[
https://issues.apache.org/jira/browse/YARN-1458?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14126498#comment-14126498
]
zhihai xu commented on YARN-1458:
---------------------------------
Hi [~kasha], I just found an example to prove the first approach doesn't work
when minShare is not zero(all queues have none zero minShare).
The following is the example:
We have 4 queues A,B,C and D: each have 0.25 weight, each have minShare 1024,
The cluster have resource 6144(6*1024)
using the first approach to compare with previous result, we will exit early in
the loop with each Queue's fair share is 1024.
The reason is that computeShare will return minShare value 1024 when rMax
<=2048 in the following code:
{code}
private static int computeShare(Schedulable sched, double w2rRatio,
ResourceType type) {
double share = sched.getWeights().getWeight(type) * w2rRatio;
share = Math.max(share, getResourceValue(sched.getMinShare(), type));
share = Math.min(share, getResourceValue(sched.getMaxShare(), type));
return (int) share;
}
{code}
So for the first 12 iterations, the currentRU is not changed which is sum of
all queues' minShare(4096).
If we use second approach, we will get the correct result: each Queue's fair
share is 1536.
In this case, the second approach is definitely better than the first approach,
the first approach can't handle the case:all queues have none zero minShare.
I will create a new test case in the second approach patch.
> In Fair Scheduler, size based weight can cause update thread to hold lock
> indefinitely
> --------------------------------------------------------------------------------------
>
> Key: YARN-1458
> URL: https://issues.apache.org/jira/browse/YARN-1458
> Project: Hadoop YARN
> Issue Type: Bug
> Components: scheduler
> Affects Versions: 2.2.0
> Environment: Centos 2.6.18-238.19.1.el5 X86_64
> hadoop2.2.0
> Reporter: qingwu.fu
> Assignee: zhihai xu
> Labels: patch
> Fix For: 2.2.1
>
> Attachments: YARN-1458.001.patch, YARN-1458.002.patch,
> YARN-1458.003.patch, YARN-1458.004.patch, YARN-1458.alternative0.patch,
> YARN-1458.alternative1.patch, YARN-1458.patch, yarn-1458-5.patch
>
> Original Estimate: 408h
> Remaining Estimate: 408h
>
> The ResourceManager$SchedulerEventDispatcher$EventProcessor blocked when
> clients submit lots jobs, it is not easy to reapear. We run the test cluster
> for days to reapear it. The output of jstack command on resourcemanager pid:
> {code}
> "ResourceManager Event Processor" prio=10 tid=0x00002aaab0c5f000 nid=0x5dd3
> waiting for monitor entry [0x0000000043aa9000]
> java.lang.Thread.State: BLOCKED (on object monitor)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler.removeApplication(FairScheduler.java:671)
> - waiting to lock <0x000000070026b6e0> (a
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler.handle(FairScheduler.java:1023)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler.handle(FairScheduler.java:112)
> at
> org.apache.hadoop.yarn.server.resourcemanager.ResourceManager$SchedulerEventDispatcher$EventProcessor.run(ResourceManager.java:440)
> at java.lang.Thread.run(Thread.java:744)
> ……
> "FairSchedulerUpdateThread" daemon prio=10 tid=0x00002aaab0a2c800 nid=0x5dc8
> runnable [0x00000000433a2000]
> java.lang.Thread.State: RUNNABLE
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler.getAppWeight(FairScheduler.java:545)
> - locked <0x000000070026b6e0> (a
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.AppSchedulable.getWeights(AppSchedulable.java:129)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.policies.ComputeFairShares.computeShare(ComputeFairShares.java:143)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.policies.ComputeFairShares.resourceUsedWithWeightToResourceRatio(ComputeFairShares.java:131)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.policies.ComputeFairShares.computeShares(ComputeFairShares.java:102)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.policies.FairSharePolicy.computeShares(FairSharePolicy.java:119)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FSLeafQueue.recomputeShares(FSLeafQueue.java:100)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FSParentQueue.recomputeShares(FSParentQueue.java:62)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler.update(FairScheduler.java:282)
> - locked <0x000000070026b6e0> (a
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler)
> at
> org.apache.hadoop.yarn.server.resourcemanager.scheduler.fair.FairScheduler$UpdateThread.run(FairScheduler.java:255)
> at java.lang.Thread.run(Thread.java:744)
> {code}
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
