* [PATCH v2 1/4] sched/eevdf: Fix vruntime adjustment on reweight
2023-11-15 3:36 [PATCH v2 0/4] sched/eevdf: Optimize reweight and pick Abel Wu
@ 2023-11-15 3:36 ` Abel Wu
2023-11-15 3:36 ` [PATCH v2 2/4] sched/eevdf: Sort the rbtree by virtual deadline Abel Wu
` (2 subsequent siblings)
3 siblings, 0 replies; 7+ messages in thread
From: Abel Wu @ 2023-11-15 3:36 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider
Cc: Barry Song, Benjamin Segall, Chen Yu, Daniel Jordan,
Gautham R . Shenoy, Joel Fernandes, K Prateek Nayak,
Mike Galbraith, Qais Yousef, Tim Chen, Yicong Yang,
Youssef Esmat, linux-kernel, Abel Wu
vruntime of the (on_rq && !0-lag) entity needs to be adjusted when
it gets re-weighted, and the calculations can be simplified based
on the fact that re-weight won't change the w-average of all the
entities. Please check the proofs in comments.
But adjusting vruntime can also cause position change in RB-tree
hence require re-queue to fix up which might be costly. This might
be avoided by deferring adjustment to the time the entity actually
leaves tree (dequeue/pick), but that will negatively affect task
selection and probably not good enough either.
Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy")
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
---
kernel/sched/fair.c | 151 +++++++++++++++++++++++++++++++++++++-------
1 file changed, 128 insertions(+), 23 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2048138ce54b..025d90925bf6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3666,41 +3666,140 @@ static inline void
dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
#endif
+static void reweight_eevdf(struct cfs_rq *cfs_rq, struct sched_entity *se,
+ unsigned long weight)
+{
+ unsigned long old_weight = se->load.weight;
+ u64 avruntime = avg_vruntime(cfs_rq);
+ s64 vlag, vslice;
+
+ /*
+ * VRUNTIME
+ * ========
+ *
+ * COROLLARY #1: The virtual runtime of the entity needs to be
+ * adjusted if re-weight at !0-lag point.
+ *
+ * Proof: For contradiction assume this is not true, so we can
+ * re-weight without changing vruntime at !0-lag point.
+ *
+ * Weight VRuntime Avg-VRuntime
+ * before w v V
+ * after w' v' V'
+ *
+ * Since lag needs to be preserved through re-weight:
+ *
+ * lag = (V - v)*w = (V'- v')*w', where v = v'
+ * ==> V' = (V - v)*w/w' + v (1)
+ *
+ * Let W be the total weight of the entities before reweight,
+ * since V' is the new weighted average of entities:
+ *
+ * V' = (WV + w'v - wv) / (W + w' - w) (2)
+ *
+ * by using (1) & (2) we obtain:
+ *
+ * (WV + w'v - wv) / (W + w' - w) = (V - v)*w/w' + v
+ * ==> (WV-Wv+Wv+w'v-wv)/(W+w'-w) = (V - v)*w/w' + v
+ * ==> (WV - Wv)/(W + w' - w) + v = (V - v)*w/w' + v
+ * ==> (V - v)*W/(W + w' - w) = (V - v)*w/w' (3)
+ *
+ * Since we are doing at !0-lag point which means V != v, we
+ * can simplify (3):
+ *
+ * ==> W / (W + w' - w) = w / w'
+ * ==> Ww' = Ww + ww' - ww
+ * ==> W * (w' - w) = w * (w' - w)
+ * ==> W = w (re-weight indicates w' != w)
+ *
+ * So the cfs_rq contains only one entity, hence vruntime of
+ * the entity @v should always equal to the cfs_rq's weighted
+ * average vruntime @V, which means we will always re-weight
+ * at 0-lag point, thus breach assumption. Proof completed.
+ *
+ *
+ * COROLLARY #2: Re-weight does NOT affect weighted average
+ * vruntime of all the entities.
