2023-09-15 09:18:48

by Hongyan Xia

Subject: Re: [RFC PATCH 2/7] sched/pelt: Add a new function to approximate runtime to reach given util

On 28/08/2023 00:31, Qais Yousef wrote:
> It is basically the ramp-up time from 0 to a given value. Will be used
> later to implement new tunable to control response time for schedutil.
>
> Signed-off-by: Qais Yousef (Google) <[email protected]>
> ---
> kernel/sched/pelt.c | 21 +++++++++++++++++++++
> kernel/sched/sched.h | 1 +
> 2 files changed, 22 insertions(+)
>
> diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
> index 50322005a0ae..f673b9ab92dc 100644
> --- a/kernel/sched/pelt.c
> +++ b/kernel/sched/pelt.c
> @@ -487,3 +487,24 @@ unsigned long approximate_util_avg(unsigned long util, u64 delta)
>
> return sa.util_avg;
> }
> +
> +/*
> + * Approximate the required amount of runtime in ms required to reach @util.
> + */
> +u64 approximate_runtime(unsigned long util)
> +{
> + struct sched_avg sa = {};
> + u64 delta = 1024; // period = 1024 = ~1ms
> + u64 runtime = 0;
> +
> + if (unlikely(!util))
> + return runtime;
> +
> + while (sa.util_avg < util) {
> + accumulate_sum(delta, &sa, 0, 0, 1);

This looks a bit uncomfortable as the existing comment says that we assume:

if (!load)
runnable = running = 0;

I haven't looked at the math in detail, but if this is okay, maybe a
comment saying why this is okay despite the existing comment says otherwise?

> + ___update_load_avg(&sa, 0);
> + runtime++;
> + }
> +
> + return runtime;
> +} > [...]

2023-09-16 22:48:44

by Qais Yousef

Subject: Re: [RFC PATCH 2/7] sched/pelt: Add a new function to approximate runtime to reach given util

On 09/15/23 10:15, Hongyan Xia wrote:
> On 28/08/2023 00:31, Qais Yousef wrote:
> > It is basically the ramp-up time from 0 to a given value. Will be used
> > later to implement new tunable to control response time for schedutil.
> >
> > Signed-off-by: Qais Yousef (Google) <[email protected]>
> > ---
> > kernel/sched/pelt.c | 21 +++++++++++++++++++++
> > kernel/sched/sched.h | 1 +
> > 2 files changed, 22 insertions(+)
> >
> > diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
> > index 50322005a0ae..f673b9ab92dc 100644
> > --- a/kernel/sched/pelt.c
> > +++ b/kernel/sched/pelt.c
> > @@ -487,3 +487,24 @@ unsigned long approximate_util_avg(unsigned long util, u64 delta)
> > return sa.util_avg;
> > }
> > +
> > +/*
> > + * Approximate the required amount of runtime in ms required to reach @util.
> > + */
> > +u64 approximate_runtime(unsigned long util)
> > +{
> > + struct sched_avg sa = {};
> > + u64 delta = 1024; // period = 1024 = ~1ms
> > + u64 runtime = 0;
> > +
> > + if (unlikely(!util))
> > + return runtime;
> > +
> > + while (sa.util_avg < util) {
> > + accumulate_sum(delta, &sa, 0, 0, 1);
>
> This looks a bit uncomfortable as the existing comment says that we assume:
>
> if (!load)
> runnable = running = 0;
>
> I haven't looked at the math in detail, but if this is okay, maybe a comment
> saying why this is okay despite the existing comment says otherwise?

Yeah as Dietmar highlighted I should pass 1 for load and it was my bad
misreading the code.

So it should be

accumulate_sum(delta, &sa, 1, 0, 1);

If that's what you meant, yes.


Thanks!

--
Qais Yousef