hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Charles Lamb (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-6247) Avoid timeouts for replaceBlock() call by sending intermediate responses to Balancer
Date Fri, 25 Jul 2014 14:43:40 GMT

    [ https://issues.apache.org/jira/browse/HDFS-6247?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14074441#comment-14074441
] 

Charles Lamb commented on HDFS-6247:
------------------------------------

30 seconds would be fine, or maybe even some time based on the socket timeout. Presently the
socket timeout is a constant, but I could see that perhaps being turned into a configuration
parameter in the future. How about .1 * socketTimeout for the hearbeat interval? Does that
make sense?


> Avoid timeouts for replaceBlock() call by sending intermediate responses to Balancer
> ------------------------------------------------------------------------------------
>
>                 Key: HDFS-6247
>                 URL: https://issues.apache.org/jira/browse/HDFS-6247
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: balancer, datanode
>    Affects Versions: 2.4.0
>            Reporter: Vinayakumar B
>            Assignee: Vinayakumar B
>         Attachments: HDFS-6247.patch, HDFS-6247.patch, HDFS-6247.patch, HDFS-6247.patch
>
>
> Currently there is no response sent from target Datanode to Balancer for the replaceBlock()
calls.
> Since the Block movement for balancing is throttled, complete block movement will take
time and this could result in timeout at Balancer, which will be trying to read the status
message.
>  
> To Avoid this during replaceBlock() call in in progress Datanode  can send IN_PROGRESS
status messages to Balancer to avoid timeouts and treat BlockMovement as  failed.



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

Mime
View raw message