From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Rafael J. Wysocki" Subject: Re: [PATCH v3 1/3] cpufreq: ondemand: Change the calculation of target frequency Date: Fri, 14 Jun 2013 14:46:38 +0200 Message-ID: <1469773.K3KVgsTfzW@vostro.rjw.lan> References: <1645236.hTWQPUhyIx@vostro.rjw.lan> <20130613223740.GE32112@pd.tnic> Mime-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: In-Reply-To: <20130613223740.GE32112@pd.tnic> Sender: cpufreq-owner@vger.kernel.org To: Borislav Petkov Cc: Stratos Karafotis , Borislav Petkov , Viresh Kumar , Thomas Gleixner , Ingo Molnar , "H. Peter Anvin" , linux-pm@vger.kernel.org, cpufreq@vger.kernel.org, linux-kernel@vger.kernel.org List-Id: linux-pm@vger.kernel.org On Friday, June 14, 2013 12:37:41 AM Borislav Petkov wrote: > On Fri, Jun 14, 2013 at 12:15:36AM +0200, Rafael J. Wysocki wrote: > > On Thursday, June 13, 2013 11:40:08 PM Borislav Petkov wrote: >=20 > [ =E2=80=A6 ] >=20 > > > Not bad. However, exec_test and fork_test are kinda unexpected wi= th such > > > a high improvement percentage. Happen to have an explanation? > > >=20 > > > FWIW, if we don't find any serious perf/power regressions with > > > this patch, I'd say it is worth applying even solely for the code > > > simplification it brings. > >=20 > > May I take this as an ACK? ;-) > >=20 > > Well, that's my opinion too, actually. >=20 > I know - you told me and I like that aspect :-). And from the test > results so far, the code simplification is maybe the most persuasive > one. The slight improvements in perf/power are then the cherry on top= =2E >=20 > Although, I'm not sure we're exhaustive with the benchmarks and we > should maybe run a couple more. Although, judging by the results, > generally no serious outliers should be expected (except exec_test an= d > fork_test funsies above), which are actually positive outliers. >=20 > Judging by the code change, the only worry we should have, AFAIU, is > any raise in power consumption due to spending longer periods in the > intermediary P-states now and not going straight to the lowest P-stat= e. > But this compensates with improvement in runtime of the workloads. >=20 > Hmm, I dunno - I'm just thinking out loud here... OK, so here's a deal. After 3.10-rc1 goes out, I'll put this into linu= x-next for 3.12, so that people have a few more weeks to complain. If they do= n't, it'll go into 3.12. Thanks, Rafael --=20 I speak only for myself. Rafael J. Wysocki, Intel Open Source Technology Center.