mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: K Prateek Nayak <kprateek.nayak@amd.com>
To: Andrea Righi <arighi@nvidia.com>
Cc: Ingo Molnar <mingo@redhat.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Juri Lelli <juri.lelli@redhat.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Ben Segall <bsegall@google.com>, "Mel Gorman" <mgorman@suse.de>,
	Valentin Schneider <vschneid@redhat.com>,
	"Christian Loehle" <christian.loehle@arm.com>,
	Koba Ko <kobak@nvidia.com>,
	"Felix Abecassis" <fabecassis@nvidia.com>,
	Balbir Singh <balbirs@nvidia.com>, <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/4] sched/fair: Prefer fully-idle SMT cores in asym-capacity idle selection
Date: Mon, 30 Mar 2026 15:47:07 +0530	[thread overview]
Message-ID: <258e2e94-ee42-4ea4-998c-4770732cbad0@amd.com> (raw)
In-Reply-To: <acay1ya8DGdjNmtj@gpd4>

Hello Andrea,

On 3/27/2026 10:09 PM, Andrea Righi wrote:
>> My naive eyes say it should be equivalent of what you have but maybe
>> I'm wrong?
> 
> It seems correct to my naive eyes as well. Will test this out to make sure.

So I found one small problem with fits > 0 && !preferred_core where even
though it is an ideal target, we don't end up preferring it because of
the larger "fits" value.

Here is an updated diff:

  (Only build tested)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 226509231e67..580218656865 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7949,6 +7949,7 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, bool
 static int
 select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 {
+	bool prefers_idle_core = sched_smt_active() && test_idle_cores(target);
 	unsigned long task_util, util_min, util_max, best_cap = 0;
 	int fits, best_fits = 0;
 	int cpu, best_cpu = -1;
@@ -7962,6 +7963,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 	util_max = uclamp_eff_value(p, UCLAMP_MAX);
 
 	for_each_cpu_wrap(cpu, cpus, target) {
+		bool preferred_core = !prefers_idle_core || is_core_idle(cpu);
 		unsigned long cpu_cap = capacity_of(cpu);
 
 		if (!choose_idle_cpu(cpu, p))
@@ -7970,7 +7972,7 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 		fits = util_fits_cpu(task_util, util_min, util_max, cpu);
 
 		/* This CPU fits with all requirements */
-		if (fits > 0)
+		if (fits > 0 && preferred_core)
 			return cpu;
 		/*
 		 * Only the min performance hint (i.e. uclamp_min) doesn't fit.
@@ -7978,9 +7980,30 @@ select_idle_capacity(struct task_struct *p, struct sched_domain *sd, int target)
 		 */
 		else if (fits < 0)
 			cpu_cap = get_actual_cpu_capacity(cpu);
+		/*
+		 * fits > 0 implies we are not on a preferred core
+		 * but the util fits CPU capacity. Set fits to -2 so
+		 * the effective range becomes [-2, 0] where:
+		 *    0 - does not fit
+		 *   -1 - fits with the exception of UCLAMP_MIN
+		 *   -2 - fits with the exception of preferred_core
+		 */
+		else if (fits > 0)
+			fits = -2;
+
+		/*
+		 * If we are on an preferred core, translate the range of fits
+		 * of [-1, 0] to [-4, -3]. This ensures that an idle core
+		 * is always given priority over (partially) busy core.
+		 *
+		 * A fully fitting idle core would have returned early and hence
+		 * fits > 0 for preferred_core need not be dealt with.
+		 */
+		if (preferred_core)
+			fits -= 3;
 
 		/*
-		 * First, select CPU which fits better (-1 being better than 0).
+		 * First, select CPU which fits better (lower is more preferred).
 		 * Then, select the one with best capacity at same level.
 		 */
 		if ((fits < best_fits) ||
---

Sorry for the oversight but this should now be equivalent to your
Patch 1. I'll let Vincent comment if he prefers this to the original
or not :-)

-- 
Thanks and Regards,
Prateek


  reply	other threads:[~2026-03-30 10:17 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-03-26 15:02 [PATCH 0/4] sched/fair: SMT-aware asymmetric CPU capacity Andrea Righi
2026-03-26 15:02 ` [PATCH 1/4] sched/fair: Prefer fully-idle SMT cores in asym-capacity idle selection Andrea Righi
2026-03-27  8:09   ` Vincent Guittot
2026-03-27  9:46     ` Andrea Righi
2026-03-27 10:44   ` K Prateek Nayak
2026-03-27 10:58     ` Andrea Righi
2026-03-27 11:14       ` K Prateek Nayak
2026-03-27 16:39         ` Andrea Righi
2026-03-30 10:17           ` K Prateek Nayak [this message]
2026-03-30 13:07             ` Vincent Guittot
2026-03-30 13:22             ` Andrea Righi
2026-03-30 13:46               ` Andrea Righi
2026-03-26 15:02 ` [PATCH 2/4] sched/fair: Reject misfit pulls onto busy SMT siblings on asym-capacity Andrea Righi
2026-03-26 15:02 ` [PATCH 3/4] sched/fair: Enable EAS with SMT on SD_ASYM_CPUCAPACITY systems Andrea Righi
2026-03-27  8:09   ` Vincent Guittot
2026-03-27  9:45     ` Andrea Righi
2026-03-26 15:02 ` [PATCH 4/4] sched/fair: Prefer fully-idle SMT core for NOHZ idle load balancer Andrea Righi
2026-03-27  8:45   ` Vincent Guittot
2026-03-27  9:44     ` Andrea Righi
2026-03-27 11:34       ` K Prateek Nayak
2026-03-27 20:36         ` Andrea Righi
2026-03-27 22:45           ` Andrea Righi
2026-03-30 17:29         ` Andrea Righi
2026-03-27 13:44   ` Shrikanth Hegde
2026-03-26 16:33 ` [PATCH 0/4] sched/fair: SMT-aware asymmetric CPU capacity Christian Loehle
2026-03-27  6:52   ` Andrea Righi
2026-03-27 16:31 ` Shrikanth Hegde
2026-03-27 17:08   ` Andrea Righi
2026-03-28  6:51     ` Shrikanth Hegde
2026-03-28 13:03 ` Balbir Singh
2026-03-28 22:50   ` Andrea Righi
2026-03-29 21:36     ` Balbir Singh
2026-03-30 22:30 ` Dietmar Eggemann
2026-03-31  9:04   ` Andrea Righi
2026-04-01 11:57     ` Dietmar Eggemann
2026-04-01 12:08       ` Vincent Guittot
2026-04-01 12:42         ` Andrea Righi
2026-04-01 13:12           ` Andrea Righi
2026-04-03 11:47             ` Dietmar Eggemann
2026-04-03 14:45               ` Andrea Righi
2026-04-03 20:44                 ` Andrea Righi
2026-04-07 11:50                   ` Dietmar Eggemann
2026-04-07 19:16                     ` Andrea Righi
2026-04-03 11:47           ` Dietmar Eggemann

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=258e2e94-ee42-4ea4-998c-4770732cbad0@amd.com \
    --to=kprateek.nayak@amd.com \
    --cc=arighi@nvidia.com \
    --cc=balbirs@nvidia.com \
    --cc=bsegall@google.com \
    --cc=christian.loehle@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=fabecassis@nvidia.com \
    --cc=juri.lelli@redhat.com \
    --cc=kobak@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@suse.de \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.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

Powered by JetHome