| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-Id: <20180406153607.17815-6-dietmar.eggemann@arm.com>
Date: Fri, 6 Apr 2018 16:36:06 +0100
From: Dietmar Eggemann <dietmar.eggemann@....com>
To: linux-kernel@...r.kernel.org,
Peter Zijlstra <peterz@...radead.org>,
Quentin Perret <quentin.perret@....com>,
Thara Gopinath <thara.gopinath@...aro.org>
Cc: linux-pm@...r.kernel.org,
Morten Rasmussen <morten.rasmussen@....com>,
Chris Redpath <chris.redpath@....com>,
Patrick Bellasi <patrick.bellasi@....com>,
Valentin Schneider <valentin.schneider@....com>,
"Rafael J . Wysocki" <rjw@...ysocki.net>,
Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
Vincent Guittot <vincent.guittot@...aro.org>,
Viresh Kumar <viresh.kumar@...aro.org>,
Todd Kjos <tkjos@...gle.com>,
Joel Fernandes <joelaf@...gle.com>,
Juri Lelli <juri.lelli@...hat.com>,
Steve Muckle <smuckle@...gle.com>,
Eduardo Valentin <edubezval@...il.com>
Subject: [RFC PATCH v2 5/6] sched/fair: Select an energy-efficient CPU on task wake-up
From: Quentin Perret <quentin.perret@....com>
In case an energy model is available, waking tasks are re-routed into a
new energy-aware placement algorithm. The eligible CPUs to be used in the
energy-aware wakeup path are restricted to the highest non-overutilized
sched_domain containing prev_cpu and this_cpu. If no such domain is found,
the tasks go through the usual wake-up path, hence energy-aware placement
happens only in lightly utilized scenarios.
The selection of the most energy-efficient CPU for a task is achieved by
estimating the impact on system-level active energy resulting from the
placement of the task on the CPU with the highest spare capacity in each
frequency domain. The best CPU energy-wise is then selected if it saves
a large enough amount of energy with respect to prev_cpu.
Although it has already shown significant benefits on some existing
targets, this approach cannot scale to platforms with numerous CPUs.
This patch is an attempt to do something useful as writing a fast
heuristic that performs reasonably well on a broad spectrum of
architectures isn't an easy task. As a consequence, the scope of
usability of the energy-aware wake-up path is restricted to systems
with the SD_ASYM_CPUCAPACITY flag set. These systems not only show the
most promising opportunities for saving energy but also typically
feature a limited number of logical CPUs.
Moreover, the energy-aware wake-up path is accessible only if
sched_energy_enabled() is true. For systems which don't meet all
dependencies for EAS (CONFIG_PM_OPP for ex.) at compile time,
sched_enegy_enabled() defaults to a constant "false" value, hence letting
the compiler remove the unused EAS code entirely.
