I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500
I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing.
I was going to do "killall -SIGUSR1 cpuspeed" to attempt to get 2500+ cpu speed.
I am compiling wine right now so I havent gotten back into the BIOS. Is there another way to get the FULL cpu speed.
THanks,
Jerry
AMD processors labeling has not followed the speed in Mhz for a few years now. The 2500+ is just a designation and not processor speed in Mhz.
That is still low as my searching states it should be around 1743Mhz. The BIOS is probably not set correctly if auto detection is not set or if auto detection is set, the bios may not recognize the processor and may need to be updated.
Chris
geisj@pagestation.com 05/04/06 10:13 am >>>
I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500
I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing.
I was going to do "killall - SIGUSR1 cpuspeed" to attempt to get 2500+ cpu speed.
I am compiling wine right now so I havent gotten back into the BIOS. Is there another way to get the FULL cpu speed.
THanks,
Jerry
_______________________________________________ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
-- This message has been scanned for viruses and dangerous content by MailScanner, and is believed to be clean.
Michel Daggelinckx wrote:
/ Jerry Geis wrote:
/>/ />>/ I have a desktop unit with a sempron 2500+ to play with. />>/ doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500 />>/ />>/ I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in />>/ nothing. />>/ I did service cpuspeed start. No errors reported. />>/ ps ax | grep cpuspeed resulted in nothing. /
Sounds like cpuspeed could be crashing. Make sure there is no cpuspeed running as daemon then try running it as root with no args. Check /var/log/messages if it blows chunks.
Cpuspeed is crashing. when I run it from the command line it says:
could not open file for writing "/sys/devices/system/cpu/cpu0/cpufreq/scaling_governor"
the cpufreq directorty is not present....
I tried to use mkdir and create it as root but it says "operation not permitted".
Jerry
Jerry Geis wrote on Thu, 04 May 2006 13:37:02 -0400:
"operation not permitted".
SELinux?
Kai
Kai Schaetzl wrote:
Jerry Geis wrote on Thu, 04 May 2006 13:37:02 -0400:
"operation not permitted".
SELinux?
No, not selinux. You can't create dirs in /sys from usermode.
I guess there is trouble with the kernel module (which is actually part of the monolithic kernel for Fedora anyway) that does cpuspeed for your brand of CPU.
cat /var/log/messages | grep power or dmesg | grep power
I get something like this:
# dmesg | grep power powernow-k8: Found 2 AMD Athlon 64 / Opteron processors (version 1.60.0) powernow-k8: 0 : fid 0xe (2200 MHz), vid 0xa (1300 mV) powernow-k8: 1 : fid 0xc (2000 MHz), vid 0xa (1300 mV) powernow-k8: 2 : fid 0xa (1800 MHz), vid 0xc (1250 mV) powernow-k8: 3 : fid 0x2 (1000 MHz), vid 0x12 (1100 mV)
indicating powernow-k8, the module that does the cpuspeed dirty work, is happy. The lack of the /sys entry may suggest the module was unhappy in your case at boot time, it which case you might find a complaint instead.
-Andy
On Thu, 4 May 2006, Andy Green wrote:
I guess there is trouble with the kernel module (which is actually part of the monolithic kernel for Fedora anyway) that does cpuspeed for your brand of CPU.
powernow-k7 is a built-in module in CentOS-4. I had the same problem on my laptop, it ran at ~800MHz rather than 1666MHz (the normal frequency for this XP-M 2000+). Kernel messages indicated that it is a problem that is fairly common:
--- powernow: PowerNOW! Technology present. Can scale: frequency and voltage. powernow: No PST tables match this cpuid (0x781) powernow: This is indicative of a broken BIOS. powernow: Trying ACPI perflib powernow: ACPI perflib can not be used in this platform powernow: ACPI and legacy methods failed powernow: See http://www.codemonkey.org.uk/projects/cpufreq/powernow-k7.shtml ---
The strange thing is that on this laptop powernow-k7 also succeeds every now and then:
--- powernow: PowerNOW! Technology present. Can scale: frequency and voltage. powernow: SGTC: 13333 powernow: Minimum speed 799 MHz. Maximum speed 1666 MHz. ---
I haven't decided yet whether I will ditch this driver or not. But it is not really urgent when I don't need Eclipse for the day :).
-- Daniel
I use AMD chips all the time. To my understanding of how AMD chips work AMD calls it a 2500 because its suppose to be equal to an INTEL chip that runs as 2500 even though the actual clock shows it slower. They started doing that with the XP chips which Sempron replaced.
-----Original Message----- From: centos-bounces@centos.org [mailto:centos-bounces@centos.org] On Behalf Of Jerry Geis Sent: Thursday, May 04, 2006 9:14 AM To: centos@centos.org Subject: [CentOS] sempron 2500+ running at 1044 cpu speed.
I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500
I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing.
I was going to do "killall -SIGUSR1 cpuspeed" to attempt to get 2500+ cpu speed.
I am compiling wine right now so I havent gotten back into the BIOS. Is there another way to get the FULL cpu speed.
THanks,
Jerry
_______________________________________________ CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
On Thu, 2006-05-04 at 09:23 -0500, Chris Peikert wrote:
I use AMD chips all the time. To my understanding of how AMD chips work AMD calls it a 2500 because its suppose to be equal to an INTEL chip that runs as 2500 even though the actual clock shows it slower. They started doing that with the XP chips which Sempron replaced.
-----Original Message----- From: centos-bounces@centos.org [mailto:centos-bounces@centos.org] On Behalf Of Jerry Geis Sent: Thursday, May 04, 2006 9:14 AM
<snip>
Good Grief! And I thought I was always the last to know! Chris is right. But the change occurred around 1997 (8?) or so? About 10 yrs ago? It was because the average consumer only knows MHz as the performance indicator and is not aware of pipelines, on-board cache, instruction sets, multiple decode, predictive ...
So AMD needed a way that could immediately clue the clueless that this was "approximately equal to Intel at xxx MHz". It worked ... sorta. They took a lot of heat about it from the old-guard tech types. But they managed to avoid bankruptcy and are still bringing superior products to market.
Jerry Geis wrote:
I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500
I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing.
I was going to do "killall -SIGUSR1 cpuspeed" to attempt to get 2500+ cpu speed.
I am compiling wine right now so I havent gotten back into the BIOS. Is there another way to get the FULL cpu speed.
THanks,
Jerry
CentOS mailing list CentOS@centos.org http://lists.centos.org/mailman/listinfo/centos
AMD labels a 2500+ as being equal in speed to an intel processor. This doesn't mean the sempron is runing at that speed. Its only to compare the proccesing power of the sempron with an equal intel processor. However 1044Mhz looks still slow as it should be 1743Mhz. Maybee you should check to see if your bios is set up correctly.
Michel Daggelinckx wrote:
Jerry Geis wrote:
I have a desktop unit with a sempron 2500+ to play with. doing "more /proc/cpuinfo" indicates cpu Mhz as1044 not the 2500
I am familiar with cpuspeed. doing ps ax | grep cpuspeed resulting in nothing. I did service cpuspeed start. No errors reported. ps ax | grep cpuspeed resulted in nothing.
Sounds like cpuspeed could be crashing. Make sure there is no cpuspeed running as daemon then try running it as root with no args. Check /var/log/messages if it blows chunks.
-Andy
-
Andy Green -
Chris Hammond -
Chris Peikert -
Daniel de Kok -
Jerry Geis -
Kai Schaetzl -
Michel Daggelinckx -
William L. Maltby