From mboxrd@z Thu Jan 1 00:00:00 1970 From: Quentin Perret Subject: Re: [PATCH 2/2] sched: Document Energy Aware Scheduling Date: Fri, 18 Jan 2019 11:26:58 +0000 Message-ID: <20190118112655.cd5q5x7n4ahv3r5f@queper01-lin> References: <20190110110546.8101-1-quentin.perret@arm.com> <20190110110546.8101-3-quentin.perret@arm.com> <20190117155117.GG14385@localhost.localdomain> <20190118091652.xn6iw52tccwh6vap@queper01-lin> <20190118103359.jqctbopx25h3zvqs@queper01-lin> <20190118111114.dytdk7oq63illgkg@queper01-lin> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: Sender: linux-kernel-owner@vger.kernel.org To: "Rafael J. Wysocki" Cc: Juri Lelli , Jonathan Corbet , Peter Zijlstra , "Rafael J. Wysocki" , Ingo Molnar , Morten Rasmussen , qais.yousef@arm.com, Patrick Bellasi , Dietmar Eggemann , "open list:DOCUMENTATION" , Linux PM , Linux Kernel Mailing List List-Id: linux-pm@vger.kernel.org On Friday 18 Jan 2019 at 12:20:57 (+0100), Rafael J. Wysocki wrote: > On Fri, Jan 18, 2019 at 12:11 PM Quentin Perret wrote: > > > > On Friday 18 Jan 2019 at 12:01:35 (+0100), Rafael J. Wysocki wrote: > > > On Fri, Jan 18, 2019 at 11:58 AM Rafael J. Wysocki wrote: > > > > > > > > On Fri, Jan 18, 2019 at 11:34 AM Quentin Perret wrote: > > > > > > > > > > Hi Rafael, > > > > > > > > > > On Friday 18 Jan 2019 at 10:57:08 (+0100), Rafael J. Wysocki wrote: > > > > > > On Fri, Jan 18, 2019 at 10:16 AM Quentin Perret wrote: > > > > > > > > > > > > > > Hi Juri, > > > > > > > > > > > > > > On Thursday 17 Jan 2019 at 16:51:17 (+0100), Juri Lelli wrote: > > > > > > > > On 10/01/19 11:05, Quentin Perret wrote: > > > > > > > [...] > > > > > > > > > +The idea behind introducing an EM is to allow the scheduler to evaluate the > > > > > > > > > +implications of its decisions rather than blindly applying energy-saving > > > > > > > > > +techniques that may have positive effects only on some platforms. At the same > > > > > > > > > +time, the EM must be as simple as possible to minimize the scheduler latency > > > > > > > > > +impact. > > > > > > > > > + > > > > > > > > > +In short, EAS changes the way CFS tasks are assigned to CPUs. When it is time > > > > > > > > > > > > > > > > Not sure if we want to remark the fact that EAS is looking at CFS tasks > > > > > > > > only ATM. > > > > > > > > > > > > > > Oh, what's wrong about mentioning it ? I mean, it is a fact ATM ... > > > > > > > > > > > > But it won't hurt to mention that it may cover other scheduling > > > > > > classes in the future. IOW, the scope limit is not fundamental. > > > > > > > > > > Agreed, I can do that. > > > > > > > > > > > > > > +for the scheduler to decide where a task should run (during wake-up), the EM > > > > > > > > > +is used to break the tie between several good CPU candidates and pick the one > > > > > > > > > +that is predicted to yield the best energy consumption without harming the > > > > > > > > > +system's throughput. The predictions made by EAS rely on specific elements of > > > > > > > > > +knowledge about the platform's topology, which include the 'capacity' of CPUs, > > > > > > > > > > > > > > > > Add a reference to DT bindings docs defining 'capacity' (or define it > > > > > > > > somewhere)? > > > > > > > > > > > > > > Right, I can mention this is defined in the next section. But are you > > > > > > > sure about the reference to the DT bindings ? They're arm-specific right ? > > > > > > > Maybe I can give that as an example or something ... > > > > > > > > > > > > Example sounds right. > > > > > > > > > > > > You also can point to the section below from here. > > > > > > > > > > Sounds good. > > > > > > > > > > > Side note: If the doc is in the .rst format (which Peter won't like > > > > > > I'm sure :-)), you can actually use cross-references in it and you get > > > > > > a translation to an HTML doc (hosted at kernel.org) for free and the > > > > > > cross-references become clickable links in that. > > > > > > > > > > Right, I personally don't mind the .rst format, but the existing files > > > > > in Documentation/power/ and Documentation/scheduler/ are good old txt > > > > > files so I just wanted to keep things consistent. > > > > > > > > In fact, Documentation/power/ is under a slow on-going transition to > > > > .rst (due to the benefits mentioned above). > > > > > > > > > I don't mind converting to rst if necessary :-) > > > > > > > > It is not necessary, but maybe worth considering. > > > > > > That said, as this is targeted at Documentation/scheduler/, being > > > consistent with the other material in there is probably more > > > important. > > > > Right. Patch 01/02 is targeted at Documentation/power/ though. So if > > that makes your life easier I can turn that one into a .rst file, no > > problem at all. > > Yes, I'd prefer it that way. And please put it into > Documentation/driver-api/pm/. Will do in v2. Thanks, Quentin