[RFC PATCH 1/2] sched/fair: Introduce UTIL_FITS_CAPACITY feature
From: Mathieu Desnoyers
Date: Wed Oct 18 2023 - 16:45:16 EST
Introduce the UTIL_FITS_CAPACITY scheduler feature. The runqueue
selection picks the previous, target, or recent runqueues if they have
enough remaining capacity to enqueue the task before scanning for an
idle cpu.
This feature is introduced in preparation for the SELECT_BIAS_PREV
scheduler feature. Its performance benefits are noticeable when combined
with the SELECT_BIAS_PREV feature.
The following benchmarks only cover the UTIL_FITS_CAPACITY feature.
Those are performed on a v6.5.5 kernel with mitigations=off.
The following hackbench workload on a 192 cores AMD EPYC 9654 96-Core
Processor (over 2 sockets) keeps relatively the same wall time (49s).
hackbench -g 32 -f 20 --threads --pipe -l 480000 -s 100
We can observe that the number of migrations is reduced significantly
with this patch (improvement):
Baseline: 117M cpu-migrations (9.355 K/sec)
With patch: 67M cpu-migrations (5.470 K/sec)
The task-clock utilization is reduced (degradation):
Baseline: 253.275 CPUs utilized
With patch: 223.130 CPUs utilized
The number of context-switches is increased (degradation):
Baseline: 445M context-switches (35.516 K/sec)
With patch: 581M context-switches (47.548 K/sec)
So the improvement due to reduction of migrations is countered by the
degradation in CPU utilization and context-switches. The following
SELECT_BIAS_PREV feature will address this.
Link: https://lore.kernel.org/r/09e0f469-a3f7-62ef-75a1-e64cec2dcfc5@xxxxxxx
Link: https://lore.kernel.org/lkml/20230725193048.124796-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/20230810140635.75296-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/20230810140635.75296-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/f6dc1652-bc39-0b12-4b6b-29a2f9cd8484@xxxxxxx/
Link: https://lore.kernel.org/lkml/20230822113133.643238-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/20230823060832.454842-1-aaron.lu@xxxxxxxxx/
Link: https://lore.kernel.org/lkml/20230905171105.1005672-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/cover.1695704179.git.yu.c.chen@xxxxxxxxx/
Link: https://lore.kernel.org/lkml/20230929183350.239721-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/20231012203626.1298944-1-mathieu.desnoyers@xxxxxxxxxxxx/
Link: https://lore.kernel.org/lkml/20231017221204.1535774-1-mathieu.desnoyers@xxxxxxxxxxxx/
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@xxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Valentin Schneider <vschneid@xxxxxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Ben Segall <bsegall@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Cc: Daniel Bristot de Oliveira <bristot@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Swapnil Sapkal <Swapnil.Sapkal@xxxxxxx>
Cc: Aaron Lu <aaron.lu@xxxxxxxxx>
Cc: Chen Yu <yu.c.chen@xxxxxxxxx>
Cc: Tim Chen <tim.c.chen@xxxxxxxxx>
Cc: K Prateek Nayak <kprateek.nayak@xxxxxxx>
Cc: Gautham R . Shenoy <gautham.shenoy@xxxxxxx>
Cc: x86@xxxxxxxxxx
---
kernel/sched/fair.c | 49 ++++++++++++++++++++++++++++++++++++-----
kernel/sched/features.h | 6 +++++
kernel/sched/sched.h | 5 +++++
3 files changed, 54 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1d9c2482c5a3..8058058afb11 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4497,6 +4497,37 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
trace_sched_util_est_se_tp(&p->se);
}
+/*
+ * Returns true if adding the task utilization to the estimated
+ * utilization of the runnable tasks on @cpu does not exceed the
+ * capacity of @cpu.
+ *
+ * This considers only the utilization of _runnable_ tasks on the @cpu
+ * runqueue, excluding blocked and sleeping tasks. This is achieved by
+ * using the runqueue util_est.enqueued, and by estimating the capacity
+ * of @cpu based on arch_scale_cpu_capacity and arch_scale_thermal_pressure
+ * rather than capacity_of() because capacity_of() considers
+ * blocked/sleeping tasks in other scheduler classes.
