hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Vladimir Rodionov (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-7336) HFileBlock.readAtOffset does not work well with multiple threads
Date Sun, 16 Nov 2014 18:46:34 GMT

    [ https://issues.apache.org/jira/browse/HBASE-7336?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14214002#comment-14214002
] 

Vladimir Rodionov commented on HBASE-7336:
------------------------------------------

[~lhofhansl]

Yes that would be helpful for some use cases (compaction + 1 application scanner). There is
a (not so simple) patch in HBASE-12031 that fixes the issue for all use cases (compaction
+ N application scanners) but it seems that nobody has tried it yet. Phoenix parallel intra
region scanners would benefit from HBASE-12031 the most. 

> HFileBlock.readAtOffset does not work well with multiple threads
> ----------------------------------------------------------------
>
>                 Key: HBASE-7336
>                 URL: https://issues.apache.org/jira/browse/HBASE-7336
>             Project: HBase
>          Issue Type: Sub-task
>          Components: Performance
>            Reporter: Lars Hofhansl
>            Assignee: Lars Hofhansl
>            Priority: Critical
>             Fix For: 0.94.4, 0.95.0
>
>         Attachments: 7336-0.94.txt, 7336-0.96.txt
>
>
> HBase grinds to a halt when many threads scan along the same set of blocks and neither
read short circuit is nor block caching is enabled for the dfs client ... disabling the block
cache makes sense on very large scans.
> It turns out that synchronizing in istream in HFileBlock.readAtOffset is the culprit.



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

Mime
View raw message