2022-11-16 10:09:50

by Honglei Wang

Subject: [PATCH] sched/core: use correct cpu_capacity in wake_affine_weight()

It seems make more sense to do the load weight calculation with
respective cpu_capacity.

Signed-off-by: Honglei Wang <[email protected]>
---
kernel/sched/fair.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e4a0b8bd941c..a9f75040969b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6262,13 +6262,13 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
this_eff_load += task_load;
if (sched_feat(WA_BIAS))
this_eff_load *= 100;
- this_eff_load *= capacity_of(prev_cpu);
+ this_eff_load *= capacity_of(this_cpu);

prev_eff_load = cpu_load(cpu_rq(prev_cpu));
prev_eff_load -= task_load;
if (sched_feat(WA_BIAS))
prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
- prev_eff_load *= capacity_of(this_cpu);
+ prev_eff_load *= capacity_of(prev_cpu);

/*
* If sync, adjust the weight of prev_eff_load such that if
--
2.14.1

2022-11-16 11:26:13

by Vincent Guittot

Subject: Re: [PATCH] sched/core: use correct cpu_capacity in wake_affine_weight()

On Wed, 16 Nov 2022 at 10:12, Honglei Wang <[email protected]> wrote:
>
> It seems make more sense to do the load weight calculation with
> respective cpu_capacity.
>
> Signed-off-by: Honglei Wang <[email protected]>
> ---
> kernel/sched/fair.c | 4 ++--
> 1 file changed, 2 insertions(+), 2 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index e4a0b8bd941c..a9f75040969b 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -6262,13 +6262,13 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
> this_eff_load += task_load;
> if (sched_feat(WA_BIAS))
> this_eff_load *= 100;
> - this_eff_load *= capacity_of(prev_cpu);
> + this_eff_load *= capacity_of(this_cpu);
>
> prev_eff_load = cpu_load(cpu_rq(prev_cpu));
> prev_eff_load -= task_load;
> if (sched_feat(WA_BIAS))
> prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
> - prev_eff_load *= capacity_of(this_cpu);
> + prev_eff_load *= capacity_of(prev_cpu);

we want to test :
(cpu_load(this_rq) + task_h_load(p) ) / capacity_of(this_cpu) <
cpu_load(prev_rq) / capacity_of(prev_cpu)

but instead of doing expensive division, we do the below which gives
the same result
(cpu_load(this_rq) + task_h_load(p) ) * capacity_of(prev_cpu) <
cpu_load(prev_rq) * capacity_of(this_cpu)


>
> /*
> * If sync, adjust the weight of prev_eff_load such that if
> --
> 2.14.1
>

2022-11-16 11:51:54

by Honglei Wang

Subject: Re: [PATCH] sched/core: use correct cpu_capacity in wake_affine_weight()

On 2022/11/16 19:00, Vincent Guittot wrote:
> On Wed, 16 Nov 2022 at 10:12, Honglei Wang <[email protected]> wrote:
>>
>> It seems make more sense to do the load weight calculation with
>> respective cpu_capacity.
>>
>> Signed-off-by: Honglei Wang <[email protected]>
>> ---
>> kernel/sched/fair.c | 4 ++--
>> 1 file changed, 2 insertions(+), 2 deletions(-)
>>
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index e4a0b8bd941c..a9f75040969b 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -6262,13 +6262,13 @@ wake_affine_weight(struct sched_domain *sd, struct task_struct *p,
>> this_eff_load += task_load;
>> if (sched_feat(WA_BIAS))
>> this_eff_load *= 100;
>> - this_eff_load *= capacity_of(prev_cpu);
>> + this_eff_load *= capacity_of(this_cpu);
>>
>> prev_eff_load = cpu_load(cpu_rq(prev_cpu));
>> prev_eff_load -= task_load;
>> if (sched_feat(WA_BIAS))
>> prev_eff_load *= 100 + (sd->imbalance_pct - 100) / 2;
>> - prev_eff_load *= capacity_of(this_cpu);
>> + prev_eff_load *= capacity_of(prev_cpu);
>
> we want to test :
> (cpu_load(this_rq) + task_h_load(p) ) / capacity_of(this_cpu) <
> cpu_load(prev_rq) / capacity_of(prev_cpu)
>
> but instead of doing expensive division, we do the below which gives
> the same result
> (cpu_load(this_rq) + task_h_load(p) ) * capacity_of(prev_cpu) <
> cpu_load(prev_rq) * capacity_of(this_cpu)
>
>

ha, I misunderstand the strategy, thanks for coaching, Vincent.

>>
>> /*
>> * If sync, adjust the weight of prev_eff_load such that if
>> --
>> 2.14.1
>>