+ *
+ * Proof: According to corollary #1, Eq. (1) should be:
+ *
+ * (V - v)*w = (V' - v')*w'
+ * ==> v' = V' - (V - v)*w/w' (4)
+ *
+ * According to the weighted average formula, we have:
+ *
+ * V' = (WV - wv + w'v') / (W - w + w')
+ * = (WV - wv + w'(V' - (V - v)w/w')) / (W - w + w')
+ * = (WV - wv + w'V' - Vw + wv) / (W - w + w')
+ * = (WV + w'V' - Vw) / (W - w + w')
+ *
+ * ==> V'*(W - w + w') = WV + w'V' - Vw
+ * ==> V' * (W - w) = (W - w) * V (5)
+ *
+ * If the entity is the only one in the cfs_rq, then reweight
+ * always occurs at 0-lag point, so V won't change. Or else
+ * there are other entities, hence W != w, then Eq. (5) turns
+ * into V' = V. So V won't change in either case, proof done.
+ *
+ *
+ * So according to corollary #1 & #2, the effect of re-weight
+ * on vruntime should be:
+ *
+ * v' = V' - (V - v) * w / w' (4)
+ * = V - (V - v) * w / w'
+ * = V - vl * w / w'
+ * = V - vl'
+ */
+ if (avruntime != se->vruntime) {
+ vlag = (s64)(avruntime - se->vruntime);
+ vlag = div_s64(vlag * old_weight, weight);
+ se->vruntime = avruntime - vlag;
+ }
+
+ /*
+ * DEADLINE
+ * ========
+ *
+ * When the weight changes, the virtual time slope changes and
+ * we should adjust the relative virtual deadline accordingly.
+ *
+ * d' = v' + (d - v)*w/w'
+ * = V' - (V - v)*w/w' + (d - v)*w/w'
+ * = V - (V - v)*w/w' + (d - v)*w/w'
+ * = V + (d - V)*w/w'
+ */
+ vslice = (s64)(se->deadline - avruntime);
+ vslice = div_s64(vslice * old_weight, weight);
+ se->deadline = avruntime + vslice;
+}
+
static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
unsigned long weight)
{
- unsigned long old_weight = se->load.weight;
+ bool curr = cfs_rq->curr == se;
if (se->on_rq) {
/* commit outstanding execution time */
- if (cfs_rq->curr == se)
+ if (curr)
update_curr(cfs_rq);
else
- avg_vruntime_sub(cfs_rq, se);
+ __dequeue_entity(cfs_rq, se);
update_load_sub(&cfs_rq->load, se->load.weight);
}
dequeue_load_avg(cfs_rq, se);
- update_load_set(&se->load, weight);
-
if (!se->on_rq) {
/*
* Because we keep se->vlag = V - v_i, while: lag_i = w_i*(V - v_i),
* we need to scale se->vlag when w_i changes.
*/
- se->vlag = div_s64(se->vlag * old_weight, weight);
+ se->vlag = div_s64(se->vlag * se->load.weight, weight);
} else {
- s64 deadline = se->deadline - se->vruntime;
- /*
- * When the weight changes, the virtual time slope changes and
- * we should adjust the relative virtual deadline accordingly.
- */
- deadline = div_s64(deadline * old_weight, weight);
- se->deadline = se->vruntime + deadline;
- if (se != cfs_rq->curr)
- min_deadline_cb_propagate(&se->run_node, NULL);
+ reweight_eevdf(cfs_rq, se, weight);
}
+ update_load_set(&se->load, weight);
+
#ifdef CONFIG_SMP
do {
u32 divider = get_pelt_divider(&se->avg);
@@ -3712,8 +3811,17 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
enqueue_load_avg(cfs_rq, se);
if (se->on_rq) {
update_load_add(&cfs_rq->load, se->load.weight);
- if (cfs_rq->curr != se)
- avg_vruntime_add(cfs_rq, se);
+ if (!curr) {
+ /*
+ * The entity's vruntime has been adjusted, so let's check
+ * whether the rq-wide min_vruntime needs updated too. Since
+ * the calculations above require stable min_vruntime rather
+ * than up-to-date one, we do the update at the end of the
+ * reweight process.
