[PATCH v3 8/8] sched/fair: Add latency list

From: Vincent Guittot
Date: Fri Sep 09 2022 - 09:04:55 EST

Add a rb tree for latency sensitive entities so we can schedule the most
sensitive one first even when it failed to preempt current at wakeup or
when it got quickly preempted by another entity of higher priority.

In order to keep fairness, the latency is used once at wakeup to get a
minimum slice and not during the following scheduling slice to prevent
long running entity to got more running time than allocated to his nice
priority.

The rb tree nebales to cover the last corner case where latency
sensitive entity can't got schedule quickly after the wakeup.

hackbench -l 10000 -g $group &
cyclictest --policy other -D 5 -q -n
latency 0 latency -20
group min avg max min avg max
0 17 19 29 17 18 30
1 65 306 7149 64 83 208
4 50 395 15731 56 80 271
8 56 781 41548 54 80 301
16 60 1392 87237 59 86 490

group = 0 means that hackbench is not running.

Both avg and max are significantly improved with nice latency -20. If we
add the histogram parameters to get details of latency, we have :

hackbench -l 10000 -g 16 &
cyclictest --policy other -D 5 -q -n -H 20000 --histfile data.txt
latency 0 latency -20
Min Latencies: 60 61
Avg Latencies: 1077 86
Max Latencies: 87311 444
50% latencies: 92 85
75% latencies: 554 90
85% latencies: 1019 93
90% latencies: 1346 96
95% latencies: 5400 100
99% latencies: 19044 110

Signed-off-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
---
include/linux/sched.h | 2 +
kernel/sched/fair.c | 96 +++++++++++++++++++++++++++++++++++++++++--
kernel/sched/sched.h | 1 +
3 files changed, 96 insertions(+), 3 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 2d2a361d65ee..8b7bf0cb4ee9 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -537,6 +537,8 @@ struct sched_entity {
/* For load-balancing: */
struct load_weight load;
struct rb_node run_node;
+ struct rb_node latency_node;
+ unsigned int on_latency;
struct list_head group_node;
unsigned int on_rq;

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 7563fb16aba1..58657cafaa9b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -664,7 +664,77 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)

return __node_2_se(last);
}
+#endif

+/**************************************************************
+ * Scheduling class tree data structure manipulation methods:
+ * for latency
+ */
+
+static inline bool latency_before(struct sched_entity *a,
+ struct sched_entity *b)
+{
+ return (s64)(a->vruntime + a->latency_offset - b->vruntime - b->latency_offset) < 0;
+}
+
+#define __latency_node_2_se(node) \
+ rb_entry((node), struct sched_entity, latency_node)
+
+static inline bool __latency_less(struct rb_node *a, const struct rb_node *b)
+{
+ return latency_before(__latency_node_2_se(a), __latency_node_2_se(b));
+}
+
+/*
+ * Enqueue an entity into the latency rb-tree:
+ */
+static void __enqueue_latency(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
+{
+
+ /* Only latency sensitive entity can be added to the list */
+ if (se->latency_offset >= 0)
+ return;
+
+ if (se->on_latency)
+ return;
+
+ /*
+ * An execution time less than sysctl_sched_min_granularity means that
+ * the entity has been preempted by a higher sched class or an entity
+ * with higher latency constraint.
+ * Put it back in the list so it gets a chance to run 1st during the
+ * next slice.
+ */
+ if (!(flags & ENQUEUE_WAKEUP)) {
+ u64 delta_exec = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+
+ if (delta_exec >= sysctl_sched_min_granularity)
+ return;
+ }
+
+ rb_add_cached(&se->latency_node, &cfs_rq->latency_timeline, __latency_less);
+ se->on_latency = 1;
+}
+
+static void __dequeue_latency(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ if (se->on_latency) {
+ rb_erase_cached(&se->latency_node, &cfs_rq->latency_timeline);
+ se->on_latency = 0;
+ }
+}
+
+struct sched_entity *__pick_first_latency(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *left = rb_first_cached(&cfs_rq->latency_timeline);
+
+ if (!left)
+ return NULL;
+
+ return __latency_node_2_se(left);
+}
+
+#ifdef CONFIG_SCHED_DEBUG
/**************************************************************
* Scheduling class statistics methods:
*/
@@ -4455,8 +4525,10 @@ enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)
check_schedstat_required();
update_stats_enqueue_fair(cfs_rq, se, flags);
check_spread(cfs_rq, se);
- if (!curr)
+ if (!curr) {
__enqueue_entity(cfs_rq, se);
+ __enqueue_latency(cfs_rq, se, flags);
+ }
se->on_rq = 1;

