I'm using the k8-powernow for powersaving on my X2-4200+ with cpufreq and cpudyn. When I start up, the k8-powernow statements are as follows: powernow-k8: Found 2 AMD Athlon 64 / Opteron processors (version 1.50.4) powernow-k8: 0 : fid 0xe (2200 MHz), vid 0x8 (1350 mV) powernow-k8: 1 : fid 0x2 (1000 MHz), vid 0x12 (1100 mV) This is confirmed by scaling_available_frequencies which echos 2200000 1000000 However, scaling_min_freq is 1452000 and that's what the powersave module pushes down to. if I force it to 1000000, my machine locks up. I've posted to the forums but nobody responds so I'm thinking this is a kernel bug with my system. Specs: Motherboard: gigabyte GA-K8NF-9 BIOS F10 (latest) Processor: Athlon 64 4200+ emerge info: Portage 2.0.53 (default-linux/amd64/2005.1, gcc-3.4.4, glibc-2.3.6-r1, 2.6.14-ck7 x86_64) ================================================================= System uname: 2.6.14-ck7 x86_64 AMD Athlon(tm) 64 X2 Dual Core Processor 4200+ Gentoo Base System version 1.6.13 distcc 2.18.3 x86_64-pc-linux-gnu (protocols 1 and 2) (default port 3632) [enabled] ccache version 2.4 [enabled] dev-lang/python: 2.4.2 sys-apps/sandbox: 1.2.12 sys-devel/autoconf: 2.13, 2.59-r6 sys-devel/automake: 1.4_p6, 1.5, 1.6.3, 1.7.9-r1, 1.8.5-r3, 1.9.6-r1 sys-devel/binutils: 2.16.1-r1 sys-devel/libtool: 1.5.20 virtual/os-headers: 2.6.11-r2 ACCEPT_KEYWORDS="amd64" AUTOCLEAN="yes" CBUILD="x86_64-pc-linux-gnu" CFLAGS="-O3 -march=athlon64 -pipe -msse3" CHOST="x86_64-pc-linux-gnu" CONFIG_PROTECT="/etc /usr/kde/2/share/config /usr/kde/3/share/config /usr/share/X11/xkb /usr/share/config /var/qmail/control" CONFIG_PROTECT_MASK="/etc/gconf /etc/terminfo /etc/env.d" CXXFLAGS="-O3 -march=athlon64 -pipe -msse3" DISTDIR="/usr/portage/distfiles" FEATURES="autoconfig buildpkg ccache distcc distlocks prelink sandbox sfperms strict" GENTOO_MIRRORS="http://mirror.phy.olemiss.edu/mirror/gentoo http://gentoo.chem.wisc.edu/gentoo/ http://distro.ibiblio.org/pub/linux/distributions/gentoo/ http://mirror.datapipe.net/gentoo" LDFLAGS="-Wl,-O1" MAKEOPTS="-j3" PKGDIR="/mnt/windows/pkgdir" PORTAGE_TMPDIR="/mnt/windows/tmp" PORTDIR="/usr/portage" PORTDIR_OVERLAY="/usr/local/portage" SYNC="rsync://rsync.gentoo.org/gentoo-portage" USE="amd64 X aac acpi alsa apache2 audiofile avi berkdb bidi bitmap-fonts blas bmp bonobo browserplugin bzip2 cairo cdb cdparanoia cdr crypt cups curl dbus dlloader dri dts dvd dvdr dvdread eds emboss emul-linux-x86 encode esd ethereal evo exif expat fam fbcon ffmpeg firefox flac foomaticdb fortran ftp gd gdbm gif glut gnome gpm gstreamer gtk gtk2 gtkhtml guile hal icq idn ieee1394 imagemagick imlib ipv6 java jpeg lapack lcms libwww lm_sensors lzw lzw-tiff mad maildir mbox mhash mime mng motif mp3 mpeg msn nas ncurses nls nptl nsplugin nvidia offensive ogg oggvorbis openal opengl oscar pam pcre pda pdflib perl php pic plotutils png ppds python qt quicktime readline recode samba sdl smp sndfile snmp soap sockets sox speex spell ssl tcltk tcpd theora threads tidy tiff truetype truetype-fonts type1-fonts udev usb userlocales v4l vcd videos vorbis wifi wxwindows xine xml xml2 xmms xpm xv xvid zlib userland_GNU kernel_linux elibc_glibc" Unset: ASFLAGS, CTARGET, LANG, LC_ALL, LINGUAS
just upgraded to 2.6.15 and it's still there...
Please reproduce with the latest development kernel (currently 2.6.16-rc1)
Okay, under 2.6.16-rc1: powernow-k8 still shows the same two frequencies at boot (version 1.60.0). My scaling_min_freq is at 2200000. Under powersave or ondemand or any other governor, no scaling down happens. On the upside, they're both at 2200000 now...
Need more info there. If scaling_min_freq is at 2200000 then no governer will attempt to go below that value. You are supposed to modify that manually if it is not what is desired. Does the lockup still happen if you go down to 1000000? Does scaling_available_frequencies still show that as available?
The lockup still happens. If I echo 1000000 to scaling_min_freq, the system locks. scaling_available_frequencies still shows 2200000 1000000 I made a mistake cpuinfo_min_freq is 1000000
echoing 1452000 to scaling_min_freq still has it scale down to that amount.
Please file this as an upstream bug against 2.6.16-rc1 at http://bugzilla.kernel.org and post the new bug URL here.
As requested! http://bugzilla.kernel.org/show_bug.cgi?id=5934
upstream bug is closed