linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Peter Zijlstra <peterz@infradead.org>
To: mgorman@techsingularity.net, vincent.guittot@linaro.org
Cc: peterz@infradead.org, linux-kernel@vger.kernel.org,
	aubrey.li@linux.intel.com, mingo@redhat.com,
	juri.lelli@redhat.com, valentin.schneider@arm.com,
	qais.yousef@arm.com, dietmar.eggemann@arm.com,
	rostedt@goodmis.org, bsegall@google.com,
	tim.c.chen@linux.intel.com, benbjiang@gmail.com
Subject: [RFC][PATCH 2/5] sched/fair: Make select_idle_cpu() proportional to cores
Date: Mon, 14 Dec 2020 17:48:24 +0100	[thread overview]
Message-ID: <20201214170017.938791025@infradead.org> (raw)
In-Reply-To: 20201214164822.402812729@infradead.org

Instead of calculating how many (logical) CPUs to scan, compute how
many cores to scan.

This changes behaviour for anything !SMT2.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/core.c |   19 ++++++++++++++-----
 kernel/sched/fair.c |   12 ++++++++++--
 2 files changed, 24 insertions(+), 7 deletions(-)

--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7454,11 +7454,20 @@ int sched_cpu_activate(unsigned int cpu)
 	balance_push_set(cpu, false);
 
 #ifdef CONFIG_SCHED_SMT
-	/*
-	 * When going up, increment the number of cores with SMT present.
-	 */
-	if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-		static_branch_inc_cpuslocked(&sched_smt_present);
+	do {
+		int weight = cpumask_weight(cpu_smt_mask(cpu));
+		extern int sched_smt_weight;
+
+		if (weight > sched_smt_weight)
+			sched_smt_weight = weight;
+
+		/*
+		 * When going up, increment the number of cores with SMT present.
+		 */
+		if (weight == 2)
+			static_branch_inc_cpuslocked(&sched_smt_present);
+
+	} while (0);
 #endif
 	set_cpu_active(cpu, true);
 
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6010,6 +6010,8 @@ static inline int find_idlest_cpu(struct
 DEFINE_STATIC_KEY_FALSE(sched_smt_present);
 EXPORT_SYMBOL_GPL(sched_smt_present);
 
+int sched_smt_weight = 1;
+
 static inline void set_idle_cores(int cpu, int val)
 {
 	struct sched_domain_shared *sds;
@@ -6124,6 +6126,8 @@ static int select_idle_smt(struct task_s
 
 #else /* CONFIG_SCHED_SMT */
 
+#define sched_smt_weight	1
+
 static inline int select_idle_core(struct task_struct *p, struct sched_domain *sd, int target)
 {
 	return -1;
@@ -6136,6 +6140,8 @@ static inline int select_idle_smt(struct
 
 #endif /* CONFIG_SCHED_SMT */
 
+#define sis_min_cores		2
+
 /*
  * Scan the LLC domain for idle CPUs; this is dynamically regulated by
  * comparing the average scan cost (tracked in sd->avg_scan_cost) against the
@@ -6166,10 +6172,12 @@ static int select_idle_cpu(struct task_s
 		avg_cost = this_sd->avg_scan_cost + 1;
 
 		span_avg = sd->span_weight * avg_idle;
-		if (span_avg > 4*avg_cost)
+		if (span_avg > sis_min_cores * avg_cost)
 			nr = div_u64(span_avg, avg_cost);
 		else
-			nr = 4;
+			nr = sis_min_cores;
+
+		nr *= sched_smt_weight;
 
 		time = cpu_clock(this);
 	}



  parent reply	other threads:[~2020-12-14 17:13 UTC|newest]

Thread overview: 31+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-12-14 16:48 [RFC][PATCH 0/5] select_idle_sibling() wreckage Peter Zijlstra
2020-12-14 16:48 ` [RFC][PATCH 1/5] sched/fair: Fix select_idle_cpu()s cost accounting Peter Zijlstra
2020-12-15  3:36   ` Li, Aubrey
2020-12-15  7:59     ` Peter Zijlstra
2020-12-15 11:45       ` Mel Gorman
2020-12-15 12:13       ` Li, Aubrey
2021-01-08 10:27       ` Mel Gorman
2021-01-08 13:01         ` Qais Yousef
2021-01-08 13:47           ` Mel Gorman
2021-01-08 13:41         ` Vincent Guittot
2021-01-08 14:40           ` Mel Gorman
2021-01-08 15:10             ` Vincent Guittot
2021-01-08 16:14               ` Mel Gorman
2021-01-11 14:36                 ` Vincent Guittot
2021-01-11 15:58                   ` Mel Gorman
2021-01-08 19:45               ` Peter Zijlstra
2021-01-09 14:12                 ` Mel Gorman
2021-01-11 14:39                 ` Vincent Guittot
2021-01-08 19:49               ` Peter Zijlstra
2021-01-11 14:52                 ` Vincent Guittot
2021-01-08 20:21         ` Peter Zijlstra
2021-01-09 13:59           ` Mel Gorman
2020-12-14 16:48 ` Peter Zijlstra [this message]
2020-12-23 13:31   ` [RFC][PATCH 2/5] sched/fair: Make select_idle_cpu() proportional to cores Vincent Guittot
2020-12-14 16:48 ` [RFC][PATCH 3/5] sched/fair: Remove select_idle_smt() Peter Zijlstra
2020-12-14 16:48 ` [RFC][PATCH 4/5] sched/fair: Merge select_idle_core/cpu() Peter Zijlstra
2020-12-14 16:48 ` [RFC][PATCH 5/5] sched/fair: SIS_PROP the idle core scan Peter Zijlstra
2020-12-16 12:59 ` [RFC][PATCH 0/5] select_idle_sibling() wreckage Li, Aubrey
2020-12-16 18:07   ` Vincent Guittot
2020-12-23 13:23     ` Vincent Guittot
2021-01-04 15:40       ` Mel Gorman

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=20201214170017.938791025@infradead.org \
    --to=peterz@infradead.org \
    --cc=aubrey.li@linux.intel.com \
    --cc=benbjiang@gmail.com \
    --cc=bsegall@google.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mgorman@techsingularity.net \
    --cc=mingo@redhat.com \
    --cc=qais.yousef@arm.com \
    --cc=rostedt@goodmis.org \
    --cc=tim.c.chen@linux.intel.com \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    /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;
as well as URLs for NNTP newsgroup(s).