[
https://issues.apache.org/jira/browse/YARN-7844?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16344581#comment-16344581
]
Wei Yan commented on YARN-7844:
-------------------------------
After enabling the metrics, the JMX will have one more item like:
{code:java}
{
"name" : "Hadoop:service=ResourceManager,name=SchedulerOpMetrics",
"modelerType" : "SchedulerOpMetrics",
"tag.Hostname" : "hostname",
"AllocateCallNumOps" : 0,
"AllocateCallAvgTime" : 0.0,
"AllocateCallStdevTime" : 0.0,
"AllocateCallIMinTime" : 3.4028234663852886E38,
"AllocateCallIMaxTime" : 1.401298464324817E-45,
"AllocateCallMinTime" : 3.4028234663852886E38,
"AllocateCallMaxTime" : 1.401298464324817E-45,
"AllocateCallINumOps" : 0,
"NodeAddedCallNumOps" : 1,
"NodeAddedCallAvgTime" : 7.0,
"NodeRemovedCallNumOps" : 0,
"NodeRemovedCallAvgTime" : 0.0,
"NodeUpdateCallNumOps" : 19,
"NodeUpdateCallAvgTime" : 0.16666666666666666,
"NodeResourceUpdateCallNumOps" : 0,
"NodeResourceUpdateCallAvgTime" : 0.0,
"NodeLabelsUpdateCallNumOps" : 1,
"NodeLabelsUpdateCallAvgTime" : 2.0,
"AppAddedCallNumOps" : 0,
"AppAddedCallAvgTime" : 0.0,
"AppRemovedCallNumOps" : 0,
"AppRemovedCallAvgTime" : 0.0,
"AppAttemptAddedCallNumOps" : 0,
"AppAttemptAddedCallAvgTime" : 0.0,
"AppAttemptRemovedCallNumOps" : 0,
"AppAttemptRemovedCallAvgTime" : 0.0,
"ContainerExpiredCallNumOps" : 0,
"ContainerExpiredCallAvgTime" : 0.0,
"ReleaseContainerCallNumOps" : 0,
"ReleaseContainerCallAvgTime" : 0.0,
"KillReservedContainerCallNumOps" : 0,
"KillReservedContainerCallAvgTime" : 0.0,
"MarkContainerForPreemptionCallNumOps" : 0,
"MarkContainerForPreemptionCallAvgTime" : 0.0,
"MarkContainerForKillableCallNumOps" : 0,
"MarkContainerForKillableCallAvgTime" : 0.0,
"MarkContainerForNonKillableCallNumOps" : 0,
"MarkContainerForNonKillableCallAvgTime" : 0.0,
"ManageQueueCallNumOps" : 0,
"ManageQueueCallAvgTime" : 0.0
}, {{code}
> Expose metrics for scheduler operation (allocate, schedulerEvent) to JMX
> ------------------------------------------------------------------------
>
> Key: YARN-7844
> URL: https://issues.apache.org/jira/browse/YARN-7844
> Project: Hadoop YARN
> Issue Type: Improvement
> Components: scheduler
> Reporter: Wei Yan
> Assignee: Wei Yan
> Priority: Minor
> Attachments: YARN-7844.000.patch
>
>
> Currently FairScheduler's FSOpDurations records some scheduler operation
> metrics: nodeUpdateCall, preemptCall, etc. We may need similar for
> CapacityScheduler. Also, need to add more metrics there. This could help
> monitor the RM scheduler performance, and get more insights whether scheduler
> is under-pressure.
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
