You are viewing a plain text version of this content. The canonical link for it is here.
Posted to yarn-issues@hadoop.apache.org by "Miles Crawford (JIRA)" <ji...@apache.org> on 2016/12/01 17:24:58 UTC
[jira] [Comment Edited] (YARN-4931) Preempted resources go back to
the same application
[ https://issues.apache.org/jira/browse/YARN-4931?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15712538#comment-15712538 ]
Miles Crawford edited comment on YARN-4931 at 12/1/16 5:24 PM:
---------------------------------------------------------------
{code}
<?xml version="1.0"?>
<allocations>
<defaultQueueSchedulingPolicy>drf</defaultQueueSchedulingPolicy>
<defaultMinSharePreemptionTimeout>5</defaultMinSharePreemptionTimeout>
<defaultFairSharePreemptionTimeout>20</defaultFairSharePreemptionTimeout>
<defaultFairSharePreemptionThreshold>0.8</defaultFairSharePreemptionThreshold>
<defaultQueueSchedulingPolicy>fair</defaultQueueSchedulingPolicy>
</allocations>
{code}
We use Amazon's EMR, so the yarn-site and mapred-site.xml are a part of their managed setup.
was (Author: milesc):
```<?xml version="1.0"?>
<allocations>
<defaultQueueSchedulingPolicy>drf</defaultQueueSchedulingPolicy>
<defaultMinSharePreemptionTimeout>5</defaultMinSharePreemptionTimeout>
<defaultFairSharePreemptionTimeout>20</defaultFairSharePreemptionTimeout>
<defaultFairSharePreemptionThreshold>0.8</defaultFairSharePreemptionThreshold>
<defaultQueueSchedulingPolicy>fair</defaultQueueSchedulingPolicy>
</allocations>
```
We use Amazon's EMR, so the yarn-site and mapred-site.xml are a part of their managed setup.
> Preempted resources go back to the same application
> ---------------------------------------------------
>
> Key: YARN-4931
> URL: https://issues.apache.org/jira/browse/YARN-4931
> Project: Hadoop YARN
> Issue Type: Bug
> Components: fairscheduler
> Affects Versions: 2.7.2
> Reporter: Miles Crawford
> Attachments: resourcemanager.log
>
>
> Sometimes a queue that needs resources causes preemption - but the preempted containers are just allocated right back to the application that just released them!
> Here is a tiny application (0007) that wants resources, and a container is preempted from application 0002 to satisfy it:
> {code}
> 2016-04-07 21:08:13,463 INFO org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler (FairSchedulerUpdateThread): Should preempt <memory:448, vCores:0> res for queue root.default: resDueToMinShare = <memory:0, vCores:0>, resDueToFairShare = <memory:448, vCores:0>
> 2016-04-07 21:08:13,463 INFO org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler (FairSchedulerUpdateThread): Preempting container (prio=1res=<memory:15264, vCores:1>) from queue root.milesc
> 2016-04-07 21:08:13,463 INFO org.apache.hadoop.yarn.server.resourcemanager.rmapp.attempt.RMAppAttemptMetrics (FairSchedulerUpdateThread): Non-AM container preempted, current appAttemptId=appattempt_1460047303577_0002_000001, containerId=container_1460047303577_0002_01_001038, resource=<memory:15264, vCores:1>
> 2016-04-07 21:08:13,463 INFO org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainerImpl (FairSchedulerUpdateThread): container_1460047303577_0002_01_001038 Container Transitioned from RUNNING to KILLED
> {code}
> But then a moment later, application 00002 gets the container right back:
> {code}
> 2016-04-07 21:08:13,844 INFO org.apache.hadoop.yarn.server.resourcemanager.scheduler.SchedulerNode (ResourceManager Event Processor): Assigned container container_1460047303577_0002_01_001039 of capacity <memory:15264, vCores:1> on host ip-10-12-40-63.us-west-2.compute.internal:8041, which has 13 containers, <memory:241248, vCores:18> used and <memory:416, vCores:46> available after allocation
> 2016-04-07 21:08:14,555 INFO org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainerImpl (IPC Server handler 59 on 8030): container_1460047303577_0002_01_001039 Container Transitioned from ALLOCATED to ACQUIRED
> 2016-04-07 21:08:14,845 INFO org.apache.hadoop.yarn.server.resourcemanager.rmcontainer.RMContainerImpl (ResourceManager Event Processor): container_1460047303577_0002_01_001039 Container Transitioned from ACQUIRED to RUNNING
> {code}
> This results in new applications being unable to even get an AM, and never starting at all.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org