All of lore.kernel.org
 help / color / mirror / Atom feed
From: Steve Muckle <steve.muckle@linaro.org>
To: Peter Zijlstra <peterz@infradead.org>, Ingo Molnar <mingo@redhat.com>
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>,
	Juri Lelli <Juri.Lelli@arm.com>,
	Patrick Bellasi <patrick.bellasi@arm.com>,
	Michael Turquette <mturquette@baylibre.com>
Subject: [RFCv6 PATCH 10/10] sched: rt scheduler sets capacity requirement
Date: Tue,  8 Dec 2015 22:19:31 -0800	[thread overview]
Message-ID: <1449641971-20827-11-git-send-email-smuckle@linaro.org> (raw)
In-Reply-To: <1449641971-20827-1-git-send-email-smuckle@linaro.org>

From: Vincent Guittot <vincent.guittot@linaro.org>

RT tasks don't provide any running constraints like deadline ones
except their running priority. The only current usable input to
estimate the capacity needed by RT tasks is the rt_avg metric. We use
it to estimate the CPU capacity needed for the RT scheduler class.

In order to monitor the evolution for RT task load, we must
peridiocally check it during the tick.

Then, we use the estimated capacity of the last activity to estimate
the next one which can not be that accurate but is a good starting
point without any impact on the wake up path of RT tasks.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Steve Muckle <smuckle@linaro.org>
---
 kernel/sched/rt.c | 49 ++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 48 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 8ec86ab..9694204 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1426,6 +1426,41 @@ static void check_preempt_curr_rt(struct rq *rq, struct task_struct *p, int flag
 #endif
 }
 
+#ifdef CONFIG_SMP
+static void sched_rt_update_capacity_req(struct rq *rq)
+{
+	u64 total, used, age_stamp, avg;
+	s64 delta;
+
+	if (!sched_freq())
+		return;
+
+	sched_avg_update(rq);
+	/*
+	 * Since we're reading these variables without serialization make sure
+	 * we read them once before doing sanity checks on them.
+	 */
+	age_stamp = READ_ONCE(rq->age_stamp);
+	avg = READ_ONCE(rq->rt_avg);
+	delta = rq_clock(rq) - age_stamp;
+
+	if (unlikely(delta < 0))
+		delta = 0;
+
+	total = sched_avg_period() + delta;
+
+	used = div_u64(avg, total);
+	if (unlikely(used > SCHED_CAPACITY_SCALE))
+		used = SCHED_CAPACITY_SCALE;
+
+	set_rt_cpu_capacity(rq->cpu, 1, (unsigned long)(used));
+}
+#else
+static inline void sched_rt_update_capacity_req(struct rq *rq)
+{ }
+
+#endif
+
 static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq,
 						   struct rt_rq *rt_rq)
 {
@@ -1494,8 +1529,17 @@ pick_next_task_rt(struct rq *rq, struct task_struct *prev)
 	if (prev->sched_class == &rt_sched_class)
 		update_curr_rt(rq);
 
-	if (!rt_rq->rt_queued)
+	if (!rt_rq->rt_queued) {
+		/*
+		 * The next task to be picked on this rq will have a lower
+		 * priority than rt tasks so we can spend some time to update
+		 * the capacity used by rt tasks based on the last activity.
+		 * This value will be the used as an estimation of the next
+		 * activity.
+		 */
+		sched_rt_update_capacity_req(rq);
 		return NULL;
+	}
 
 	put_prev_task(rq, prev);
 
@@ -2212,6 +2256,9 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 
 	update_curr_rt(rq);
 
+	if (rq->rt.rt_nr_running)
+		sched_rt_update_capacity_req(rq);
+
 	watchdog(rq, p);
 
 	/*
-- 
2.4.10


  parent reply	other threads:[~2015-12-09  6:20 UTC|newest]