+ */
+ __enqueue_entity(cfs_rq, se);
+ update_min_vruntime(cfs_rq);
+ }
}
}
@@ -3857,14 +3965,11 @@ static void update_cfs_group(struct sched_entity *se)
#ifndef CONFIG_SMP
shares = READ_ONCE(gcfs_rq->tg->shares);
-
- if (likely(se->load.weight == shares))
- return;
#else
- shares = calc_group_shares(gcfs_rq);
+ shares = calc_group_shares(gcfs_rq);
#endif
-
- reweight_entity(cfs_rq_of(se), se, shares);
+ if (unlikely(se->load.weight != shares))
+ reweight_entity(cfs_rq_of(se), se, shares);
}
#else /* CONFIG_FAIR_GROUP_SCHED */
--
2.37.3
^ permalink raw reply [flat|nested] 7+ messages in thread* [PATCH v2 2/4] sched/eevdf: Sort the rbtree by virtual deadline
2023-11-15 3:36 [PATCH v2 0/4] sched/eevdf: Optimize reweight and pick Abel Wu
2023-11-15 3:36 ` [PATCH v2 1/4] sched/eevdf: Fix vruntime adjustment on reweight Abel Wu
@ 2023-11-15 3:36 ` Abel Wu
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Abel Wu
2023-11-15 3:36 ` [PATCH v2 3/4] sched/eevdf: O(1) fastpath for task selection Abel Wu
2023-11-15 3:36 ` [PATCH v2 4/4] sched/stats: Add statistics for pick_eevdf() Abel Wu
3 siblings, 1 reply; 7+ messages in thread
From: Abel Wu @ 2023-11-15 3:36 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider
Cc: Barry Song, Benjamin Segall, Chen Yu, Daniel Jordan,
Gautham R . Shenoy, Joel Fernandes, K Prateek Nayak,
Mike Galbraith, Qais Yousef, Tim Chen, Yicong Yang,
Youssef Esmat, linux-kernel, Abel Wu
Sort the task timeline by virtual deadline and keep the min_vruntime
in the augmented tree, so we can avoid doubling the worst case cost
and make full use of the cached leftmost node to enable O(1) fastpath
picking in next patch.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
---
include/linux/sched.h | 2 +-
kernel/sched/debug.c | 11 ++-
kernel/sched/fair.c | 168 +++++++++++++++++-------------------------
kernel/sched/sched.h | 1 +
4 files changed, 77 insertions(+), 105 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c31697248..cd56d4018527 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -553,7 +553,7 @@ struct sched_entity {
struct load_weight load;
struct rb_node run_node;
u64 deadline;
- u64 min_deadline;
+ u64 min_vruntime;
struct list_head group_node;
unsigned int on_rq;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4580a450700e..168eecc209b4 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -628,8 +628,8 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
- s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
- struct sched_entity *last, *first;
+ s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+ struct sched_entity *last, *first, *root;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
@@ -644,15 +644,20 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SPLIT_NS(cfs_rq->exec_clock));
raw_spin_rq_lock_irqsave(rq, flags);
+ root = __pick_root_entity(cfs_rq);
+ if (root)
+ left_vruntime = root->min_vruntime;
first = __pick_first_entity(cfs_rq);
if (first)
- left_vruntime = first->vruntime;
+ left_deadline = first->deadline;
last = __pick_last_entity(cfs_rq);
if (last)
right_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline",
+ SPLIT_NS(left_deadline));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
SPLIT_NS(left_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 025d90925bf6..e1d686196528 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
static inline bool entity_before(const struct sched_entity *a,
const struct sched_entity *b)
{
- return (s64)(a->vruntime - b->vruntime) < 0;
+ /*
+ * Tiebreak on vruntime seems unnecessary since it can
+ * hardly happen.
+ */
+ return (s64)(a->deadline - b->deadline) < 0;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -720,7 +724,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
* Note: using 'avg_vruntime() > se->vruntime' is inacurate due
* to the loss in precision caused by the division.
*/
-int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
{
struct sched_entity *curr = cfs_rq->curr;
s64 avg = cfs_rq->avg_vruntime;
@@ -733,7 +737,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
load += weight;
}
- return avg >= entity_key(cfs_rq, se) * load;
+ return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+}
+
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ return vruntime_eligible(cfs_rq, se->vruntime);
}
static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -752,9 +761,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_first_entity(cfs_rq);
+ struct sched_entity *se = __pick_root_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
-
u64 vruntime = cfs_rq->min_vruntime;
if (curr) {
@@ -766,9 +774,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
if (se) {
if (!curr)
- vruntime = se->vruntime;
+ vruntime = se->min_vruntime;
else
- vruntime = min_vruntime(vruntime, se->vruntime);
+ vruntime = min_vruntime(vruntime, se->min_vruntime);
}
/* ensure we never gain time by being placed backwards. */
@@ -781,34 +789,34 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
return entity_before(__node_2_se(a), __node_2_se(b));
}
-#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
-static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node)
{
if (node) {
struct sched_entity *rse = __node_2_se(node);
- if (deadline_gt(min_deadline, se, rse))
- se->min_deadline = rse->min_deadline;
+ if (vruntime_gt(min_vruntime, se, rse))
+ se->min_vruntime = rse->min_vruntime;
}
}
/*
- * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
*/
-static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
{
- u64 old_min_deadline = se->min_deadline;
+ u64 old_min_vruntime = se->min_vruntime;
struct rb_node *node = &se->run_node;
- se->min_deadline = se->deadline;
- __update_min_deadline(se, node->rb_right);
- __update_min_deadline(se, node->rb_left);
+ se->min_vruntime = se->vruntime;
+ __min_vruntime_update(se, node->rb_right);
+ __min_vruntime_update(se, node->rb_left);
- return se->min_deadline == old_min_deadline;
+ return se->min_vruntime == old_min_vruntime;
}
-RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
- run_node, min_deadline, min_deadline_update);
+RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
+ run_node, min_vruntime, min_vruntime_update);
/*
* Enqueue an entity into the rb-tree:
@@ -816,18 +824,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
avg_vruntime_add(cfs_rq, se);
- se->min_deadline = se->deadline;
+ se->min_vruntime = se->vruntime;
rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- __entity_less, &min_deadline_cb);
+ __entity_less, &min_vruntime_cb);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- &min_deadline_cb);
+ &min_vruntime_cb);
avg_vruntime_sub(cfs_rq, se);
}
+struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;
+
+ if (!root)
+ return NULL;
+
+ return __node_2_se(root);
+}
+
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
@@ -850,23 +868,28 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
* with the earliest virtual deadline.
*
* We can do this in O(log n) time due to an augmented RB-tree. The
- * tree keeps the entries sorted on service, but also functions as a
- * heap based on the deadline by keeping:
+ * tree keeps the entries sorted on deadline, but also functions as a
+ * heap based on the vruntime by keeping:
*
- * se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ * se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
*
- * Which allows an EDF like search on (sub)trees.
+ * Which allows tree pruning through eligibility.
*/
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
- struct sched_entity *best_left = NULL;
+
+ /*
+ * We can safely skip eligibility check if there is only one entity
+ * in this cfs_rq, saving some cycles.
+ */
+ if (cfs_rq->nr_running == 1)
+ return curr && curr->on_rq ? curr : __node_2_se(node);
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
- best = curr;
/*
* Once selected, run a task until it either becomes non-eligible or
@@ -875,95 +898,38 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
return curr;
+ /* Heap search for the EEVD entity */
while (node) {
struct sched_entity *se = __node_2_se(node);
+ struct rb_node *left = node->rb_left;
/*
- * If this entity is not eligible, try the left subtree.
+ * Eligible entities in left subtree are always better
+ * choices, since they have earlier deadlines.
*/
- if (!entity_eligible(cfs_rq, se)) {
- node = node->rb_left;
+ if (left && vruntime_eligible(cfs_rq,
+ __node_2_se(left)->min_vruntime)) {
+ node = left;
continue;
}
/*
- * Now we heap search eligible trees for the best (min_)deadline
+ * The left subtree either is empty or has no eligible
+ * entity, so check the current node since it is the one
+ * with earliest deadline that might be eligible.
*/
- if (!best || deadline_gt(deadline, best, se))
+ if (entity_eligible(cfs_rq, se)) {
best = se;
-
- /*
- * Every se in a left branch is eligible, keep track of the
- * branch with the best min_deadline
- */
- if (node->rb_left) {
- struct sched_entity *left = __node_2_se(node->rb_left);
-
- if (!best_left || deadline_gt(min_deadline, best_left, left))
- best_left = left;
-
- /*
- * min_deadline is in the left branch. rb_left and all
- * descendants are eligible, so immediately switch to the second
- * loop.
- */
- if (left->min_deadline == se->min_deadline)
- break;
- }
-
- /* min_deadline is at this node, no need to look right */
- if (se->deadline == se->min_deadline)
break;
-
- /* else min_deadline is in the right branch. */
- node = node->rb_right;
- }
-
- /*
- * We ran into an eligible node which is itself the best.
- * (Or nr_running == 0 and both are NULL)
- */
- if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
- return best;
-
- /*
- * Now best_left and all of its children are eligible, and we are just
- * looking for deadline == min_deadline
- */
- node = &best_left->run_node;
- while (node) {
- struct sched_entity *se = __node_2_se(node);
-
- /* min_deadline is the current node */
- if (se->deadline == se->min_deadline)
- return se;
-
- /* min_deadline is in the left branch */
- if (node->rb_left &&
- __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
- node = node->rb_left;
- continue;
}
- /* else min_deadline is in the right branch */
node = node->rb_right;
}
- return NULL;
-}
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
-{
- struct sched_entity *se = __pick_eevdf(cfs_rq);
-
- if (!se) {
- struct sched_entity *left = __pick_first_entity(cfs_rq);
- if (left) {
- pr_err("EEVDF scheduling fail, picking leftmost\n");
- return left;
- }
- }
+ if (!best || (curr && entity_before(curr, best)))
+ best = curr;
- return se;
+ return best;
}
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a95486a42..539c7e763f15 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2822,6 +2822,7 @@ DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
double_rq_lock(_T->lock, _T->lock2),
double_rq_unlock(_T->lock, _T->lock2))
+extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
--
2.37.3
^ permalink raw reply [flat|nested] 7+ messages in thread* [tip: sched/core] sched/eevdf: Sort the rbtree by virtual deadline
2023-11-15 3:36 ` [PATCH v2 2/4] sched/eevdf: Sort the rbtree by virtual deadline Abel Wu
@ 2023-11-15 9:04 ` tip-bot2 for Abel Wu
0 siblings, 0 replies; 7+ messages in thread
From: tip-bot2 for Abel Wu @ 2023-11-15 9:04 UTC (permalink / raw)
To: linux-tip-commits; +Cc: Abel Wu, Peter Zijlstra (Intel), x86, linux-kernel
The following commit has been merged into the sched/core branch of tip:
Commit-ID: 2227a957e1d5b1941be4e4207879ec74f4bb37f8
Gitweb: https://git.kernel.org/tip/2227a957e1d5b1941be4e4207879ec74f4bb37f8
Author: Abel Wu <wuyun.abel@bytedance.com>
AuthorDate: Wed, 15 Nov 2023 11:36:45 +08:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 15 Nov 2023 09:57:47 +01:00
sched/eevdf: Sort the rbtree by virtual deadline
Sort the task timeline by virtual deadline and keep the min_vruntime
in the augmented tree, so we can avoid doubling the worst case cost
and make full use of the cached leftmost node to enable O(1) fastpath
picking in next patch.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231115033647.80785-3-wuyun.abel@bytedance.com
---
include/linux/sched.h | 2 +-
kernel/sched/debug.c | 11 ++-
kernel/sched/fair.c | 168 ++++++++++++++++-------------------------
kernel/sched/sched.h | 1 +-
4 files changed, 77 insertions(+), 105 deletions(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 292c316..cd56d40 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -553,7 +553,7 @@ struct sched_entity {
struct load_weight load;
struct rb_node run_node;
u64 deadline;
- u64 min_deadline;
+ u64 min_vruntime;
struct list_head group_node;
unsigned int on_rq;
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 4580a45..168eecc 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -628,8 +628,8 @@ static void print_rq(struct seq_file *m, struct rq *rq, int rq_cpu)
void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
{
- s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, spread;
- struct sched_entity *last, *first;
+ s64 left_vruntime = -1, min_vruntime, right_vruntime = -1, left_deadline = -1, spread;
+ struct sched_entity *last, *first, *root;
struct rq *rq = cpu_rq(cpu);
unsigned long flags;
@@ -644,15 +644,20 @@ void print_cfs_rq(struct seq_file *m, int cpu, struct cfs_rq *cfs_rq)
SPLIT_NS(cfs_rq->exec_clock));
raw_spin_rq_lock_irqsave(rq, flags);
+ root = __pick_root_entity(cfs_rq);
+ if (root)
+ left_vruntime = root->min_vruntime;
first = __pick_first_entity(cfs_rq);
if (first)
- left_vruntime = first->vruntime;
+ left_deadline = first->deadline;
last = __pick_last_entity(cfs_rq);
if (last)
right_vruntime = last->vruntime;
min_vruntime = cfs_rq->min_vruntime;
raw_spin_rq_unlock_irqrestore(rq, flags);
+ SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_deadline",
+ SPLIT_NS(left_deadline));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "left_vruntime",
SPLIT_NS(left_vruntime));
SEQ_printf(m, " .%-30s: %Ld.%06ld\n", "min_vruntime",
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 44b5262..31bca05 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -551,7 +551,11 @@ static inline u64 min_vruntime(u64 min_vruntime, u64 vruntime)
static inline bool entity_before(const struct sched_entity *a,
const struct sched_entity *b)
{
- return (s64)(a->vruntime - b->vruntime) < 0;
+ /*
+ * Tiebreak on vruntime seems unnecessary since it can
+ * hardly happen.
