All of lore.kernel.org
 help / color / mirror / Atom feed
From: Qais Yousef <qyousef@layalina.io>
To: Ingo Molnar <mingo@kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Viresh Kumar <viresh.kumar@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	John Stultz <jstultz@google.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	"Chen, Yu C" <yu.c.chen@intel.com>,
	Thomas Gleixner <tglx@kernel.org>,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Qais Yousef <qyousef@layalina.io>
Subject: [PATCH v2 12/13] sched/fair: Call update_util_est() after dequeue_entities()
Date: Mon,  4 May 2026 03:00:02 +0100	[thread overview]
Message-ID: <20260504020003.71306-13-qyousef@layalina.io> (raw)
In-Reply-To: <20260504020003.71306-1-qyousef@layalina.io>

update_util_est() reads task_util() at dequeue which is updated in
dequeue_entities(). To read the accurate util_avg at dequeue, make sure
to do the read after load_avg is updated in dequeue_entities().

util_est for a periodic task before

                                periodic-3114 util_est.enqueued running
   ┌───────────────────────────────────────────────────────────────────────────────────────────────┐
183┤                ▖▗  ▐▖         ▖ ▗▙   ▗   ▗▙▖▖       ▖▖   ▖       ▖▖        ▗  ▟  ▗▄▖          │
139┤               ▐▛█▜▙▞▀▄▄▞▚▄▟█▞▙█▄▟▀▚▄▄▞▚▄▄▟▀▀▛▄▝▄▄▄▙█▛▛█▛▜▛▄▄▀▄█▙▛▛▛▙▄▀▄▄▖▜▄▟█▟▀▜▟▄▜▀▄▄▟▙▖     │
 95┤              ▐▀    ▘   ▝   ▝        ▝▘        ▘   ▘▘       ▝▘       ▝▘  ▝    ▝        ▀       │
   │              ▛                                                                                │
 51┤             ▐▘                                                                                │
  7┤      ▖▗▗  ▗▄▐                                                                                 │
   └┬─────────┬──────────┬─────────┬──────────┬─────────┬──────────┬─────────┬──────────┬─────────┬┘
  0.00      0.65       1.30      1.96       2.61      3.26       3.91      4.57       5.22     5.87

and after

                                 periodic-2977 util_est.enqueued running
     ┌─────────────────────────────────────────────────────────────────────────────────────────────┐
157.0┤               ▙▄ ▗▄  ▗▄▄▄ ▗▄  ▗▄▄▄▗▄▄  ▗▄▄▖ ▄   ▄▄▄   ▄  ▄▖▖  ▄▄▄▄▄▖▖▝▙▄▄▄▄▄▄▖ ▗▄           │
119.5┤             ▗▄▌▘▀▀ ▀▀▀ ▝▀▀▘▝▀▀▀ ▝▀▘ ▝▀▀▘ ▀▝▀▘▀▀▀▘▝▀▀▀▀▀▀▀▘▝▝▀▀ ▀   ▝▝▀  ▀   ▀▀▀▀            │
 82.0┤             ▟                                                                               │
     │             ▌                                                                               │
 44.5┤             ▌                                                                               │
  7.0┤      ▗   ▗▖ ▌                                                                               │
     └┬─────────┬─────────┬──────────┬─────────┬─────────┬─────────┬──────────┬─────────┬─────────┬┘
    0.00      0.65      1.30       1.95      2.60      3.25      3.90       4.56      5.21     5.86

Note how the signal is noisier and can peak to 183 vs 157 now.

