hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Yongjun Zhang (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6788) Improve synchronization in BPOfferService with read write lock
Date Wed, 30 Jul 2014 20:28:39 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6788?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14079913#comment-14079913
] 

Yongjun Zhang commented on HDFS-6788:
-------------------------------------

HI [~arpitagarwal], thanks for your help on the other jiras I worked on earlier. I could you
could help again on reviewing this one. The fix here is simply to replace the synchronized
methods with read write lock, I believe it will hep performance. I did not provide a unit
test case here, I wonder whether you think it's really needed after you look at the change.
Thanks a lot!


> Improve synchronization in BPOfferService with read write lock
> --------------------------------------------------------------
>
>                 Key: HDFS-6788
>                 URL: https://issues.apache.org/jira/browse/HDFS-6788
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: datanode
>    Affects Versions: 2.5.0
>            Reporter: Yongjun Zhang
>            Assignee: Yongjun Zhang
>         Attachments: HDFS-6788.001.patch
>
>
> Threads in DN (DataXceiver, PacketResponder, Async disk worker etc) may block at BPOfferService.getBlockPoolId()
when calling BPOfferService.checkBlock(), though they are just reading the same blockpool
id. This is unnecessary overhead and may cause performance hit when many threads compete.
Filing this jira to replace synchronized method with read write lock (ReentrantReadWriteLock).



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message