System clock frequency offset changes drastically across reboots

System clock frequency offset changes drastically across reboots

[John Sigler]

[ Re-sending... Please feel free to comment, even if you don't have
"The Solution". I'd just like to get some feedback. ]

Hello everyone,

I'm using 2.6.20.7-rt8 on a P3.

I've noticed that the frequency offset of my system clock (computed
either by ntpd, or by hand) changes drastically across reboots.

By drastically, I mean +/- 60 ppm every time I reboot.

Apparently this is caused by some imprecision in the frequency
estimation done in calculate_cpu_khz() (arch/i386/kernel/tsc.c)

My brutally crude work-around was to skip the computation altogether and
hard-code the "correct" value for cpu_khz.

http://linux.kernel.free.fr/cpu_khz.adlink

Has this issue been investigated more thoroughly by other users?

Regards.

System clock frequency offset changes drastically across reboots

[John Sigler]

Hello everyone,

I'm using 2.6.20.7-rt8 on a P3.

I've noticed that the frequency offset of my system clock (computed 
either by ntpd, or by hand) changes drastically across reboots.

By drastically, I mean +/- 60 ppm every time I reboot.

Apparently this is caused by some imprecision in the frequency 
estimation done in calculate_cpu_khz() (arch/i386/kernel/tsc.c)

My brutally crude work-around was to skip the computation altogether and 
hard-code the "correct" value for cpu_khz.

http://linux.kernel.free.fr/cpu_khz.adlink

Has this issue been investigated more thoroughly by other users?

Regards.

Re: System clock frequency offset changes drastically across reboots

[John Sigler]

[ Expanding recipients list ]

John Sigler wrote:

> I'm using 2.6.20.7-rt8 on a P3.

But some ntpd users have reported the problem with mainline kernels and 
different versions.

> I've noticed that the frequency offset of my system clock (computed 
> either by ntpd, or by hand) changes drastically across reboots.
> 
> By drastically, I mean +/- 60 ppm every time I reboot.
> 
> Apparently this is caused by some imprecision in the frequency 
> estimation done in calculate_cpu_khz() (arch/i386/kernel/tsc.c)
> 
> My brutally crude work-around was to skip the computation altogether and 
> hard-code the "correct" value for cpu_khz.
> 
> http://linux.kernel.free.fr/cpu_khz.adlink
> 
> Has this issue been investigated more thoroughly by other users?

Regards.

Re: System clock frequency offset changes drastically across reboots

[John Sigler]

[ Expanding recipients list to include NTP mailing list ]

> John Sigler wrote:
> 
>> I'm using 2.6.20.7-rt8 on a P3.
> 
> (But some ntpd users have reported the problem with mainline kernels and 
> different versions.)
> 
>> I've noticed that the frequency offset of my system clock (computed 
>> either by ntpd, or by hand) changes drastically across reboots.
>>
>> By drastically, I mean +/- 60 ppm every time I reboot.
>>
>> Apparently this is caused by some imprecision in the frequency 
>> estimation done in calculate_cpu_khz() (arch/i386/kernel/tsc.c)
>>
>> My brutally crude work-around was to skip the computation altogether 
>> and hard-code the "correct" value for cpu_khz.
>>
>> http://linux.kernel.free.fr/cpu_khz.adlink
>>
>> Has this issue been investigated more thoroughly by other users?

Is there, perhaps, more appropriate a forum to discuss such matters?

Regards.