[
https://issues.apache.org/jira/browse/YARN-4678?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15191208#comment-15191208
]
Sunil G commented on YARN-4678:
-------------------------------
[~brahmareddy] Thanks for sharing the scenario.
We have made changes only to parent queue in current patch. We could have been
done similar change in LeafQueue, but I had one concern. To select an under
serving queue while processing a node heartbeat, we still consider
usedCapacity(inclusive of reservedCapacity), so there might be difference is
showing queue capacity on these two cases. I still feel its fine to go ahead
with UI changes as reservation metrics are displayed in LeafQueue page.. Let me
make change to consider this scenario. Meantime if you or [~bibinchundatt] see
the above mentioned scenario as a pblm, pls share your thoughts.
> Cluster used capacity is > 100 when container reserved
> -------------------------------------------------------
>
> Key: YARN-4678
> URL: https://issues.apache.org/jira/browse/YARN-4678
> Project: Hadoop YARN
> Issue Type: Bug
> Reporter: Brahma Reddy Battula
> Assignee: Sunil G
> Attachments: 0001-YARN-4678.patch, 0002-YARN-4678.patch
>
>
> *Scenario:*
> * Start cluster with Three NM's each having 8GB (cluster memory:24GB).
> * Configure queues with elasticity and userlimitfactor=10.
> * disable pre-emption.
> * run two job with different priority in different queue at the same time
> ** yarn jar hadoop-mapreduce-examples-2.7.2.jar pi -Dyarn.app.priority=LOW
> -Dmapreduce.job.queuename=QueueA -Dmapreduce.map.memory.mb=4096
> -Dyarn.app.mapreduce.am.resource.mb=1536
> -Dmapreduce.job.reduce.slowstart.completedmaps=1.0 10 1000000000000
> ** yarn jar hadoop-mapreduce-examples-2.7.2.jar pi -Dyarn.app.priority=HIGH
> -Dmapreduce.job.queuename=QueueB -Dmapreduce.map.memory.mb=4096
> -Dyarn.app.mapreduce.am.resource.mb=1536 3 1000000000000
> * observe the cluster capacity which was used in RM web UI
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
