[ https://issues.apache.org/jira/browse/HIVE-7023?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Navis updated HIVE-7023: ------------------------ Status: Patch Available (was: Open) > Bucket mapjoin is broken when small aliases are more than two > ------------------------------------------------------------- > > Key: HIVE-7023 > URL: https://issues.apache.org/jira/browse/HIVE-7023 > Project: Hive > Issue Type: Bug > Components: Query Processor > Affects Versions: 0.13.0 > Reporter: Navis > Assignee: Navis > Attachments: HIVE-7023.1.patch.txt > > > From auto_sortmerge_join_11.q, > {noformat} > -- small 1 part, 2 bucket & big 2 part, 4 bucket > CREATE TABLE bucket_small (key string, value string) partitioned by (ds > string) CLUSTERED BY (key) INTO 2 BUCKETS STORED AS TEXTFILE; > load data local inpath '../../data/files/smallsrcsortbucket1outof4.txt' INTO > TABLE bucket_small partition(ds='2008-04-08'); > load data local inpath '../../data/files/smallsrcsortbucket2outof4.txt' INTO > TABLE bucket_small partition(ds='2008-04-08'); > CREATE TABLE bucket_big (key string, value string) partitioned by (ds string) > CLUSTERED BY (key) INTO 4 BUCKETS STORED AS TEXTFILE; > load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-08'); > load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-08'); > load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-08'); > load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-08'); > load data local inpath '../../data/files/srcsortbucket1outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-09'); > load data local inpath '../../data/files/srcsortbucket2outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-09'); > load data local inpath '../../data/files/srcsortbucket3outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-09'); > load data local inpath '../../data/files/srcsortbucket4outof4.txt' INTO TABLE > bucket_big partition(ds='2008-04-09'); > set hive.auto.convert.join=true; > set hive.ignore.mapjoin.hint=false; > set hive.auto.convert.sortmerge.join=true; > set hive.optimize.bucketmapjoin=true; > set hive.optimize.bucketmapjoin.sortedmerge=true; > select /* + MAPJOIN(a,b) */ count(*) FROM bucket_small a JOIN bucket_big b ON > a.key = b.key JOIN bucket_big c ON a.key = c.key; > {noformat} > The last query produces 0 row, instead of 180 rows, which is correct. -- This message was sent by Atlassian JIRA (v6.2#6252)