se->avg.last_update_time = n_last_update_time;
}
-
/*
* When on migration a sched_entity joins/leaves the PELT hierarchy, we need to
* propagate its contribution. The key to this propagation is the invariant
* XXX: only do this for the part of runnable > running ?
*
*/
-
static inline void
update_tg_cfs_util(struct cfs_rq *cfs_rq, struct sched_entity *se, struct cfs_rq *gcfs_rq)
{
r = removed_util;
sub_positive(&sa->util_avg, r);
- sa->util_sum = sa->util_avg * divider;
+ sub_positive(&sa->util_sum, r * divider);
+ /*
+ * Because of rounding, se->util_sum might ends up being +1 more than
+ * cfs->util_sum. Although this is not a problem by itself, detaching
+ * a lot of tasks with the rounding problem between 2 updates of
+ * util_avg (~1ms) can make cfs->util_sum becoming null whereas
+ * cfs_util_avg is not.
+ * Check that util_sum is still above its lower bound for the new
+ * util_avg. Given that period_contrib might have moved since the last
+ * sync, we are only sure that util_sum must be above or equal to
+ * util_avg * minimum possible divider
+ */
+ sa->util_sum = max_t(u32, sa->util_sum, sa->util_avg * PELT_MIN_DIVIDER);
r = removed_runnable;
sub_positive(&sa->runnable_avg, r);
se->avg.runnable_sum = se->avg.runnable_avg * divider;
- se->avg.load_sum = divider;
- if (se_weight(se)) {
- se->avg.load_sum =
- div_u64(se->avg.load_avg * se->avg.load_sum, se_weight(se));
- }
+ se->avg.load_sum = se->avg.load_avg * divider;
+ if (se_weight(se) < se->avg.load_sum)
+ se->avg.load_sum = div_u64(se->avg.load_sum, se_weight(se));
+ else
+ se->avg.load_sum = 1;
enqueue_load_avg(cfs_rq, se);
cfs_rq->avg.util_avg += se->avg.util_avg;
ideal_runtime = sched_slice(cfs_rq, curr);
delta_exec = curr->sum_exec_runtime - curr->prev_sum_exec_runtime;
if (delta_exec > ideal_runtime) {
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
/*
* The current task ran long enough, ensure it doesn't get
* re-elected due to buddy favours.
return;
if (delta > ideal_runtime)
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
}
static void
* validating it and just reschedule.
*/
if (queued) {
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
return;
}
/*
* hierarchy can be throttled
*/
if (!assign_cfs_rq_runtime(cfs_rq) && likely(cfs_rq->curr))
- resched_curr(rq_of(cfs_rq));
+ resched_curr_lazy(rq_of(cfs_rq));
}
static __always_inline
cfs_rq->throttle_count--;
if (!cfs_rq->throttle_count) {
- cfs_rq->throttled_clock_task_time += rq_clock_task(rq) -
- cfs_rq->throttled_clock_task;
+ cfs_rq->throttled_clock_pelt_time += rq_clock_pelt(rq) -
+ cfs_rq->throttled_clock_pelt;
/* Add cfs_rq with load or one or more already running entities to the list */
if (!cfs_rq_is_decayed(cfs_rq) || cfs_rq->nr_running)
/* group is entering throttled state, stop time */
if (!cfs_rq->throttle_count) {
- cfs_rq->throttled_clock_task = rq_clock_task(rq);
+ cfs_rq->throttled_clock_pelt = rq_clock_pelt(rq);
list_del_leaf_cfs_rq(cfs_rq);
}
cfs_rq->throttle_count++;
pcfs_rq = tg->parent->cfs_rq[cpu];
cfs_rq->throttle_count = pcfs_rq->throttle_count;
- cfs_rq->throttled_clock_task = rq_clock_task(cpu_rq(cpu));
+ cfs_rq->throttled_clock_pelt = rq_clock_pelt(cpu_rq(cpu));
}
/* conditionally throttle active cfs_rq's from put_prev_entity() */
if (delta < 0) {
if (task_current(rq, p))
- resched_curr(rq);
+ resched_curr_lazy(rq);
return;
}
hrtick_start(rq, delta);
{
struct cpumask *cpus = this_cpu_cpumask_var_ptr(select_idle_mask);
int i, cpu, idle_cpu = -1, nr = INT_MAX;
+ struct sched_domain_shared *sd_share;
struct rq *this_rq = this_rq();
int this = smp_processor_id();
struct sched_domain *this_sd;
time = cpu_clock(this);
}
+ if (sched_feat(SIS_UTIL)) {
+ sd_share = rcu_dereference(per_cpu(sd_llc_shared, target));
+ if (sd_share) {
+ /* because !--nr is the condition to stop scan */
+ nr = READ_ONCE(sd_share->nr_idle_scan) + 1;
+ /* overloaded LLC is unlikely to have idle cpu/core */
+ if (nr == 1)
+ return -1;
+ }
+ }
+
for_each_cpu_wrap(cpu, cpus, target + 1) {
if (has_idle_core) {
i = select_idle_core(p, cpu, cpus, &idle_cpu);
* pattern is IO completions.
*/
if (is_per_cpu_kthread(current) &&
+ in_task() &&
prev == smp_processor_id() &&
- this_rq()->nr_running <= 1) {
+ this_rq()->nr_running <= 1 &&
+ asym_fits_capacity(task_util, prev)) {
return prev;
}
return;
preempt:
- resched_curr(rq);
+ resched_curr_lazy(rq);
/*
* Only set the backward buddy when the current task is still
* on the rq. This can happen when a wakeup gets interleaved
* This is an approximation as the number of running tasks may not be
* related to the number of busy CPUs due to sched_setaffinity.
