Re: [RFC PATCH v5 4/7] sched: bias task wakeups to preferred semi-idle packages

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Mon, 2008-12-15 at 12:31 +0530, Balbir Singh wrote:

> >  kernel/sched_fair.c |   17 +++++++++++++++++
> >  1 files changed, 17 insertions(+), 0 deletions(-)
> > 
> > diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
> > index 98345e4..939f2a1 100644
> > --- a/kernel/sched_fair.c
> > +++ b/kernel/sched_fair.c
> > @@ -1027,6 +1027,23 @@ static int wake_idle(int cpu, struct task_struct *p)
> >  	cpumask_t tmp;
> >  	struct sched_domain *sd;
> >  	int i;
> > +	unsigned int chosen_wakeup_cpu;
> > +	int this_cpu;
> > +
> > +	/*
> > +	 * At POWERSAVINGS_BALANCE_WAKEUP level, if both this_cpu and prev_cpu
> > +	 * are idle and this is not a kernel thread and this task's affinity
> > +	 * allows it to be moved to preferred cpu, then just move!
> > +	 */
> > +
> > +	this_cpu = smp_processor_id();
> > +	chosen_wakeup_cpu =
> > +		cpu_rq(this_cpu)->rd->sched_mc_preferred_wakeup_cpu;
> > +
> > +	if (sched_mc_power_savings >= POWERSAVINGS_BALANCE_WAKEUP &&
> > +		idle_cpu(cpu) && idle_cpu(this_cpu) && p->mm &&
> 
> The p->mm check is racy, it needs to be done under task_lock(). The
> best way to check for a kernel thread is get_task_mm(), followed by
> put_task_mm() is the mm is not NULL. We also need to check to see if
> the task is _hot_ on cpu. We should negate this optimization in case
> chosen_wakeup_cpu is idle, so check for that as well.

Sure its racy, but so what?

The worst I can see it that we exclude a dying task from this logic,
which isn't a problem at all, since its dying anyway.

Also, I don't think you can grab task_lock() from under rq->lock...

> > +		cpu_isset(chosen_wakeup_cpu, p->cpus_allowed))
> > +		return chosen_wakeup_cpu;
> > 
> >  	/*
> >  	 * If it is idle, then it is the best cpu to run this task.
> > 
> > 
>