hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Tsz Wo (Nicholas), SZE (JIRA)" <j...@apache.org>
Subject [jira] Commented: (HDFS-1595) DFSClient may incorrectly detect datanode failure
Date Mon, 24 Jan 2011 21:45:44 GMT

    [ https://issues.apache.org/jira/browse/HDFS-1595?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12986046#action_12986046
] 

Tsz Wo (Nicholas), SZE commented on HDFS-1595:
----------------------------------------------

{quote}
What about something like this: if during completeBlock() call to the NN, ...
{quote}

There is no completeBlock() call to the NN.  We only has complete(..) call to the NN for closing
a file.

{quote}
... we have three nodes in the pipeline because we want to tolerate two failures.
{quote}

Unfortunately, the currently implementation only can tolerate *some but not all* two failure
cases.

If we really want to tolerate two failures without risking at data loss, we may
- set replication factor to 4; or
- recruit a new datanode when a datanode is removed.

> DFSClient may incorrectly detect datanode failure
> -------------------------------------------------
>
>                 Key: HDFS-1595
>                 URL: https://issues.apache.org/jira/browse/HDFS-1595
>             Project: Hadoop HDFS
>          Issue Type: Bug
>          Components: data-node, hdfs client
>    Affects Versions: 0.20.4
>            Reporter: Tsz Wo (Nicholas), SZE
>            Priority: Critical
>
> Suppose a source datanode S is writing to a destination datanode D in a write pipeline.
 We have an implicit assumption that _if S catches an exception when it is writing to D, then
D is faulty and S is fine._  As a result, DFSClient will take out D from the pipeline, reconstruct
the write pipeline with the remaining datanodes and then continue writing .
> However, we find a case that the faulty machine F is indeed S but not D.  In the case
we found, F has a faulty network interface (or a faulty switch port) in such a way that the
faulty network interface works fine when sending out a small amount of data, say 1MB, but
it fails when sending out a large amount of data, say 100MB.
> It is even worst if F is the first datanode in the pipeline.  Consider the following:
> # DFSClient creates a pipeline with three datanodes.  The first datanode is F.
> # F catches an IOException when writing to the second datanode. Then, F reports the second
datanode has error.
> # DFSClient removes the second datanode from the pipeline and continue writing with the
remaining datanode(s).
> # The pipeline now has two datanodes but (2) and (3) repeat.
> # Now, only F remains in the pipeline.  DFSClient continues writing with one replica
in F.
> # The write succeeds and DFSClient is able to *close the file successfully*.
> # The block is under replicated.  The NameNode schedules replication from F to some other
datanode D.
> # The replication fails from the same reason.  D reports to the NameNode that the replica
in F is corrupted.
> # The NameNode marks the replica in F is corrupted.
> # The block is corrupted since no replica is available.
> This is a *data loss* scenario.

-- 
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