Anubhav Dhoot commented on YARN-3920:

I am trying to have a config that works out of the box via the default 
configuration and needs tweaking only if required. Having an absolute value 
will require it to be resized for every cluster setup based on its specific 
The other option is a multiple of the increment allocation thats used by FS. We 
could a pick a default ratio of 2 as default. The problem is if you get that 
too high (such that it exceeds maximum resource allocation) one can 
accidentally disable reservation.

> FairScheduler Reserving a node for a container should be configurable to 
> allow it used only for large containers
> ----------------------------------------------------------------------------------------------------------------
>                 Key: YARN-3920
>                 URL: https://issues.apache.org/jira/browse/YARN-3920
>             Project: Hadoop YARN
>          Issue Type: Improvement
>          Components: fairscheduler
>            Reporter: Anubhav Dhoot
>            Assignee: Anubhav Dhoot
>         Attachments: yARN-3920.001.patch
> Reserving a node for a container was designed for preventing large containers 
> from starvation from small requests that keep getting into a node. Today we 
> let this be used even for a small container request. This has a huge impact 
> on scheduling since we block other scheduling requests until that reservation 
> is fulfilled. We should make this configurable so its impact can be minimized 
> by limiting it for large container requests as originally intended. 

This message was sent by Atlassian JIRA

Reply via email to