hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Varun Saxena (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-3508) Preemption processing occuring on the main RM dispatcher
Date Tue, 30 Jun 2015 21:12:05 GMT

    [ https://issues.apache.org/jira/browse/YARN-3508?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14609080#comment-14609080

Varun Saxena commented on YARN-3508:

bq. Init is used by production code, I suggest to make constructor/init signature consistent.
Yes {{SchedulingEditPolicy#init}} and constructor are consistent. init takes {{EventHandler}}
as argument just like the constructor. Anyways I will make the change.
I will therefore, change {{SchedulingEditPolicy#init}} as well (to make it consistent with
the constructor).

By the way, this is how {{SchdulingEditPolicy#init}} looked before my change.
  public void init(Configuration config, EventHandler<ContainerPreemptEvent> dispatcher,
PreemptableResourceScheduler scheduler);

And this is how ProportionalCapacityPreemptionPolicy constructor looked.
   public ProportionalCapacityPreemptionPolicy(Configuration config, EventHandler<ContainerPreemptEvent>
dispatcher, CapacityScheduler scheduler)
So I merely changed {{EventHandler<ContainerPreemptEvent>}} to {{EventHandler<SchedulerEvent>}}
in the function signature.  

Will make the change and update patch shortly.

> Preemption processing occuring on the main RM dispatcher
> --------------------------------------------------------
>                 Key: YARN-3508
>                 URL: https://issues.apache.org/jira/browse/YARN-3508
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: resourcemanager, scheduler
>    Affects Versions: 2.6.0
>            Reporter: Jason Lowe
>            Assignee: Varun Saxena
>         Attachments: YARN-3508.002.patch, YARN-3508.01.patch, YARN-3508.03.patch, YARN-3508.04.patch
> We recently saw the RM for a large cluster lag far behind on the AsyncDispacher event
queue.  The AsyncDispatcher thread was consistently blocked on the highly-contended CapacityScheduler
lock trying to dispatch preemption-related events for RMContainerPreemptEventDispatcher. 
Preemption processing should occur on the scheduler event dispatcher thread or a separate
thread to avoid delaying the processing of other events in the primary dispatcher queue.

This message was sent by Atlassian JIRA

View raw message