Re: [PATCH] sched/isolation: Prefer housekeeping cpu in local node

[Wanpeng Li]

On Thu, 20 Jun 2019 at 20:38, Peter Zijlstra <peterz@xxxxxxxxxxxxx> wrote:
>
> On Thu, Jun 20, 2019 at 07:36:54PM +0800, Wanpeng Li wrote:
> > From: Wanpeng Li <wanpengli@xxxxxxxxxxx>
> >
> > In real product setup, there will be houseeking cpus in each nodes, it
> > is prefer to do housekeeping from local node, fallback to global online
> > cpumask if failed to find houseeking cpu from local node.
> >
> > Cc: Ingo Molnar <mingo@xxxxxxxxxx>
> > Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
> > Cc: Frederic Weisbecker <frederic@xxxxxxxxxx>
> > Signed-off-by: Wanpeng Li <wanpengli@xxxxxxxxxxx>
> > ---
> >  kernel/sched/isolation.c | 11 +++++++++--
> >  1 file changed, 9 insertions(+), 2 deletions(-)
> >
> > diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
> > index 123ea07..9eb6805 100644
> > --- a/kernel/sched/isolation.c
> > +++ b/kernel/sched/isolation.c
> > @@ -16,9 +16,16 @@ static unsigned int housekeeping_flags;
> >
> >  int housekeeping_any_cpu(enum hk_flags flags)
> >  {
> > +     int cpu;
> > +
> >       if (static_branch_unlikely(&housekeeping_overridden))
> > -             if (housekeeping_flags & flags)
> > -                     return cpumask_any_and(housekeeping_mask, cpu_online_mask);
> > +             if (housekeeping_flags & flags) {
> > +                     cpu = cpumask_any_and(housekeeping_mask, cpu_cpu_mask(smp_processor_id()));
> > +                     if (cpu < nr_cpu_ids)
> > +                             return cpu;
> > +                     else
> > +                             return cpumask_any_and(housekeeping_mask, cpu_online_mask);
> > +             }
> >       return smp_processor_id();
> >  }
> >  EXPORT_SYMBOL_GPL(housekeeping_any_cpu);
>
> Why not something like so? IIRC there's more places that want this, but
> I can't seem to remember quite where.

Good point, do it in v2. Btw, could you have a look this patch?
https://lkml.org/lkml/2019/6/17/1723

Regards,
Wanpeng Li