[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <32e4f1d7-26b1-802a-665f-f89de61db669@arm.com>
Date: Tue, 4 Jan 2022 12:47:14 +0100
From: Dietmar Eggemann <dietmar.eggemann@....com>
To: Vincent Guittot <vincent.guittot@...aro.org>, mingo@...hat.com,
peterz@...radead.org, juri.lelli@...hat.com, rostedt@...dmis.org,
bsegall@...gle.com, mgorman@...e.de, bristot@...hat.com,
linux-kernel@...r.kernel.org, rickyiu@...gle.com, odin@...d.al
Cc: sachinp@...ux.vnet.ibm.com, naresh.kamboju@...aro.org
Subject: Re: [PATCH v2 2/3] sched/pelt: Don't sync hardly runnable_sum with
runnable_avg
On 22/12/2021 10:38, Vincent Guittot wrote:
[...]
> @@ -3704,7 +3709,10 @@ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
>
> r = removed_runnable;
> sub_positive(&sa->runnable_avg, r);
> - sa->runnable_sum = sa->runnable_avg * divider;
> + sub_positive(&sa->runnable_sum, r * divider);
> + /* See update_tg_cfs_util() */
> + sa->runnable_sum = max_t(u32, sa->runnable_sum,
> + sa->runnable_avg * MIN_DIVIDER);
Maybe add a:
Fixes: 1c35b07e6d39 ("sched/fair: Ensure _sum and _avg values stay
consistent")
[...]
> @@ -3805,7 +3807,10 @@ static void detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
> cfs_rq->avg.util_avg * MIN_DIVIDER);
>
> sub_positive(&cfs_rq->avg.runnable_avg, se->avg.runnable_avg);
> - cfs_rq->avg.runnable_sum = cfs_rq->avg.runnable_avg * divider;
> + sub_positive(&cfs_rq->avg.runnable_sum, se->avg.runnable_sum);
> + /* See update_tg_cfs_util() */
> + cfs_rq->avg.runnable_sum = max_t(u32, cfs_rq->avg.runnable_sum,
> + cfs_rq->avg.runnable_avg * MIN_DIVIDER);
Maybe add a:
Fixes: fcf6631f3736 ("sched/pelt: Ensure that *_sum is always synced
with *_avg")
[...]
Powered by blists - more mailing lists