Namit Jain created HIVE-3892: -------------------------------- Summary: auto sort merge join does not work for sub-queries Key: HIVE-3892 URL: https://issues.apache.org/jira/browse/HIVE-3892 Project: Hive Issue Type: Bug Components: Query Processor Reporter: Namit Jain Assignee: Namit Jain
set hive.enforce.bucketing = true; set hive.enforce.sorting = true; set hive.exec.reducers.max = 1; CREATE TABLE tbl1(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; CREATE TABLE tbl2(key int, value string) CLUSTERED BY (key) SORTED BY (key) INTO 2 BUCKETS; insert overwrite table tbl1 select * from src where key < 10; insert overwrite table tbl2 select * from src where key < 10; set hive.auto.sort.merge.join=true; set hive.optimize.bucketmapjoin = true; set hive.optimize.bucketmapjoin.sortedmerge = true; set hive.auto.sort.merge.join.bigtbl.matcher = org.apache.hadoop.hive.ql.optimizer.SizeSortMergeJoinBigTableMatcher; -- The join is being performed in sub-query. It should be converted to a sort-merge join explain select count(*) from ( select a.key as key, a.value as val1, b.value as val2 from tbl1 a join tbl2 b on a.key = b.key ) subq1; Even after HIVE-3403, the test above does not convert to a sort-merge join. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira