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 "YunFan Zhou (JIRA)" <ji...@apache.org> on 2017/08/30 10:10:02 UTC

[jira] [Commented] (YARN-2497) Changes for fair scheduler to support allocate resource respect labels

    [ https://issues.apache.org/jira/browse/YARN-2497?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16147013#comment-16147013 ] 

YunFan Zhou commented on YARN-2497:
-----------------------------------

Thanks for working on this, [~templedf]. some nits:
# We should guarantee that a queue with non-label cannot access a node with a label, which is very important to us.
# Do we need to support a node with multiple labels? I found that CS has chosen not to support this feature.
# We need to support *relaxed (non-exclusive) partitions*, which is a strong demand for me. If no one is willing to invest time, I will take the time to complete this requirement.
# The node label failover mechanism needs to be considered.
# A queue should only access one label, and if we support a queue can access multiple labels, the semantics may need to be explicitly defined. The other thing is that we need to have a default label if the resource request does not specify a default label.

> Changes for fair scheduler to support allocate resource respect labels
> ----------------------------------------------------------------------
>
>                 Key: YARN-2497
>                 URL: https://issues.apache.org/jira/browse/YARN-2497
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: fairscheduler
>            Reporter: Wangda Tan
>            Assignee: Daniel Templeton
>         Attachments: YARN-2499.WIP01.patch
>
>




--
This message was sent by Atlassian JIRA
(v6.4.14#64029)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org