Thread overview: 59+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-12-09  6:19 [RFCv6 PATCH 00/10] sched: scheduler-driven CPU frequency selection Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 01/10] sched: Compute cpu capacity available at current frequency Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 02/10] cpufreq: introduce cpufreq_driver_is_slow Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 03/10] sched: scheduler-driven cpu frequency selection Steve Muckle
2015-12-11 11:04   ` Juri Lelli
2015-12-15  2:02     ` Steve Muckle
2015-12-15 10:31       ` Juri Lelli
2015-12-16  1:22         ` Steve Muckle
2015-12-16  3:48   ` Leo Yan
2015-12-17  1:24     ` Steve Muckle
2015-12-17  7:17       ` Leo Yan
2015-12-18 19:15         ` Steve Muckle
2015-12-19  5:54           ` Leo Yan
2016-01-25 12:06   ` Ricky Liang
2016-01-27  1:14     ` Steve Muckle
2016-02-01 17:10   ` Ricky Liang
2016-02-11  4:44     ` Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 04/10] sched/fair: add triggers for OPP change requests Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 05/10] sched/{core,fair}: trigger OPP change request on fork() Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 06/10] sched/fair: cpufreq_sched triggers for load balancing Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 07/10] sched/fair: jump to max OPP when crossing UP threshold Steve Muckle
2015-12-11 11:12   ` Juri Lelli
2015-12-15  2:42     ` Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 08/10] sched: remove call of sched_avg_update from sched_rt_avg_update Steve Muckle
2015-12-09  6:19 ` [RFCv6 PATCH 09/10] sched: deadline: use deadline bandwidth in scale_rt_capacity Steve Muckle
2015-12-09  8:50   ` Vincent Guittot
2015-12-10 13:27     ` Luca Abeni
2015-12-10 16:11       ` Vincent Guittot
2015-12-11  7:48         ` Luca Abeni
2015-12-14 14:02           ` Vincent Guittot
2015-12-14 14:38             ` Luca Abeni
2015-12-14 15:17   ` Peter Zijlstra
2015-12-14 15:56     ` Vincent Guittot
2015-12-14 16:07       ` Juri Lelli
2015-12-14 21:19         ` Luca Abeni
2015-12-14 16:51       ` Peter Zijlstra
2015-12-14 21:31         ` Luca Abeni
2015-12-15 12:38           ` Peter Zijlstra
2015-12-15 13:30             ` Luca Abeni
2015-12-15 13:42               ` Peter Zijlstra
2015-12-15 21:24                 ` Luca Abeni
2015-12-16  9:28                   ` Juri Lelli
2015-12-15  4:43         ` Vincent Guittot
2015-12-15 12:41           ` Peter Zijlstra
2015-12-15 12:56             ` Vincent Guittot
2015-12-14 21:12       ` Luca Abeni
2015-12-15  4:59         ` Vincent Guittot
2015-12-15  8:50           ` Luca Abeni
2015-12-15 12:20             ` Peter Zijlstra
2015-12-15 12:46               ` Vincent Guittot
2015-12-15 13:18               ` Luca Abeni
2015-12-15 12:23             ` Peter Zijlstra
2015-12-15 13:21               ` Luca Abeni
2015-12-15 12:43             ` Vincent Guittot
2015-12-15 13:39               ` Luca Abeni
2015-12-15 12:58             ` Vincent Guittot
2015-12-15 13:41               ` Luca Abeni
2015-12-09  6:19 ` Steve Muckle [this message]
2015-12-11 11:22   ` [RFCv6 PATCH 10/10] sched: rt scheduler sets capacity requirement Juri Lelli

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=1449641971-20827-11-git-send-email-smuckle@linaro.org \
    --to=steve.muckle@linaro.org \
    --cc=Juri.Lelli@arm.com \
    --cc=dietmar.eggemann@arm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=mturquette@baylibre.com \
    --cc=patrick.bellasi@arm.com \
    --cc=peterz@infradead.org \
    --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 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.