Re: [Resend PATCH] psi : calc cfs task memstall time more precisely

[Dietmar Eggemann <dietmar.eggemann@arm.com>]

On 10/11/2021 06:36, Xuewen Yan wrote:
> Hi Dietmar
> On Tue, Nov 9, 2021 at 5:43 PM Dietmar Eggemann
> <dietmar.eggemann@arm.com> wrote:
>>
>> On 08/11/2021 09:49, Xuewen Yan wrote:
>>> Hi Dietmar
>>>
>>> On Sat, Nov 6, 2021 at 1:20 AM Dietmar Eggemann
>>> <dietmar.eggemann@arm.com> wrote:
>>>>
>>>> On 05/11/2021 06:58, Zhaoyang Huang wrote:

[...]

>>>> Even the CFS part (cpu_rq(CPUx)->cfs.avg.util_avg) can be larger than
>>>> the original cpu capacity (rq->cpu_capacity_orig).
>>>>
>>>> Have a look at cpu_util(). capacity_orig_of(CPUx) and
>>>> arch_scale_cpu_capacity(CPUx) both returning rq->cpu_capacity_orig.
>>>>
>>>
>>> Well, your means is we should not use the 1024 and should use the
>>> original cpu capacity?
>>> And maybe use the "sched_cpu_util()" is a good choice just like this:
>>>
>>> +       if (current->in_memstall)
>>> +               growth_fixed = div64_ul(cpu_util_cfs(rq) * growth,
>>> sched_cpu_util(rq->cpu, capacity_orig_of(rq->cpu)));
>>
>> Not sure about this. In case util_cfs=0 you would get scale=0.
> 
> Yes , we should consider it. In addition, it also should be considered
> when util_cfs > capacity_orig because of the UTIL_EST......

We should ]-clamp cpu_util_cfs() with capacity_orig_of(), like we
currently do for the CFS internal cpu_util(). In fact, we should only
use one function for this. Sent a patch out:

https://lkml.kernel.org/r/20211112141349.155713-1-dietmar.eggemann@arm.com%3E

[...]