Re: [PATCH 1/2] sched/fair: Fix how load gets propagated from cfs_rq to its sched_entity

[Vincent Guittot]

On 28 April 2017 at 19:46, Tejun Heo <tj@xxxxxxxxxx> wrote:
> Hello, Vincent.
>
> On Thu, Apr 27, 2017 at 10:59:12AM +0200, Vincent Guittot wrote:
>> > But the only difference there is that we lose accuracy in calculation;
>> > otherwise, the end results are the same, no?
>>
>> Yes the end result is the same, it was mainly to point out the range
>> difference and explain why we need scale_load_down(shares) for the 2nd
>> argument of min.
>> This should also explain the warning issue you mentioned earlier
>
> I'm not sure this makes sense.  Practically, we're doing more shifts
> just to lose calculation accuracy.  Even conceptually, what we're
> doing is
>
>              C
>         A * ---
>              B
>
> Where A is in a different scale while B and C are in the same.  What
> you're suggesting is
>
>              scale_down(C)
>         A * ---------------
>              scale_down(B)
>
> I can't see why this is better in any way.

i'm not saying it's netter, i'm saying that it might be the cause of
the build warning you mentioned because you are mixing  u64 and
unsigned long

>
> Thanks.
>
> --
> tejun