From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH v5 02/15] sched/core: make sched_setattr able to tune the current policy Date: Wed, 7 Nov 2018 14:58:01 +0100 Message-ID: <20181107135801.GE9761@hirez.programming.kicks-ass.net> References: <20181029183311.29175-1-patrick.bellasi@arm.com> <20181029183311.29175-3-patrick.bellasi@arm.com> <20181107121126.GN9781@hirez.programming.kicks-ass.net> <20181107135039.GD14309@e110439-lin> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20181107135039.GD14309@e110439-lin> Sender: linux-kernel-owner@vger.kernel.org To: Patrick Bellasi Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, Ingo Molnar , Tejun Heo , "Rafael J . Wysocki" , Vincent Guittot , Viresh Kumar , Paul Turner , Quentin Perret , Dietmar Eggemann , Morten Rasmussen , Juri Lelli , Todd Kjos , Joel Fernandes , Steve Muckle , Suren Baghdasaryan , linux-api@vger.kernel.org List-Id: linux-pm@vger.kernel.org On Wed, Nov 07, 2018 at 01:50:39PM +0000, Patrick Bellasi wrote: > On 07-Nov 13:11, Peter Zijlstra wrote: > > On Mon, Oct 29, 2018 at 06:32:56PM +0000, Patrick Bellasi wrote: > > > > > @@ -50,11 +52,13 @@ > > > #define SCHED_FLAG_RESET_ON_FORK 0x01 > > > #define SCHED_FLAG_RECLAIM 0x02 > > > #define SCHED_FLAG_DL_OVERRUN 0x04 > > > -#define SCHED_FLAG_UTIL_CLAMP 0x08 > > > +#define SCHED_FLAG_TUNE_POLICY 0x08 > > > +#define SCHED_FLAG_UTIL_CLAMP 0x10 > > > > That seems to suggest you want to do this patch first, but you didn't.. > > I've kept it here just to better highlight this change, suggested by > Juri, since we was not entirely sure you are fine with it... > > If you think it's ok adding a SCHED_FLAG_TUNE_POLICY behavior to the > sched_setattr syscall, I can certainly squash into the previous patch, > which gives more context on why we need it. I'm fine with the idea I think. It's the details I worry about. Which fields in particular are not updated with this. Are flags? Also, I'm not too keen on the name; since it explicitly does not modify the policy and its related parameters, so TUNE_POLICY is actively wrong. But the thing that confused me most is how fiddled the numbers to fit this before UTIL_CLAMP. > Since we are at that, are we supposed to document some{where,how} > these API changes ? I'm pretty sure there's a manpage somewhere... SCHED_SETATTR(2) seems to exist on my machine. So that wants updates.