[
https://issues.apache.org/jira/browse/HDFS-17129?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17807069#comment-17807069
]
ASF GitHub Bot commented on HDFS-17129:
---------------------------------------
slfan1989 commented on PR #6244:
URL: https://github.com/apache/hadoop/pull/6244#issuecomment-1893176509
> I'd like to share our situation in more detail. In my company, we are
using [hadoop-3](https://issues.apache.org/jira/browse/HADOOP-3).3.0 with many
patches. We had a problem with IBR becoming very slow, which is exactly the
issue described in
[HDFS-16898](https://issues.apache.org/jira/browse/HDFS-16898). Then, we
backported [HDFS-16016](https://issues.apache.org/jira/browse/HDFS-16016) and
the problem was solved
([HDFS-16898](https://issues.apache.org/jira/browse/HDFS-16898) didn't exist at
that time).
>
> Now, I have confirmed that our problem is fixed by
[HDFS-16898](https://issues.apache.org/jira/browse/HDFS-16898) without
[HDFS-16016](https://issues.apache.org/jira/browse/HDFS-16016). So, I would
suggest only reverting
[HDFS-16016](https://issues.apache.org/jira/browse/HDFS-16016) for now. It may
no longer be needed.
@tasanuma Thanks for your feedback! It's very valuable. I will only revert
HDFS-16016.
> mis-order of ibr and fbr on datanode
> -------------------------------------
>
> Key: HDFS-17129
> URL: https://issues.apache.org/jira/browse/HDFS-17129
> Project: Hadoop HDFS
> Issue Type: Bug
> Affects Versions: 3.4.0, 3.3.9, 3.3.6
> Environment: hdfs3.4.0
> Reporter: liuguanghua
> Assignee: liuguanghua
> Priority: Blocker
> Labels: pull-request-available
>
> HDFS-16016 , provide new thread to handler IBR. That is a greate improvement.
> But it maybe casue the mis-order of ibr and fbr
--
This message was sent by Atlassian Jira
(v8.20.10#820010)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
