@@ -6384,6 +6384,137 @@ compute_energy(struct task_struct *p, int dst_cpu, struct perf_domain *pd)
return energy;
}
+/*
+ * find_energy_efficient_cpu(): Find most energy-efficient target CPU for the
+ * waking task. find_energy_efficient_cpu() looks for the CPU with maximum
+ * spare capacity in each performance domain and uses it as a potential
+ * candidate to execute the task. Then, it uses the Energy Model to figure
+ * out which of the CPU candidates is the most energy-efficient.
+ *
+ * The rationale for this heuristic is as follows. In a performance domain,
+ * all the most energy efficient CPU candidates (according to the Energy
+ * Model) are those for which we'll request a low frequency. When there are
+ * several CPUs for which the frequency request will be the same, we don't
+ * have enough data to break the tie between them, because the Energy Model
+ * only includes active power costs. With this model, if we assume that
+ * frequency requests follow utilization (e.g. using schedutil), the CPU with
+ * the maximum spare capacity in a performance domain is guaranteed to be among
+ * the best candidates of the performance domain.
+ *
+ * In practice, it could be preferable from an energy standpoint to pack
+ * small tasks on a CPU in order to let other CPUs go in deeper idle states,
+ * but that could also hurt our chances to go cluster idle, and we have no
+ * ways to tell with the current Energy Model if this is actually a good
+ * idea or not. So, find_energy_efficient_cpu() basically favors
+ * cluster-packing, and spreading inside a cluster. That should at least be
+ * a good thing for latency, and this is consistent with the idea that most
+ * of the energy savings of EAS come from the asymmetry of the system, and
+ * not so much from breaking the tie between identical CPUs. That's also the
+ * reason why EAS is enabled in the topology code only for systems where
+ * SD_ASYM_CPUCAPACITY is set.
+ *
+ * NOTE: Forkees are not accepted in the energy-aware wake-up path because
+ * they don't have any useful utilization data yet and it's not possible to
+ * forecast their impact on energy consumption. Consequently, they will be
+ * placed by find_idlest_cpu() on the least loaded CPU, which might turn out
+ * to be energy-inefficient in some use-cases. The alternative would be to
+ * bias new tasks towards specific types of CPUs first, or to try to infer
+ * their util_avg from the parent task, but those heuristics could hurt
+ * other use-cases too. So, until someone finds a better way to solve this,
+ * let's keep things simple by re-using the existing slow path.
+ */
+
+static int find_energy_efficient_cpu(struct task_struct *p, int prev_cpu)
+{
+ unsigned long prev_energy = ULONG_MAX, best_energy = ULONG_MAX;
+ struct root_domain *rd = cpu_rq(smp_processor_id())->rd;
+ int cpu, best_energy_cpu = prev_cpu;
+ struct perf_domain *head, *pd;
+ unsigned long cpu_cap, util;
+ struct sched_domain *sd;
+
+ rcu_read_lock();
+ pd = rcu_dereference(rd->pd);
+ if (!pd || READ_ONCE(rd->overutilized))
+ goto fail;
+ head = pd;
+
+ /*
+ * Energy-aware wake-up happens on the lowest sched_domain starting
+ * from sd_asym_cpucapacity spanning over this_cpu and prev_cpu.
+ */
+ sd = rcu_dereference(*this_cpu_ptr(&sd_asym_cpucapacity));
+ while (sd && !cpumask_test_cpu(prev_cpu, sched_domain_span(sd)))
+ sd = sd->parent;
+ if (!sd)
+ goto fail;
+
+ sync_entity_load_avg(&p->se);
+ if (!task_util_est(p))
+ goto unlock;
+
+ for (; pd; pd = pd->next) {
+ unsigned long cur_energy, spare_cap, max_spare_cap = 0;
+ int max_spare_cap_cpu = -1;
+
+ for_each_cpu_and(cpu, perf_domain_span(pd), sched_domain_span(sd)) {
+ if (!cpumask_test_cpu(cpu, &p->cpus_allowed))
+ continue;
+
+ /* Skip CPUs that will be overutilized. */
+ util = cpu_util_next(cpu, p, cpu);
+ cpu_cap = capacity_of(cpu);
+ if (cpu_cap * 1024 < util * capacity_margin)
+ continue;
+
+ /* Always use prev_cpu as a candidate. */
+ if (cpu == prev_cpu) {
+ prev_energy = compute_energy(p, prev_cpu, head);
+ best_energy = min(best_energy, prev_energy);
+ continue;
+ }
+
+ /*
+ * Find the CPU with the maximum spare capacity in
+ * the performance domain
+ */
+ 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, head);
+ if (cur_energy < best_energy) {
+ best_energy = cur_energy;
+ best_energy_cpu = max_spare_cap_cpu;
+ }
+ }
+ }
+unlock:
+ rcu_read_unlock();
+
+ /*
+ * Pick the best CPU if prev_cpu cannot be used, or if it saves at
+ * least 6% of the energy used by prev_cpu.
+ */
+ if (prev_energy == ULONG_MAX)
+ return best_energy_cpu;
+
+ if ((prev_energy - best_energy) > (prev_energy >> 4))
+ return best_energy_cpu;
+
+ return prev_cpu;
+
+fail:
+ rcu_read_unlock();
+
+ return -1;
+}
+
/*
* 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,
@@ -6407,8 +6538,16 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
if (sd_flag & SD_BALANCE_WAKE) {
record_wakee(p);
- want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
- && cpumask_test_cpu(cpu, &p->cpus_allowed);
+
+ if (static_branch_unlikely(&sched_energy_present)) {
+ new_cpu = find_energy_efficient_cpu(p, prev_cpu);
+ if (new_cpu >= 0)
+ return new_cpu;
+ new_cpu = prev_cpu;
+ }
+
+ want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu) &&
+ cpumask_test_cpu(cpu, &p->cpus_allowed);
}
rcu_read_lock();
If an Energy Model (EM) is available and if the system isn't overutilized, re-route waking tasks into an energy-aware placement algorithm. The selection of an 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 performance domain. This strategy spreads tasks in a performance domain and avoids overly aggressive task packing. 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 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 such, the scope of usability of the energy-aware wake-up path is restricted to systems with the SD_ASYM_CPUCAPACITY flag set, and where the EM isn't too complex. Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Quentin Perret <quentin.perret@arm.com> --- kernel/sched/fair.c | 143 +++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 141 insertions(+), 2 deletions(-)