Linux Power Management development
 help / color / mirror / Atom feed
From: Christian Loehle <christian.loehle@arm.com>
To: Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Valentin Schneider <vschneid@redhat.com>,
	K Prateek Nayak <kprateek.nayak@amd.com>,
	Beata Michalska <beata.michalska@arm.com>,
	Elif Topuz <elif.topuz@arm.com>,
	"Rafael J . Wysocki" <rafael@kernel.org>,
	Daniel Lezcano <daniel.lezcano@kernel.org>,
	Shubhang Kaushik <sh@gentwo.org>,
	Christoph Lameter <cl@gentwo.org>,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Christian Loehle <christian.loehle@arm.com>
Subject: [PATCH 2/2] sched/fair: Randomize equally shallow slow-path candidates
Date: Wed, 16 Sep 2026 11:01:16 +0100	[thread overview]
Message-ID: <20260916100116.701206-3-christian.loehle@arm.com> (raw)
In-Reply-To: <20260916100116.701206-1-christian.loehle@arm.com>

Picking the first eligible idle CPU leaves a scan-order bias. Concurrent
slow-path selectors can choose the same CPU before either task is enqueued.

Use reservoir sampling in the tie branch, resetting the candidate count
when a lower advertised exit latency is found. Use the per-CPU scheduler
PRNG and reciprocal_scale() to avoid variable division or a second scan.

This reduces deterministic convergence without reserving the chosen CPU.

Signed-off-by: Christian Loehle <christian.loehle@arm.com>
---
 kernel/sched/fair.c | 11 ++++++++---
 1 file changed, 8 insertions(+), 3 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ff5793bddc35..6836a8364440 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -24,6 +24,7 @@
 #include <linux/mmap_lock.h>
 #include <linux/hugetlb_inline.h>
 #include <linux/jiffies.h>
+#include <linux/math.h>
 #include <linux/mm_api.h>
 #include <linux/highmem.h>
 #include <linux/hrtimer.h>
@@ -8459,6 +8460,7 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 {
 	unsigned long load, min_load = ULONG_MAX;
 	unsigned int min_exit_latency = UINT_MAX;
+	unsigned int nr_candidates = 0;
 	int least_loaded_cpu = this_cpu;
 	int shallowest_idle_cpu = -1;
 	int i;
@@ -8482,9 +8484,12 @@ sched_balance_find_dst_group_cpu(struct sched_group *group, struct task_struct *
 			if (idle && idle->exit_latency < min_exit_latency) {
 				min_exit_latency = idle->exit_latency;
 				shallowest_idle_cpu = i;
+				nr_candidates = 1;
-			} else if ((!idle || idle->exit_latency == min_exit_latency) &&
-				   shallowest_idle_cpu == -1) {
-				shallowest_idle_cpu = i;
+			} else if (!idle || idle->exit_latency == min_exit_latency) {
+				nr_candidates++;
+				if (nr_candidates == 1 ||
+				    !reciprocal_scale(sched_rng(), nr_candidates))
+					shallowest_idle_cpu = i;
 			}
 		} else if (shallowest_idle_cpu == -1) {
 			load = cpu_load(cpu_rq(i));
-- 
2.34.1

  parent reply	other threads:[~2026-09-16 10:01 UTC|newest]

Thread overview: 18+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-16 10:01 [PATCH 0/2] sched/fair: Randomize equally shallow idle CPU picks Christian Loehle
2026-09-16 10:01 ` [PATCH 1/2] sched/fair: Drop idle recency from slow-path CPU selection Christian Loehle
2026-09-17 13:28   ` Vincent Guittot
2026-09-16 10:01 ` Christian Loehle [this message]
2026-09-16 11:06   ` [PATCH 2/2] sched/fair: Randomize equally shallow slow-path candidates Kayra Cizmeci
2026-09-16 11:10     ` Christian Loehle
2026-09-16 11:12   ` Christian Loehle
2026-09-16 11:46     ` Kayra Cizmeci
2026-09-16 19:43   ` Shubhang
2026-09-17  7:47     ` Christian Loehle
2026-09-17  9:58       ` Christian Loehle
2026-09-17 14:02         ` Vincent Guittot
2026-09-17 14:16         ` Kayra Cizmeci
2026-09-17 14:08   ` Vincent Guittot
2026-09-17 14:22     ` Christian Loehle
2026-09-17 15:08       ` Vincent Guittot
2026-09-17 15:17         ` Christian Loehle
2026-09-24 12:44 ` [PATCH 0/2] sched/fair: Randomize equally shallow idle CPU picks Muhammad Usama Anjum

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=20260916100116.701206-3-christian.loehle@arm.com \
    --to=christian.loehle@arm.com \
    --cc=beata.michalska@arm.com \
    --cc=cl@gentwo.org \
    --cc=daniel.lezcano@kernel.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=elif.topuz@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=kprateek.nayak@amd.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rafael@kernel.org \
    --cc=rostedt@goodmis.org \
    --cc=sh@gentwo.org \
    --cc=vincent.guittot@linaro.org \
    --cc=vschneid@redhat.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox