[
https://issues.apache.org/jira/browse/YARN-3153?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16347144#comment-16347144
]
Manikandan R commented on YARN-3153:
------------------------------------
[~leftnoteasy] [~sunilg]
I am interested in working on this. I like proposal mentioned in
https://issues.apache.org/jira/browse/YARN-3153?focusedCommentId=14317255&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-14317255
except the name. Instead of
{{yarn.scheduler.capacity.maximum-am-capacity-per-queue}}, we can use
{{yarn.scheduler.capacity.maximum-am-capacity}} like mentioned in [~cwelch]
comment as anyway this property is meant for queue only.
Reg inheritance, We can make it similar to "disable_preemption" property.
1. For "root" queue, default value could be
DEFAULT_MAXIMUM_APPLICATIONMASTERS_RESOURCE_CAPACITY and can be used if value
is not configured at root level.
2. Whereas, for "leaf"' queues, default value could be o/p of #1 and can be
used if value is not configured at leaf queue level.
Please share your thoughts.
> Capacity Scheduler max AM resource limit for queues is defined as percentage
> but used as ratio
> ----------------------------------------------------------------------------------------------
>
> Key: YARN-3153
> URL: https://issues.apache.org/jira/browse/YARN-3153
> Project: Hadoop YARN
> Issue Type: Bug
> Reporter: Wangda Tan
> Assignee: Wangda Tan
> Priority: Critical
>
> In existing Capacity Scheduler, it can limit max applications running within
> a queue. The config is yarn.scheduler.capacity.maximum-am-resource-percent,
> but actually, it is used as "ratio", in implementation, it assumes input will
> be \[0,1\]. So now user can specify it up to 100, which makes AM can use 100x
> of queue capacity. We should fix that.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
