[
https://issues.apache.org/jira/browse/HDFS-17723?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=18073859#comment-18073859
]
ASF GitHub Bot commented on HDFS-17723:
---------------------------------------
kokonguyen191 commented on PR #8396:
URL: https://github.com/apache/hadoop/pull/8396#issuecomment-4257775239
> Just wonder what will it happen if remove mount points one by one and cost
a long time. IMO, this will be one low frequency operation, any cases need to
improve the performance? Thanks.
Hi @Hexiaoqiao, I think it mostly depends on how the cluster is run. In our
cluster, we have a lot of mount points and housekeeping them takes a few
minutes each time. It's a small improvement with no drawback for peeps who do a
lot of admin mount ops.
Though, internally, we run batches of all mount table operations at the same
time instead of just adding/removing/updating, and at much higher frequency for
migrations. But it's a rather niche situation. The difference in run time for
this particular use case with vs. without the improvement is months vs. days.
> RBF: Optimize multiple mount point removal
> ------------------------------------------
>
> Key: HDFS-17723
> URL: https://issues.apache.org/jira/browse/HDFS-17723
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Felix N
> Assignee: Felix N
> Priority: Minor
> Labels: pull-request-available
>
> Since each remove operation forces an update on all routers, removing a lot
> of mount points in one go when there are a decent number of routers can take
> a long time. It's better to just remove all of them in a batch and force
> update only once. Useful for nuking old unused mount points.
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