+ *
+ * The utilization vs capacity comparison is done without the margin
+ * provided by fits_capacity(), because fits_capacity() is used to
+ * validate whether the utilization of a task fits within the overall
+ * capacity of a cpu, whereas this function validates whether the task
+ * utilization fits within the _remaining_ capacity of the cpu, which is
+ * more precise.
+ */
+static inline bool task_fits_remaining_cpu_capacity(unsigned long task_util,
+ int cpu)
+{
+ unsigned long total_util, capacity;
+
+ if (!sched_util_fits_capacity_active())
+ return false;
+ total_util = READ_ONCE(cpu_rq(cpu)->cfs.avg.util_est.enqueued) + task_util;
+ capacity = arch_scale_cpu_capacity(cpu) - arch_scale_thermal_pressure(cpu);
+ return total_util <= capacity;
+}
+
static inline int util_fits_cpu(unsigned long util,
unsigned long uclamp_min,
unsigned long uclamp_max,
@@ -7124,12 +7155,15 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
int i, recent_used_cpu;
/*
- * On asymmetric system, update task utilization because we will check
- * that the task fits with cpu's capacity.
+ * With the UTIL_FITS_CAPACITY feature and on asymmetric system,
+ * update task utilization because we will check that the task
+ * fits with cpu's capacity.
*/
- if (sched_asym_cpucap_active()) {
+ if (sched_util_fits_capacity_active() || sched_asym_cpucap_active()) {
sync_entity_load_avg(&p->se);
task_util = task_util_est(p);
+ }
+ if (sched_asym_cpucap_active()) {
util_min = uclamp_eff_value(p, UCLAMP_MIN);
util_max = uclamp_eff_value(p, UCLAMP_MAX);
}
@@ -7139,7 +7173,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
*/
lockdep_assert_irqs_disabled();
- if ((available_idle_cpu(target) || sched_idle_cpu(target)) &&
+ if ((available_idle_cpu(target) || sched_idle_cpu(target) ||
+ task_fits_remaining_cpu_capacity(task_util, target)) &&
asym_fits_cpu(task_util, util_min, util_max, target))
return target;
@@ -7147,7 +7182,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
* If the previous CPU is cache affine and idle, don't be stupid:
*/
if (prev != target && cpus_share_cache(prev, target) &&
- (available_idle_cpu(prev) || sched_idle_cpu(prev)) &&
+ (available_idle_cpu(prev) || sched_idle_cpu(prev) ||
+ task_fits_remaining_cpu_capacity(task_util, prev)) &&
asym_fits_cpu(task_util, util_min, util_max, prev))
return prev;
@@ -7173,7 +7209,8 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target)
if (recent_used_cpu != prev &&
recent_used_cpu != target &&
cpus_share_cache(recent_used_cpu, target) &&
- (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) &&
+ (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu) ||
+ task_fits_remaining_cpu_capacity(task_util, recent_used_cpu)) &&
cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) &&
asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) {
return recent_used_cpu;
diff --git a/kernel/sched/features.h b/kernel/sched/features.h
index ee7f23c76bd3..9a84a1401123 100644
--- a/kernel/sched/features.h
+++ b/kernel/sched/features.h
@@ -97,6 +97,12 @@ SCHED_FEAT(WA_BIAS, true)
SCHED_FEAT(UTIL_EST, true)
SCHED_FEAT(UTIL_EST_FASTUP, true)
+/*
+ * Select the previous, target, or recent runqueue if they have enough
+ * remaining capacity to enqueue the task. Requires UTIL_EST.
+ */
+SCHED_FEAT(UTIL_FITS_CAPACITY, true)
+
SCHED_FEAT(LATENCY_WARN, false)
SCHED_FEAT(ALT_PERIOD, true)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index e93e006a942b..463e75084aed 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2090,6 +2090,11 @@ static const_debug __maybe_unused unsigned int sysctl_sched_features =
#endif /* SCHED_DEBUG */
+static __always_inline bool sched_util_fits_capacity_active(void)
+{
+ return sched_feat(UTIL_EST) && sched_feat(UTIL_FITS_CAPACITY);
+}
+
extern struct static_key_false sched_numa_balancing;
extern struct static_key_false sched_schedstats;
--
2.39.2