Hello,
Using kernel: 2.6.18-92.1.13.el5.centos.plus
the cpu throttling works as desired (see 2 traces below)
------------- trace snips -------------- dmesg | grep -i pow ACPI: SSDT (v001 PTLTD POWERNOW 0x00000001 LTP 0x00000001) @ 0x3fff9b40 powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 4600+ processors ( 2 cpu cores) (version 2.20.00) powernow-k8: 0 : fid 0x10 (2400 MHz), vid 0x8 powernow-k8: 1 : fid 0xe (2200 MHz), vid 0xa powernow-k8: 2 : fid 0xc (2000 MHz), vid 0xc powernow-k8: 3 : fid 0xa (1800 MHz), vid 0xe powernow-k8: 4 : fid 0x2 (1000 MHz), vid 0x12 ACPI: Power Button (FF) [PWRF] ACPI: Power Button (CM) [PWRB]
#cpufreq-info cpufrequtils 002: cpufreq-info (C) Dominik Brodowski 2004-2006 Report errors and bugs to linux@brodo.de, please. analyzing CPU 0: driver: powernow-k8 CPUs which need to switch frequency at the same time: 0 1 hardware limits: 1000 MHz - 2.40 GHz available frequency steps: 2.40 GHz, 2.20 GHz, 2.00 GHz, 1.80 GHz, 1000 MHz available cpufreq governors: ondemand, userspace, performance current policy: frequency should be within 1000 MHz and 2.40 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 1000 MHz (asserted by call to hardware). (ditto for cpu 1)
------------- end snip ----------
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
I noticed that the 92* kernel has no separate powernow-k8.ko module, while the 128* kernel does. Does this module now need to be force loaded?
This box is used as a desktop.
On Thu, 2009-04-09 at 22:39 -0700, Mark Pryor wrote:
Hello,
Using kernel: 2.6.18-92.1.13.el5.centos.plus
the cpu throttling works as desired (see 2 traces below)
------------- trace snips -------------- dmesg | grep -i pow ACPI: SSDT (v001 PTLTD POWERNOW 0x00000001 LTP 0x00000001) @ 0x3fff9b40 powernow-k8: Found 1 AMD Athlon(tm) 64 X2 Dual Core Processor 4600+ processors ( 2 cpu cores) (version 2.20.00) powernow-k8: 0 : fid 0x10 (2400 MHz), vid 0x8 powernow-k8: 1 : fid 0xe (2200 MHz), vid 0xa powernow-k8: 2 : fid 0xc (2000 MHz), vid 0xc powernow-k8: 3 : fid 0xa (1800 MHz), vid 0xe powernow-k8: 4 : fid 0x2 (1000 MHz), vid 0x12 ACPI: Power Button (FF) [PWRF] ACPI: Power Button (CM) [PWRB]
#cpufreq-info cpufrequtils 002: cpufreq-info (C) Dominik Brodowski 2004-2006 Report errors and bugs to linux@brodo.de, please. analyzing CPU 0: driver: powernow-k8 CPUs which need to switch frequency at the same time: 0 1 hardware limits: 1000 MHz - 2.40 GHz available frequency steps: 2.40 GHz, 2.20 GHz, 2.00 GHz, 1.80 GHz, 1000 MHz available cpufreq governors: ondemand, userspace, performance current policy: frequency should be within 1000 MHz and 2.40 GHz. The governor "ondemand" may decide which speed to use within this range. current CPU frequency is 1000 MHz (asserted by call to hardware). (ditto for cpu 1)
------------- end snip ----------
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
I noticed that the 92* kernel has no separate powernow-k8.ko module, while the 128* kernel does. Does this module now need to be force loaded?
This box is used as a desktop.
Have a look at /etc/sysconf/apmd CPUFREQ="performance" And /etc/sysconfig/cpuspeed Self explanatory. Also there is a Gnome Applet you can add to the Gnome Panel called cpufreq scalling monitor. "The Easy Way"
To use the above you may have to load the correct driver for them and restart the cpuspeed service.
JohnStanley
Mark Pryor wrote on Thu, 9 Apr 2009 22:39:53 -0700 (PDT):
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
FYI: It works like before with the normal kernels, no problems.
Kai
Mark Pryor wrote:
Using kernel: 2.6.18-92.1.13.el5.centos.plus the cpu throttling works as desired (see 2 traces below)
...
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
This is an issue that came up in the early 5.2 days, and has been recurring since. I lost cpuspeed control on my desktop at home as well ( amdx24800/m2n) with the kernel update. Have not started digging into this, but the last time I did upstream blamed it on badly done acpi code in the system BIOS. It *should* now be possible to blacklist the powernow-k8.ko code and let the kernel fallback to using the generic acpi layer again. YMMV.
