You are viewing a plain text version of this content. The canonical link for it is here.
Posted to common-issues@hadoop.apache.org by "Tao Jie (JIRA)" <ji...@apache.org> on 2018/01/26 08:34:00 UTC
[jira] [Updated] (HADOOP-15194) Some properties for FairCallQueue
should be reloadable
[ https://issues.apache.org/jira/browse/HADOOP-15194?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Tao Jie updated HADOOP-15194:
-----------------------------
Affects Version/s: 2.8.2
> Some properties for FairCallQueue should be reloadable
> ------------------------------------------------------
>
> Key: HADOOP-15194
> URL: https://issues.apache.org/jira/browse/HADOOP-15194
> Project: Hadoop Common
> Issue Type: Improvement
> Affects Versions: 2.8.2
> Reporter: Tao Jie
> Priority: Major
>
> When trying to make use of FairCallQueue for a large cluster, it is not easy to set the properties appropriately at the first time. User may adjust those properties frequently and restarting the namenode costs a lot for a large multi-user hadoop clluster. We should support to reload some of those properties in configuration without restarting.
> Related properties:
> ipc.8020.faircallqueue.multiplexer.weights
> ipc.8020.faircallqueue.decay-scheduler.thresholds
> ipc.8020.decay-scheduler.backoff.responsetime.thresholds
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: common-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: common-issues-help@hadoop.apache.org