[ https://issues.apache.org/jira/browse/YARN-6384?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16197265#comment-16197265 ]
Miklos Szegedi commented on YARN-6384: -------------------------------------- My opinion is that the distinction between strict and non-strict mode should be, whether cpu.cfs_quota_us or cpu.shares is used. My view of non-strict mode is that there are no upper limits and the scheduler shares the CPU resources based on the shares specified. > 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 > Attachments: YARN-6384-0.patch, YARN-6384-1.patch, YARN-6384-2.patch > > > 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 (v6.4.14#64029) --------------------------------------------------------------------- To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org