[
https://issues.apache.org/jira/browse/YARN-2026?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14055861#comment-14055861
]
Ashwin Shankar commented on YARN-2026:
--------------------------------------
[~kasha],
I see your point. I had a quick chat with couple of ops and dev guys in my team
and here is the concern they have with your proposal and they had a suggestion -
they want to be able to look at queues in the scheduler page, and be able to
say that *queue X should kickoff preemption since its starving for fair share*.
We won't be able to infer that with your proposal since preemption is happening
based on internal dynamic fair share, rather than what is displayed on the UI.
Quick example describing the concern :
queue1 : static fair share=10% dynamic fair share=50% usage=20% demand=50%
queue2 : static fair share=10 % dynamic fair share=50% usage=80%
Both queues would appear ORANGE(above static fair share) on the scheduler
page,which seems like preemption will not happen,but actually it would,
since queue1's usage is below half dynamic fair share. We couldn't have
inferred this by looking at the UI.
*Suggestion* : If we do not want to replace static fair share by dynamic on the
UI,can we show both ?
basically there would be an extra line indicating dynamic fair share,apart from
the existing dotted line
which indicates static fair share. Also the usage would turn ORANGE only when
we go beyond dynamic fair share
instead of static.
Thoughts ?
> 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
(v6.2#6252)
