hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Rohit Kochar (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-4581) DataNode#checkDiskError should not be called on network errors
Date Mon, 11 Mar 2013 05:03:13 GMT

    [ https://issues.apache.org/jira/browse/HDFS-4581?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13598539#comment-13598539
] 

Rohit Kochar commented on HDFS-4581:
------------------------------------

We are facing an issue in which most of checkDiskError() invocations are happening due to
network related exceptions in BlockReciever$PacketResponder.run() and DataNode$DataTransfer.run().
Since the current code has a common catch clause for all types of exceptions hence even for
network related IO Exceptions chedkDiskError() in executed which lead to check storm thereby
slowing the datanode.
                
> DataNode#checkDiskError should not be called on network errors
> --------------------------------------------------------------
>
>                 Key: HDFS-4581
>                 URL: https://issues.apache.org/jira/browse/HDFS-4581
>             Project: Hadoop HDFS
>          Issue Type: Bug
>            Reporter: Rohit Kochar
>


--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira

Mime
View raw message