Rafael.Vanoni at Sun.COM wrote:

> Li, Aubrey wrote:
>> Rafael.Vanoni wrote:
>> 
>>> Li, Aubrey wrote:
>>>> Rafael Vanoni wrote:
>>>> 
>>>>> The problem was that the xcalls probe fires N times within
>>>>> xc_common, and the script was zeroing the variable with the
>>>>> address of the xcall function after the first one.
>>>>> 
>>>>> This export contains all the changes from the previous with this
>>>>> issue fixed. Let me know what you think.
>>>>> 
>> 
>> I was using cpu-option.diff from this email and got the following
>> report. ============================= Cn                      Avg   
>> residency 
>> C0 (cpu running)             (88.8%)
>> C1                      0.6ms   (11.2%)
>> =============================
>> when my system is in IDLE(mpstat told me all cpus are 100% idle).
>> 
>> This is in curse mode. C-state residency report in dump mode is okay.
>> Did I do anything wrong? I can look more details tomorrow.
> 
> Hmm.. were you running with the -c option?

Yes, I did it.

> 
> I've been testing the new option by running one PowerTOP instance per
> CPU and then binding a CPU intensive process to each core.
> 

Just keep the whole system in idle, look if you see the similar report with me.

Thanks,
-Aubrey

Reply via email to