[
https://issues.apache.org/jira/browse/HDFS-4796?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13766786#comment-13766786
]
Ted Yu commented on HDFS-4796:
------------------------------
Plan to resolve this since there is no activity.
> Port HDFS-4721 'Speed up lease/block recovery when DN fails and a block goes
> into recovery' to branch 1
> -------------------------------------------------------------------------------------------------------
>
> Key: HDFS-4796
> URL: https://issues.apache.org/jira/browse/HDFS-4796
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Ted Yu
>
> This was observed while doing HBase WAL recovery. HBase uses append to write
> to its write ahead log. So initially the pipeline is setup as
> DN1 --> DN2 --> DN3
> This WAL needs to be read when DN1 fails since it houses the HBase
> regionserver for the WAL.
> HBase first recovers the lease on the WAL file. During recovery, we choose
> DN1 as the primary DN to do the recovery even though DN1 has failed and is
> not heartbeating any more.
> To speedup lease/block recovery, we always choose the datanode with the most
> recent heartbeat.
--
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
