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 "Vinod Kumar Vavilapalli (JIRA)" <ji...@apache.org> on 2017/02/24 04:25:44 UTC
[jira] [Commented] (YARN-5517) Add GPU as a resource type for
scheduling
[ https://issues.apache.org/jira/browse/YARN-5517?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15881918#comment-15881918 ]
Vinod Kumar Vavilapalli commented on YARN-5517:
-----------------------------------------------
bq. There is the issue(YARN-3926) which proposed to extend the YARN resource model.
bq. But these issues didn’t release yet so I just added GPU resource type like memory and cpu.
YARN-3926 is much further along now, though it did take a bit of time. Further, as the size of the patch here demonstrates, it's better to support arbitrary resources in a pluggable manner instead of continuing to hard-code them into the core.
I propose we close this as a dup of YARN-3926.
> Add GPU as a resource type for scheduling
> -----------------------------------------
>
> Key: YARN-5517
> URL: https://issues.apache.org/jira/browse/YARN-5517
> Project: Hadoop YARN
> Issue Type: Improvement
> Components: scheduler
> Reporter: Jaeboo Jeong
> Attachments: aggregate_resource_allocation.jpg, container_example.jpg, RM-scheduler_metrics.jpg, YARN-5517-branch-2.7.1.patch
>
>
> Currently YARN only support scheduling based on memory and cpu.
> There is the issue(YARN-3926) which proposed to extend the YARN resource model.
> And there is the issue(YARN-4122) to add support for GPU as a resource using docker.
> But these issues didn’t release yet so I just added GPU resource type like memory and cpu.
> I don’t consider GPU isolation like YARN-4122.
> The properties for GPU resource type is similar to cpu core.
> mapred-default.xml
> mapreduce.map.gpu.cores (default 0)
> mapreduce.reduce.gpu.cores (default 0)
> yarn.app.mapreduce.am.resource.gpu-cores (default 0)
> yarn-default.xml
> yarn.scheduler.minimum-allocation-gcores (default 0)
> yarn.scheduler.maximum-allocation-gcores (default 8)
> yarn.nodemanager.resource.gcores (default 0)
> I attached the patch for branch-2.7.1
--
This message was sent by Atlassian JIRA
(v6.3.15#6346)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org