hbase-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Duo Zhang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HBASE-16890) Analyze the performance of AsyncWAL and fix the same
Date Tue, 25 Oct 2016 05:31:58 GMT

    [ https://issues.apache.org/jira/browse/HBASE-16890?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15604261#comment-15604261
] 

Duo Zhang commented on HBASE-16890:
-----------------------------------

The only possible way that AsyncFSWAL does more work on checksuming is that, it syncs more
than FSHLog. The packets sent to datanode need to be aligned with checksum boundary. So if
the data is not aligned, we will copy the unaligned data to the beginning of the buffer and
its checksum will be calucated again next time. So if AsyncFSWAL syncs more, it is more likely
that the checksum of the same piece of data will also be calculated more times.

> Analyze the performance of AsyncWAL and fix the same
> ----------------------------------------------------
>
>                 Key: HBASE-16890
>                 URL: https://issues.apache.org/jira/browse/HBASE-16890
>             Project: HBase
>          Issue Type: Sub-task
>          Components: wal
>    Affects Versions: 2.0.0
>            Reporter: ramkrishna.s.vasudevan
>            Assignee: ramkrishna.s.vasudevan
>             Fix For: 2.0.0
>
>         Attachments: contention.png, contention_defaultWAL.png
>
>
> Tests reveal that AsyncWAL under load in single node cluster performs slower than the
Default WAL. This task is to analyze and see if we could fix it.
> See some discussions in the tail of JIRA HBASE-15536.



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

Mime
View raw message