ hive/trunk/ql/src/java/org/apache/hadoop/hive/ql/optimizer/MapJoinProcessor.java Thu Mar 24 05:05:09 2011
@@ -129,16 +129,11 @@ public class MapJoinProcessor implements
.entrySet()) {
String alias = entry.getKey();
Operator<? extends Serializable> op = entry.getValue();
- // get table scan op
- if (!(op instanceof TableScanOperator)) {
- throw new SemanticException("top op is not table scan");
- }
- TableScanOperator tableScanOp = (TableScanOperator) op;
// if the table scan is for big table; then skip it
// tracing down the operator tree from the table scan operator
- Operator<? extends Serializable> parentOp = tableScanOp;
- Operator<? extends Serializable> childOp = tableScanOp.getChildOperators().get(0);
+ Operator<? extends Serializable> parentOp = op;
+ Operator<? extends Serializable> childOp = op.getChildOperators().get(0);
while ((childOp != null) && (!childOp.equals(mapJoinOp))) {
parentOp = childOp;
assert parentOp.getChildOperators().size() == 1;
@@ -155,7 +150,7 @@ public class MapJoinProcessor implements
continue;
}
// set alias to work and put into smallTableAliasList
- newLocalWork.getAliasToWork().put(alias, tableScanOp);
+ newLocalWork.getAliasToWork().put(alias, op);
smallTableAliasList.add(alias);
// get input path and remove this alias from pathToAlias
// because this file will be fetched by fetch operator
Added: hive/trunk/ql/src/test/queries/clientpositive/auto_join27.q
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/queries/clientpositive/auto_join27.q?rev=1084847&view=auto
==============================================================================
--- hive/trunk/ql/src/test/queries/clientpositive/auto_join27.q (added)
+++ hive/trunk/ql/src/test/queries/clientpositive/auto_join27.q Thu Mar 24 05:05:09 2011
@@ -0,0 +1,25 @@
+set hive.auto.convert.join = true;
+
+explain
+SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200;
+
+
+SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200;
Added: hive/trunk/ql/src/test/results/clientpositive/auto_join27.q.out
URL: http://svn.apache.org/viewvc/hive/trunk/ql/src/test/results/clientpositive/auto_join27.q.out?rev=1084847&view=auto
==============================================================================
--- hive/trunk/ql/src/test/results/clientpositive/auto_join27.q.out (added)
+++ hive/trunk/ql/src/test/results/clientpositive/auto_join27.q.out Thu Mar 24 05:05:09 2011
@@ -0,0 +1,425 @@
+PREHOOK: query: explain
+SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200
+PREHOOK: type: QUERY
+POSTHOOK: query: explain
+SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200
+POSTHOOK: type: QUERY
+ABSTRACT SYNTAX TREE:
+ (TOK_QUERY (TOK_FROM (TOK_JOIN (TOK_SUBQUERY (TOK_UNION (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value))))) (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECTDI (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key)) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value)))))) src_12) (TOK_SUBQUERY (TOK_QUERY (TOK_FROM (TOK_TABREF (TOK_TABNAME src))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) key) k) (TOK_SELEXPR (. (TOK_TABLE_OR_COL src) value) v)))) src3) (AND (= (. (TOK_TABLE_OR_COL src_12) key) (. (TOK_TABLE_OR_COL src3) k)) (< (. (TOK_TABLE_OR_COL src3) k) 200)))) (TOK_INSERT (TOK_DESTINATION (TOK_DIR TOK_TMP_FILE)) (TOK_SELECT (TOK_SELEXPR (TOK_FUNCTION count 1)))))
+
+STAGE DEPENDENCIES:
+ Stage-1 is a root stage
+ Stage-8 depends on stages: Stage-1, Stage-4 , consists of Stage-9, Stage-10, Stage-2
+ Stage-9 has a backup stage: Stage-2
+ Stage-6 depends on stages: Stage-9
+ Stage-3 depends on stages: Stage-2, Stage-6, Stage-7
+ Stage-10 has a backup stage: Stage-2
+ Stage-7 depends on stages: Stage-10
+ Stage-2
+ Stage-4 is a root stage
+ Stage-0 is a root stage
+
+STAGE PLANS:
+ Stage: Stage-1
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery2:src_12-subquery2:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: key, value
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ mode: hash
+ outputColumnNames: _col0, _col1
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ sort order: ++
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ tag: -1
+ Reduce Operator Tree:
+ Group By Operator
+ bucketGroup: false
+ keys:
+ expr: KEY._col0
+ type: string
+ expr: KEY._col1
+ type: string
+ mode: mergepartial
+ outputColumnNames: _col0, _col1
+ Select Operator
+ expressions:
+ expr: _col0
+ type: string
