From mboxrd@z Thu Jan 1 00:00:00 1970 From: "Peter Oruba" Subject: Re: cpufreq issue with K8 performance governor Date: Tue, 29 May 2007 18:20:06 +0200 Message-ID: <200705291820.06896.peter.oruba@amd.com> References: <200705291547.10134.peter.oruba@amd.com> <20070529160621.GC13235@redhat.com> Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============1022454369==" Return-path: In-Reply-To: <20070529160621.GC13235@redhat.com> List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Sender: cpufreq-bounces@lists.linux.org.uk Errors-To: cpufreq-bounces+glkc-cpufreq=gmane.org+glkc-cpufreq=gmane.org@lists.linux.org.uk To: cpufreq@lists.linux.org.uk --===============1022454369== Content-Type: multipart/signed; boundary=nextPart2668689.myGYOuVNfE; protocol="application/pgp-signature"; micalg=pgp-sha1 --nextPart2668689.myGYOuVNfE Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Content-Disposition: inline Am Dienstag, 29. Mai 2007 18:06:21 schrieben Sie: > On Tue, May 29, 2007 at 03:47:00PM +0200, Peter Oruba wrote: > > Dave, > >=20 > > I am contacting you regarding a frequency scaling issue that I encount= ered with the performance governor in combination with CPU hotplug. In cpuf= req.c CPU frequency is reduced to its=20 > > minimum before the CPU gets unregistered and set offline. Does that ha= ve a particular reason? Since the (k8-)governor does not monitor CPU freque= ncy that setting also applies then to the remaining CPU > > as well and lets the system run on the lowest frequency although perfo= rmance is chose as the policy. > >=20 > > --- > > static int cpufreq_cpu_callback(struct notifier_block *nfb, > > unsigned long action, void *hc= pu) > > { > >=20 > > [......] > >=20 > > case CPU_DOWN_PREPARE_FROZEN: > > if (unlikely(lock_policy_rwsem_write(cpu))) > > BUG(); > >=20 > > policy =3D cpufreq_cpu_data[cpu]; > > if (policy) { > > __cpufreq_driver_target(policy, policy= =2D>min, > > CPUFREQ_RELATION_H); > > } > > __cpufreq_remove_dev(sys_dev); >=20 > This is the path taken when we call suspend. > To be honest, I doubt that reducing the speed has any benefit at all, > as we're about to put the CPU to sleep anyway. >=20 > (btw, in future sending questions to cpufreq@lists.linux.org.uk is a bett= er > idea. The subsystem is sufficiently complex that at times, others can > answer questions better than I can, especially with the various > implementations all being subtley different). >=20 > Thanks, >=20 > Dave >=20 Okay, removing the __cpufreq_driver_target call would solve would obviously= solve that problem (which btw also exists on Core2, as I tested a couple o= f minutes ago). Is it planned to be changed=20 in the near future? Thanks, Peter =2D-=20 AMD Saxony Limited Liability Company & Co. KG Operating System Research Center Wilschdorfer Landstr. 101, 01109 Dresden, Germany Register Court Dresden: HRA 4896 General Partner authorized to represent: AMD Saxony LLC (Wilmington, Delaware, US) General Manager of AMD Saxony LLC: Dr. Hans-R. Deppe, Thomas McCoy --nextPart2668689.myGYOuVNfE Content-Type: application/pgp-signature; name=signature.asc Content-Description: This is a digitally signed message part. Content-Transfer-Encoding: 7bit -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.5 (GNU/Linux) iD8DBQBGXFK238rmLONd5dwRAuJlAJ4pKN6eM50RpzxVgJfUj8B825cKaQCgyBUd VjdhMKADczLKoGbzw1g3gkc= =stNH -----END PGP SIGNATURE----- --nextPart2668689.myGYOuVNfE-- --===============1022454369== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ Cpufreq mailing list Cpufreq@lists.linux.org.uk http://lists.linux.org.uk/mailman/listinfo/cpufreq --===============1022454369==--