*/
-static inline bool allow_numa_imbalance(int dst_running, int dst_weight)
+static inline bool
+allow_numa_imbalance(unsigned int running, unsigned int weight)
{
- return (dst_running < (dst_weight >> 2));
+ return (running < (weight >> 2));
}
/*
return idlest;
#endif
/*
- * Otherwise, keep the task on this node to stay close
- * its wakeup source and improve locality. If there is
- * a real need of migration, periodic load balance will
- * take care of it.
+ * Otherwise, keep the task close to the wakeup source
+ * and improve locality if the number of running tasks
+ * would remain below threshold where an imbalance is
+ * allowed. If there is a real need of migration,
+ * periodic load balance will take care of it.
*/
- if (allow_numa_imbalance(local_sgs.sum_nr_running, sd->span_weight))
+ if (allow_numa_imbalance(local_sgs.sum_nr_running + 1, local_sgs.group_weight))
return NULL;
}
return idlest;
}
+static void update_idle_cpu_scan(struct lb_env *env,
+ unsigned long sum_util)
+{
+ struct sched_domain_shared *sd_share;
+ int llc_weight, pct;
+ u64 x, y, tmp;
+ /*
+ * Update the number of CPUs to scan in LLC domain, which could
+ * be used as a hint in select_idle_cpu(). The update of sd_share
+ * could be expensive because it is within a shared cache line.
+ * So the write of this hint only occurs during periodic load
+ * balancing, rather than CPU_NEWLY_IDLE, because the latter
+ * can fire way more frequently than the former.
+ */
+ if (!sched_feat(SIS_UTIL) || env->idle == CPU_NEWLY_IDLE)
+ return;
+
+ llc_weight = per_cpu(sd_llc_size, env->dst_cpu);
+ if (env->sd->span_weight != llc_weight)
+ return;
+
+ sd_share = rcu_dereference(per_cpu(sd_llc_shared, env->dst_cpu));
+ if (!sd_share)
+ return;
+
+ /*
+ * The number of CPUs to search drops as sum_util increases, when
+ * sum_util hits 85% or above, the scan stops.
+ * The reason to choose 85% as the threshold is because this is the
+ * imbalance_pct(117) when a LLC sched group is overloaded.
+ *
+ * let y = SCHED_CAPACITY_SCALE - p * x^2 [1]
+ * and y'= y / SCHED_CAPACITY_SCALE
+ *
+ * x is the ratio of sum_util compared to the CPU capacity:
+ * x = sum_util / (llc_weight * SCHED_CAPACITY_SCALE)
+ * y' is the ratio of CPUs to be scanned in the LLC domain,
+ * and the number of CPUs to scan is calculated by:
+ *
+ * nr_scan = llc_weight * y' [2]
+ *
+ * When x hits the threshold of overloaded, AKA, when
+ * x = 100 / pct, y drops to 0. According to [1],
+ * p should be SCHED_CAPACITY_SCALE * pct^2 / 10000
+ *
+ * Scale x by SCHED_CAPACITY_SCALE:
+ * x' = sum_util / llc_weight; [3]
+ *
+ * and finally [1] becomes:
+ * y = SCHED_CAPACITY_SCALE -
+ * x'^2 * pct^2 / (10000 * SCHED_CAPACITY_SCALE) [4]
+ *
+ */
+ /* equation [3] */
+ x = sum_util;
+ do_div(x, llc_weight);
+
+ /* equation [4] */
+ pct = env->sd->imbalance_pct;
+ tmp = x * x * pct * pct;
+ do_div(tmp, 10000 * SCHED_CAPACITY_SCALE);
+ tmp = min_t(long, tmp, SCHED_CAPACITY_SCALE);
+ y = SCHED_CAPACITY_SCALE - tmp;
+
+ /* equation [2] */
+ y *= llc_weight;
+ do_div(y, SCHED_CAPACITY_SCALE);
+ if ((int)y != sd_share->nr_idle_scan)
+ WRITE_ONCE(sd_share->nr_idle_scan, (int)y);
+}
+
/**
* update_sd_lb_stats - Update sched_domain's statistics for load balancing.
* @env: The load balancing environment.
struct sched_group *sg = env->sd->groups;
struct sg_lb_stats *local = &sds->local_stat;
struct sg_lb_stats tmp_sgs;
+ unsigned long sum_util = 0;
int sg_status = 0;
do {
sds->total_load += sgs->group_load;
sds->total_capacity += sgs->group_capacity;
+ sum_util += sgs->group_util;
sg = sg->next;
} while (sg != env->sd->groups);
WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
}
+
+ update_idle_cpu_scan(env, sum_util);
}
#define NUMA_IMBALANCE_MIN 2
/* Consider allowing a small imbalance between NUMA groups */
if (env->sd->flags & SD_NUMA) {
env->imbalance = adjust_numa_imbalance(env->imbalance,
- busiest->sum_nr_running, busiest->group_weight);
+ local->sum_nr_running + 1, local->group_weight);
}
return;
* 'current' within the tree based on its new key value.
*/
swap(curr->vruntime, se->vruntime);
- resched_curr(rq);
+ resched_curr_lazy(rq);
}
se->vruntime -= cfs_rq->min_vruntime;
*/
if (task_current(rq, p)) {
if (p->prio > oldprio)
- resched_curr(rq);
+ resched_curr_lazy(rq);
} else
check_preempt_curr(rq, p, 0);
}
{
int i;
- destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
-
for_each_possible_cpu(i) {
if (tg->cfs_rq)
kfree(tg->cfs_rq[i]);
struct rq *rq;
int cpu;
+ destroy_cfs_bandwidth(tg_cfs_bandwidth(tg));
+
for_each_possible_cpu(cpu) {
if (tg->se[cpu])
remove_entity_load_avg(tg->se[cpu]);