public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
* cpuinfo_cur_freq always max
@ 2007-12-17 17:51 Stephen Clark
  2007-12-17 21:27 ` Johannes Weiner
  0 siblings, 1 reply; 6+ messages in thread
From: Stephen Clark @ 2007-12-17 17:51 UTC (permalink / raw)
  To: linux-kernel

Hello,

Running linux 2.6.23.1-21.fc7 
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq
correctly reflects the cpu speed, when idle it is 996000 and when 
compiling it is 1826000.
Its also the same as what is in /proc/cpuinfo.

But with 2.6.23.8-34.fc7 
/sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq
is always the max cpu speed of 1826000.

While cpuinfo_cur_freq is the max 1826000 /proc/cpuinfo relflects the 
correct speed when idle of
996000

This is on an asus laptop with an intel core 2 duo T5600 processor.

Anyone else see this problem.

Regards,
Steve

-- 

"They that give up essential liberty to obtain temporary safety, 
deserve neither liberty nor safety."  (Ben Franklin)

"The course of history shows that as a government grows, liberty 
decreases."  (Thomas Jefferson)




^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: cpuinfo_cur_freq always max
  2007-12-17 17:51 cpuinfo_cur_freq always max Stephen Clark
@ 2007-12-17 21:27 ` Johannes Weiner
       [not found]   ` <4766ECDB.1040203@seclark.us>
  0 siblings, 1 reply; 6+ messages in thread
From: Johannes Weiner @ 2007-12-17 21:27 UTC (permalink / raw)
  To: Stephen.Clark; +Cc: linux-kernel

Hi Steve,

Stephen Clark <Stephen.Clark@seclark.us> writes:

> But with 2.6.23.8-34.fc7
> /sys/devices/system/cpu/cpu0/cpufreq/cpuinfo_cur_freq
> is always the max cpu speed of 1826000.
>
> While cpuinfo_cur_freq is the max 1826000 /proc/cpuinfo relflects the
> correct speed when idle of
> 996000

Which governor are you using?  ondemand?

	Hannes

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: cpuinfo_cur_freq always max
       [not found]   ` <4766ECDB.1040203@seclark.us>
@ 2007-12-17 22:09     ` Johannes Weiner
  2007-12-18 15:19       ` Stephen Clark
  0 siblings, 1 reply; 6+ messages in thread
From: Johannes Weiner @ 2007-12-17 22:09 UTC (permalink / raw)
  To: Stephen.Clark; +Cc: Linux Kernel Mailing List

Hi,

Stephen Clark <Stephen.Clark@seclark.us> writes:

>>Which governor are you using?  ondemand?
> Not sure - but the only thing that is changed is the kernel - if I go
> back to 2.6.23.1 it works correctly.

Have a look at /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor

	Hannes

PS: Steve, please keep the list in CC.

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: cpuinfo_cur_freq always max
  2007-12-17 22:09     ` Johannes Weiner
@ 2007-12-18 15:19       ` Stephen Clark
  2007-12-18 16:04         ` Johannes Weiner
  0 siblings, 1 reply; 6+ messages in thread
From: Stephen Clark @ 2007-12-18 15:19 UTC (permalink / raw)
  To: Johannes Weiner; +Cc: Linux Kernel Mailing List

Johannes Weiner wrote:

>Hi,
>
>Stephen Clark <Stephen.Clark@seclark.us> writes:
>
>  
>
>>>Which governor are you using?  ondemand?
>>>      
>>>
>>Not sure - but the only thing that is changed is the kernel - if I go
>>back to 2.6.23.1 it works correctly.
>>    
>>
>
>Have a look at /sys/devices/system/cpu/cpu0/cpufreq/scaling_governor
>
>	Hannes
>
>PS: Steve, please keep the list in CC.
>
>  
>
userspace



-- 

"They that give up essential liberty to obtain temporary safety, 
deserve neither liberty nor safety."  (Ben Franklin)

"The course of history shows that as a government grows, liberty 
decreases."  (Thomas Jefferson)




^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: cpuinfo_cur_freq always max
  2007-12-18 15:19       ` Stephen Clark
@ 2007-12-18 16:04         ` Johannes Weiner
  2007-12-18 21:39           ` Stephen Clark
  0 siblings, 1 reply; 6+ messages in thread
From: Johannes Weiner @ 2007-12-18 16:04 UTC (permalink / raw)
  To: Stephen.Clark; +Cc: Linux Kernel Mailing List, Dave Jones

Hi,

Stephen Clark <Stephen.Clark@seclark.us> writes:

> userspace

Please supply the full dmesg output on the non-working kernel the
corresponding .config (or /proc/config.gz).

Added Dave to CC.

	Hannes

^ permalink raw reply	[flat|nested] 6+ messages in thread

* Re: cpuinfo_cur_freq always max
  2007-12-18 16:04         ` Johannes Weiner
@ 2007-12-18 21:39           ` Stephen Clark
  0 siblings, 0 replies; 6+ messages in thread
From: Stephen Clark @ 2007-12-18 21:39 UTC (permalink / raw)
  To: Johannes Weiner; +Cc: Linux Kernel Mailing List, Dave Jones

Johannes Weiner wrote:

>Hi,
>
>Stephen Clark <Stephen.Clark@seclark.us> writes:
>
>  
>
>>userspace
>>    
>>
>
>Please supply the full dmesg output on the non-working kernel the
>corresponding .config (or /proc/config.gz).
>
>Added Dave to CC.
>
>	Hannes
>
>  
>
Duh - I rebooted into the new kernel and no longer see the behavior I 
described above. Maybe I had something going in
the background i didn't realize. Thing was I even started a bash empty 
while loop to see if /proc/cpuinfo speed would go
up and it did.

I have an applet that displays on my kde kicker panel that every 2 
seconds reads /sys/.../cpuinfo_cur_freq and it was
sitting on the max speed all the time. Hmmm.

Well Thanks for the response and sorry for the false alarm.

Steve

-- 

"They that give up essential liberty to obtain temporary safety, 
deserve neither liberty nor safety."  (Ben Franklin)

"The course of history shows that as a government grows, liberty 
decreases."  (Thomas Jefferson)




^ permalink raw reply	[flat|nested] 6+ messages in thread

end of thread, other threads:[~2007-12-18 21:40 UTC | newest]

Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2007-12-17 17:51 cpuinfo_cur_freq always max Stephen Clark
2007-12-17 21:27 ` Johannes Weiner
     [not found]   ` <4766ECDB.1040203@seclark.us>
2007-12-17 22:09     ` Johannes Weiner
2007-12-18 15:19       ` Stephen Clark
2007-12-18 16:04         ` Johannes Weiner
2007-12-18 21:39           ` Stephen Clark

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox