Re: [PATCH v3 3/4] sched: reduce sched slice for SCHED_IDLE entities

[Josh Don]

Hi Jiang,

On Tue, Aug 24, 2021 at 3:25 AM Jiang Biao <benbjiang@xxxxxxxxx> wrote:
>
> Why not just ignore min granularity when normal entities compete with
> a SCHED_IDLE entity? something like this,
>
> @@ -697,8 +710,14 @@ static u64 sched_slice(struct cfs_rq *cfs_rq,
> struct sched_entity *se)
>                  slice = __calc_delta(slice, se->load.weight, load);
>          }
>
>  -       if (sched_feat(BASE_SLICE))
>  -               slice = max(slice, (u64)sysctl_sched_min_granularity);
>  +       if (sched_feat(BASE_SLICE)
>  +          && (!se_is_idle(init_se) || sched_idle_cfs_rq(cfs_rq)))
>  +               slice = max(slice, (u64)sysctl_sched_min_granularity);
>
>          return slice;
>   }
> If so, there seems no need to introduce sysctl_sched_idle_min_granularity? :)

Ignoring min_gran entirely could lead to some really tiny slices; see
discussion at https://lkml.org/lkml/2021/8/12/651.