@@ -544,6 +544,7 @@ struct sched_entity {
unsigned int on_rq;
u64 exec_start;
+ u64 delta_exec;
u64 sum_exec_runtime;
u64 prev_sum_exec_runtime;
u64 vruntime;
@@ -4318,6 +4318,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
p->se.on_rq = 0;
p->se.exec_start = 0;
+ p->se.delta_exec = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
p->se.nr_migrations = 0;
@@ -1118,6 +1118,7 @@ static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
curr->exec_start = now;
curr->sum_exec_runtime += delta_exec;
+ curr->delta_exec = delta_exec;
if (schedstat_enabled()) {
struct sched_statistics *stats;
@@ -1126,7 +1127,6 @@ static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
__schedstat_set(stats->exec_max,
max(delta_exec, stats->exec_max));
}
-
return delta_exec;
}
@@ -4890,16 +4890,20 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
if (!sched_feat(UTIL_EST))
return;
- /*
- * Skip update of task's estimated utilization when the task has not
- * yet completed an activation, e.g. being migrated.
- */
- if (!task_sleep)
- return;
-
/* Get current estimate of utilization */
ewma = READ_ONCE(p->se.avg.util_est);
+ /*
+ * If a task is running, update util_est ignoring utilization
+ * invariance so that if the task suddenly becomes busy we will rampup
+ * quickly to settle down to our new util_avg.
+ */
+ if (!task_sleep) {
+ ewma &= ~UTIL_AVG_UNCHANGED;
+ ewma = approximate_util_avg(ewma, p->se.delta_exec / 1000);
+ goto done;
+ }
+
/*
* If the PELT values haven't changed since enqueue time,
* skip the util_est update.
@@ -4968,6 +4972,14 @@ static inline void util_est_update(struct cfs_rq *cfs_rq,
trace_sched_util_est_se_tp(&p->se);
}
+static inline void util_est_update_running(struct cfs_rq *cfs_rq,
+ struct task_struct *p)
+{
+ util_est_dequeue(cfs_rq, p);
+ util_est_update(cfs_rq, p, false);
+ util_est_enqueue(cfs_rq, p);
+}
+
static inline unsigned long get_actual_cpu_capacity(int cpu)
{
unsigned long capacity = arch_scale_cpu_capacity(cpu);
@@ -5164,13 +5176,13 @@ static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf)
static inline void
util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
-
static inline void
util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
-
static inline void
-util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p,
- bool task_sleep) {}
+util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep) {}
+static inline void
+util_est_update_running(struct cfs_rq *cfs_rq, struct task_struct *p) {}
+
static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
#endif /* CONFIG_SMP */
@@ -6906,6 +6918,8 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
rq->next_balance = jiffies;
dequeue_throttle:
+ if (task_sleep)
+ p->se.delta_exec = 0;
util_est_update(&rq->cfs, p, task_sleep);
hrtick_update(rq);
}
@@ -8546,6 +8560,9 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
set_next_entity(cfs_rq, se);
}
+ if (prev->on_rq)
+ util_est_update_running(&rq->cfs, prev);
+
goto done;
simple:
#endif
@@ -12710,6 +12727,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
entity_tick(cfs_rq, se, queued);
}
+ util_est_update_running(&rq->cfs, curr);
+
if (static_branch_unlikely(&sched_numa_balancing))
task_tick_numa(rq, curr);
Utilization invariance can cause big delays. When tasks are running, accumulate non-invairiant version of utilization to help tasks to settle down to their new util_avg values faster. Keep track of delta_exec during runnable across activations to help update util_est for a long running task accurately. util_est shoudl still behave the same at enqueue/dequeue. Before this patch the a busy task tamping up would experience the following transitions, running on M1 Mac Mini rampup-6338 util_avg running ┌─────────────────────────────────────────────────────────────────────────┐ 986.0┤ ▄▄▄▄▄▟▀▀▀▀│ │ ▗▄▄▟▀▀▀▘ │ │ ▗▄▟▀▀ │ │ ▄▟▀▀ │ 739.5┤ ▄▟▀▘ │ │ ▗▄▛▘ │ │ ▗▟▀ │ 493.0┤ ▗▛▀ │ │ ▗▄▛▀ │ │ ▄▟▀ │ │ ▄▛▘ │ 246.5┤ ▗▟▀▘ │ │ ▄▟▀▀ │ │ ▗▄▄▛▘ │ │ ▗▄▄▄▟▀ │ 0.0┤ ▗ ▗▄▄▟▀▀ │ └┬───────┬───────┬───────┬───────┬───────┬───────┬───────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 ───────────────── rampup-6338 util_avg running residency (ms) ────────────────── 0.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.5 15.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 7.9 36.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 8.0 57.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 8.0 78.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 7.9 98.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.0 117.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.0 137.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.0 156.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 4.0 176.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 191.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 4.0 211.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 4.0 230.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 248.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 266.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 277.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 294.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.6 311.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.4 327.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 340.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 358.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 371.0 ▇▇▇▇▇▇▇▇▇ 1.0 377.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 389.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 401.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 413.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 431.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 442.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 456.0 ▇▇▇▇▇▇▇▇▇ 1.0 ───────────────────────── Sum Time Running on CPU (ms) ───────────────────────── CPU0.0 ▇▇▇▇▇ 90.39 CPU4.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 1156.93 6338 rampup CPU0.0 Frequency ┌──────────────────────────────────────────────────────────────────────────┐ 2.06┤ ▛▀▀ │ │ ▌ │ │ ▌ │ │ ▌ │ 1.70┤ ▛▀▀▘ │ │ ▌ │ │ ▌ │ 1.33┤ ▗▄▄▄▌ │ │ ▐ │ │ ▐ │ │ ▐ │ 0.97┤ ▗▄▄▄▟ │ │ ▐ │ │ ▐ │ │ ▐ │ 0.60┤ ▗ ▗▄▄▄▄▄▄▄▄▟ │ └┬───────┬───────┬───────┬───────┬────────┬───────┬───────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 6338 rampup CPU4.0 Frequency ┌──────────────────────────────────────────────────────────────────────────┐ 3.20┤ ▐▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀▀│ │ ▐ │ │ ▛▀▀ │ │ ▌ │ 2.78┤ ▐▀▀▘ │ │ ▗▄▟ │ │ ▌ │ 2.35┤ ▗▄▄▌ │ │ ▐ │ │ ▄▄▟ │ │ ▌ │ 1.93┤ ▗▄▄▌ │ │ ▐ │ │ ▐ │ │ ▐ │ 1.50┤ ▗▄▄▟ │ └┬───────┬───────┬───────┬───────┬────────┬───────┬───────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 ───────────────── 6338 rampup CPU0.0 Frequency residency (ms) ────────────────── 0.6 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 37.300000000000004 0.972 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 15.0 1.332 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 15.0 1.704 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 11.0 2.064 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 12.1 ───────────────── 6338 rampup CPU4.0 Frequency residency (ms) ────────────────── 1.5 ▇▇▇▇▇▇▇▇▇▇ 11.9 1.956 ▇▇▇▇▇▇▇▇ 10.0 2.184 ▇▇▇▇▇▇▇▇ 10.0 2.388 ▇▇▇▇▇▇▇▇▇ 11.0 2.592 ▇▇▇▇▇▇▇▇ 10.0 2.772 ▇▇▇▇▇▇▇▇ 10.0 2.988 ▇▇▇▇▇▇▇▇ 10.0 3.204 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 85.3 After the patch the response is improved to rampup frequencies faster and migrate from little quicker rampup-2234 util_avg running ┌───────────────────────────────────────────────────────────────────────────┐ 984┤ ▗▄▄▄▄▄▛▀▀▀▀│ │ ▄▄▟▀▀▀▀ │ │ ▄▄▟▀▀ │ │ ▄▟▀▘ │ 738┤ ▄▟▀▘ │ │ ▗▟▀▘ │ │ ▗▟▀ │ 492┤ ▗▟▀ │ │ ▗▟▀ │ │ ▟▀ │ │ ▄▛▘ │ 246┤ ▗▟▘ │ │ ▗▟▀ │ │ ▗▟▀ │ │ ▗▟▀ │ 0┤ ▄▄▄▛▀ │ └┬───────┬───────┬────────┬───────┬───────┬───────┬────────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 ───────────────── rampup-2234 util_avg running residency (ms) ────────────────── 0.