+ */
+ return (s64)(a->deadline - b->deadline) < 0;
}
static inline s64 entity_key(struct cfs_rq *cfs_rq, struct sched_entity *se)
@@ -720,7 +724,7 @@ static void update_entity_lag(struct cfs_rq *cfs_rq, struct sched_entity *se)
* Note: using 'avg_vruntime() > se->vruntime' is inacurate due
* to the loss in precision caused by the division.
*/
-int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static int vruntime_eligible(struct cfs_rq *cfs_rq, u64 vruntime)
{
struct sched_entity *curr = cfs_rq->curr;
s64 avg = cfs_rq->avg_vruntime;
@@ -733,7 +737,12 @@ int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
load += weight;
}
- return avg >= entity_key(cfs_rq, se) * load;
+ return avg >= (s64)(vruntime - cfs_rq->min_vruntime) * load;
+}
+
+int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se)
+{
+ return vruntime_eligible(cfs_rq, se->vruntime);
}
static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
@@ -752,9 +761,8 @@ static u64 __update_min_vruntime(struct cfs_rq *cfs_rq, u64 vruntime)
static void update_min_vruntime(struct cfs_rq *cfs_rq)
{
- struct sched_entity *se = __pick_first_entity(cfs_rq);
+ struct sched_entity *se = __pick_root_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
-
u64 vruntime = cfs_rq->min_vruntime;
if (curr) {
@@ -766,9 +774,9 @@ static void update_min_vruntime(struct cfs_rq *cfs_rq)
if (se) {
if (!curr)
- vruntime = se->vruntime;
+ vruntime = se->min_vruntime;
else
- vruntime = min_vruntime(vruntime, se->vruntime);
+ vruntime = min_vruntime(vruntime, se->min_vruntime);
}
/* ensure we never gain time by being placed backwards. */
@@ -781,34 +789,34 @@ static inline bool __entity_less(struct rb_node *a, const struct rb_node *b)
return entity_before(__node_2_se(a), __node_2_se(b));
}
-#define deadline_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
+#define vruntime_gt(field, lse, rse) ({ (s64)((lse)->field - (rse)->field) > 0; })
-static inline void __update_min_deadline(struct sched_entity *se, struct rb_node *node)
+static inline void __min_vruntime_update(struct sched_entity *se, struct rb_node *node)
{
if (node) {
struct sched_entity *rse = __node_2_se(node);
- if (deadline_gt(min_deadline, se, rse))
- se->min_deadline = rse->min_deadline;
+ if (vruntime_gt(min_vruntime, se, rse))
+ se->min_vruntime = rse->min_vruntime;
}
}
/*
- * se->min_deadline = min(se->deadline, left->min_deadline, right->min_deadline)
+ * se->min_vruntime = min(se->vruntime, {left,right}->min_vruntime)
*/
-static inline bool min_deadline_update(struct sched_entity *se, bool exit)
+static inline bool min_vruntime_update(struct sched_entity *se, bool exit)
{
- u64 old_min_deadline = se->min_deadline;
+ u64 old_min_vruntime = se->min_vruntime;
struct rb_node *node = &se->run_node;
- se->min_deadline = se->deadline;
- __update_min_deadline(se, node->rb_right);
- __update_min_deadline(se, node->rb_left);
+ se->min_vruntime = se->vruntime;
+ __min_vruntime_update(se, node->rb_right);
+ __min_vruntime_update(se, node->rb_left);
- return se->min_deadline == old_min_deadline;
+ return se->min_vruntime == old_min_vruntime;
}
-RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
- run_node, min_deadline, min_deadline_update);
+RB_DECLARE_CALLBACKS(static, min_vruntime_cb, struct sched_entity,
+ run_node, min_vruntime, min_vruntime_update);
/*
* Enqueue an entity into the rb-tree:
@@ -816,18 +824,28 @@ RB_DECLARE_CALLBACKS(static, min_deadline_cb, struct sched_entity,
static void __enqueue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
avg_vruntime_add(cfs_rq, se);
- se->min_deadline = se->deadline;
