You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@ozone.apache.org by "Mark Gui (Jira)" <ji...@apache.org> on 2021/08/23 13:00:00 UTC
[jira] [Commented] (HDDS-5657) Basic Throttling For
ReplicationManager
[ https://issues.apache.org/jira/browse/HDDS-5657?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17403172#comment-17403172 ]
Mark Gui commented on HDDS-5657:
--------------------------------
A design doc for discussion here:
https://docs.google.com/document/d/1Y-xrcmqySXoo4DCX8ESp322wxmNwjejtTqsGS_KWS7Q/edit?usp=sharing
> Basic Throttling For ReplicationManager
> ---------------------------------------
>
> Key: HDDS-5657
> URL: https://issues.apache.org/jira/browse/HDDS-5657
> Project: Apache Ozone
> Issue Type: Improvement
> Reporter: Mark Gui
> Assignee: Mark Gui
> Priority: Major
>
> For now, SCM ReplicationManager has no limit to deliver replication works to Datanodes, this may cause some Datanodes to be overloaded. Moreover, SCM could be busy looping a huge number of containers while keep Datanodes idle.
> So we should have some throttling mechanism to prevent these potential cases.
--
This message was sent by Atlassian Jira
(v8.3.4#803005)
---------------------------------------------------------------------
To unsubscribe, e-mail: issues-unsubscribe@ozone.apache.org
For additional commands, e-mail: issues-help@ozone.apache.org