[ https://issues.apache.org/jira/browse/YARN-10352?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=17161699#comment-17161699 ]
Wangda Tan commented on YARN-10352: ----------------------------------- Also, we need to systematically handle the node heartbeat interval problem, in a cloud environment, node can be frequently commissioned, if we always wait for 10 mins timeout, it may not be good, it's better to improve the logic by preempting containers newly allocated (by not acquired) on NM which stopped heartbeating. With this, we can proactively relocate containers to different nodes before the 10 mins timeout. It can be a follow up of this Jira. > Skip schedule on not heartbeated nodes in Multi Node Placement > -------------------------------------------------------------- > > Key: YARN-10352 > URL: https://issues.apache.org/jira/browse/YARN-10352 > Project: Hadoop YARN > Issue Type: Bug > Affects Versions: 3.3.0, 3.4.0 > Reporter: Prabhu Joseph > Assignee: Prabhu Joseph > Priority: Major > Labels: capacityscheduler, multi-node-placement > Attachments: YARN-10352-001.patch, YARN-10352-002.patch, > YARN-10352-003.patch > > > When Node Recovery is Enabled, Stopping a NM won't unregister to RM. So RM > Active Nodes will be still having those stopped nodes until NM Liveliness > Monitor Expires after configured timeout > (yarn.nm.liveness-monitor.expiry-interval-ms = 10 mins). During this 10mins, > Multi Node Placement assigns the containers on those nodes. They need to > exclude the nodes which has not heartbeated for configured heartbeat interval > (yarn.resourcemanager.nodemanagers.heartbeat-interval-ms=1000ms) similar to > Asynchronous Capacity Scheduler Threads. > (CapacityScheduler#shouldSkipNodeSchedule) > *Repro:* > 1. Enable Multi Node Placement > (yarn.scheduler.capacity.multi-node-placement-enabled) + Node Recovery > Enabled (yarn.node.recovery.enabled) > 2. Have only one NM running say worker0 > 3. Stop worker0 and start any other NM say worker1 > 4. Submit a sleep job. The containers will timeout as assigned to stopped NM > worker0. -- This message was sent by Atlassian Jira (v8.3.4#803005) --------------------------------------------------------------------- To unsubscribe, e-mail: yarn-issues-unsubscr...@hadoop.apache.org For additional commands, e-mail: yarn-issues-h...@hadoop.apache.org