Signed-off-by: Qais Yousef <qyousef@layalina.io>
---
 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 d0f646b32c2d..2fec5b6a7c30 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7455,6 +7455,8 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
  */
 static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 {
+	int ret;
+
 	if (task_is_throttled(p)) {
 		dequeue_throttled_task(p, flags);
 		return true;
@@ -7463,8 +7465,9 @@ static bool dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 	if (!p->se.sched_delayed)
 		util_est_dequeue(&rq->cfs, p);
 
+	ret = dequeue_entities(rq, &p->se, flags);
 	util_est_update(&rq->cfs, p, flags & DEQUEUE_SLEEP);
-	if (dequeue_entities(rq, &p->se, flags) < 0)
+	if (ret < 0)
 		return false;
 
 	/*
-- 
2.34.1


  parent reply	other threads:[~2026-05-04  2:00 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-05-04  1:59 [PATCH v2 00/13] sched/fair/schedutil: Better manage system response time Qais Yousef
2026-05-04  1:59 ` [PATCH v2 01/13] sched: cpufreq: Rename map_util_perf to sugov_apply_dvfs_headroom Qais Yousef
2026-05-04  1:59 ` [PATCH v2 02/13] sched/pelt: Add a new function to approximate the future util_avg value Qais Yousef
2026-05-04  1:59 ` [PATCH v2 03/13] sched/pelt: Add a new function to approximate runtime to reach given util Qais Yousef
2026-05-04  1:59 ` [PATCH v2 04/13] sched/fair: Remove magic hardcoded margin in fits_capacity() Qais Yousef
2026-05-04  1:59 ` [PATCH v2 05/13] sched: cpufreq: Remove magic 1.25 headroom from sugov_apply_dvfs_headroom() Qais Yousef
2026-05-04  1:59 ` [PATCH v2 06/13] sched/fair: Extend util_est to improve rampup time Qais Yousef
2026-05-04  1:59 ` [PATCH v2 07/13] sched/fair: util_est: Take into account periodic tasks Qais Yousef
2026-05-04  1:59 ` [PATCH v2 RFC 08/13] sched/qos: Add a new sched-qos interface Qais Yousef
2026-05-06 20:38   ` Tim Chen
2026-05-07  9:55     ` Qais Yousef
2026-05-07 14:20       ` Chen, Yu C
2026-05-09  9:39         ` Qais Yousef
2026-05-11 10:57   ` Peter Zijlstra
2026-05-12  7:58     ` Qais Yousef
2026-05-12  8:30       ` Peter Zijlstra
2026-05-12  8:47         ` Qais Yousef
2026-05-04  1:59 ` [PATCH v2 09/13] sched/qos: Add rampup multiplier QoS Qais Yousef
2026-05-11 11:03   ` Peter Zijlstra
2026-05-12  7:59     ` Qais Yousef
2026-05-12  8:37       ` Christian Loehle
2026-05-12  8:53         ` Qais Yousef
2026-05-04  2:00 ` [PATCH v2 10/13] sched/fair: Disable util_est when rampup_multiplier is 0 Qais Yousef
2026-05-04  2:00 ` [PATCH v2 11/13] sched/fair: Don't mess with util_avg post init Qais Yousef
2026-05-04  2:00 ` Qais Yousef [this message]
2026-05-04  2:00 ` [PATCH v2 RFC 13/13] sched/pelt: Always allow load updates Qais Yousef
2026-05-11 17:58 ` [PATCH v2 00/13] sched/fair/schedutil: Better manage system response time John Stultz
2026-05-12  8:01   ` Qais Yousef
2026-05-13 15:09 ` Tom Gebhardt
2026-05-15  1:42   ` Qais Yousef
2026-05-15  8:24     ` Tom Gebhardt
2026-05-15 10:01       ` Christian Loehle
2026-05-15 13:57         ` Tom Gebhardt

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260504020003.71306-13-qyousef@layalina.io \
    --to=qyousef@layalina.io \
    --cc=dietmar.eggemann@arm.com \
    --cc=jstultz@google.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@kernel.org \
    --cc=tim.c.chen@linux.intel.com \
    --cc=vincent.guittot@linaro.org \
    --cc=viresh.kumar@linaro.org \
    --cc=yu.c.chen@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.