All of lore.kernel.org
 help / color / mirror / Atom feed
From: "Rafael J. Wysocki" <rjw@rjwysocki.net>
To: Linux PM <linux-pm@vger.kernel.org>
Cc: LKML <linux-kernel@vger.kernel.org>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>,
	Chen Yu <yu.c.chen@intel.com>,
	Gabriele Mazzotta <gabriele.mzt@gmail.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Quentin Perret <quentin.perret@arm.com>
Subject: [PATCH v3 3/4] cpufreq: schedutil: Simplify iowait boosting
Date: Tue, 26 Mar 2019 12:18:00 +0100	[thread overview]
Message-ID: <2864116.v8IU97Resm@aspire.rjw.lan> (raw)
In-Reply-To: <11953735.uMqeHy63Iu@aspire.rjw.lan>

From: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

There is not reason for the minimum iowait boost value in the
schedutil cpufreq governor to depend on the available range of CPU
frequencies.  In fact, that dependency is generally confusing,
because it causes the iowait boost to behave somewhat differently
on CPUs with the same maximum frequency and different minimum
frequencies, for example.

For this reason, replace the min field in struct sugov_cpu
with a constant and choose its values to be 1/8 of
SCHED_CAPACITY_SCALE (for consistency with the intel_pstate
driver's internal governor).

[Note that policy->cpuinfo.max_freq will not be a constant any more
 after a subsequent change, so this change is depended on by it.]

Link: https://lore.kernel.org/lkml/20190305083202.GU32494@hirez.programming.kicks-ass.net/T/#ee20bdc98b7d89f6110c0d00e5c3ee8c2ced93c3d
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 kernel/sched/cpufreq_schedutil.c |   12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

Index: linux-pm/kernel/sched/cpufreq_schedutil.c
===================================================================
--- linux-pm.orig/kernel/sched/cpufreq_schedutil.c
+++ linux-pm/kernel/sched/cpufreq_schedutil.c
@@ -13,6 +13,8 @@
 #include <linux/sched/cpufreq.h>
 #include <trace/events/power.h>
 
+#define IOWAIT_BOOST_MIN	(SCHED_CAPACITY_SCALE / 8)
+
 struct sugov_tunables {
 	struct gov_attr_set	attr_set;
 	unsigned int		rate_limit_us;
@@ -51,7 +53,6 @@ struct sugov_cpu {
 	u64			last_update;
 
 	unsigned long		bw_dl;
-	unsigned long		min;
 	unsigned long		max;
 
 	/* The field below is for single-CPU policies only: */
@@ -303,7 +304,7 @@ static bool sugov_iowait_reset(struct su
 	if (delta_ns <= TICK_NSEC)
 		return false;
 
-	sg_cpu->iowait_boost = set_iowait_boost ? sg_cpu->min : 0;
+	sg_cpu->iowait_boost = set_iowait_boost ? IOWAIT_BOOST_MIN : 0;
 	sg_cpu->iowait_boost_pending = set_iowait_boost;
 
 	return true;
@@ -349,7 +350,7 @@ static void sugov_iowait_boost(struct su
 	}
 
 	/* First wakeup after IO: start with minimum boost */
-	sg_cpu->iowait_boost = sg_cpu->min;
+	sg_cpu->iowait_boost = IOWAIT_BOOST_MIN;
 }
 
 /**
@@ -389,7 +390,7 @@ static unsigned long sugov_iowait_apply(
 		 * No boost pending; reduce the boost value.
 		 */
 		sg_cpu->iowait_boost >>= 1;
-		if (sg_cpu->iowait_boost < sg_cpu->min) {
+		if (sg_cpu->iowait_boost < IOWAIT_BOOST_MIN) {
 			sg_cpu->iowait_boost = 0;
 			return util;
 		}
@@ -826,9 +827,6 @@ static int sugov_start(struct cpufreq_po
 		memset(sg_cpu, 0, sizeof(*sg_cpu));
 		sg_cpu->cpu			= cpu;
 		sg_cpu->sg_policy		= sg_policy;
-		sg_cpu->min			=
-			(SCHED_CAPACITY_SCALE * policy->cpuinfo.min_freq) /
-			policy->cpuinfo.max_freq;
 	}
 
 	for_each_cpu(cpu, policy->cpus) {


  parent reply	other threads:[~2019-03-26 11:22 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-26 11:12 [PATCH v3 0/4] cpufreq: intel_pstate: Handle _PPC updates on global turbo disable/enable Rafael J. Wysocki
2019-03-26 11:15 ` [PATCH v3 1/4] cpufreq: intel_pstate: Driver-specific handling of _PPC updates Rafael J. Wysocki
2019-03-26 11:16 ` [PATCH v3 2/4] cpufreq: Add cpufreq_cpu_acquire() and cpufreq_cpu_release() Rafael J. Wysocki
2019-03-26 11:18 ` Rafael J. Wysocki [this message]
2019-03-28  9:48   ` [PATCH v3 3/4] cpufreq: schedutil: Simplify iowait boosting Quentin Perret
2019-03-28 10:24     ` Rafael J. Wysocki
2019-03-28 10:33   ` [Update][PATCH " Rafael J. Wysocki
2019-04-01  9:27     ` Rafael J. Wysocki
2019-04-01 10:29       ` Peter Zijlstra
2019-04-08  5:54     ` Viresh Kumar
2019-03-26 11:19 ` [PATCH v3 4/4] cpufreq: intel_pstate: Update max frequency on global turbo changes Rafael J. Wysocki

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=2864116.v8IU97Resm@aspire.rjw.lan \
    --to=rjw@rjwysocki.net \
    --cc=gabriele.mzt@gmail.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=peterz@infradead.org \
    --cc=quentin.perret@arm.com \
    --cc=srinivas.pandruvada@linux.intel.com \
    --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.