[
https://issues.apache.org/jira/browse/MAPREDUCE-3353?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13215901#comment-13215901
]
Bikas Saha commented on MAPREDUCE-3353:
---------------------------------------
1) Add a ClusterManager to RM that currently only provides bad node
information. All node management will incrementally be moved to it. Eg.
RmContext.RMnodes and RMContext.invalidNodes could move into ClusterManager.
This could be a new class or be an enhancement of NodesListManager.
2) Node is bad when it gets a heartbeat with health=unhealthy or when the
livenessmonitor reports lost node. In both cases a SchedulerNodeRemove event is
issued. Similar for nodes becoming healthy. Additionally, these will now emit
events to update the ClusterManager with corresponding events.
3) In AppMasterService, after calling Scheduler.allocate(), it will call
ClusterManager.getUnusableNodes(). These will be passed to RMAttempt object
which will calculate the delta with previous known bad machines. The delta will
be sent with the allocate response and the current list will be saved to
calculate the next delta.
> Need a RM->AM channel to inform AMs about faulty/unhealthy/lost nodes
> ---------------------------------------------------------------------
>
> Key: MAPREDUCE-3353
> URL: https://issues.apache.org/jira/browse/MAPREDUCE-3353
> Project: Hadoop Map/Reduce
> Issue Type: Bug
> Components: applicationmaster, mrv2, resourcemanager
> Affects Versions: 0.23.0
> Reporter: Vinod Kumar Vavilapalli
> Assignee: Bikas Saha
> Priority: Critical
> Fix For: 0.23.2
>
>
> When a node gets lost or turns faulty, AM needs to know about that event so
> that it can take some action like for e.g. re-executing map tasks whose
> intermediate output live on that faulty node.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
