[ https://issues.apache.org/jira/browse/YARN-4390?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]
Eric Payne reopened YARN-4390: ------------------------------ Assignee: Wangda Tan (was: Eric Payne) {quote} Since YARN-4108 doesn't solve all the issues. (I planned to solve this together with YARN-4108, but YARN-4108 only tackled half of the problem: when containers selected, only preempt useful containers). However, we need select container more clever based on requirement. I'm thinking about this recently and I plan to make some progresses as soon as possible. May I reopen this JIRA and take over from you? {quote} [~leftnoteasy], I had forgotten that we had closed this JIRA in favor of YARN-4108. Yes, I had noticed that the selection of containers to preempt in YARN-4108 do not actually consider the properties of the needed resources like size or locality. Even still, YARN-4108 is a big improvement and does prevent unnecessary preemption. However, you are correct, implementing this JIRA would eliminate some extra event passing and processing if killable containers are rejected over and over. I am reopening and assigning to you. > Consider container request size during CS preemption > ---------------------------------------------------- > > Key: YARN-4390 > URL: https://issues.apache.org/jira/browse/YARN-4390 > Project: Hadoop YARN > Issue Type: Bug > Components: capacity scheduler > Affects Versions: 3.0.0, 2.8.0, 2.7.3 > Reporter: Eric Payne > Assignee: Wangda Tan > > There are multiple reasons why preemption could unnecessarily preempt > containers. One is that an app could be requesting a large container (say > 8-GB), and the preemption monitor could conceivably preempt multiple > containers (say 8, 1-GB containers) in order to fill the large container > request. These smaller containers would then be rejected by the requesting AM > and potentially given right back to the preempted app. -- This message was sent by Atlassian JIRA (v6.3.4#6332)