sched: improve affine wakeups
improve affine wakeups. Maintain the 'overlap' metric based on CFS's
sum_exec_runtime - which means the amount of time a task executes
after it wakes up some other task.
Use the 'overlap' for the wakeup decisions: if the 'overlap' is short,
it means there's strong workload coupling between this task and the
woken up task. If the 'overlap' is large then the workload is decoupled
and the scheduler will move them to separate CPUs more easily.
( Also slightly move the preempt_check within try_to_wake_up() - this has
no effect on functionality but allows 'early wakeups' (for still-on-rq
tasks) to be correctly accounted as well.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 11d8e9a..3625fca 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -929,6 +929,9 @@
u64 vruntime;
u64 prev_sum_exec_runtime;
+ u64 last_wakeup;
+ u64 avg_overlap;
+
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
diff --git a/kernel/sched.c b/kernel/sched.c
index d1ad69b..adbd475 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1855,10 +1855,11 @@
schedstat_inc(p, se.nr_wakeups_remote);
update_rq_clock(rq);
activate_task(rq, p, 1);
- check_preempt_curr(rq, p);
success = 1;
out_running:
+ check_preempt_curr(rq, p);
+
p->state = TASK_RUNNING;
#ifdef CONFIG_SMP
if (p->sched_class->task_wake_up)
@@ -1892,6 +1893,8 @@
p->se.exec_start = 0;
p->se.sum_exec_runtime = 0;
p->se.prev_sum_exec_runtime = 0;
+ p->se.last_wakeup = 0;
+ p->se.avg_overlap = 0;
#ifdef CONFIG_SCHEDSTATS
p->se.wait_start = 0;
diff --git a/kernel/sched_debug.c b/kernel/sched_debug.c
index 4b5e24c..ef358ba 100644
--- a/kernel/sched_debug.c
+++ b/kernel/sched_debug.c
@@ -288,6 +288,7 @@
PN(se.exec_start);
PN(se.vruntime);
PN(se.sum_exec_runtime);
+ PN(se.avg_overlap);
nr_switches = p->nvcsw + p->nivcsw;
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index b5a3573..87c9d3a 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -556,6 +556,21 @@
account_entity_enqueue(cfs_rq, se);
}
+static void update_avg(u64 *avg, u64 sample)
+{
+ s64 diff = sample - *avg;
+ *avg += diff >> 3;
+}
+
+static void update_avg_stats(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (!se->last_wakeup)
+ return;
+
+ update_avg(&se->avg_overlap, se->sum_exec_runtime - se->last_wakeup);
+ se->last_wakeup = 0;
+}
+
static void
dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int sleep)
{
@@ -566,6 +581,7 @@
update_stats_dequeue(cfs_rq, se);
if (sleep) {
+ update_avg_stats(cfs_rq, se);
#ifdef CONFIG_SCHEDSTATS
if (entity_is_task(se)) {
struct task_struct *tsk = task_of(se);
@@ -981,12 +997,15 @@
#ifdef CONFIG_SMP
+static const struct sched_class fair_sched_class;
+
static int
-wake_affine(struct rq *rq, struct sched_domain *this_sd, struct task_struct *p,
- int prev_cpu, int this_cpu, int sync, int idx,
- unsigned long load, unsigned long this_load,
+wake_affine(struct rq *rq, struct sched_domain *this_sd, struct rq *this_rq,
+ struct task_struct *p, int prev_cpu, int this_cpu, int sync,
+ int idx, unsigned long load, unsigned long this_load,
unsigned int imbalance)
{
+ struct task_struct *curr = this_rq->curr;
unsigned long tl = this_load;
unsigned long tl_per_task;
@@ -994,10 +1013,15 @@
return 0;
/*
- * Attract cache-cold tasks on sync wakeups:
+ * If the currently running task will sleep within
+ * a reasonable amount of time then attract this newly
+ * woken task:
*/
- if (sync && !task_hot(p, rq->clock, this_sd))
- return 1;
+ if (sync && curr->sched_class == &fair_sched_class) {
+ if (curr->se.avg_overlap < sysctl_sched_migration_cost &&
+ p->se.avg_overlap < sysctl_sched_migration_cost)
+ return 1;
+ }
schedstat_inc(p, se.nr_wakeups_affine_attempts);
tl_per_task = cpu_avg_load_per_task(this_cpu);
@@ -1030,18 +1054,16 @@
struct sched_domain *sd, *this_sd = NULL;
int prev_cpu, this_cpu, new_cpu;
unsigned long load, this_load;
+ struct rq *rq, *this_rq;
unsigned int imbalance;
- struct rq *rq;
int idx;
prev_cpu = task_cpu(p);
rq = task_rq(p);
this_cpu = smp_processor_id();
+ this_rq = cpu_rq(this_cpu);
new_cpu = prev_cpu;
- if (prev_cpu == this_cpu)
- goto out;
-
/*
* 'this_sd' is the first domain that both
* this_cpu and prev_cpu are present in:
@@ -1069,11 +1091,12 @@
load = source_load(prev_cpu, idx);
this_load = target_load(this_cpu, idx);
- if (wake_affine(rq, this_sd, p, prev_cpu, this_cpu, sync, idx,
- load, this_load, imbalance)) {
- new_cpu = this_cpu;
+ if (wake_affine(rq, this_sd, this_rq, p, prev_cpu, this_cpu, sync, idx,
+ load, this_load, imbalance))
+ return this_cpu;
+
+ if (prev_cpu == this_cpu)
goto out;
- }
/*
* Start passive balancing when half the imbalance_pct
@@ -1083,8 +1106,7 @@
if (imbalance*this_load <= 100*load) {
schedstat_inc(this_sd, ttwu_move_balance);
schedstat_inc(p, se.nr_wakeups_passive);
- new_cpu = this_cpu;
- goto out;
+ return this_cpu;
}
}
@@ -1111,6 +1133,10 @@
return;
}
+ se->last_wakeup = se->sum_exec_runtime;
+ if (unlikely(se == pse))
+ return;
+
cfs_rq_of(pse)->next = pse;
/*