Received-SPF: pass (google.com: domain of linux-kernel+bounces-176370-linux.lists.archive=gmail.com@vger.kernel.org designates 139.178.88.99 as permitted sender) client-ip=139.178.88.99;
Date: Sat, 11 May 2024 03:03:03 +0100
From: Qais Yousef <qyousef@layalina.io>
To: Vincent Guittot <vincent.guittot@linaro.org>
Cc: "Rafael J. Wysocki" <rafael@kernel.org>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Ben Segall <bsegall@google.com>, Mel Gorman <mgorman@suse.de>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	Valentin Schneider <vschneid@redhat.com>,
	Christian Loehle <christian.loehle@arm.com>,
	linux-pm@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2] sched: Consolidate cpufreq updates
Message-ID: <20240511020303.c27wr52eqflft2o3@airbuntu>
References: <20240505233103.168766-1-qyousef@layalina.io>
 <CAKfTPtDvBAFauUfyWZhYRUz6f42iMAJcwcdDDQh+V8+QfDwc2Q@mail.gmail.com>
 <20240507110809.a45amdmhy5vr5cuw@airbuntu>
 <CAKfTPtDHWBKfksW4jQJ3KZVb7_GDXLZB1F7auYVZE1ddyDpgYQ@mail.gmail.com>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <CAKfTPtDHWBKfksW4jQJ3KZVb7_GDXLZB1F7auYVZE1ddyDpgYQ@mail.gmail.com>

On 05/07/24 14:53, Vincent Guittot wrote:

> No I mean going out of idle. On an idle cpu, nothing happens at CFS
> task wakeup and we have to wait for the next tick to apply the new
> freq. This happens for both short task with uclamp min or long
> running/sleeping task (i.e. with high util_est)

I think I found the problem, thanks for catching it!

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index cbe79c8ac2ed..dea9383a906e 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4714,7 +4714,7 @@ static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *s
        if (se->avg.last_update_time && !(flags & SKIP_AGE_LOAD))
                __update_load_avg_se(now, cfs_rq, se);

-       cfs_rq->decayed  = update_cfs_rq_load_avg(now, cfs_rq);
+       cfs_rq->decayed |= update_cfs_rq_load_avg(now, cfs_rq);
        cfs_rq->decayed |= propagate_entity_load_avg(se);

        if (!se->avg.last_update_time && (flags & DO_ATTACH)) {