LKML Archive on lore.kernel.org
 help / Atom feed
From: Quentin Perret <quentin.perret@arm.com>
To: peterz@infradead.org, rjw@rjwysocki.net,
	linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org
Cc: gregkh@linuxfoundation.org, mingo@redhat.com,
	dietmar.eggemann@arm.com, morten.rasmussen@arm.com,
	chris.redpath@arm.com, patrick.bellasi@arm.com,
	valentin.schneider@arm.com, vincent.guittot@linaro.org,
	thara.gopinath@linaro.org, viresh.kumar@linaro.org,
	tkjos@google.com, joel@joelfernandes.org, smuckle@google.com,
	adharmap@quicinc.com, skannan@quicinc.com,
	pkondeti@codeaurora.org, juri.lelli@redhat.com,
	edubezval@gmail.com, srinivas.pandruvada@linux.intel.com,
	currojerez@riseup.net, javi.merino@kernel.org,
	quentin.perret@arm.com
Subject: [PATCH v5 09/14] sched: Add over-utilization/tipping point indicator
Date: Tue, 24 Jul 2018 13:25:16 +0100
Message-ID: <20180724122521.22109-10-quentin.perret@arm.com> (raw)
In-Reply-To: <20180724122521.22109-1-quentin.perret@arm.com>

From: Morten Rasmussen <morten.rasmussen@arm.com>

Energy-aware scheduling is only meant to be active while the system is
_not_ over-utilized. That is, there are spare cycles available to shift
tasks around based on their actual utilization to get a more
energy-efficient task distribution without depriving any tasks. When
above the tipping point task placement is done the traditional way based
on load_avg, spreading the tasks across as many cpus as possible based
on priority scaled load to preserve smp_nice. Below the tipping point we
want to use util_avg instead. We need to define a criteria for when we
make the switch.

The util_avg for each cpu converges towards 100% (1024) regardless of
how many task additional task we may put on it. If we define
over-utilized as:

sum_{cpus}(rq.cfs.avg.util_avg) + margin > sum_{cpus}(rq.capacity)

some individual cpus may be over-utilized running multiple tasks even
when the above condition is false. That should be okay as long as we try
to spread the tasks out to avoid per-cpu over-utilization as much as
possible and if all tasks have the _same_ priority. If the latter isn't
true, we have to consider priority to preserve smp_nice.

For example, we could have n_cpus nice=-10 util_avg=55% tasks and
n_cpus/2 nice=0 util_avg=60% tasks. Balancing based on util_avg we are
likely to end up with nice=-10 tasks sharing cpus and nice=0 tasks
getting their own as we 1.5*n_cpus tasks in total and 55%+55% is less
over-utilized than 55%+60% for those cpus that have to be shared. The
system utilization is only 85% of the system capacity, but we are
breaking smp_nice.

To be sure not to break smp_nice, we have defined over-utilization
conservatively as when any cpu in the system is fully utilized at its
highest frequency instead:

cpu_rq(any).cfs.avg.util_avg + margin > cpu_rq(any).capacity

IOW, as soon as one cpu is (nearly) 100% utilized, we switch to load_avg
to factor in priority to preserve smp_nice.

With this definition, we can skip periodic load-balance as no cpu has an
always-running task when the system is not over-utilized. All tasks will
be periodic and we can balance them at wake-up. This conservative
condition does however mean that some scenarios that could benefit from
energy-aware decisions even if one cpu is fully utilized would not get
those benefits.

For systems where some cpus might have reduced capacity on some cpus
(RT-pressure and/or big.LITTLE), we want periodic load-balance checks as
soon a just a single cpu is fully utilized as it might one of those with
reduced capacity and in that case we want to migrate it.

cc: Ingo Molnar <mingo@redhat.com>
cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Quentin Perret <quentin.perret@arm.com>
---
 kernel/sched/fair.c  | 48 ++++++++++++++++++++++++++++++++++++++++++--
 kernel/sched/sched.h |  4 ++++
 2 files changed, 50 insertions(+), 2 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index fcc97fa3be94..4aaa9132e840 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5043,6 +5043,24 @@ static inline void hrtick_update(struct rq *rq)
 }
 #endif
 
+#ifdef CONFIG_SMP
+static inline unsigned long cpu_util(int cpu);
+static unsigned long capacity_of(int cpu);
+
+static inline bool cpu_overutilized(int cpu)
+{
+	return (capacity_of(cpu) * 1024) < (cpu_util(cpu) * capacity_margin);
+}
+
+static inline void update_overutilized_status(struct rq *rq)
+{
+	if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+		WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
+}
+#else
+static inline void update_overutilized_status(struct rq *rq) { }
+#endif
+
 /*
  * The enqueue_task method is called before nr_running is
  * increased. Here we update the fair scheduling stats and
@@ -5100,8 +5118,17 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
 		update_cfs_group(se);
 	}
 
