Mark.Haywood at Sun.COM wrote:

> Li, Aubrey wrote:
>> Bill.Holler at Sun.COM wrote:
>> 
>>> It will be useful to have c-state information observable (including
>>> latency and power savings) during development and testing.  Should
>>> c-state information be in a kstat such as the cpu_info kstat?
>>> 
>>> Thanks,
>>> Bill
>> 
>> Now p-state info in the kstat is architecture independent. Both SPARC
>> and X86 support speed transition.
>> Does SPARC support C-state?
>> If so, add the information to the kstat of cpu_info will be easy.
> 
> I believe that we already have a couple of x86 only statistics in
> cpu_info. No problem adding these.
> 
Thanks, I'm asking it should be added to the common part or just x86
part, ;-)

-Aubrey

>> 
>>> 
>>> Li, Aubrey wrote:
>>>> Alexander Kolbasov wrote:
>>>> 
>>>> 
>>>>> Eric pointed to me that cpu_info kstats now contain both the
>>>>> current CPU frequency and the frequency range for each CPU. I
>>>>> hacked /usr/sbin/psrinfo a bit to show this information when
>>>>> running psrinfo -v. It shows output like this:
>>>>> 
>>>>> $ psrinfo -v
>>>>> Status of virtual processor 0 as of: 12/04/2007 17:55:03
>>>>>  on-line since 11/26/2007 15:06:47.
>>>>>  The i386 processor operates at
>>>>> [1596 MHz - 2660 MHz]
>>>>> 
>>>> It's not a range, but only several steps.
>>>> The suggested format is confused.
>>>> A format like supported_frequencies_Hz member of cpu_info may be
>>>> better, ;-) 
>>>> 
>>>> Thanks,
>>>> -Aubrey
>>>> _______________________________________________
>>>> tesla-dev mailing list
>>>> tesla-dev at opensolaris.org
>>>> http://mail.opensolaris.org/mailman/listinfo/tesla-dev
>> _______________________________________________
>> tesla-dev mailing list
>> tesla-dev at opensolaris.org
>> http://mail.opensolaris.org/mailman/listinfo/tesla-dev

Reply via email to