hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "dhruba borthakur (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HDFS-724) Pipeline close hangs if one of the datanode is not responsive.
Date Fri, 06 Nov 2009 20:30:32 GMT

    [ https://issues.apache.org/jira/browse/HDFS-724?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12774395#action_12774395

dhruba borthakur commented on HDFS-724:

3. another option would be to make the dfsclient send a heartbeat-packet via the pipeline.
Each BlockReceiver in the datanode(s)  recognizes it as a heartbeat packet, and forward it
to the next one in the pipeline. The last datanode , on receipt of this heartbeat-packet triggers
it's PacketResponder to the send back the heartbeat to the previous datanode in the pipeline.
The heartbeat message finally arrives back on the client. This way, we can test that the entire
pipeline (both forward and backward channels) are alive and active.

> Pipeline close hangs if one of the datanode is not responsive.
> --------------------------------------------------------------
>                 Key: HDFS-724
>                 URL: https://issues.apache.org/jira/browse/HDFS-724
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: data-node, hdfs client
>            Reporter: Tsz Wo (Nicholas), SZE
>            Assignee: Hairong Kuang
>         Attachments: h724_20091021.patch
> In the new pipeline design, pipeline close is implemented by sending an additional empty
packet.  If one of the datanode does not response to this empty packet, the pipeline hangs.
 It seems that there is no timeout.

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

View raw message