-	if (!se)
+	if (!se) {
 		add_nr_running(rq, 1);
+		/*
+		 * The utilization of a new task is 'wrong' so wait for it
+		 * to build some utilization history before trying to detect
+		 * the overutilized flag.
+		 */
+		if (flags & ENQUEUE_WAKEUP)
+			update_overutilized_status(rq);
+
+	}
 
 	hrtick_update(rq);
 }
@@ -7837,6 +7864,9 @@ static inline void update_sg_lb_stats(struct lb_env *env,
 		if (nr_running > 1)
 			*sg_status |= SG_OVERLOAD;
 
+		if (cpu_overutilized(i))
+			*sg_status |= SG_OVERUTILIZED;
+
 #ifdef CONFIG_NUMA_BALANCING
 		sgs->nr_numa_running += rq->nr_numa_running;
 		sgs->nr_preferred_running += rq->nr_preferred_running;
@@ -8046,8 +8076,15 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
 		env->fbq_type = fbq_classify_group(&sds->busiest_stat);
 
 	if (!env->sd->parent) {
+		struct root_domain *rd = env->dst_rq->rd;
+
 		/* update overload indicator if we are at root domain */
-		env->dst_rq->rd->overload = sg_status & SG_OVERLOAD;
+		rd->overload = sg_status & SG_OVERLOAD;
+
+		/* Update over-utilization (tipping point, U >= 0) indicator */
+		WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
+	} else if (sg_status & SG_OVERUTILIZED) {
+		WRITE_ONCE(env->dst_rq->rd->overutilized, SG_OVERUTILIZED);
 	}
 }
 
@@ -8267,6 +8304,11 @@ static struct sched_group *find_busiest_group(struct lb_env *env)
 	 * this level.
 	 */
 	update_sd_lb_stats(env, &sds);
+
+	if (rd_freq_domain(env->dst_rq->rd) &&
+				!READ_ONCE(env->dst_rq->rd->overutilized))
+		goto out_balanced;
+
 	local = &sds.local_stat;
 	busiest = &sds.busiest_stat;
 
@@ -9624,6 +9666,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
 
 	if (static_branch_unlikely(&sched_numa_balancing))
 		task_tick_numa(rq, curr);
+
+	update_overutilized_status(task_rq(curr));
 }
 
 /*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 99b5bf245eab..6d08ccd1e7a4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -709,6 +709,7 @@ struct freq_domain {
 
 /* Scheduling group status flags */
 #define SG_OVERLOAD		0x1 /* More than one runnable task on a CPU. */
+#define SG_OVERUTILIZED		0x2 /* One or more CPUs are over-utilized. */
 
 /*
  * We add the notion of a root-domain which will be used to define per-domain
@@ -728,6 +729,9 @@ struct root_domain {
 	/* Indicate more than one runnable task for any CPU */
 	int			overload;
 
+	/* Indicate one or more cpus over-utilized (tipping point) */
+	int			overutilized;
+
 	/*
 	 * The bit corresponding to a CPU gets set here if such CPU has more
 	 * than one runnable -deadline task (as it is below for RT tasks).
-- 
2.18.0


