[
https://issues.apache.org/jira/browse/HBASE-26347?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17427413#comment-17427413
]
Xiaolin Ha commented on HBASE-26347:
------------------------------------
Hi, [~zhangduo], we don't maintain exclude DNs in RS or WAL, currently only
exclude bad DNs in the retry logic of addBlock().
I have implemented a preliminary version of this idea, and the test result is
good. I'll upload a detailed design doc recently.
Thanks for attention.
> Support detect and exclude slow DNs in fan-out of WAL
> -----------------------------------------------------
>
> Key: HBASE-26347
> URL: https://issues.apache.org/jira/browse/HBASE-26347
> Project: HBase
> Issue Type: New Feature
> Components: wal
> Affects Versions: 2.0.0, 3.0.0-alpha-2
> Reporter: Xiaolin Ha
> Assignee: Xiaolin Ha
> Priority: Major
>
> We all knows the WAL sync performance directly affects the RPC process time.
> And we use self-designed FanOutOneBlockAsyncDFSOutput to sync WAL entries,
> which connect straightly to all the block located DNs. But when even one DN
> of the locations is slow, e.g. some disk hardware failures, the WAL syncs
> slow. And what's more, the hardware failure detected by the lower layer HDFS
> system is not so sensitive.
> We can detect slow DNs by the ACK time of packets in
> FanOutOneBlockAsyncDFSOutput, and exclude them when add new blocks after log
> rolled(rolling log can also be triggered by slow syncs). And shows this info
> in UI. We can also invalid these excluded DN cache after a duration, to aware
> the recovery of those DNs.
> I think this idea can quickly reduce the influence of slow DNs, and improve
> the service availability.
>
>
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
