volcano icon indicating copy to clipboard operation
volcano copied to clipboard

Add podgroup limit in queue

Open DeliangFan opened this issue 5 years ago • 9 comments

Is this a BUG REPORT or FEATURE REQUEST?:

/kind feature

What happened:

Similarly to yarn, a queue need to limit the maximum podgroup(job/application).

And an alternative implementation could be,

  • Add maxPodgroup in queue spec.
  • Implement the maximum podgroup checking in podgroup webhook.

DeliangFan avatar Aug 20 '20 03:08 DeliangFan

There are many other attributes from yarn queue, but i am not aware of what's the usecase, as we have Capability? We can use hard limit provided by capacity.

hzxuzhonghu avatar Aug 20 '20 06:08 hzxuzhonghu

There are many other attributes from yarn queue, but i am not aware of what's the usecase, as we have Capability? We can use hard limit provided by capacity.

Capacity with some extra implement in podgroup webhook could meet the requirement too. We need a webhook to avoid the user to create too much podgroups.

For example, when a podgroup is created, the podgroup create validatation webhook calculate the numbers podgroup of the queue, if it's more than the queue.capability.maxPodgroup, then reject the requests.

DeliangFan avatar Aug 20 '20 08:08 DeliangFan

I would want to know the deeper reason why you need to limit the podgroup number per queue? If it is reasonable, we are happy to do that

hzxuzhonghu avatar Aug 20 '20 12:08 hzxuzhonghu

I would want to know the deeper reason why you need to limit the podgroup number per queue? If it is reasonable, we are happy to do that

We got tens of thouthands of jobs in offline cluster and we want to limit the number podgroup per queue to avoid a queue submitted too much jobs.

DeliangFan avatar Aug 21 '20 09:08 DeliangFan

IC, make sense in some degree

hzxuzhonghu avatar Aug 22 '20 02:08 hzxuzhonghu

Hello 👋 Looks like there was no activity on this issue for last 90 days. Do you mind updating us on the status? Is this still reproducible or needed? If yes, just comment on this PR or push a commit. Thanks! 🤗 If there will be no activity for 60 days, this issue will be closed (we can always reopen an issue if we need!).

stale[bot] avatar Nov 20 '20 03:11 stale[bot]

Closing for now as there was no activity for last 60 days after marked as stale, let us know if you need this to be reopened! 🤗

stale[bot] avatar Jan 19 '21 05:01 stale[bot]

/reopen

lowang-bh avatar Apr 06 '24 01:04 lowang-bh

@lowang-bh: Reopened this issue.

In response to this:

/reopen

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes/test-infra repository.

volcano-sh-bot avatar Apr 06 '24 01:04 volcano-sh-bot