hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Yu Li (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-17215) Separate small/large file delete threads in HFileCleaner to accelerate archived hfile cleanup speed
Date Thu, 30 Mar 2017 05:55:41 GMT

    [ https://issues.apache.org/jira/browse/HBASE-17215?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15948464#comment-15948464
] 

Yu Li commented on HBASE-17215:
-------------------------------

bq. cleaning up large files would free up disk space more quickly.
Agreed, and this is the main reason to separate large file deletion from small ones. But if
we plan to delete in the order of file size, we will need to do sorting, which requires getting
the whole set of files first. And if there're many files, getting such a list could be quite
slow thus blocking the deletion. Just a special note here before follow-up actions (smile).

Will prepare a patch addressing existing review comment soon.

> Separate small/large file delete threads in HFileCleaner to accelerate archived hfile
cleanup speed
> ---------------------------------------------------------------------------------------------------
>
>                 Key: HBASE-17215
>                 URL: https://issues.apache.org/jira/browse/HBASE-17215
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: Yu Li
>            Assignee: Yu Li
>         Attachments: HBASE-17215.patch
>
>
> When using PCIe-SSD the flush speed will be really quick, and although we have per CF
flush, we still have the {{hbase.regionserver.optionalcacheflushinterval}} setting and some
other mechanism to avoid data kept in memory for too long to flush small hfiles. In our online
environment we found the single thread cleaner kept cleaning earlier flushed small files while
large files got no chance, which caused disk full then many other problems.
> Deleting hfiles in parallel with too many threads will also increase the workload of
namenode, so here we propose to separate large/small hfile cleaner threads just like we do
for compaction, and it turned out to work well in our cluster.



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

Mime
View raw message