From: Peter Zijlstra Subject: Re: [Update][PATCH v3 3/4] cpufreq: schedutil: Simplify iowait boosting Date: Mon, 1 Apr 2019 12:29:48 +0200 Message-ID: <20190401102948.GI11158@hirez.programming.kicks-ass.net> References: <11953735.uMqeHy63Iu@aspire.rjw.lan> <2864116.v8IU97Resm@aspire.rjw.lan> <3714586.Xfz7sSM4fi@aspire.rjw.lan> <388546350.6JbkPPd9ra@aspire.rjw.lan> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Return-path: Content-Disposition: inline In-Reply-To: <388546350.6JbkPPd9ra@aspire.rjw.lan> Sender: linux-kernel-owner@vger.kernel.org To: "Rafael J. Wysocki" Cc: Linux PM , Quentin Perret , LKML , Viresh Kumar , Srinivas Pandruvada , Chen Yu , Gabriele Mazzotta List-Id: linux-pm@vger.kernel.org On Mon, Apr 01, 2019 at 11:27:25AM +0200, Rafael J. Wysocki wrote: > On Thursday, March 28, 2019 11:33:21 AM CEST Rafael J. Wysocki wrote: > > From: Rafael J. Wysocki > > > > There is not reason for the minimum iowait boost value in the > > schedutil cpufreq governor to depend on the available range of CPU > > frequencies. In fact, that dependency is generally confusing, > > because it causes the iowait boost to behave somewhat differently > > on CPUs with the same maximum frequency and different minimum > > frequencies, for example. > > > > For this reason, replace the min field in struct sugov_cpu > > with a constant and choose its values to be 1/8 of > > SCHED_CAPACITY_SCALE (for consistency with the intel_pstate > > driver's internal governor). > > > > [Note that policy->cpuinfo.max_freq will not be a constant any more > > after a subsequent change, so this change is depended on by it.] > > > > Link: https://lore.kernel.org/lkml/20190305083202.GU32494@hirez.programming.kicks-ass.net/T/#ee20bdc98b7d89f6110c0d00e5c3ee8c2ced93c3d > > Suggested-by: Peter Zijlstra > > Signed-off-by: Rafael J. Wysocki > Any more comments on this patch? I obviously like it :-) Acked-by: Peter Zijlstra (Intel) > If not, I'll queue it up along with the rest of the series. Thanks!