[
https://issues.apache.org/jira/browse/HBASE-20902?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16546110#comment-16546110
]
chenxu commented on HBASE-20902:
--------------------------------
[~Apache9] FYI
> when WAL sync failed, we should bypass the failed DN that previously used
> -------------------------------------------------------------------------
>
> Key: HBASE-20902
> URL: https://issues.apache.org/jira/browse/HBASE-20902
> Project: HBase
> Issue Type: Bug
> Components: wal
> Reporter: chenxu
> Priority: Major
> Attachments: HBASE-20902-master-v1.patch
>
>
> in our prod env, there happened to be a slow DN, all WAL#sync with that DN
> are failed,
> during Log rolling, we should bypass the slow DN that the previously Log used.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
