You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Giovanni Matteo Fumarola (JIRA)" <ji...@apache.org> on 2018/08/21 20:08:00 UTC
[jira] [Comment Edited] (YARN-8581) [AMRMProxy] Add sub-cluster
timeout in LocalityMulticastAMRMProxyPolicy
[ https://issues.apache.org/jira/browse/YARN-8581?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16586549#comment-16586549 ]
Giovanni Matteo Fumarola edited comment on YARN-8581 at 8/21/18 8:07 PM:
-------------------------------------------------------------------------
Thanks [~botong] . Committed to trunk and branch-2.
was (Author: giovanni.fumarola):
Thanks [~botong] . Committed to trunk.
> [AMRMProxy] Add sub-cluster timeout in LocalityMulticastAMRMProxyPolicy
> -----------------------------------------------------------------------
>
> Key: YARN-8581
> URL: https://issues.apache.org/jira/browse/YARN-8581
> Project: Hadoop YARN
> Issue Type: Sub-task
> Components: amrmproxy, federation
> Reporter: Botong Huang
> Assignee: Botong Huang
> Priority: Major
> Attachments: YARN-8581-branch-2.v2.patch, YARN-8581.v1.patch, YARN-8581.v2.patch
>
>
> In Federation, every time an AM heartbeat comes in, LocalityMulticastAMRMProxyPolicy in AMRMProxy splits the asks according to the list of active and enabled sub-clusters. However, if we haven't been able to heartbeat to a sub-cluster for some time (network issues, or we keep hitting some exception from YarnRM, or YarnRM master-slave switch is taking a long time etc.), we should consider the sub-cluster as unhealthy and stop routing asks there, until the heartbeat channel becomes healthy again.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org