Re: [PATCH 3/3] mm: memcg: use non-unified stats flushing for userspace reads

[Yosry Ahmed]

On Mon, Aug 28, 2023 at 10:27 AM Waiman Long <longman@xxxxxxxxxx> wrote:
>
>
> On 8/28/23 13:07, Yosry Ahmed wrote:
> >
> >> Here I agree with you. Let's go with the approach which is easy to
> >> undo for now. Though I prefer the new explicit interface for flushing,
> >> that step would be very hard to undo. Let's reevaluate if the proposed
> >> approach shows negative impact on production traffic and I think
> >> Cloudflare folks can give us the results soon.
> > Do you prefer we also switch to using a mutex (with preemption
> > disabled) to avoid the scenario Michal described where flushers give
> > up the lock and sleep resulting in an unbounded wait time in the worst
> > case?
>
> Locking with mutex with preemption disabled is an oxymoron. Use spinlock
> if you want to have preemption disabled. The purpose of usiing mutex is
> to allow the lock owner to sleep, but you can't sleep with preemption
> disabled. You need to enable preemption first. You can disable
> preemption for a short time in a non-sleeping section of the lock
> critical section, but I would not recommend disabling preemption for the
> whole critical section.

I thought using a mutex with preemption disabled would at least allow
waiters to sleep rather than spin, is this not correct (or doesn't
matter) ?

>
> Cheers,
> Longman
>