On 26/03/2021 11:34, Peter Zijlstra wrote:
> The current sched_slice() seems to have issues; there's two possible
> things that could be improved:
>
> - the 'nr_running' used for __sched_period() is daft when cgroups are
> considered. Using the RQ wide h_nr_running seems like a much more
> consistent number.
>
> - (esp) cgroups can slice it real fine, which makes for easy
> over-scheduling, ensure min_gran is what the name says.
So ALT_PERIOD considers all runnable CFS tasks now and BASE_SLICE
guarantees min_gran as a floor for cgroup (hierarchies) with small
weight value(s)?
>
> Signed-off-by: Peter Zijlstra (Intel) <pet...@infradead.org>
> ---
> kernel/sched/fair.c | 15 ++++++++++++++-
> kernel/sched/features.h | 3 +++
> 2 files changed, 17 insertions(+), 1 deletion(-)
>
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -680,7 +680,16 @@ static u64 __sched_period(unsigned long
> */
> static u64 sched_slice(struct cfs_rq *cfs_rq, struct sched_entity *se)
> {
> - u64 slice = __sched_period(cfs_rq->nr_running + !se->on_rq);
> + unsigned int nr_running = cfs_rq->nr_running;
> + u64 slice;
> +
> + if (sched_feat(ALT_PERIOD))
> + nr_running = rq_of(cfs_rq)->cfs.h_nr_running;
> +
> + slice = __sched_period(nr_running + !se->on_rq);
> +
> + if (sched_feat(BASE_SLICE))
> + slice -= sysctl_sched_min_granularity;
>
> for_each_sched_entity(se) {
> struct load_weight *load;
> @@ -697,6 +706,10 @@ static u64 sched_slice(struct cfs_rq *cf
> }
> slice = __calc_delta(slice, se->load.weight, load);
> }
> +
> + if (sched_feat(BASE_SLICE))
> + slice += sysctl_sched_min_granularity;
> +
> return slice;
> }
>
> --- a/kernel/sched/features.h
> +++ b/kernel/sched/features.h
> @@ -90,3 +90,6 @@ SCHED_FEAT(WA_BIAS, true)
> */
> SCHED_FEAT(UTIL_EST, true)
> SCHED_FEAT(UTIL_EST_FASTUP, true)
> +
> +SCHED_FEAT(ALT_PERIOD, true)
> +SCHED_FEAT(BASE_SLICE, true)
>
>