+ expr: _col1
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-8
+ Conditional Operator
+
+ Stage: Stage-9
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ src3:src
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ src3:src
+ TableScan
+ alias: src
+ Filter Operator
+ predicate:
+ expr: (key < 200)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: _col0
+ Filter Operator
+ predicate:
+ expr: (_col0 < 200)
+ type: boolean
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+
+ Stage: Stage-6
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10002
+ Union
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10004
+ Union
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 0
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-3
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10003
+ Reduce Output Operator
+ sort order:
+ tag: -1
+ value expressions:
+ expr: _col0
+ type: bigint
+ Reduce Operator Tree:
+ Group By Operator
+ aggregations:
+ expr: count(VALUE._col0)
+ bucketGroup: false
+ mode: mergepartial
+ outputColumnNames: _col0
+ Select Operator
+ expressions:
+ expr: _col0
+ type: bigint
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.TextInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveIgnoreKeyTextOutputFormat
+
+ Stage: Stage-10
+ Map Reduce Local Work
+ Alias -> Map Local Tables:
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10002
+ Fetch Operator
+ limit: -1
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10004
+ Fetch Operator
+ limit: -1
+ Alias -> Map Local Operator Tree:
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10002
+ Union
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10004
+ Union
+ HashTable Sink Operator
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+
+ Stage: Stage-7
+ Map Reduce
+ Alias -> Map Operator Tree:
+ src3:src
+ TableScan
+ alias: src
+ Filter Operator
+ predicate:
+ expr: (key < 200)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: _col0
+ Filter Operator
+ predicate:
+ expr: (_col0 < 200)
+ type: boolean
+ Map Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ keys:
+ 0 [Column[_col0]]
+ 1 [Column[_col0]]
+ Position of Big Table: 1
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+ Local Work:
+ Map Reduce Local Work
+
+ Stage: Stage-2
+ Map Reduce
+ Alias -> Map Operator Tree:
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10002
+ Union
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ file:/tmp/njain/hive_2011-03-23_22-02-43_416_1632994873933518743/-mr-10004
+ Union
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 0
+ src3:src
+ TableScan
+ alias: src
+ Filter Operator
+ predicate:
+ expr: (key < 200)
+ type: boolean
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ outputColumnNames: _col0
+ Filter Operator
+ predicate:
+ expr: (_col0 < 200)
+ type: boolean
+ Reduce Output Operator
+ key expressions:
+ expr: _col0
+ type: string
+ sort order: +
+ Map-reduce partition columns:
+ expr: _col0
+ type: string
+ tag: 1
+ Reduce Operator Tree:
+ Join Operator
+ condition map:
+ Inner Join 0 to 1
+ condition expressions:
+ 0
+ 1
+ handleSkewJoin: false
+ Select Operator
+ Group By Operator
+ aggregations:
+ expr: count(1)
+ bucketGroup: false
+ mode: hash
+ outputColumnNames: _col0
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-4
+ Map Reduce
+ Alias -> Map Operator Tree:
+ null-subquery1:src_12-subquery1:src
+ TableScan
+ alias: src
+ Select Operator
+ expressions:
+ expr: key
+ type: string
+ expr: value
+ type: string
+ outputColumnNames: _col0, _col1
+ File Output Operator
+ compressed: false
+ GlobalTableId: 0
+ table:
+ input format: org.apache.hadoop.mapred.SequenceFileInputFormat
+ output format: org.apache.hadoop.hive.ql.io.HiveSequenceFileOutputFormat
+
+ Stage: Stage-0
+ Fetch Operator
+ limit: -1
+
+
+PREHOOK: query: SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200
+PREHOOK: type: QUERY
+PREHOOK: Input: default@src
+PREHOOK: Output: file:/tmp/njain/hive_2011-03-23_22-02-44_469_912794075622273367/-mr-10000
+POSTHOOK: query: SELECT count(1)
+FROM
+(
+SELECT src.key, src.value from src
+UNION ALL
+SELECT DISTINCT src.key, src.value from src
+) src_12
+JOIN
+(SELECT src.key as k, src.value as v from src) src3
+ON src_12.key = src3.k AND src3.k < 200
+POSTHOOK: type: QUERY
+POSTHOOK: Input: default@src
+POSTHOOK: Output: file:/tmp/njain/hive_2011-03-23_22-02-44_469_912794075622273367/-mr-10000
+548