linux-pm.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Fabio Baltieri <fabio.baltieri@linaro.org>
To: "Rafael J. Wysocki" <rjw@sisk.pl>,
	cpufreq@vger.kernel.org, linux-pm@vger.kernel.org
Cc: Rickard Andersson <rickard.andersson@stericsson.com>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Linus Walleij <linus.walleij@linaro.org>,
	Lee Jones <lee.jones@linaro.org>,
	linux-kernel@vger.kernel.org,
	Fabio Baltieri <fabio.baltieri@linaro.org>
Subject: [PATCH 4/5] cpufreq: conservative: call dbs_check_cpu only when necessary
Date: Mon, 26 Nov 2012 17:39:55 +0100	[thread overview]
Message-ID: <1353947996-26723-5-git-send-email-fabio.baltieri@linaro.org> (raw)
In-Reply-To: <1353947996-26723-1-git-send-email-fabio.baltieri@linaro.org>

Modify conservative timer to not resample CPU utilization if recently
sampled from another SW coordinated core.

Signed-off-by: Fabio Baltieri <fabio.baltieri@linaro.org>
---
 drivers/cpufreq/cpufreq_conservative.c | 47 +++++++++++++++++++++++++++++-----
 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/drivers/cpufreq/cpufreq_conservative.c b/drivers/cpufreq/cpufreq_conservative.c
index b9d7f14..5d8e894 100644
--- a/drivers/cpufreq/cpufreq_conservative.c
+++ b/drivers/cpufreq/cpufreq_conservative.c
@@ -111,22 +111,57 @@ static void cs_check_cpu(int cpu, unsigned int load)
 	}
 }
 
-static void cs_dbs_timer(struct work_struct *work)
+static void cs_timer_update(struct cs_cpu_dbs_info_s *dbs_info, bool sample,
+			    struct delayed_work *dw)
 {
-	struct cs_cpu_dbs_info_s *dbs_info = container_of(work,
-			struct cs_cpu_dbs_info_s, cdbs.work.work);
 	unsigned int cpu = dbs_info->cdbs.cpu;
 	int delay = delay_for_sampling_rate(cs_tuners.sampling_rate);
 
+	if (sample)
+		dbs_check_cpu(&cs_dbs_data, cpu);
+
+	schedule_delayed_work_on(smp_processor_id(), dw, delay);
+}
+
+static void cs_timer_coordinated(struct cs_cpu_dbs_info_s *dbs_info_local,
+				 struct delayed_work *dw)
+{
+	struct cs_cpu_dbs_info_s *dbs_info;
+	ktime_t time_now;
+	s64 delta_us;
+	bool sample = true;
+
+	/* use leader CPU's dbs_info */
+	dbs_info = &per_cpu(cs_cpu_dbs_info, dbs_info_local->cdbs.cpu);
 	mutex_lock(&dbs_info->cdbs.timer_mutex);
 
-	dbs_check_cpu(&cs_dbs_data, cpu);
+	time_now = ktime_get();
+	delta_us = ktime_us_delta(time_now, dbs_info->cdbs.time_stamp);
 
-	schedule_delayed_work_on(smp_processor_id(), &dbs_info->cdbs.work,
-			delay);
+	/* Do nothing if we recently have sampled */
+	if (delta_us < (s64)(cs_tuners.sampling_rate / 2))
+		sample = false;
+	else
+		dbs_info->cdbs.time_stamp = time_now;
+
+	cs_timer_update(dbs_info, sample, dw);
 	mutex_unlock(&dbs_info->cdbs.timer_mutex);
 }
 
+static void cs_dbs_timer(struct work_struct *work)
+{
+	struct delayed_work *dw = to_delayed_work(work);
+	struct cs_cpu_dbs_info_s *dbs_info = container_of(work,
+			struct cs_cpu_dbs_info_s, cdbs.work.work);
+
+	if (dbs_sw_coordinated_cpus(&dbs_info->cdbs)) {
+		cs_timer_coordinated(dbs_info, dw);
+	} else {
+		mutex_lock(&dbs_info->cdbs.timer_mutex);
+		cs_timer_update(dbs_info, true, dw);
+		mutex_unlock(&dbs_info->cdbs.timer_mutex);
+	}
+}
 static int dbs_cpufreq_notifier(struct notifier_block *nb, unsigned long val,
 		void *data)
 {
-- 
1.7.12.1


  parent reply	other threads:[~2012-11-26 16:41 UTC|newest]

Thread overview: 11+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-11-26 16:39 [PATCH v5 0/5] cpufreq: handle SW coordinated CPUs Fabio Baltieri
2012-11-26 16:39 ` [PATCH 1/5] " Fabio Baltieri
2012-11-27 22:05   ` Rafael J. Wysocki
2012-11-28 10:51     ` Fabio Baltieri
2012-11-28 12:49       ` Rafael J. Wysocki
2012-11-26 16:39 ` [PATCH 2/5] cpufreq: star/stop cpufreq timers on cpu hotplug Fabio Baltieri
2012-11-26 16:39 ` [PATCH 3/5] cpufreq: ondemand: call dbs_check_cpu only when necessary Fabio Baltieri
2012-11-26 16:39 ` Fabio Baltieri [this message]
2012-11-26 16:39 ` [PATCH 5/5] cpufreq: ondemand: use all CPUs in update_sampling_rate Fabio Baltieri
2013-01-11 22:40 ` [PATCH v5 0/5] cpufreq: handle SW coordinated CPUs Rafael J. Wysocki
  -- strict thread matches above, loose matches on Subject: below --
2012-12-27 14:55 [PATCH v6 " Fabio Baltieri
2012-12-27 14:55 ` [PATCH 4/5] cpufreq: conservative: call dbs_check_cpu only when necessary Fabio Baltieri

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=1353947996-26723-5-git-send-email-fabio.baltieri@linaro.org \
    --to=fabio.baltieri@linaro.org \
    --cc=cpufreq@vger.kernel.org \
    --cc=lee.jones@linaro.org \
    --cc=linus.walleij@linaro.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=rickard.andersson@stericsson.com \
    --cc=rjw@sisk.pl \
    --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).