Cc: Ingo Molnar <mingo@...hat.com>
Cc: Peter Zijlstra <peterz@...radead.org>
Signed-off-by: Quentin Perret <quentin.perret@....com>
Signed-off-by: Dietmar Eggemann <dietmar.eggemann@....com>
---
kernel/sched/fair.c | 97 ++++++++++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 93 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 8cb9fb04fff2..5ebb2d0306c7 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6700,6 +6700,81 @@ static unsigned long compute_energy(struct task_struct *p, int dst_cpu)
return energy;
}
+static int find_energy_efficient_cpu(struct sched_domain *sd,
+ struct task_struct *p, int prev_cpu)
+{
+ unsigned long cur_energy, prev_energy, best_energy, cpu_cap;
+ unsigned long task_util = task_util_est(p);
+ int cpu, best_energy_cpu = prev_cpu;
+ struct freq_domain *fd;
+
+ if (!task_util)
+ return prev_cpu;
+
+ if (cpumask_test_cpu(prev_cpu, &p->cpus_allowed))
+ prev_energy = best_energy = compute_energy(p, prev_cpu);
+ else
+ prev_energy = best_energy = ULONG_MAX;
+
+ for_each_freq_domain(fd) {
+ unsigned long spare_cap, max_spare_cap = 0;
+ int max_spare_cap_cpu = -1;
+ unsigned long util;
+
+ /* Find the CPU with the max spare cap in the freq. dom. */
+ for_each_cpu_and(cpu, freq_domain_span(fd), sched_domain_span(sd)) {
+ if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ continue;
+
+ if (cpu == prev_cpu)
+ continue;
+
+ util = cpu_util_wake(cpu, p);
+ cpu_cap = capacity_of(cpu);
+ if (!util_fits_capacity(util + task_util, cpu_cap))
+ continue;
+
+ spare_cap = cpu_cap - util;
+ if (spare_cap > max_spare_cap) {
+ max_spare_cap = spare_cap;
+ max_spare_cap_cpu = cpu;
+ }
+ }
+
+ /* Evaluate the energy impact of using this CPU. */
+ if (max_spare_cap_cpu >= 0) {
+ cur_energy = compute_energy(p, max_spare_cap_cpu);
+ if (cur_energy < best_energy) {
+ best_energy = cur_energy;
+ best_energy_cpu = max_spare_cap_cpu;
+ }
+ }
+ }
+
+ /*
+ * We pick the best CPU only if it saves at least 1.5% of the
+ * energy used by prev_cpu.
+ */
+ if ((prev_energy - best_energy) > (prev_energy >> 6))
+ return best_energy_cpu;
+
+ return prev_cpu;
+}
+
+static inline bool wake_energy(struct task_struct *p, int prev_cpu)
+{
+ struct sched_domain *sd;
+
+ if (!sched_energy_enabled())
+ return false;
+
+ sd = rcu_dereference_sched(cpu_rq(prev_cpu)->sd);
+ if (!sd || sd_overutilized(sd))
+ return false;
+
+ return true;
+}
+
/*
* select_task_rq_fair: Select target runqueue for the waking task in domains
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
@@ -6716,18 +6791,22 @@ static int
select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_flags)
{
struct sched_domain *tmp, *affine_sd = NULL, *sd = NULL;
+ struct sched_domain *energy_sd = NULL;
int cpu = smp_processor_id();
int new_cpu = prev_cpu;
- int want_affine = 0;
+ int want_affine = 0, want_energy = 0;
int sync = (wake_flags & WF_SYNC) && !(current->flags & PF_EXITING);
+ rcu_read_lock();
+
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
+ want_energy = wake_energy(p, prev_cpu);
want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
- && cpumask_test_cpu(cpu, &p->cpus_allowed);
+ && cpumask_test_cpu(cpu, &p->cpus_allowed)
+ && !want_energy;
}
- rcu_read_lock();
for_each_domain(cpu, tmp) {
if (!(tmp->flags & SD_LOAD_BALANCE))
break;
@@ -6742,6 +6821,14 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
break;
}
+ /*
+ * Energy-aware task placement is performed on the highest
+ * non-overutilized domain spanning over cpu and prev_cpu.
+ */
+ if (want_energy && !sd_overutilized(tmp) &&
+ cpumask_test_cpu(prev_cpu, sched_domain_span(tmp)))
+ energy_sd = tmp;
+
if (tmp->flags & sd_flag)
sd = tmp;
else if (!want_affine)
@@ -6765,7 +6852,9 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
sync_entity_load_avg(&p->se);
}
- if (!sd) {
+ if (energy_sd) {
+ new_cpu = find_energy_efficient_cpu(energy_sd, p, prev_cpu);
+ } else if (!sd) {
pick_cpu:
if (sd_flag & SD_BALANCE_WAKE) { /* XXX always ? */
new_cpu = select_idle_sibling(p, prev_cpu, new_cpu);
--
2.11.0
Powered by blists - more mailing lists