hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Todd Lipcon (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HDFS-101) DFS write pipeline : DFSClient sometimes does not detect second datanode failure
Date Fri, 18 Dec 2009 01:42:18 GMT

    [ https://issues.apache.org/jira/browse/HDFS-101?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12792285#action_12792285
] 

Todd Lipcon commented on HDFS-101:
----------------------------------

Just applied https://issues.apache.org/jira/secure/attachment/12428383/detectDownDN1-0.20.patch
and tested on the cluster. I think the other error I mentioned above is just HDFS-630, since
I'm testing on 0.20 on a 3-node cluster, so +1 on this patch.

bq. clientName.len == 0 means that this is a block copy for replication. It has nothing to
do if this is the last DN in pipeline or not.

Right, but my question is whether clientName.len can ever be 0 when there's a mirror. My belief
is no. Perhaps it's worth an assert there (since we're now cool with assertions in HDFS)

> DFS write pipeline : DFSClient sometimes does not detect second datanode failure 
> ---------------------------------------------------------------------------------
>
>                 Key: HDFS-101
>                 URL: https://issues.apache.org/jira/browse/HDFS-101
>             Project: Hadoop HDFS
>          Issue Type: Bug
>    Affects Versions: 0.20.1
>            Reporter: Raghu Angadi
>            Assignee: Hairong Kuang
>            Priority: Blocker
>             Fix For: 0.21.0
>
>         Attachments: detectDownDN-0.20.patch, detectDownDN1-0.20.patch, detectDownDN2.patch,
hdfs-101.tar.gz
>
>
> When the first datanode's write to second datanode fails or times out DFSClient ends
up marking first datanode as the bad one and removes it from the pipeline. Similar problem
exists on DataNode as well and it is fixed in HADOOP-3339. From HADOOP-3339 : 
> "The main issue is that BlockReceiver thread (and DataStreamer in the case of DFSClient)
interrupt() the 'responder' thread. But interrupting is a pretty coarse control. We don't
know what state the responder is in and interrupting has different effects depending on responder
state. To fix this properly we need to redesign how we handle these interactions."
> When the first datanode closes its socket from DFSClient, DFSClient should properly read
all the data left in the socket.. Also, DataNode's closing of the socket should not result
in a TCP reset, otherwise I think DFSClient will not be able to read from the socket.

-- 
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