[ https://issues.apache.org/jira/browse/YARN-3054?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15191538#comment-15191538 ]
Karthik Kambatla commented on YARN-3054: ---------------------------------------- Thanks [~peng.zhang]. I understand it now. The elegant way of handling this would be to have a preemption priority or even a preemption cost per container, which is different from the priority that is used for allocation. That is a larger conversation to be had. Let us move this out of this umbrella and look at it for both schedulers together. That said, I would expect MapReduce to realize that pending mappers are blocked on waiting reducers and resolve this. MAPREDUCE-6302 and co. attempt to fix this, so you shouldn't see issues with job completion itself. > Preempt policy in FairScheduler may cause mapreduce job never finish > -------------------------------------------------------------------- > > Key: YARN-3054 > URL: https://issues.apache.org/jira/browse/YARN-3054 > Project: Hadoop YARN > Issue Type: Sub-task > Components: fairscheduler > Affects Versions: 2.6.0 > Reporter: Peng Zhang > > Preemption policy is related with schedule policy now. Using comparator of > schedule policy to find preemption candidate cannot guarantee a subset of > containers never be preempted. And this may cause tasks to be preempted > periodically before they finish. So job cannot make any progress. > I think preemption in YARN should got below assurance: > 1. Mapreduce jobs can get additional resources when others are idle; > 2. Mapreduce jobs for one user in one queue can still progress with its min > share when others preempt resources back. > Maybe always preempt the latest app and container can get this? -- This message was sent by Atlassian JIRA (v6.3.4#6332)