hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "nkeywal (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (HDFS-3703) Decrease the datanode failure detection time
Date Mon, 10 Sep 2012 20:59:07 GMT

    [ https://issues.apache.org/jira/browse/HDFS-3703?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13452439#comment-13452439

nkeywal commented on HDFS-3703:


Sure. The scenario is:
- open a file for writing, write some data, keep the file open
- kill one of the datanodes storing one of the replica of the last blocks (ex: unplug the
computer from the network).
- open the file for reading on another machine

During the "open", he DFSClient will try to get the file length, this requires to connect
(via ipc.Client) to one of the datanodes owning the last block. If you're going to the dead
datanodes, the ipc call will fail. It will retry ten times (by default), and will log the
error (in my case, it was a noRouteToHost, but it could be socketTimeout or alike).

In HBase, we have this when we try to read the Write-Ahead-Log after a regionserver crash.

> Decrease the datanode failure detection time
> --------------------------------------------
>                 Key: HDFS-3703
>                 URL: https://issues.apache.org/jira/browse/HDFS-3703
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: data-node, name-node
>    Affects Versions: 1.0.3, 2.0.0-alpha
>            Reporter: nkeywal
>            Assignee: Suresh Srinivas
>         Attachments: HDFS-3703-branch2.patch, HDFS-3703.patch, HDFS-3703-trunk-read-only.patch,
HDFS-3703-trunk-read-only.patch, HDFS-3703-trunk-with-write.patch
> By default, if a box dies, the datanode will be marked as dead by the namenode after
10:30 minutes. In the meantime, this datanode will still be proposed  by the nanenode to write
blocks or to read replicas. It happens as well if the datanode crashes: there is no shutdown
hooks to tell the nanemode we're not there anymore.
> It especially an issue with HBase. HBase regionserver timeout for production is often
30s. So with these configs, when a box dies HBase starts to recover after 30s and, while 10
minutes, the namenode will consider the blocks on the same box as available. Beyond the write
errors, this will trigger a lot of missed reads:
> - during the recovery, HBase needs to read the blocks used on the dead box (the ones
in the 'HBase Write-Ahead-Log')
> - after the recovery, reading these data blocks (the 'HBase region') will fail 33% of
the time with the default number of replica, slowering the data access, especially when the
errors are socket timeout (i.e. around 60s most of the time). 
> Globally, it would be ideal if HDFS settings could be under HBase settings. 
> As a side note, HBase relies on ZooKeeper to detect regionservers issues.

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

View raw message