[v6] sched/fair: task load tracking optimization and cleanup

[PATCH v6 9/9] sched/fair: don't init util/runnable_avg for !fair task

Posted by Chengming Zhou 3 years, 7 months ago

post_init_entity_util_avg() init task util_avg according to the cpu util_avg
at the time of fork, which will decay when switched_to_fair() some time later,
we'd better to not set them at all in the case of !fair task.

Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
---
 kernel/sched/fair.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 93d7c7b110dd..621bd19e10ae 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -833,20 +833,6 @@ void post_init_entity_util_avg(struct task_struct *p)
 	long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
 	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
 
-	if (cap > 0) {
-		if (cfs_rq->avg.util_avg != 0) {
-			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
-			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
-
-			if (sa->util_avg > cap)
-				sa->util_avg = cap;
-		} else {
-			sa->util_avg = cap;
-		}
-	}
-
-	sa->runnable_avg = sa->util_avg;
-
 	if (p->sched_class != &fair_sched_class) {
 		/*
 		 * For !fair tasks do:
@@ -861,6 +847,20 @@ void post_init_entity_util_avg(struct task_struct *p)
 		se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
 		return;
 	}
+
+	if (cap > 0) {
+		if (cfs_rq->avg.util_avg != 0) {
+			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
+			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+			if (sa->util_avg > cap)
+				sa->util_avg = cap;
+		} else {
+			sa->util_avg = cap;
+		}
+	}
+
+	sa->runnable_avg = sa->util_avg;
 }
 
 #else /* !CONFIG_SMP */
-- 
2.37.2

Re: [PATCH v6 9/9] sched/fair: don't init util/runnable_avg for !fair task

Posted by Vincent Guittot 3 years, 7 months ago

On Thu, 18 Aug 2022 at 14:48, Chengming Zhou
<zhouchengming@bytedance.com> wrote:
>
> post_init_entity_util_avg() init task util_avg according to the cpu util_avg
> at the time of fork, which will decay when switched_to_fair() some time later,
> we'd better to not set them at all in the case of !fair task.
>
> Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
> Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>

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

> ---
>  kernel/sched/fair.c | 28 ++++++++++++++--------------
>  1 file changed, 14 insertions(+), 14 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 93d7c7b110dd..621bd19e10ae 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -833,20 +833,6 @@ void post_init_entity_util_avg(struct task_struct *p)
>         long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
>         long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
>
> -       if (cap > 0) {
> -               if (cfs_rq->avg.util_avg != 0) {
> -                       sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
> -                       sa->util_avg /= (cfs_rq->avg.load_avg + 1);
> -
> -                       if (sa->util_avg > cap)
> -                               sa->util_avg = cap;
> -               } else {
> -                       sa->util_avg = cap;
> -               }
> -       }
> -
> -       sa->runnable_avg = sa->util_avg;
> -
>         if (p->sched_class != &fair_sched_class) {
>                 /*
>                  * For !fair tasks do:
> @@ -861,6 +847,20 @@ void post_init_entity_util_avg(struct task_struct *p)
>                 se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
>                 return;
>         }
> +
> +       if (cap > 0) {
> +               if (cfs_rq->avg.util_avg != 0) {
> +                       sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
> +                       sa->util_avg /= (cfs_rq->avg.load_avg + 1);
> +
> +                       if (sa->util_avg > cap)
> +                               sa->util_avg = cap;
> +               } else {
> +                       sa->util_avg = cap;
> +               }
> +       }
> +
> +       sa->runnable_avg = sa->util_avg;
>  }
>
>  #else /* !CONFIG_SMP */
> --
> 2.37.2
>

[tip: sched/core] sched/fair: Don't init util/runnable_avg for !fair task

Posted by tip-bot2 for Chengming Zhou 3 years, 7 months ago

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

Commit-ID:     e4fe074d6c359c19b74564fa1364fe48343cfa5d
Gitweb:        https://git.kernel.org/tip/e4fe074d6c359c19b74564fa1364fe48343cfa5d
Author:        Chengming Zhou <zhouchengming@bytedance.com>
AuthorDate:    Thu, 18 Aug 2022 20:48:05 +08:00
Committer:     Peter Zijlstra <peterz@infradead.org>
CommitterDate: Tue, 23 Aug 2022 11:01:20 +02:00

sched/fair: Don't init util/runnable_avg for !fair task

post_init_entity_util_avg() init task util_avg according to the cpu util_avg
at the time of fork, which will decay when switched_to_fair() some time later,
we'd better to not set them at all in the case of !fair task.

Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Chengming Zhou <zhouchengming@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20220818124805.601-10-zhouchengming@bytedance.com
---
 kernel/sched/fair.c | 28 ++++++++++++++--------------
 1 file changed, 14 insertions(+), 14 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ef325b5..e8c1b88 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -833,20 +833,6 @@ void post_init_entity_util_avg(struct task_struct *p)
 	long cpu_scale = arch_scale_cpu_capacity(cpu_of(rq_of(cfs_rq)));
 	long cap = (long)(cpu_scale - cfs_rq->avg.util_avg) / 2;
 
-	if (cap > 0) {
-		if (cfs_rq->avg.util_avg != 0) {
-			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
-			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
-
-			if (sa->util_avg > cap)
-				sa->util_avg = cap;
-		} else {
-			sa->util_avg = cap;
-		}
-	}
-
-	sa->runnable_avg = sa->util_avg;
-
 	if (p->sched_class != &fair_sched_class) {
 		/*
 		 * For !fair tasks do:
@@ -861,6 +847,20 @@ void post_init_entity_util_avg(struct task_struct *p)
 		se->avg.last_update_time = cfs_rq_clock_pelt(cfs_rq);
 		return;
 	}
+
+	if (cap > 0) {
+		if (cfs_rq->avg.util_avg != 0) {
+			sa->util_avg  = cfs_rq->avg.util_avg * se->load.weight;
+			sa->util_avg /= (cfs_rq->avg.load_avg + 1);
+
+			if (sa->util_avg > cap)
+				sa->util_avg = cap;
+		} else {
+			sa->util_avg = cap;
+		}
+	}
+
+	sa->runnable_avg = sa->util_avg;
 }
 
 #else /* !CONFIG_SMP */