hadoop-yarn-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Karthik Kambatla (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (YARN-6193) FairScheduler might not trigger preemption when using DRF
Date Fri, 17 Feb 2017 20:50:41 GMT

    [ https://issues.apache.org/jira/browse/YARN-6193?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15872500#comment-15872500
] 

Karthik Kambatla commented on YARN-6193:
----------------------------------------

Latest patch (003) focuses only on the problem at hand. The patch:
# Replaces the check {{Resources.fitsIn}} that checks if all resources fit in, with {{!Resources.lessThan(policy_calculator)}}
that defers to the policy on what resources to consider. In case of DRF, this is the dominant
resource.
# TestFairSchedulerPreemption
## Adds DRF-based profiles
## verifyPreemption waits longer to address flakiness being noticed on HadoopQA runs. 


> FairScheduler might not trigger preemption when using DRF
> ---------------------------------------------------------
>
>                 Key: YARN-6193
>                 URL: https://issues.apache.org/jira/browse/YARN-6193
>             Project: Hadoop YARN
>          Issue Type: Sub-task
>          Components: fairscheduler
>    Affects Versions: 2.8.0
>            Reporter: Karthik Kambatla
>            Assignee: Karthik Kambatla
>         Attachments: YARN-6193.000.patch, YARN-6193.001.patch, YARN-6193.002.patch, YARN-6193.003.patch
>
>
> {{FSAppAttempt#canContainerBePreempted}} verifies preempting a container doesn't lead
to new starvation ({{Resources.fitsIn}}). When using DRF, this leads to verifying both resources
instead of just the dominant resource. Ideally, the check should be based on policy. 
> Note that current implementation of {{DominantResourceFairnessPolicy#checkIfUsageOverFairShare}}
is broken. 



--
This message was sent by Atlassian JIRA
(v6.3.15#6346)

---------------------------------------------------------------------
To unsubscribe, e-mail: yarn-issues-unsubscribe@hadoop.apache.org
For additional commands, e-mail: yarn-issues-help@hadoop.apache.org


Mime
View raw message