Re: [PATCH v3] sched/rt: Do not account migrate-disabled tasks as pushable

From: Peter Zijlstra

Date: Tue Nov 17 2026 - 10:11:01 EST


On Tue, Nov 17, 2026 at 02:27:38PM +0000, Mel Gorman wrote:
> On Fri, Nov 13, 2026 at 04:06:55PM +0000, Mel Gorman wrote:
> > RT_PUSH_IPI is intended to minimise latency and rq lock contention when
> > migrating tasks to balance RT task distribution. The problem is that
> > if a CPU is rt_overloaded but has no tasks that can be pushed then IPIs
> > can be fired continually at the same CPU but fail to move any task due
> > to migrate_disable() on PREEMPT_RT. A specific case was "pgrep" running
> > at RT priority, its CPU being the target of a continuous stream of IPIs
> > without any task moving. While the pgrep can be bound to another CPU by
> > the application, the underlying problem was that pgrep is spinlock-intensive
> > which disables migration on PREEMPT_RT.
> >
>
> I know the rate of scheduler patches at the moment is completely insane
> but is there anything else I should do with this patch?

IKR :/ Let me go have a look.