[
https://issues.apache.org/jira/browse/YARN-326?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13567323#comment-13567323
]
Karthik Kambatla commented on YARN-326:
---------------------------------------
Thanks for posting this, Sandy.
# In your example, by "cluster has <8000 MB, 4 CPUs>", do you mean available
resources or the total capacity of the cluster? Think it should be total
capacity.
# Regarding allocation to queue, I would think it should be dominantShare(x, y,
cluster-capacity). If our goal is for all entities to have an equal share of
the *cluster* , we would want to give some more to those with less than equal
share of the *cluster* .
> Add multi-resource scheduling to the fair scheduler
> ---------------------------------------------------
>
> Key: YARN-326
> URL: https://issues.apache.org/jira/browse/YARN-326
> Project: Hadoop YARN
> Issue Type: New Feature
> Components: scheduler
> Affects Versions: 2.0.2-alpha
> Reporter: Sandy Ryza
> Assignee: Sandy Ryza
>
> With YARN-2 in, the capacity scheduler has the ability to schedule based on
> multiple resources, using dominant resource fairness. The fair scheduler
> should be able to do multiple resource scheduling as well, also using
> dominant resource fairness.
> More details to come on how the corner cases with fair scheduler configs such
> as min and max resources will be handled.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira
