Re: [PATCH 3/4] sched/deadline: Make DL capacity-aware

From: Juri Lelli <juri.lelli@redhat.com>
To: luca abeni <luca.abeni@santannapisa.it>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Steven Rostedt <rostedt@goodmis.org>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	Wei Wang <wvw@google.com>, Quentin Perret <qperret@google.com>,
	Alessio Balsini <balsini@google.com>,
	Pavan Kondeti <pkondeti@codeaurora.org>,
	Patrick Bellasi <patrick.bellasi@matbug.net>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Valentin Schneider <valentin.schneider@arm.com>,
	Qais Yousef <qais.yousef@arm.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/4] sched/deadline: Make DL capacity-aware
Date: Thu, 16 Apr 2020 15:19:38 +0200	[thread overview]
Message-ID: <20200416131938.GI9767@localhost.localdomain> (raw)
In-Reply-To: <20200415184203.50862783@sweethome>

On 15/04/20 18:42, luca abeni wrote:
> Hi Juri,
> 
> On Wed, 15 Apr 2020 15:20:04 +0200
> Juri Lelli <juri.lelli@redhat.com> wrote:
> [...]
> > > > I'm thinking that, while dl_task_fits_capacity() works well when
> > > > selecting idle cpus, in this case we should consider the fact
> > > > that curr might be deadline as well and already consuming some of
> > > > the rq capacity.
> > > > 
> > > > Do you think we should try to take that into account, maybe using
> > > > dl_rq->this_bw ?  
> > > 
> > > So you're saying that cpudl_find(..., later_mask) could return 1 (w/
> > > best_cpu (cp->elements[0].cpu) in later_mask).
> > > 
> > > And that this best_cpu could be a non-fitting CPU for p.
> > > 
> > > This could happen if cp->free_cpus is empty (no idle CPUs) so we
> > > take cpudl_find()'s else path and in case p's deadline <
> > > cp->elements[0] deadline.
> > > 
> > > We could condition the 'return 1' on best_cpu fitting p.
> > > 
> > > But should we do this for cpudl_find(..., NULL) calls from
> > > check_preempt_equal_dl() as well or will this break GEDF?  
> > 
> > So, even by not returning best_cpu, as above, if it doesn't fit p's bw
> > requirement, I think we would be breaking GEDF, which however doesn't
> > take asym capacities into account.
> 
> Well, gEDF could take asymmetric capacities into account by scheduling
> the earliest deadline task on the fastest CPU (and the task with the
> second earliest deadline on the second fastest CPU, and so on...)
> 
> But this could cause a lot of unneeded migrations (I tried to discuss
> this issue in a previous OSPM presentation). My original approach to
> work around this issue was to schedule a task on the slowest core on
> which the task can fit (some experiments revealed that this heuristic
> can approximate the gEDF behaviour without causing too many
> migrations)... But this patch is not included on the current patchset,
> and will be proposed later, after the most important patches have been
> merged.

OK, makes sense to me. And I'm ok also with a 2 steps approach. Asym
idle now and asym busy with a later series.

Best,

Juri