Re: [RESEND PATCH 2/2] sched/fair: Optimize __update_sched_avg()

[Yuyang Du <yuyang.du@intel.com>]

Hi Peter,

On Wed, Mar 29, 2017 at 12:41:26PM +0200, Peter Zijlstra wrote:
> On Wed, Mar 29, 2017 at 08:04:42AM +0800, Yuyang Du wrote:
> > Yes, you need to, and let me do it too and learn how you will rewrite
> > it.
> 
> I've meanwhile written this. Does that work for you?
 
It works. You sort it out.

I hope I get along with going into detail too ...

Some grammar and typo issues:

> ---
> Subject: sched/fair: Optimize ___update_sched_avg()
> From: Yuyang Du <yuyang.du@intel.com>
> Date: Mon, 13 Feb 2017 05:44:23 +0800
> 
> The main PELT function ___update_load_avg(), that implements the
                                               ~~~~
                                               which
                 
> accumulation and progression of the geometric average series, is
> implemented along the following lines for the scenario where the time
> delta spans all 3 possible sections (see figure below):
> 
>   1. add the remainder of the last incomplete period
>   2. decay old sum
>   3. accumulate new sum in full periods since last_update_time
>   4. accumulate the current incomplete period
>   5. update averages
> 
> Or:
> 
>             d1          d2           d3
>             ^           ^            ^
>             |           |            |
>           |<->|<----------------->|<--->|
>   ... |---x---|------| ... |------|-----x (now)
> 
> 
>   load_sum' = (load_sum + weight * scale * d1) * y^(p+1) +	(1,2)
> 
>                                         p
> 	      weight * scale * 1024 * \Sum y^n +		(3)
>                                        n=1
> 
> 	      weight * sclae * d3 * y^0				(4)
                       ~~~~~
                       scale

Thanks,
Yuyang