  parent reply index

Thread overview: 72+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-07-24 12:25 [PATCH v5 00/14] Energy Aware Scheduling Quentin Perret
2018-07-24 12:25 ` [PATCH v5 01/14] sched: Relocate arch_scale_cpu_capacity Quentin Perret
2018-07-24 12:25 ` [PATCH v5 02/14] sched/cpufreq: Factor out utilization to frequency mapping Quentin Perret
2018-07-24 12:25 ` [PATCH v5 03/14] PM: Introduce an Energy Model management framework Quentin Perret
2018-08-09 21:52   ` Rafael J. Wysocki
2018-08-10  8:15     ` Quentin Perret
2018-08-10  8:41       ` Rafael J. Wysocki
2018-08-10  9:12         ` Quentin Perret
2018-08-10 11:13           ` Rafael J. Wysocki
2018-08-10 12:30             ` Quentin Perret
2018-08-12  9:49               ` Rafael J. Wysocki
2018-07-24 12:25 ` [PATCH v5 04/14] PM / EM: Expose the Energy Model in sysfs Quentin Perret
2018-07-24 12:25 ` [PATCH v5 05/14] sched/topology: Reference the Energy Model of CPUs when available Quentin Perret
2018-07-24 12:25 ` [PATCH v5 06/14] sched/topology: Lowest energy aware balancing sched_domain level pointer Quentin Perret
2018-07-26 16:00   ` Valentin Schneider
2018-07-26 17:01     ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 07/14] sched/topology: Introduce sched_energy_present static key Quentin Perret
2018-07-24 12:25 ` [PATCH v5 08/14] sched/fair: Clean-up update_sg_lb_stats parameters Quentin Perret
2018-07-24 12:25 ` Quentin Perret [this message]
2018-08-02 12:26   ` [PATCH v5 09/14] sched: Add over-utilization/tipping point indicator Peter Zijlstra
2018-08-02 13:03     ` Quentin Perret
2018-08-02 13:08       ` Peter Zijlstra
2018-08-02 13:18         ` Quentin Perret
2018-08-02 13:48           ` Vincent Guittot
2018-08-02 14:14             ` Quentin Perret
2018-08-02 15:14               ` Vincent Guittot
2018-08-02 15:30                 ` Quentin Perret
2018-08-02 15:55                   ` Vincent Guittot
2018-08-02 16:00                     ` Quentin Perret
2018-08-02 16:07                       ` Vincent Guittot
2018-08-02 16:10                         ` Quentin Perret
2018-08-02 16:38                           ` Vincent Guittot
2018-08-02 16:59                             ` Quentin Perret
2018-08-03  7:48                               ` Vincent Guittot
2018-08-03  8:18                                 ` Quentin Perret
2018-08-03 13:49                                   ` Vincent Guittot
2018-08-03 14:21                                     ` Vincent Guittot
2018-08-03 15:55                                     ` Quentin Perret
2018-08-06  8:40                                       ` Vincent Guittot
2018-08-06  9:43                                         ` Quentin Perret
2018-08-06 10:45                                           ` Vincent Guittot
2018-08-06 11:02                                             ` Quentin Perret
2018-08-06 10:08                                         ` Dietmar Eggemann
2018-08-06 10:33                                           ` Vincent Guittot
2018-08-06 12:29                                             ` Dietmar Eggemann
2018-08-06 12:37                                               ` Vincent Guittot
2018-08-06 13:20                                                 ` Dietmar Eggemann
2018-08-09  9:30   ` Vincent Guittot
2018-08-09  9:38     ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 10/14] sched/cpufreq: Refactor the utilization aggregation method Quentin Perret
2018-07-30 19:35   ` skannan
2018-07-31  7:59     ` Quentin Perret
2018-07-31 19:31       ` skannan
2018-08-01  7:32         ` Rafael J. Wysocki
2018-08-01  8:23           ` Quentin Perret
2018-08-01  8:35             ` Rafael J. Wysocki
2018-08-01  9:23               ` Quentin Perret
2018-08-01  9:40                 ` Rafael J. Wysocki
2018-08-02 13:04                 ` Peter Zijlstra
2018-08-02 15:39                   ` Quentin Perret
2018-08-03 13:04                     ` Quentin Perret
2018-08-02 12:33     ` Peter Zijlstra
2018-08-02 12:45       ` Peter Zijlstra
2018-08-02 15:21         ` Quentin Perret
2018-08-02 17:36           ` Peter Zijlstra
2018-08-03 12:42             ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 11/14] sched/fair: Introduce an energy estimation helper function Quentin Perret
2018-07-24 12:25 ` [PATCH v5 12/14] sched/fair: Select an energy-efficient CPU on task wake-up Quentin Perret
2018-08-02 13:54   ` Peter Zijlstra
2018-08-02 16:21     ` Quentin Perret
2018-07-24 12:25 ` [PATCH v5 13/14] OPTIONAL: arch_topology: Start Energy Aware Scheduling Quentin Perret
2018-07-24 12:25 ` [PATCH v5 14/14] OPTIONAL: cpufreq: dt: Register an Energy Model Quentin Perret

Reply instructions:

You may reply publically 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=20180724122521.22109-10-quentin.perret@arm.com \
    --to=quentin.perret@arm.com \
    --cc=adharmap@quicinc.com \
    --cc=chris.redpath@arm.com \
    --cc=currojerez@riseup.net \
    --cc=dietmar.eggemann@arm.com \
    --cc=edubezval@gmail.com \
    --cc=gregkh@linuxfoundation.org \
    --cc=javi.merino@kernel.org \
    --cc=joel@joelfernandes.org \
    --cc=juri.lelli@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pm@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=morten.rasmussen@arm.com \
    --cc=patrick.bellasi@arm.com \
    --cc=peterz@infradead.org \
    --cc=pkondeti@codeaurora.org \
    --cc=rjw@rjwysocki.net \
    --cc=skannan@quicinc.com \
    --cc=smuckle@google.com \
    --cc=srinivas.pandruvada@linux.intel.com \
    --cc=thara.gopinath@linaro.org \
    --cc=tkjos@google.com \
    --cc=valentin.schneider@arm.com \
    --cc=vincent.guittot@linaro.org \
    --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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org linux-kernel@archiver.kernel.org
	public-inbox-index lkml


Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/ public-inbox