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.6000000000000005 15.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 8.0 39.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.0 61.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 4.0 85.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 99.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 120.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.0 144.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 160.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 176.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 192.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 210.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 228.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 246.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 263.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 282.0 ▇▇▇▇▇▇▇ 1.0 291.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 309.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 327.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 344.0 ▇▇▇▇▇▇▇ 1.0 354.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 373.0 ▇▇▇▇▇▇▇ 1.0 382.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 400.0 ▇▇▇▇▇▇▇ 1.0 408.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 425.0 ▇▇▇▇▇▇▇ 1.0 434.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 2.0 452.0 ▇▇▇▇▇▇▇ 1.0 2234 rampup CPU1.0 Frequency ┌──────────────────────────────────────────────────────────────────────────┐ 2.06┤ ▐▀ │ │ ▐ │ │ ▐ │ │ ▐ │ 1.70┤ ▛▀ │ │ ▌ │ │ ▌ │ 1.33┤ ▄▌ │ │ ▌ │ │ ▌ │ │ ▌ │ 0.97┤ ▗▄▌ │ │ ▐ │ │ ▐ │ │ ▐ │ 0.60┤ ▗▄▄▟ │ └┬───────┬───────┬───────┬───────┬────────┬───────┬───────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 2234 rampup CPU4.0 Frequency ┌──────────────────────────────────────────────────────────────────────────┐ 3.10┤ ▐▀▀▀▀▀▀▀▀▀▀▀▀▀│ │ ▛▀▀▀▀▀▀▀▀▀▀▀ │ │ ▌ │ │ ▐▀▀▀▀▘ │ 2.70┤ ▐ │ │ ▐▀▀▀▀ │ │ ▐ │ 2.30┤ ▛▀▀ │ │ ▌ │ │ ▐▀▀▘ │ │ ▐ │ 1.90┤ ▐▀▀ │ │ ▐ │ │ ▗▄▟ │ │ ▐ │ 1.50┤ ▗▟ │ └┬───────┬───────┬───────┬───────┬────────┬───────┬───────┬───────┬───────┬┘ 1.700 1.733 1.767 1.800 1.833 1.867 1.900 1.933 1.967 2.000 ───────────────────────── Sum Time Running on CPU (ms) ───────────────────────── CPU1.0 ▇▇▇▇ 32.53 CPU4.0 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 540.3 ───────────────── 2234 rampup CPU1.0 Frequency residency (ms) ────────────────── 0.6 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 12.1 0.972 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 6.5 1.332 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 3.7 1.704 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 5.5 2.064 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 4.8 ───────────────── 2234 rampup CPU4.0 Frequency residency (ms) ────────────────── 1.5 ▇▇▇▇▇ 4.0 1.728 ▇▇▇▇▇▇▇▇▇▇ 8.0 1.956 ▇▇▇▇▇▇▇▇▇▇▇▇ 9.0 2.184 ▇▇▇▇▇▇▇▇▇▇▇▇ 9.0 2.388 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 11.0 2.592 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 16.0 2.772 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 18.0 2.988 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 47.0 3.096 ▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 53.4 Signed-off-by: Qais Yousef <qyousef@layalina.io> --- include/linux/sched.h | 1 + kernel/sched/core.c | 1 + kernel/sched/fair.c | 43 +++++++++++++++++++++++++++++++------------ 3 files changed, 33 insertions(+), 12 deletions(-)