Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1640438 > unrolled thread

Re: [PATCH v2 for-4.12-fixes 2/2] sched/fair: Fix O(# total cgroups) in load balance path

Back to article view | Back to linux.kernel

This discussion starts older than the indexed window; earlier articles aren't shown. The article labeled Started by below is the oldest one visible, not the original post.

Contents

  Re: [PATCH v2 for-4.12-fixes 2/2] sched/fair: Fix O(# total cgroups)  in load balance path Tejun Heo <tj@kernel.org> - 2017-05-12 15:20 +0200
    Re: [PATCH v2 for-4.12-fixes 2/2] sched/fair: Fix O(# total cgroups)  in load balance path Vincent Guittot <vincent.guittot@linaro.org> - 2017-05-12 16:40 +0200

#1640438 — Re: [PATCH v2 for-4.12-fixes 2/2] sched/fair: Fix O(# total cgroups) in load balance path

Hello, Vincent.

On Thu, May 11, 2017 at 09:02:22AM +0200, Vincent Guittot wrote:
> Sorry, what i mean is:
> When the group entity of a cfs_rq is enqueued, we are sure that either
> the parents is already enqueued or it will be enqueued in the same
> sequence. We must be sure that no other branch will be enqueued in the
> middle of the sequence and will reset tmp_alone_branch.
> This is true with current implementation but I  wondered it can happen
> if we del/add the cfs_rq out of order
> 
> That said i haven't find a use case that break the sequence

Hmm... a cfs_rq can be removed from leaf list iff it's empty and
dequeued, and enqueueing is always from top down.  If an ancestor is
already enqueued, it's guaranteed to be on the leaf list; otherwise,
it's guaranteed to be enqueued beforehand and thus put on the leaf
list too.  I think it should be fine.

Thanks.

-- 
tejun

[toc] | [next] | [standalone]

#1640515

On 12 May 2017 at 15:16, Tejun Heo <tj@kernel.org> wrote:
> Hello, Vincent.
>
> On Thu, May 11, 2017 at 09:02:22AM +0200, Vincent Guittot wrote:
>> Sorry, what i mean is:
>> When the group entity of a cfs_rq is enqueued, we are sure that either
>> the parents is already enqueued or it will be enqueued in the same
>> sequence. We must be sure that no other branch will be enqueued in the
>> middle of the sequence and will reset tmp_alone_branch.
>> This is true with current implementation but I  wondered it can happen
>> if we del/add the cfs_rq out of order
>>
>> That said i haven't find a use case that break the sequence
>
> Hmm... a cfs_rq can be removed from leaf list iff it's empty and
> dequeued, and enqueueing is always from top down.  If an ancestor is
> already enqueued, it's guaranteed to be on the leaf list; otherwise,
> it's guaranteed to be enqueued beforehand and thus put on the leaf
> list too.  I think it should be fine.

I agree

FWIW
Acked-by: Vincent Guittot <vincent.guittot@linaro.org>

>
> Thanks.
>
> --
> tejun

[toc] | [prev] | [standalone]

Back to top | Article view | linux.kernel

csiph-web