You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@hbase.apache.org by "Tak-Lon (Stephen) Wu (Jira)" <ji...@apache.org> on 2021/09/22 16:44:00 UTC
[jira] [Commented] (HBASE-26274) Create an option to reintroduce
BlockCache to mapreduce job
[ https://issues.apache.org/jira/browse/HBASE-26274?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17418710#comment-17418710 ]
Tak-Lon (Stephen) Wu commented on HBASE-26274:
----------------------------------------------
it's a clean cherry-pick to branch-2, branch-2.3, branch-2.4, I pushed to all of them.
> Create an option to reintroduce BlockCache to mapreduce job
> -----------------------------------------------------------
>
> Key: HBASE-26274
> URL: https://issues.apache.org/jira/browse/HBASE-26274
> Project: HBase
> Issue Type: Bug
> Components: BlockCache, HFile, mapreduce
> Affects Versions: 3.0.0-alpha-1, 2.4.6
> Reporter: Tak-Lon (Stephen) Wu
> Assignee: Tak-Lon (Stephen) Wu
> Priority: Major
>
> In HBASE-21498 (see [this commit|https://github.com/apache/hbase/commit/27a0f205c52f83fe7500ee2ffc6cf6582f565a63#diff-8a3e39e6df1afe47811fc17702da598fe0d80496d66e579bea4bd224c6d8da03R218], it change the behavior that only region server can initialize on-heap BlockCache/LruBlockCache, this should be the right change for HMaster.
> Other downstream dependency that uses getScanner from a file-based region and read HStore/HFile lost the BlockCache for caching INDEX/LEAF_INDEX (at least still a problem with HBase-2.4) after this change (it worked before) and caused performance impact with 2x slower.
> One way to bring back the performance is to allow non-RS and non-HMaster can use a compact version of blockcache with smaller memory and less hbase internal configuration.
> Or if we can find a way to cache or skip reading the same {{LEAF_INDEX}} when scanning the DATA block with HFile.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)