Re: [patch] sched: beef up wake_wide()

[Mike Galbraith <umgwanakikbuti@gmail.com>]

On Thu, 2015-07-09 at 15:26 +0200, Peter Zijlstra wrote:
> On Wed, Jul 08, 2015 at 08:13:46AM +0200, Mike Galbraith wrote:
> > 
> > +/*
> > + * Detect 1:N waker/wakee relationship via a switching-frequency heuristic.
> > + * A waker of many should wake a different task than the one last awakened
> > + * at a frequency roughly N times higher than one of its wakees.  In order
> > + * to determine whether we should let the load spread vs consolodating to
> > + * shared cache, we look for a minimum 'flip' frequency of llc_size in one
> > + * partner, and a factor of lls_size higher frequency in the other.  With
> > + * both conditions met, we can be relatively sure that we are seeing a 1:N
> > + * relationship, and that load size exceeds socket size.
> > + */
> >  static int wake_wide(struct task_struct *p)
> >  {
> > +	unsigned int waker_flips = current->wakee_flips;
> > +	unsigned int wakee_flips = p->wakee_flips;
> >  	int factor = this_cpu_read(sd_llc_size);
> >  
> > +	if (waker_flips < wakee_flips)
> > +		swap(waker_flips, wakee_flips);
> 
> This makes the wakee/waker names useless, the end result is more like
> wakee_flips := client_flips, waker_flips := server_flips.

True, perhaps a rename is in order.

> > +	if (wakee_flips < factor || waker_flips < wakee_flips * factor)
> > +		return 0;
> 
> I don't get the first condition... why would the client ever flip? It
> only talks to that one server.

So I was thinking too, and I initially cemented the relationship by
flipping both.  However, the thing works in virgin source, ie clients do
in fact flip, so I removed that cementing based on the hard evidence.

> > @@ -5021,14 +5015,17 @@ select_task_rq_fair(struct task_struct *
> >  {
> >  	struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
> >  	int cpu = smp_processor_id();
> > +	int new_cpu = prev_cpu;
> >  	int want_affine = 0;
> >  	int sync = wake_flags & WF_SYNC;
> >  
> >  	rcu_read_lock();
> > +	if (sd_flag & SD_BALANCE_WAKE) {
> > +		want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
> > +		if (!want_affine)
> > +			goto select_idle;
> > +	}
> 
> So this preserves/makes worse the bug Morten spotted, even without
> want_affine we should still attempt SD_BALANCE_WAKE if set.

Yeah.  I can redo it if you want, but it seems a shame to traverse for
nothing given we know SD_BALANCE_WAKE is so painful that nobody really
really wants to do that.  One has to override the other in any case, no?

	-Mike