hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "dengkai (JIRA)" <j...@apache.org>
Subject [jira] [Comment Edited] (YARN-6384) Add configuratin to set max cpu usage when strict-resource-usage is false with cgroups
Date Mon, 27 Mar 2017 16:01:41 GMT

    [ https://issues.apache.org/jira/browse/YARN-6384?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15943508#comment-15943508
] 

dengkai edited comment on YARN-6384 at 3/27/17 4:00 PM:
--------------------------------------------------------

This may be confused, the yarn.nodemanager.resource.percentage-physical-cpu-limit can limit
sum of cpu-usage of all containers, but there has no upper limit for each one container. So
a container with few vcores will use much cpu more than promised, I think it's unreasonable
even the cluster has massive spare resources.


was (Author: lolee_k):
This may be confused, the yarn.nodemanager.resource.percentage-physical-cpu-limit can limit
sum of cpu-usage of all containers, but there has no upper limit for each one container. So
a container with few vcores will use much cpu more than promised, I think it's unreasonable
even the cluster has massive spare resources.
[#https://issues.apache.org/jira/browse/YARN-6384?focusedCommentId=15940051&page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#comment-15940051]

> Add configuratin to set max cpu usage when strict-resource-usage is false with cgroups
> --------------------------------------------------------------------------------------
>
>                 Key: YARN-6384
>                 URL: https://issues.apache.org/jira/browse/YARN-6384
>             Project: Hadoop YARN
>          Issue Type: Improvement
>            Reporter: dengkai
>
> When using cgroups on yarn, if yarn.nodemanager.linux-container-executor.cgroups.strict-resource-usage
is false, user may get very more cpu time than expected based on the vcores. There should
be a upper limit even resource-usage is not strict, just like a percentage which user can
get more than promised by vcores. I think it's important in a shared cluster.



--
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


Mime
View raw message