[HIVE-3218] Stream table of SMBJoin/BucketMapJoin with two or more partitions is not handled properly

• Type: Bug
• Status: Closed
• Priority: Critical
• Resolution: Fixed
• Affects Version/s: 0.10.0
• Fix Version/s: 0.10.0
• Component/s: Query Processor
• Hadoop Flags: Reviewed
• Assignee: Navis Ryu
• Reporter: Navis Ryu
• Created: 30/Jun/12 00:33
• Updated: 10/Jan/13 19:53
• Resolved: 30/Jul/12 07:22

Description

drop table hive_test_smb_bucket1;
drop table hive_test_smb_bucket2;

create table hive_test_smb_bucket1 (key int, value string) partitioned by (ds string) clustered by (key) sorted by (key) into 2 buckets;
create table hive_test_smb_bucket2 (key int, value string) partitioned by (ds string) clustered by (key) sorted by (key) into 2 buckets;

set hive.enforce.bucketing = true;
set hive.enforce.sorting = true;

insert overwrite table hive_test_smb_bucket1 partition (ds='2010-10-14') select key, value from src;
insert overwrite table hive_test_smb_bucket1 partition (ds='2010-10-15') select key, value from src;
insert overwrite table hive_test_smb_bucket2 partition (ds='2010-10-15') select key, value from src;


set hive.optimize.bucketmapjoin = true;
set hive.optimize.bucketmapjoin.sortedmerge = true;
set hive.input.format = org.apache.hadoop.hive.ql.io.BucketizedHiveInputFormat;

SELECT /* + MAPJOIN(b) */ * FROM hive_test_smb_bucket1 a JOIN hive_test_smb_bucket2 b ON a.key = b.key;

which make bucket join context..

Alias Bucket Output File Name Mapping:
        hdfs://localhost:9000/user/hive/warehouse/hive_test_smb_bucket1/ds=2010-10-14/000000_0 0
        hdfs://localhost:9000/user/hive/warehouse/hive_test_smb_bucket1/ds=2010-10-14/000001_0 1
        hdfs://localhost:9000/user/hive/warehouse/hive_test_smb_bucket1/ds=2010-10-15/000000_0 0
        hdfs://localhost:9000/user/hive/warehouse/hive_test_smb_bucket1/ds=2010-10-15/000001_0 1

fails with exception

java.lang.RuntimeException: Hive Runtime Error while closing operators
	at org.apache.hadoop.hive.ql.exec.ExecMapper.close(ExecMapper.java:226)
	at org.apache.hadoop.mapred.MapRunner.run(MapRunner.java:57)
	at org.apache.hadoop.mapred.MapTask.runOldMapper(MapTask.java:391)
	at org.apache.hadoop.mapred.MapTask.run(MapTask.java:325)
	at org.apache.hadoop.mapred.Child$4.run(Child.java:270)
	at java.security.AccessController.doPrivileged(Native Method)
	at javax.security.auth.Subject.doAs(Subject.java:416)
	at org.apache.hadoop.security.UserGroupInformation.doAs(UserGroupInformation.java:1127)
	at org.apache.hadoop.mapred.Child.main(Child.java:264)
Caused by: org.apache.hadoop.hive.ql.metadata.HiveException: Unable to rename output from: hdfs://localhost:9000/tmp/hive-navis/hive_2012-06-29_22-17-49_574_6018646381714861925/_task_tmp.-ext-10001/_tmp.000001_0 to: hdfs://localhost:9000/tmp/hive-navis/hive_2012-06-29_22-17-49_574_6018646381714861925/_tmp.-ext-10001/000001_0
	at org.apache.hadoop.hive.ql.exec.FileSinkOperator$FSPaths.commit(FileSinkOperator.java:198)
	at org.apache.hadoop.hive.ql.exec.FileSinkOperator$FSPaths.access$300(FileSinkOperator.java:100)
	at org.apache.hadoop.hive.ql.exec.FileSinkOperator.closeOp(FileSinkOperator.java:717)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:557)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:566)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:566)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:566)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:566)
	at org.apache.hadoop.hive.ql.exec.Operator.close(Operator.java:566)
	at org.apache.hadoop.hive.ql.exec.ExecMapper.close(ExecMapper.java:193)
	... 8 more

Issue Links

• blocks: HIVE-3171 Bucketed sort merge join doesn't work when multiple files exist for small alias
• breaks: HIVE-3429 Bucket map join involving table with more than 1 partition column causes FileNotFoundException