Re: [PATCH 04/19] sched: Prepare for Core-wide rq->lock

From: Don Hiatt
Date: Wed May 05 2021 - 12:20:55 EST


On Tue, May 4, 2021 at 12:38 AM Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Thu, Apr 29, 2021 at 01:39:54PM -0700, Josh Don wrote:
>
> > > > +void double_rq_lock(struct rq *rq1, struct rq *rq2)
> > > > +{
> > > > + lockdep_assert_irqs_disabled();
> > > > +
> > > > + if (rq1->cpu > rq2->cpu)
> > >
> > > It's still a bit hard for me to digest this function, I guess using (rq->cpu)
> > > can't guarantee the sequence of locking when coresched is enabled.
> > >
> > > - cpu1 and cpu7 shares lockA
> > > - cpu2 and cpu8 shares lockB
> > >
> > > double_rq_lock(1,8) leads to lock(A) and lock(B)
> > > double_rq_lock(7,2) leads to lock(B) and lock(A)
>
> Good one!

Hi Peter,

I've been running the same set-cookie tests on your latest repo for
the last 24 hours and haven't had a single lockup. Thank you very
much!

don