[ https://issues.apache.org/jira/browse/YARN-1489?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15167132#comment-15167132 ]
Junping Du commented on YARN-1489: ---------------------------------- Another big problem is we don't actually notify a restarted AM the "finished-in-the-interim" containers. In YARN-1041, RM only report the running containers to AM new attempt, but if container get finished during this time, new AM attempt has no ways to know it - that make different behaviors for AMs - MR will rely on job history log to recover tasks, while Distributed Shell will launch these (finished) containers again. I think we should enhance this. Will file a separated JIRA if we don't have it yet. > [Umbrella] Work-preserving ApplicationMaster restart > ---------------------------------------------------- > > Key: YARN-1489 > URL: https://issues.apache.org/jira/browse/YARN-1489 > Project: Hadoop YARN > Issue Type: Bug > Reporter: Vinod Kumar Vavilapalli > Assignee: Vinod Kumar Vavilapalli > Attachments: Work preserving AM restart.pdf > > > Today if AMs go down, > - RM kills all the containers of that ApplicationAttempt > - New ApplicationAttempt doesn't know where the previous containers are > running > - Old running containers don't know where the new AM is running. > We need to fix this to enable work-preserving AM restart. The later two > potentially can be done at the app level, but it is good to have a common > solution for all apps where-ever possible. -- This message was sent by Atlassian JIRA (v6.3.4#6332)