[PATCH] sched/fair: Return early from update_tg_cfs_load() if delta == 0

[PATCH] sched/fair: Return early from update_tg_cfs_load() if delta == 0

[Dietmar Eggemann]

In case the _avg delta is 0 there is no need to update se's _avg
(level n) nor cfs_rq's _avg (level n-1). These values stay the same.

Since cfs_rq's _avg isn't changed, i.e. no load is propagated down,
cfs_rq's _sum should stay the same as well.

So bail out after se's _sum has been updated.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
---

This patch is against current tip/sched/urgent, commit f268c3737eca
("tick/nohz: Only check for RCU deferred wakeup on user/guest entry
when needed").
It needs commit 7c7ad626d9a0 ("sched/fair: Keep load_avg and load_sum
synced"). 

 kernel/sched/fair.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e7c8277e3d54..ce8e0e10e5d4 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3548,9 +3548,12 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, divider);
 
+	se->avg.load_sum = runnable_sum;
+
 	delta = load_avg - se->avg.load_avg;
+	if (!delta)
+		return;
 
-	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
 
 	add_positive(&cfs_rq->avg.load_avg, delta);
-- 
2.25.1

Re: [PATCH] sched/fair: Return early from update_tg_cfs_load() if delta == 0

[Vincent Guittot]

On Tue, 1 Jun 2021 at 10:36, Dietmar Eggemann <dietmar.eggemann@arm.com> wrote:
>
> In case the _avg delta is 0 there is no need to update se's _avg
> (level n) nor cfs_rq's _avg (level n-1). These values stay the same.
>
> Since cfs_rq's _avg isn't changed, i.e. no load is propagated down,
> cfs_rq's _sum should stay the same as well.
>
> So bail out after se's _sum has been updated.
>
> Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>

Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>

> ---
>
> This patch is against current tip/sched/urgent, commit f268c3737eca
> ("tick/nohz: Only check for RCU deferred wakeup on user/guest entry
> when needed").
> It needs commit 7c7ad626d9a0 ("sched/fair: Keep load_avg and load_sum
> synced").
>
>  kernel/sched/fair.c | 5 ++++-
>  1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index e7c8277e3d54..ce8e0e10e5d4 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3548,9 +3548,12 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
>         load_sum = (s64)se_weight(se) * runnable_sum;
>         load_avg = div_s64(load_sum, divider);
>
> +       se->avg.load_sum = runnable_sum;
> +
>         delta = load_avg - se->avg.load_avg;
> +       if (!delta)
> +               return;
>
> -       se->avg.load_sum = runnable_sum;
>         se->avg.load_avg = load_avg;
>
>         add_positive(&cfs_rq->avg.load_avg, delta);
> --
> 2.25.1
>

[tip: sched/core] sched/fair: Return early from update_tg_cfs_load() if delta == 0

[tip-bot2 for Dietmar Eggemann]

The following commit has been merged into the sched/core branch of tip:

Commit-ID:     83c5e9d573e1f0757f324d01adb6ee77b49c3f0e
Gitweb:        https://git.kernel.org/tip/83c5e9d573e1f0757f324d01adb6ee77b49c3f0e
Author:        Dietmar Eggemann <dietmar.eggemann@arm.com>
AuthorDate:    Tue, 01 Jun 2021 10:36:16 +02:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Thu, 17 Jun 2021 14:11:42 +02:00

sched/fair: Return early from update_tg_cfs_load() if delta == 0

In case the _avg delta is 0 there is no need to update se's _avg
(level n) nor cfs_rq's _avg (level n-1). These values stay the same.

Since cfs_rq's _avg isn't changed, i.e. no load is propagated down,
cfs_rq's _sum should stay the same as well.

So bail out after se's _sum has been updated.

Signed-off-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20210601083616.804229-1-dietmar.eggemann@arm.com
---
 kernel/sched/fair.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 198514d..06c8ba7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3502,9 +3502,12 @@ update_tg_cfs_load(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq
 	load_sum = (s64)se_weight(se) * runnable_sum;
 	load_avg = div_s64(load_sum, divider);
 
+	se->avg.load_sum = runnable_sum;
+
 	delta = load_avg - se->avg.load_avg;
+	if (!delta)
+		return;
 
-	se->avg.load_sum = runnable_sum;
 	se->avg.load_avg = load_avg;
 
 	add_positive(&cfs_rq->avg.load_avg, delta);