Ashwin Shankar commented on YARN-2026:

Sure, we can incorporate fair share for active queues in FairSharePolicy and 
DominantResourceFairnessPolicy rather than creating new ones.

However regarding having two notions of fairness, I have couple of concerns :
1. Confusion/Debugging inconvenience : users looking at the UI would be 
confused since fair share preemption would be happening randomly(based on
internal dynamic fair share) rather than when usage is below "half fair share" 
shown on the UI. Also it might become a nightmare to debug when we have lots of 
preemption happening and we have two notions of fair share.
2. Code becomes kind of complicated - we would call ComputeFairShares twice at 
each node in the queue hierarchy,one with active child queues and other with 
all child queues. OR if you are thinking of changing ComputeFairShares itself 
rather than calling it twice, it still would look kinda messy with
setting dynamic/static fair shares inside it based on active queues.

I hope I'm making sense here. Thoughts ?
Is there a strong reason why we can't just show the dynamic fair share on the 
UI,which is the reality ?

> Fair scheduler : Fair share for inactive queues causes unfair allocation in 
> some scenarios
> ------------------------------------------------------------------------------------------
>                 Key: YARN-2026
>                 URL: https://issues.apache.org/jira/browse/YARN-2026
>             Project: Hadoop YARN
>          Issue Type: Bug
>          Components: scheduler
>            Reporter: Ashwin Shankar
>            Assignee: Ashwin Shankar
>              Labels: scheduler
>         Attachments: YARN-2026-v1.txt, YARN-2026-v2.txt
> Problem1- While using hierarchical queues in fair scheduler,there are few 
> scenarios where we have seen a leaf queue with least fair share can take 
> majority of the cluster and starve a sibling parent queue which has greater 
> weight/fair share and preemption doesn’t kick in to reclaim resources.
> The root cause seems to be that fair share of a parent queue is distributed 
> to all its children irrespective of whether its an active or an inactive(no 
> apps running) queue. Preemption based on fair share kicks in only if the 
> usage of a queue is less than 50% of its fair share and if it has demands 
> greater than that. When there are many queues under a parent queue(with high 
> fair share),the child queue’s fair share becomes really low. As a result when 
> only few of these child queues have apps running,they reach their *tiny* fair 
> share quickly and preemption doesn’t happen even if other leaf 
> queues(non-sibling) are hogging the cluster.
> This can be solved by dividing fair share of parent queue only to active 
> child queues.
> Here is an example describing the problem and proposed solution:
> root.lowPriorityQueue is a leaf queue with weight 2
> root.HighPriorityQueue is parent queue with weight 8
> root.HighPriorityQueue has 10 child leaf queues : 
> root.HighPriorityQueue.childQ(1..10)
> Above config,results in root.HighPriorityQueue having 80% fair share
> and each of its ten child queue would have 8% fair share. Preemption would 
> happen only if the child queue is <4% (0.5*8=4). 
> Lets say at the moment no apps are running in any of the 
> root.HighPriorityQueue.childQ(1..10) and few apps are running in 
> root.lowPriorityQueue which is taking up 95% of the cluster.
> Up till this point,the behavior of FS is correct.
> Now,lets say root.HighPriorityQueue.childQ1 got a big job which requires 30% 
> of the cluster. It would get only the available 5% in the cluster and 
> preemption wouldn't kick in since its above 4%(half fair share).This is bad 
> considering childQ1 is under a highPriority parent queue which has *80% fair 
> share*.
> Until root.lowPriorityQueue starts relinquishing containers,we would see the 
> following allocation on the scheduler page:
> *root.lowPriorityQueue = 95%*
> *root.HighPriorityQueue.childQ1=5%*
> This can be solved by distributing a parent’s fair share only to active 
> queues.
> So in the example above,since childQ1 is the only active queue
> under root.HighPriorityQueue, it would get all its parent’s fair share i.e. 
> 80%.
> This would cause preemption to reclaim the 30% needed by childQ1 from 
> root.lowPriorityQueue after fairSharePreemptionTimeout seconds.
> Problem2 - Also note that similar situation can happen between 
> root.HighPriorityQueue.childQ1 and root.HighPriorityQueue.childQ2,if childQ2 
> hogs the cluster. childQ2 can take up 95% cluster and childQ1 would be stuck 
> at 5%,until childQ2 starts relinquishing containers. We would like each of 
> childQ1 and childQ2 to get half of root.HighPriorityQueue  fair share ie 
> 40%,which would ensure childQ1 gets upto 40% resource if needed through 
> preemption.

This message was sent by Atlassian JIRA

Reply via email to