[jira] [Updated] (YARN-8179) Preemption does not happen due to natural_termination_factor when DRF is used

["Jonathan Hung (Jira)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/YARN-8179?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Jonathan Hung updated YARN-8179:
--------------------------------
    Fix Version/s: 2.10.1

> Preemption does not happen due to natural_termination_factor when DRF is used
> -----------------------------------------------------------------------------
>
>                 Key: YARN-8179
>                 URL: https://issues.apache.org/jira/browse/YARN-8179
>             Project: Hadoop YARN
>          Issue Type: Bug
>            Reporter: kyungwan nam
>            Assignee: kyungwan nam
>            Priority: Major
>             Fix For: 3.2.0, 3.1.1, 3.0.3, 2.10.1
>
>         Attachments: YARN-8179.001.patch, YARN-8179.002.patch, YARN-8179.003.patch
>
>
> cluster
> * DominantResourceCalculator
> * QueueA : 50 (capacity) ~ 100 (max capacity)
> * QueueB : 50 (capacity) ~ 50 (max capacity)
> all of resources have been allocated to QueueA. (all Vcores are allocated to QueueA)
> if App1 is submitted to QueueB, over-utilized QueueA should be preempted.
> but, I’ve met the problem, which preemption does not happen. it caused that App1 AM can not allocated.
> when App1 is submitted, pending resources for asking App1 AM would be <Memory:2048, Vcores:1>
> so, Vcores which need to be preempted from QueueB should be 1.
> but, it can be 0 due to natural_termination_factor (default is 0.2)
> we should guarantee that resources not to be 0 even though applying natural_termination_factor



--
This message was sent by Atlassian Jira
(v8.3.4#803005)

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