Re: [Xen-devel] [v1] x86/cpuidle: get accurate C0 value with xenpm tool

["Jan Beulich" <JBeulich@xxxxxxxx>]

>>> On 17.04.15 at 09:36, <huaitong.han@xxxxxxxxx> wrote:
> From: Jan Beulich [mailto:JBeulich@xxxxxxxx] 
> Sent: Thursday, April 16, 2015 4:49 PM
>>>> On 16.04.15 at 08:03, <huaitong.han@xxxxxxxxx> wrote:
>> When checking the ACPI funciton of C-status, after 100 seconds sleep, 
>> the sampling value of C0 C-status from the xenpm tool decreases.
>> Because C0=NOW()-C1-C2-C3-C4, when NOW() value is during idle time,
>> NOW() value is bigger than last C-status update time, and C0 value is 
>> also bigger than ture value. if margin of the second error cannot make 
>> up for margin of the first error, the value of C0 would decrease.
> 
> How big of an error are we taking about here? And does that error increase 
> over time?
> 
> The max error value is about 1s that depends on max C-status time.
> Error does not increase over time, because C1,C2,C3 and C4 is accurate, and 
> NOW() is random.

So if the error doesn't increase over time and the values reported to
the caller are stale (inaccurate) by the time it gets to see them
anyway, is it really worth adjusting the code like you propose?

Jan


_______________________________________________
Xen-devel mailing list
Xen-devel@xxxxxxxxxxxxx
http://lists.xen.org/xen-devel