+ se->min_vruntime = se->vruntime;
rb_add_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- __entity_less, &min_deadline_cb);
+ __entity_less, &min_vruntime_cb);
}
static void __dequeue_entity(struct cfs_rq *cfs_rq, struct sched_entity *se)
{
rb_erase_augmented_cached(&se->run_node, &cfs_rq->tasks_timeline,
- &min_deadline_cb);
+ &min_vruntime_cb);
avg_vruntime_sub(cfs_rq, se);
}
+struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq)
+{
+ struct rb_node *root = cfs_rq->tasks_timeline.rb_root.rb_node;
+
+ if (!root)
+ return NULL;
+
+ return __node_2_se(root);
+}
+
struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
{
struct rb_node *left = rb_first_cached(&cfs_rq->tasks_timeline);
@@ -850,23 +868,28 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
* with the earliest virtual deadline.
*
* We can do this in O(log n) time due to an augmented RB-tree. The
- * tree keeps the entries sorted on service, but also functions as a
- * heap based on the deadline by keeping:
+ * tree keeps the entries sorted on deadline, but also functions as a
+ * heap based on the vruntime by keeping:
*
- * se->min_deadline = min(se->deadline, se->{left,right}->min_deadline)
+ * se->min_vruntime = min(se->vruntime, se->{left,right}->min_vruntime)
*
- * Which allows an EDF like search on (sub)trees.
+ * Which allows tree pruning through eligibility.
*/
-static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
+static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
- struct sched_entity *best_left = NULL;
+
+ /*
+ * We can safely skip eligibility check if there is only one entity
+ * in this cfs_rq, saving some cycles.
+ */
+ if (cfs_rq->nr_running == 1)
+ return curr && curr->on_rq ? curr : __node_2_se(node);
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
- best = curr;
/*
* Once selected, run a task until it either becomes non-eligible or
@@ -875,95 +898,38 @@ static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq)
if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
return curr;
+ /* Heap search for the EEVD entity */
while (node) {
struct sched_entity *se = __node_2_se(node);
+ struct rb_node *left = node->rb_left;
/*
- * If this entity is not eligible, try the left subtree.
+ * Eligible entities in left subtree are always better
+ * choices, since they have earlier deadlines.
*/
- if (!entity_eligible(cfs_rq, se)) {
- node = node->rb_left;
+ if (left && vruntime_eligible(cfs_rq,
+ __node_2_se(left)->min_vruntime)) {
+ node = left;
continue;
}
/*
- * Now we heap search eligible trees for the best (min_)deadline
+ * The left subtree either is empty or has no eligible
+ * entity, so check the current node since it is the one
+ * with earliest deadline that might be eligible.
*/
- if (!best || deadline_gt(deadline, best, se))
+ if (entity_eligible(cfs_rq, se)) {
best = se;
-
- /*
- * Every se in a left branch is eligible, keep track of the
- * branch with the best min_deadline
- */
- if (node->rb_left) {
- struct sched_entity *left = __node_2_se(node->rb_left);
-
- if (!best_left || deadline_gt(min_deadline, best_left, left))
- best_left = left;
-
- /*
- * min_deadline is in the left branch. rb_left and all
- * descendants are eligible, so immediately switch to the second
- * loop.
- */
- if (left->min_deadline == se->min_deadline)
- break;
- }
-
- /* min_deadline is at this node, no need to look right */
- if (se->deadline == se->min_deadline)
break;
-
- /* else min_deadline is in the right branch. */
- node = node->rb_right;
- }
-
- /*
- * We ran into an eligible node which is itself the best.
