[ https://issues.apache.org/jira/browse/YARN-6578?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16482142#comment-16482142 ]
Yang Wang commented on YARN-6578: --------------------------------- [~Naganarasimha] thanks for your comment. Currently we just return pmem/vmem/vcores in ContainerStatus#getUtilization. Just as you mentioned, do we need to make ResourceUtilization extensible like Resource? Get the utilization of extensible resource (gpu/fpga) is not easy as pmem/vmem/vcores. In most use case, scheduling opportunistic containers or increase/decrease container resource, utilization of pmem/vmem/vcores is enough. > Return container resource utilization from NM ContainerStatus call > ------------------------------------------------------------------ > > Key: YARN-6578 > URL: https://issues.apache.org/jira/browse/YARN-6578 > Project: Hadoop YARN > Issue Type: Improvement > Reporter: Yang Wang > Assignee: Yang Wang > Priority: Major > Attachments: YARN-6578.001.patch, YARN-6578.002.patch, > YARN-6578.003.patch > > > When the applicationMaster wants to change(increase/decrease) resources of an > allocated container, resource utilization is an important reference indicator > for decision making. So, when AM call NMClient.getContainerStatus, resource > utilization needs to be returned. > Also container resource utilization need to report to RM to make better > scheduling. > So put resource utilization in ContainerStatus. -- This message was sent by Atlassian JIRA (v7.6.3#76005) --------------------------------------------------------------------- To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org