Re: [PATCH v5 1/4] sched/fair: add util_est on top of PELT

From: Patrick Bellasi <patrick.bellasi@arm.com>
To: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Ingo Molnar <mingo@redhat.com>,
	"Rafael J . Wysocki" <rafael.j.wysocki@intel.com>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Paul Turner <pjt@google.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Juri Lelli <juri.lelli@redhat.com>, Todd Kjos <tkjos@android.com>,
	Joel Fernandes <joelaf@google.com>,
	Steve Muckle <smuckle@google.com>
Subject: Re: [PATCH v5 1/4] sched/fair: add util_est on top of PELT
Date: Wed, 7 Mar 2018 15:16:49 +0000	[thread overview]
Message-ID: <20180307151649.GD2211@e110439-lin> (raw)
In-Reply-To: <20180307122607.GN25181@hirez.programming.kicks-ass.net>

On 07-Mar 13:26, Peter Zijlstra wrote:
> On Wed, Mar 07, 2018 at 11:47:11AM +0000, Patrick Bellasi wrote:
> > On 06-Mar 20:02, Peter Zijlstra wrote:
> > > On Thu, Feb 22, 2018 at 05:01:50PM +0000, Patrick Bellasi wrote:
> > > > +struct util_est {
> > > > +	unsigned int			enqueued;
> > > > +	unsigned int			ewma;
> > > > +#define UTIL_EST_WEIGHT_SHIFT		2
> > > > +};
> > > 
> > > > +	ue = READ_ONCE(p->se.avg.util_est);
> > > 
> > > > +	WRITE_ONCE(p->se.avg.util_est, ue);
> > > 
> > > That is actually quite dodgy... and relies on the fact that we have the
> > > 8 byte case in __write_once_size() and __read_once_size()
> > > unconditionally. It then further relies on the compiler DTRT for 32bit
> > > platforms, which is generating 2 32bit loads/stores.
> > >
> > > The advantage is of course that it will use single u64 loads/stores
> > > where available.
> > 
> > Yes, that's mainly an "optimization" for 64bit targets... but perhaps
> > the benefits are negligible.
> > 
> > Do you prefer to keep more "under control" the generated code by using
> > two {READ,WRITE}_ONCEs?

Any specific preference on this previous point?

> > IMO here we can also go with just the WRITE_ONCEs. I don't see a case
> > for the compiler to mangle load/store. While the WRITE_ONCE are still
> > required to sync with non rq-lock serialized code.
> > But... maybe I'm missing something... ?
> 
> I'm not sure we rely on READ/WRITE_ONCE() of 64bit variables on 32bit
> targets to be sane anywhere else (we could be, I just dont know).

My understating is that, since here we are in an rq-lock protected
section, and only in this section we can write these vars, then the
load is a dependency for the store and the compiler cannot screw up...

> I suspect it all works as expected... but its a tad tricky.

Then let's keep them for the time being... meanwhile I try to get
some more "internal" feedback before next posting.

-- 
#include <best/regards.h>

Patrick Bellasi