From mboxrd@z Thu Jan 1 00:00:00 1970 From: Peter Zijlstra Subject: Re: [PATCH 2/2] sched: cpufreq: use rt_avg as estimate of required RT CPU capacity Date: Thu, 1 Sep 2016 09:12:30 +0200 Message-ID: <20160901071230.GI10153@twins.programming.kicks-ass.net> References: <1472236848-17038-1-git-send-email-smuckle@linaro.org> <1472236848-17038-3-git-send-email-smuckle@linaro.org> <20160831143907.GX10121@twins.programming.kicks-ass.net> <20160831150846.GN5599@graphite.smuckle.net> <20160831164009.GF10153@twins.programming.kicks-ass.net> <20160831170002.GK9337@e106622-lin> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <20160831170002.GK9337@e106622-lin> Sender: linux-kernel-owner@vger.kernel.org To: Juri Lelli Cc: Thomas Gleixner , Steve Muckle , Ingo Molnar , "Rafael J . Wysocki" , linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org, Vincent Guittot , Morten Rasmussen , Dietmar Eggemann , Patrick Bellasi List-Id: linux-pm@vger.kernel.org On Wed, Aug 31, 2016 at 06:00:02PM +0100, Juri Lelli wrote: > On 31/08/16 18:40, Peter Zijlstra wrote: > > Another problem is that we have many semi related knobs; we have the > > global RT runtime limit knob, but that doesn't affect cpufreq (maybe it > > should) > > Maybe we could create this sort of link when using the cgroup RT > throttling interface as well? It should still then fit well once we > replace the underlying mechanism with DL reservations. And, AFAIK, the > interface is used by Android folks already. Tricky, but possible I suppose. Since minimal cpufreq is 'global', the cgroup reservation only matters if there are no tasks in any of its parent groups. Computing the effective rt min then again becomes somewhat tricky, since we'd have to iterate the cgroup tree.