Karthik Kambatla commented on YARN-2395:

I see the issue now. Thanks for catching it, Ashwin.

Wei and I discussed this offline to see what might be the best way to handle 
this, and here is what I think might work: 
# Starved leaf queues will continue to be handled the way they are in the 
latest patch.
# YARN-2154 changes the behavior for leaf queues to look at actual 
ResourceRequests and preempt only matching containers. 
# YARN-2457: For each starved parent queue, pick an application with positive 
demand and the least disadvantaged in terms of allocation and preempt 
containers that match that. 

I propose we get this in and follow up on other items in respective JIRAs. 

> FairScheduler: Preemption timeout should be configurable per queue
> ------------------------------------------------------------------
>                 Key: YARN-2395
>                 URL: https://issues.apache.org/jira/browse/YARN-2395
>             Project: Hadoop YARN
>          Issue Type: New Feature
>          Components: fairscheduler
>            Reporter: Ashwin Shankar
>            Assignee: Wei Yan
>         Attachments: YARN-2395-1.patch, YARN-2395-2.patch, YARN-2395-3.patch, 
> YARN-2395-3.patch
> Currently in fair scheduler, the preemption logic considers fair share 
> starvation only at leaf queue level. This jira is created to implement it at 
> the parent queue as well.
> It involves :
> 1. Making "check for fair share starvation" and "amount of resource to 
> preempt"  recursive such that they traverse the queue hierarchy from root to 
> leaf.
> 2. Currently fairSharePreemptionTimeout is a global config. We could make it 
> configurable on a per queue basis,so that we can specify different timeouts 
> for parent queues.

This message was sent by Atlassian JIRA

Reply via email to