if (cfs_rq->nr_running == 1) {
@@ -4542,8 +4614,10 @@ dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags)

clear_buddies(cfs_rq, se);

- if (se != cfs_rq->curr)
+ if (se != cfs_rq->curr) {
__dequeue_entity(cfs_rq, se);
+ __dequeue_latency(cfs_rq, se);
+ }
se->on_rq = 0;
account_entity_dequeue(cfs_rq, se);

@@ -4631,6 +4705,7 @@ set_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
*/
update_stats_wait_end_fair(cfs_rq, se);
__dequeue_entity(cfs_rq, se);
+ __dequeue_latency(cfs_rq, se);
update_load_avg(cfs_rq, se, UPDATE_TG);
}

@@ -4669,7 +4744,7 @@ static struct sched_entity *
pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
{
struct sched_entity *left = __pick_first_entity(cfs_rq);
- struct sched_entity *se;
+ struct sched_entity *latency, *se;

/*
* If curr is set we have to see if its left of the leftmost entity
@@ -4711,6 +4786,12 @@ pick_next_entity(struct cfs_rq *cfs_rq, struct sched_entity *curr)
se = cfs_rq->last;
}

+ /* Check for latency sensitive entity waiting for running */
+ latency = __pick_first_latency(cfs_rq);
+ if (latency && (latency != se) &&
+ wakeup_preempt_entity(latency, se) < 1)
+ se = latency;
+
return se;
}

@@ -4734,6 +4815,7 @@ static void put_prev_entity(struct cfs_rq *cfs_rq, struct sched_entity *prev)
update_stats_wait_start_fair(cfs_rq, prev);
/* Put 'current' back into the tree. */
__enqueue_entity(cfs_rq, prev);
+ __enqueue_latency(cfs_rq, prev, 0);
/* in !on_rq case, update occurred at dequeue */
update_load_avg(cfs_rq, prev, 0);
}
@@ -11718,6 +11800,7 @@ static void set_next_task_fair(struct rq *rq, struct task_struct *p, bool first)
void init_cfs_rq(struct cfs_rq *cfs_rq)
{
cfs_rq->tasks_timeline = RB_ROOT_CACHED;
+ cfs_rq->latency_timeline = RB_ROOT_CACHED;
u64_u32_store(cfs_rq->min_vruntime, (u64)(-(1LL << 20)));
#ifdef CONFIG_SMP
raw_spin_lock_init(&cfs_rq->removed.lock);
@@ -12026,8 +12109,15 @@ int sched_group_set_latency(struct task_group *tg, long latency)

for_each_possible_cpu(i) {
struct sched_entity *se = tg->se[i];
+ struct rq *rq = cpu_rq(i);
+ struct rq_flags rf;
+
+ rq_lock_irqsave(rq, &rf);

+ __dequeue_latency(se->cfs_rq, se);
WRITE_ONCE(se->latency_offset, latency);
+
+ rq_unlock_irqrestore(rq, &rf);
}

mutex_unlock(&shares_mutex);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 117b23dfb912..294a4a39f3eb 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -597,6 +597,7 @@ struct cfs_rq {
#endif

struct rb_root_cached tasks_timeline;
+ struct rb_root_cached latency_timeline;

/*
* 'curr' points to currently running entity on this cfs_rq.
--
2.17.1