[procps] Re: C-States handling - new switch?

On Feb 7, 2012, at 12:05 PM, Jaromir Capik wrote:

>> Yep, just one cycle.
>> 
> 
> The following real data collected on 3.2.8 looks for me like periodic
> switching on and off ... (several times per second).
> 
> # top -d 0.25 | grep "Cpu2 "
> Cpu2  :  0.0%us,  0.0%sy,  0.0%ni,100.0%id,  0.0%wa,  0.0%hi,  0.0%si,  0.0%st
> Cpu2  :  0.0%us,  0.0%sy,  0.0%ni,  0.0%id,  0.0%wa,  0.0%hi,  0.0%si,  0.0%st
> ...
> And now imagine a case where some process produces very short
> periodic 'user' peaks followed by absolute idle state.
> In that case such malicious state (where only user ticks are registered)
> could appear quite frequently. Am I wrong?

Hi Jaromir,

Somehow you got ahead of me on freelists.  I've got one email in the pipeline 
that hasn't been echoed yet.

Anyway, before speculating on what old top might do or if your scenario is even 
possible, can you please tell me the delay interval that produced those results.

Thanks,
Jim

Other related posts: