hive-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Gopal V (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HIVE-13809) Hybrid Grace Hash Join memory usage estimation didn't take into account the bloom filter size
Date Fri, 20 May 2016 20:49:12 GMT

    [ https://issues.apache.org/jira/browse/HIVE-13809?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15294166#comment-15294166
] 

Gopal V commented on HIVE-13809:
--------------------------------

[~wzheng]: before we actually subtract such a large amount of memory from the join algorithms,
maybe we should figure out the input parameters to the bloom filter creation.

The reason it wasn't accounted for strictly was because of the relatively small size of bloom
filters - a 4 million keyset with 0.5% false positive rate should result in a bloom filter
which is approx ~6Mb.

Would be a good idea to figure out the false positive rate + estimated key count of the bloom
filter which grew to hundreds of Mbs and see if there's an implementation issue there.

> Hybrid Grace Hash Join memory usage estimation didn't take into account the bloom filter
size
> ---------------------------------------------------------------------------------------------
>
>                 Key: HIVE-13809
>                 URL: https://issues.apache.org/jira/browse/HIVE-13809
>             Project: Hive
>          Issue Type: Bug
>          Components: Hive
>    Affects Versions: 2.0.0, 2.1.0
>            Reporter: Wei Zheng
>            Assignee: Wei Zheng
>
> Memory estimation is important during hash table loading, because we need to make the
decision of whether to load the next hash partition in memory or spill it. If the assumption
is there's enough memory but it turns out not the case, we will run into OOM problem.
> Currently hybrid grace hash join memory usage estimation didn't take into account the
bloom filter size. In large test cases (TB scale) the bloom filter grows as big as hundreds
of MB, big enough to cause estimation error.
> The solution is to count in the bloom filter size into memory estimation.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)

Mime
View raw message