hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Haohui Mai (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-5276) FileSystem.Statistics got performance issue on multi-thread read/write.
Date Mon, 30 Sep 2013 23:04:24 GMT

    [ https://issues.apache.org/jira/browse/HDFS-5276?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13782394#comment-13782394

Haohui Mai commented on HDFS-5276:

[~chengxiang li], can you post the detailed configuration of the test, for example, what kinds
of cpu are you using to run the test?

And can you test the differences of end-to-end latency before and after the patch?

Although this JIRA do bring up a good point, it seems that many of us are still yet to be
convinced that this is a real problem in production settings.
Since there're many research proposals available since 80's, I believe that it will be straightforward
to apply one of them once the community is convinced that it affects the performance significantly,
by a detailed analysis of the behavior of real-world Hadoop workload.

> FileSystem.Statistics got performance issue on multi-thread read/write.
> -----------------------------------------------------------------------
>                 Key: HDFS-5276
>                 URL: https://issues.apache.org/jira/browse/HDFS-5276
>             Project: Hadoop HDFS
>          Issue Type: Bug
>    Affects Versions: 2.0.4-alpha
>            Reporter: Chengxiang Li
>         Attachments: DisableFSReadWriteBytesStat.patch, HDFSStatisticTest.java, hdfs-test.PNG,
> FileSystem.Statistics is a singleton variable for each FS scheme, each read/write on
HDFS would lead to a AutomicLong.getAndAdd(). AutomicLong does not perform well in multi-threads(let's
say more than 30 threads). so it may cause  serious performance issue. during our spark test
profile, 32 threads read data from HDFS, about 70% cpu time is spent on FileSystem.Statistics.incrementBytesRead().

This message was sent by Atlassian JIRA

View raw message