Date: Mon, 30 Jun 2008 16:31:46 -0700 From: David Wolfskill <david@catwhisker.org> To: John Baldwin <jhb@freebsd.org> Cc: freebsd-acpi@freebsd.org Subject: Re: How/why would dev.cpu.0.freq_levels change??!? Message-ID: <20080630233146.GQ13924@bunrab.catwhisker.org> In-Reply-To: <200806301511.11294.jhb@freebsd.org> References: <200806281738.40672.jhb@freebsd.org> <20080629003216.3AA074500E@ptavv.es.net> <20080629185738.GG13924@bunrab.catwhisker.org> <200806301511.11294.jhb@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
--DCA/C9WSnDtl50zu Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Mon, Jun 30, 2008 at 03:11:11PM -0400, John Baldwin wrote: > ... > Are you sure it is really a problem? Presumably the machine is overheati= ng or=20 > something that is causing the BIOS to request that the CPU speed is lower= ed=20 > (I wonder if Windows changes CPU speed when _PSS changes so that the BIO= S=20 > writer figured changing _PSS was sufficient to force the CPU to be=20 > throttled). Presumably if the BIOS really is trying to protect the hardw= are=20 > not doing what it wants might result in physical damage to the machine of= =20 > some sort. Yeah, I'm pretty sure. Evidence: * The behavior is markedly different from what it had been up to about a week ago. In particular, building RELENG_6, RELENG_7, and HEAD daily, the fans would normally vary in speed (based on pitch & intensity of sound, rather than from a sysctl variable) generally in an "expected" way based on the reported CPU temperature (this was from sysctl variable). Now, in contrast, the machinee runs for a bit, then the fans kick in, the CPU acts as if it maxes out at half speed. And the *only* way I've found to even slow the fans down is to power-cycle -- even though the reported CPU temperature is way low -- around 45C. (Exhaust air from the fans isn't especially warm, either.) * As a result, a full "make buildworld" takes several hours longer than it did as recently as a week ago. * I am now able to reproduce the problem just booting the machine to the BIOS config/setup stage. * The fan noise is freaking annoying. :-/ In any case, I've dropped the machine off for hardware repair. I should soon find out whether "repair" is a feasible option or I should look at replacement. Thanks for all your help! Peace, david --=20 David H. Wolfskill david@catwhisker.org I submit that "conspiracy" would be an appropriate collective noun for cats. See http://www.catwhisker.org/~david/publickey.gpg for my public key. --DCA/C9WSnDtl50zu Content-Type: application/pgp-signature Content-Disposition: inline -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.0 (FreeBSD) iEYEARECAAYFAkhpbOIACgkQmprOCmdXAD08uACZAcMCJKD1ri/fy8x+pU8r9gve rbMAn1oTaJmDW6lwbLnYw8PqWhLYN+oK =YFkN -----END PGP SIGNATURE----- --DCA/C9WSnDtl50zu--
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20080630233146.GQ13924>