hadoop-common-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "dhruba borthakur (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HADOOP-1149) DFS Scalability: high cpu usage in addStoredBlock
Date Wed, 28 Mar 2007 23:24:25 GMT

    [ https://issues.apache.org/jira/browse/HADOOP-1149?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12485023
] 

dhruba borthakur commented on HADOOP-1149:
------------------------------------------

I agree with you observation. I am surprised why processOverReplicatedBlock() was called so
often on one of my test runs. if you think it is worthwhile, please go ahead an make the change
to make processOverReplicatedBlock() a no-op if blocks are not over-replicated.

> DFS Scalability: high cpu usage in addStoredBlock
> -------------------------------------------------
>
>                 Key: HADOOP-1149
>                 URL: https://issues.apache.org/jira/browse/HADOOP-1149
>             Project: Hadoop
>          Issue Type: Bug
>          Components: dfs
>            Reporter: dhruba borthakur
>         Assigned To: Raghu Angadi
>
> I have seen addStoredBlock() consume lots of CPU. One possible cause is that it invokes
proccessOverReplicatedBlock. The logic to find and purge over-replicated blocks can be done
much less often.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message