linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Vincent Guittot <vincent.guittot@linaro.org>
To: peterz@infradead.org, mingo@kernel.org, linux-kernel@vger.kernel.org
Cc: rjw@rjwysocki.net, juri.lelli@redhat.com,
	dietmar.eggemann@arm.com, Morten.Rasmussen@arm.com,
	viresh.kumar@linaro.org, valentin.schneider@arm.com,
	patrick.bellasi@arm.com, joel@joelfernandes.org,
	daniel.lezcano@linaro.org, quentin.perret@arm.com,
	luca.abeni@santannapisa.it, claudio@evidence.eu.com,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Ingo Molnar <mingo@redhat.com>
Subject: [PATCH 09/11] sched: use pelt for scale_rt_capacity()
Date: Thu, 28 Jun 2018 17:45:12 +0200	[thread overview]
Message-ID: <1530200714-4504-10-git-send-email-vincent.guittot@linaro.org> (raw)
In-Reply-To: <1530200714-4504-1-git-send-email-vincent.guittot@linaro.org>

The utilization of the CPU by rt, dl and interrupts are now tracked with
PELT so we can use these metrics instead of rt_avg to evaluate the remaining
capacity available for cfs class.

scale_rt_capacity() behavior has been changed and now returns the remaining
capacity available for cfs instead of a scaling factor because rt, dl and
interrupt provide now absolute utilization value.

The same formula as schedutil is used:
  irq util_avg + (1 - irq util_avg / max capacity ) * /Sum rq util_avg
but the implementation is different because it doesn't return the same value
and doesn't benefit of the same optimization

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/deadline.c |  2 --
 kernel/sched/fair.c     | 41 +++++++++++++++++++----------------------
 kernel/sched/pelt.c     |  2 +-
 kernel/sched/rt.c       |  2 --
 4 files changed, 20 insertions(+), 27 deletions(-)

diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index f4de2698..68b8a9f 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1180,8 +1180,6 @@ static void update_curr_dl(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (dl_entity_is_special(dl_se))
 		return;
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index d2758e3..ce0dcbf 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -7550,39 +7550,36 @@ static inline int get_sd_load_idx(struct sched_domain *sd,
 static unsigned long scale_rt_capacity(int cpu)
 {
 	struct rq *rq = cpu_rq(cpu);
-	u64 total, used, age_stamp, avg;
-	s64 delta;
-
-	/*
-	 * 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_broken(rq) - age_stamp;
+	unsigned long max = arch_scale_cpu_capacity(NULL, cpu);
+	unsigned long used, irq, free;
 
-	if (unlikely(delta < 0))
-		delta = 0;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	irq = READ_ONCE(rq->avg_irq.util_avg);
 
-	total = sched_avg_period() + delta;
+	if (unlikely(irq >= max))
+		return 1;
+#endif
 
-	used = div_u64(avg, total);
+	used = READ_ONCE(rq->avg_rt.util_avg);
+	used += READ_ONCE(rq->avg_dl.util_avg);
 
-	if (likely(used < SCHED_CAPACITY_SCALE))
-		return SCHED_CAPACITY_SCALE - used;
+	if (unlikely(used >= max))
+		return 1;
 
-	return 1;
+	free = max - used;
+#if defined(CONFIG_IRQ_TIME_ACCOUNTING) || defined(CONFIG_PARAVIRT_TIME_ACCOUNTING)
+	free *= (max - irq);
+	free /= max;
+#endif
+	return free;
 }
 
 static void update_cpu_capacity(struct sched_domain *sd, int cpu)
 {
-	unsigned long capacity = arch_scale_cpu_capacity(sd, cpu);
+	unsigned long capacity = scale_rt_capacity(cpu);
 	struct sched_group *sdg = sd->groups;
 
-	cpu_rq(cpu)->cpu_capacity_orig = capacity;
-
-	capacity *= scale_rt_capacity(cpu);
-	capacity >>= SCHED_CAPACITY_SHIFT;
+	cpu_rq(cpu)->cpu_capacity_orig = arch_scale_cpu_capacity(sd, cpu);
 
 	if (!capacity)
 		capacity = 1;
diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
index ead6d8b..35475c0 100644
--- a/kernel/sched/pelt.c
+++ b/kernel/sched/pelt.c
@@ -237,7 +237,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load, unsigned long runna
 	 */
 	sa->load_avg = div_u64(load * sa->load_sum, divider);
 	sa->runnable_load_avg =	div_u64(runnable * sa->runnable_load_sum, divider);
-	sa->util_avg = sa->util_sum / divider;
+	WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
 }
 
 /*
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 0e3e57a..2a881bd 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -970,8 +970,6 @@ static void update_curr_rt(struct rq *rq)
 	curr->se.exec_start = now;
 	cgroup_account_cputime(curr, delta_exec);
 
