Re: [PATCH] sched/eevdf: Delayed dequeue task can't preempt

[Peter Zijlstra]

On Thu, Jul 02, 2026 at 09:53:13AM +0200, Vincent Guittot wrote:
> On Thu, 2 Jul 2026 at 09:43, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
> >
> > On Wed, Jul 01, 2026 at 06:49:20PM +0200, Vincent Guittot wrote:
> > > Load balancing can migrate delayed dequeue tasks to even the load between
> > > CPUs.
> > >
> > > sched_balance_rq()
> > >   -> detach_task()
> > >     -> deactivate_task(DEQUEUE_NOCLOCK)
> > >     -> set_task_cpu(dst_cpu)
> > >
> > >   -> attach_task()
> > >     -> activate_task(ENQUEUE_NOCLOCK)
> > >     -> wakeup_preempt()
> > >
> > > A delayed task with shorter slice can be dequeued during pick_next_entity()
> > > but then jump to preempt because eligible.
> >
> > Cute.
> >
> > Perhaps we can look at enqueue()'s place entity and determine
> > eligibility there and complete the delayed dequeue there. But that's
> > definitely something for after the holidays I suppose.
> >
> > I'll go stick it in tip/sched/core.
> 
> Maybe better in tip/sched/urgent because of the warn triggered in set_next_buddy

Hmm, but the Fixes tag you gave it reference a patch in sched/core; is
that tag wrong? Or do I just need to imbibe more wakeup juice?