[ https://issues.apache.org/jira/browse/MAPREDUCE-828?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12837357#action_12837357 ]
Amar Kamat commented on MAPREDUCE-828: -------------------------------------- Another way of looking at this is allowing the JobTracker to pause some of its activities like job-submission, scheduling, etc. The reason why I bring this up is because when the JobTracker runs high on heap, one huge job crashes the JobTracker. In such a case, I think pausing the job-submission and waiting for the *loaded* JobTracker to become free might help. A manual control might be an interim solution until we reach a stage where the JobTracker is capable of making *intelligent* decisions based on how *loaded* it is. > Provide a mechanism to pause the jobtracker > ------------------------------------------- > > Key: MAPREDUCE-828 > URL: https://issues.apache.org/jira/browse/MAPREDUCE-828 > Project: Hadoop Map/Reduce > Issue Type: New Feature > Components: jobtracker > Reporter: Hemanth Yamijala > > We've seen scenarios when we have needed to stop the namenode for a > maintenance activity. In such scenarios, if the jobtracker (JT) continues to > run, jobs would fail due to initialization or task failures (due to DFS). We > could restart the JT enabling job recovery, during such scenarios. But > restart has proved to be a very intrusive activity, particularly if the JT is > not at fault itself and does not require a restart. The ask is for a > admin-controlled feature to pause the JT which would take it to a state > somewhat analogous to the safe mode of DFS. -- This message is automatically generated by JIRA. - You can reply to this email to add a comment to the issue online.