[
https://issues.apache.org/jira/browse/HDFS-15757?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17278649#comment-17278649
]
Xiaoqiao He commented on HDFS-15757:
------------------------------------
Thanks [~fengnanli] for your works and update. The new patch looks good to me.
One concerned that if it will involve extra cost for end-to-end latency. For
the original implement it has chance to multiplex connection for the same <ugi,
namenode> request (maybe it is a low-probability) due to postpone recycle.
After changes the reused probability will be reduced IMO. And setup new
connection is more cost operation compare to reused. So do you observe
end-to-end latency cost.
Please correct me if something wrong. Thanks.
> RBF: Improving Router Connection Management
> -------------------------------------------
>
> Key: HDFS-15757
> URL: https://issues.apache.org/jira/browse/HDFS-15757
> Project: Hadoop HDFS
> Issue Type: Improvement
> Components: rbf
> Reporter: Fengnan Li
> Assignee: Fengnan Li
> Priority: Major
> Labels: pull-request-available
> Attachments: RBF_ Improving Router Connection Management_v2.pdf, RBF_
> Improving Router Connection Management_v3.pdf, RBF_ Router Connection
> Management.pdf
>
> Time Spent: 3h 10m
> Remaining Estimate: 0h
>
> We have seen high number of connections from Router to namenodes, leaving
> namenodes unstable.
> This ticket is trying to reduce connections through some changes. Please take
> a look at the design and leave comments.
> Thanks!
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