-	sched_rt_avg_update(rq, delta_exec);
-
 	if (!rt_bandwidth_enabled())
 		return;
 
-- 
2.7.4


  parent reply	other threads:[~2018-06-28 15:46 UTC|newest]

Thread overview: 44+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-06-28 15:45 [PATCH v7 00/11] track CPU utilization Vincent Guittot
2018-06-28 15:45 ` [PATCH 01/11] sched/pelt: Move pelt related code in a dedicated file Vincent Guittot
2018-07-15 23:26   ` [tip:sched/core] sched/pelt: Move PELT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 02/11] sched/rt: add rt_rq utilization tracking Vincent Guittot
2018-07-15 23:27   ` [tip:sched/core] sched/rt: Add " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 03/11] cpufreq/schedutil: use rt " Vincent Guittot
2018-07-06  5:56   ` Viresh Kumar
2018-07-15 23:27   ` [tip:sched/core] cpufreq/schedutil: Use RT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 04/11] sched/dl: add dl_rq " Vincent Guittot
2018-07-15 23:28   ` [tip:sched/core] sched/dl: Add " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 05/11] cpufreq/schedutil: use dl " Vincent Guittot
2018-07-06  5:59   ` Viresh Kumar
2018-07-15 23:28   ` [tip:sched/core] cpufreq/schedutil: Use DL " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 06/11] sched/irq: add irq " Vincent Guittot
2018-07-15 23:29   ` [tip:sched/core] sched/irq: Add IRQ " tip-bot for Vincent Guittot
2018-07-26  3:09   ` [PATCH 06/11] sched/irq: add irq " Wanpeng Li
2018-07-30 16:43     ` Vincent Guittot
2018-07-31  3:32       ` Wanpeng Li
2018-07-31  8:21         ` Vincent Guittot
2018-06-28 15:45 ` [PATCH 07/11] cpufreq/schedutil: take into account interrupt Vincent Guittot
2018-07-06  6:00   ` Viresh Kumar
2018-07-06  9:14     ` Peter Zijlstra
2018-07-06  9:21       ` Vincent Guittot
2018-07-15 23:29   ` [tip:sched/core] cpufreq/schedutil: Take time spent in interrupts into account tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 08/11] sched: schedutil: remove sugov_aggregate_util() Vincent Guittot
2018-07-06  6:02   ` Viresh Kumar
2018-07-15 23:30   ` [tip:sched/core] sched/cpufreq: Remove sugov_aggregate_util() tip-bot for Vincent Guittot
2018-06-28 15:45 ` Vincent Guittot [this message]
2018-07-15 22:15   ` [PATCH 09/11] sched: use pelt for scale_rt_capacity() Ingo Molnar
2018-07-15 22:46     ` Joe Perches
2018-07-16 11:24     ` Vincent Guittot
2018-07-16 11:39       ` Ingo Molnar
2018-07-15 23:32   ` [tip:sched/core] sched/core: Use PELT " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 10/11] sched: remove rt_avg code Vincent Guittot
2018-07-15 23:33   ` [tip:sched/core] sched/core: Remove the " tip-bot for Vincent Guittot
2018-06-28 15:45 ` [PATCH 11/11] proc/sched: remove unused sched_time_avg_ms Vincent Guittot
2018-06-28 15:51   ` Luis R. Rodriguez
2018-06-29  5:49     ` Vincent Guittot
2018-07-15 23:33   ` [tip:sched/core] sched/sysctl: Remove unused sched_time_avg_ms sysctl tip-bot for Vincent Guittot
2018-07-05 12:36 ` [PATCH v7 00/11] track CPU utilization Peter Zijlstra
2018-07-05 13:32   ` Vincent Guittot
2018-07-06  6:05   ` Viresh Kumar
2018-07-06  9:18     ` Peter Zijlstra
2018-07-15 23:34   ` [tip:sched/core] sched/cpufreq: Clarify sugov_get_util() tip-bot for Peter Zijlstra

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=1530200714-4504-10-git-send-email-vincent.guittot@linaro.org \
    --to=vincent.guittot@linaro.org \
    --cc=Morten.Rasmussen@arm.com \
    --cc=claudio@evidence.eu.com \
    --cc=daniel.lezcano@linaro.org \
    --cc=dietmar.eggemann@arm.com \
    --cc=joel@joelfernandes.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luca.abeni@santannapisa.it \
    --cc=mingo@kernel.org \
    --cc=mingo@redhat.com \
    --cc=patrick.bellasi@arm.com \
    --cc=peterz@infradead.org \
    --cc=quentin.perret@arm.com \
    --cc=rjw@rjwysocki.net \
    --cc=valentin.schneider@arm.com \
    --cc=viresh.kumar@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).