On Fri, 2009-04-10 at 12:16 +0100, Karanbir Singh wrote:
Mark Pryor wrote:
Using kernel: 2.6.18-92.1.13.el5.centos.plus the cpu throttling works as desired (see 2 traces below)
...
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
This is an issue that came up in the early 5.2 days, and has been recurring since. I lost cpuspeed control on my desktop at home as well ( amdx24800/m2n) with the kernel update. Have not started digging into this, but the last time I did upstream blamed it on badly done acpi code in the system BIOS. It *should* now be possible to blacklist the powernow-k8.ko code and let the kernel fallback to using the generic acpi layer again. YMMV.
--- Good thing to know it's just not happening to me also. I also have client machines this has affected and my own personal machines. This was with the p4-clockmod driver. Motherbords all were Asus. Also affected one Celeron machine on an Asus board.
JohnStanley
On Fri, 2009-04-10 at 11:37 -0400, JohnS wrote:
On Fri, 2009-04-10 at 12:16 +0100, Karanbir Singh wrote:
Mark Pryor wrote:
Using kernel: 2.6.18-92.1.13.el5.centos.plus the cpu throttling works as desired (see 2 traces below)
...
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
This is an issue that came up in the early 5.2 days, and has been recurring since. I lost cpuspeed control on my desktop at home as well ( amdx24800/m2n) with the kernel update. Have not started digging into this, but the last time I did upstream blamed it on badly done acpi code in the system BIOS. It *should* now be possible to blacklist the powernow-k8.ko code and let the kernel fallback to using the generic acpi layer again. YMMV.
Good thing to know it's just not happening to me also. I also have client machines this has affected and my own personal machines. This was with the p4-clockmod driver. Motherbords all were Asus. Also affected one Celeron machine on an Asus board.
JohnStanley
I have some older socket 604 533 FSB Xeon's with supermicro x5da8 motherboards and I've never gotten any of the power management, or even the poweroff or suspend command to work with any linux kernel on these boards. The bios code could be blamed, but I've booted other OSes that are capable of doing power management on this board.
In any case, are there particular motherboards, i.e. Intel, Tyan, Asus, Supermicro and/or brands of systems, i.e. Dell, HP that are known to work well with CentOS and support power management properly?
Nataraj
CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
On Fri, 2009-04-10 at 13:07 -0700, Nataraj wrote:
On Fri, 2009-04-10 at 11:37 -0400, JohnS wrote:
On Fri, 2009-04-10 at 12:16 +0100, Karanbir Singh wrote:
Mark Pryor wrote:
Using kernel: 2.6.18-92.1.13.el5.centos.plus the cpu throttling works as desired (see 2 traces below)
...
When I update to the newer xx-128.1.6 centosplus kernel all the throttling stops and the box runs at highest speed.
This is an issue that came up in the early 5.2 days, and has been recurring since. I lost cpuspeed control on my desktop at home as well ( amdx24800/m2n) with the kernel update. Have not started digging into this, but the last time I did upstream blamed it on badly done acpi code in the system BIOS. It *should* now be possible to blacklist the powernow-k8.ko code and let the kernel fallback to using the generic acpi layer again. YMMV.
Good thing to know it's just not happening to me also. I also have client machines this has affected and my own personal machines. This was with the p4-clockmod driver. Motherbords all were Asus. Also affected one Celeron machine on an Asus board.
JohnStanley
I have some older socket 604 533 FSB Xeon's with supermicro x5da8 motherboards and I've never gotten any of the power management, or even the poweroff or suspend command to work with any linux kernel on these boards. The bios code could be blamed, but I've booted other OSes that are capable of doing power management on this board.
In any case, are there particular motherboards, i.e. Intel, Tyan, Asus, Supermicro and/or brands of systems, i.e. Dell, HP that are known to work well with CentOS and support power management properly?
Nataraj
--- I can say that the one with the Celeron Processor has an Asus OEM Board but it is a Compaq/Hp System and Suspend does work on it. Now all my desktops I have suspend turned off. That particular one i had to manually load the driver restart cpuspeed and acpi. Pretty much all Dell Server systems had the on-demand governor loaded with I dislike. Also that is correct that some Bioses are not compatable. Some brands of boards I would never suspect it to work.
JohnStanley
-
JohnS -
Kai Schaetzl -
Karanbir Singh -
Mark Pryor -
Nataraj