From mboxrd@z Thu Jan 1 00:00:00 1970 From: =?iso-8859-1?Q?Beno=EEt?= Canet Subject: Re: cpufreq and QEMU guests Date: Mon, 16 Sep 2013 17:46:04 +0200 Message-ID: <20130916154603.GK5105@irqsave.net> References: <20130916121545.GH5105@irqsave.net> <8668D877-8B37-48E3-97B8-CE36DB884E54@suse.de> <20130916150544.GJ5105@irqsave.net> <20130916153239.GD906@redhat.com> Mime-Version: 1.0 Content-Transfer-Encoding: QUOTED-PRINTABLE Return-path: Content-Disposition: inline In-Reply-To: <20130916153239.GD906@redhat.com> Sender: cpufreq-owner@vger.kernel.org List-ID: Content-Type: text/plain; charset="iso-8859-1" To: Gleb Natapov Cc: =?iso-8859-1?Q?Beno=EEt?= Canet , Alexander Graf , "cpufreq@vger.kernel.org" , "qemu-devel@nongnu.org" , "rjw@sisk.pl" , "viresh.kumar@linaro.org" , "peter.maydell@linaro.org" , "pbonzini@redhat.com" Le Monday 16 Sep 2013 =E0 18:32:39 (+0300), Gleb Natapov a =E9crit : > On Mon, Sep 16, 2013 at 05:05:45PM +0200, Beno=EEt Canet wrote: > > Le Monday 16 Sep 2013 =E0 09:39:10 (-0500), Alexander Graf a =E9cri= t : > > >=20 > > >=20 > > > Am 16.09.2013 um 07:15 schrieb Beno=EEt Canet : > > >=20 > > > >=20 > > > > Hello, > > > >=20 > > > > I know a cloud provider worried about the fact that the /proc/c= puinfo of his > > > > guests give a bogus frequency to his customer. > > > >=20 > > > > QEMU and the guests kernel currently have no way to reflect the= host frequency > > > > changes to the guests. > > > >=20 > > > > The customer compute intensive application then read this infor= mation and take > > > > wrong decisions. > > >=20 > > > Why do they care about the frequency? Is it for scheduling worklo= ads? The only other case I can think of would be the TSC and that shoul= d be fixed frequency these days. > > >=20 > > > If it's scheduling, you could maybe expose the unavailable comput= e time as steal time to the guest. Exposibg frequency in a virtual envi= ronment feels backwards. > >=20 > > The final customer have a compute intensive workload. > > At startup the code retrieve the cpu cache topology, the cpu model,= and various > > informations including the guest cpu frequency before starting the = compute job. > > The QEMU instance typicaly use -cpu host. > >=20 > > The code inspects the cpu frequency has seen by the guests to choos= e the number > > of vms to instanciate to compute the given task. > I am not sure I understand. They look at guest cpu frequency to estim= ate > guest's performance? Yes they take guest cpu count, model and frequency to estimate the perf= ormance of the guest. Next they cluster enough guests to be able to compute the job in a give= n time by using this estimate. Best regards Beno=EEt >=20 > > They even destroy and recreate some vms that would be underperformi= ng to > > mitigate the high inter vm communication costs. > >=20 > > Do you think the steal time trick would work for this ? > >=20 >=20 > -- > Gleb. > -- > To unsubscribe from this list: send the line "unsubscribe cpufreq" in > the body of a message to majordomo@vger.kernel.org > More majordomo info at http://vger.kernel.org/majordomo-info.html