[
https://issues.apache.org/jira/browse/YARN-6964?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16117694#comment-16117694
]
Miklos Szegedi commented on YARN-6964:
--------------------------------------
Thanks for the patch [~templedf].
{code}
566 Resource desiredShare =
567 Resources.componentwiseMin(getMinShare(), getDemand());
{code}
I am wondering, if this is the right thing to do. Let's say I have a container
that can run 6 threads parallel and it needs a 1GB buffer per thread. Now I
request 6 vcores and 6 GB but my min share is just 3 GB and 6 vcores. The
cluster has 1000GB and 1000 vcores. I will get a container with 6 vcores, 3 of
which I cannot use. The "dominant" in terms of min share is 3GB, so in case of
DRF, I should get 3GB and 3 vcores.
> Fair scheduler misuses Resources operations
> -------------------------------------------
>
> Key: YARN-6964
> URL: https://issues.apache.org/jira/browse/YARN-6964
> Project: Hadoop YARN
> Issue Type: Bug
> Components: fairscheduler
> Affects Versions: 3.0.0-alpha4
> Reporter: Daniel Templeton
> Assignee: Daniel Templeton
> Attachments: YARN-6964.001.patch
>
>
> There are several places where YARN uses the {{Resources}} class to do
> comparisons of {{Resource}} instances incorrectly. This patch corrects those
> mistakes.
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