- * (Or nr_running == 0 and both are NULL)
- */
- if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0)
- return best;
-
- /*
- * Now best_left and all of its children are eligible, and we are just
- * looking for deadline == min_deadline
- */
- node = &best_left->run_node;
- while (node) {
- struct sched_entity *se = __node_2_se(node);
-
- /* min_deadline is the current node */
- if (se->deadline == se->min_deadline)
- return se;
-
- /* min_deadline is in the left branch */
- if (node->rb_left &&
- __node_2_se(node->rb_left)->min_deadline == se->min_deadline) {
- node = node->rb_left;
- continue;
}
- /* else min_deadline is in the right branch */
node = node->rb_right;
}
- return NULL;
-}
-static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
-{
- struct sched_entity *se = __pick_eevdf(cfs_rq);
-
- if (!se) {
- struct sched_entity *left = __pick_first_entity(cfs_rq);
- if (left) {
- pr_err("EEVDF scheduling fail, picking leftmost\n");
- return left;
- }
- }
+ if (!best || (curr && entity_before(curr, best)))
+ best = curr;
- return se;
+ return best;
}
#ifdef CONFIG_SCHED_DEBUG
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2e5a954..539c7e7 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2822,6 +2822,7 @@ DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
double_rq_lock(_T->lock, _T->lock2),
double_rq_unlock(_T->lock, _T->lock2))
+extern struct sched_entity *__pick_root_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq);
extern struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq);
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v2 3/4] sched/eevdf: O(1) fastpath for task selection
2023-11-15 3:36 [PATCH v2 0/4] sched/eevdf: Optimize reweight and pick Abel Wu
2023-11-15 3:36 ` [PATCH v2 1/4] sched/eevdf: Fix vruntime adjustment on reweight Abel Wu
2023-11-15 3:36 ` [PATCH v2 2/4] sched/eevdf: Sort the rbtree by virtual deadline Abel Wu
@ 2023-11-15 3:36 ` Abel Wu
2023-11-15 9:04 ` [tip: sched/core] " tip-bot2 for Abel Wu
2023-11-15 3:36 ` [PATCH v2 4/4] sched/stats: Add statistics for pick_eevdf() Abel Wu
3 siblings, 1 reply; 7+ messages in thread
From: Abel Wu @ 2023-11-15 3:36 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider
Cc: Barry Song, Benjamin Segall, Chen Yu, Daniel Jordan,
Gautham R . Shenoy, Joel Fernandes, K Prateek Nayak,
Mike Galbraith, Qais Yousef, Tim Chen, Yicong Yang,
Youssef Esmat, linux-kernel, Abel Wu
Since the RB-tree is now sorted by deadline, let's first try the
leftmost entity which has the earliest virtual deadline. I've done
some benchmarks to see its effectiveness.
All the benchmarks are done inside a normal cpu cgroup in a clean
environment with cpu turbo disabled, on a dual-CPU Intel Xeon(R)
Platinum 8260 with 2 NUMA nodes each of which has 24C/48T.
hackbench: process/thread + pipe/socket + 1/2/4/8 groups
netperf: TCP/UDP + STREAM/RR + 24/48/72/96/192 threads
tbench: loopback 24/48/72/96/192 threads
schbench: 1/2/4/8 mthreads
direct: cfs_rq has only one entity
parity: RUN_TO_PARITY
fast: O(1) fastpath
slow: heap search
(%) direct parity fast slow
hackbench 92.95 2.02 4.91 0.12
netperf 68.08 6.60 24.18 1.14
tbench 67.55 11.22 20.61 0.62
schbench 69.91 2.65 25.73 1.71
The above results indicate that this fastpath really makes task
selection more efficient.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
---
kernel/sched/fair.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index e1d686196528..4197258b76ab 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -878,6 +878,7 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
@@ -886,7 +887,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
* in this cfs_rq, saving some cycles.
*/
if (cfs_rq->nr_running == 1)
- return curr && curr->on_rq ? curr : __node_2_se(node);
+ return curr && curr->on_rq ? curr : se;
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
@@ -898,9 +899,14 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
return curr;
+ /* Pick the leftmost entity if it's eligible */
+ if (se && entity_eligible(cfs_rq, se)) {
+ best = se;
+ goto found;
+ }
+
/* Heap search for the EEVD entity */
while (node) {
- struct sched_entity *se = __node_2_se(node);
struct rb_node *left = node->rb_left;
/*
@@ -913,6 +919,8 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
continue;
}
+ se = __node_2_se(node);
+
/*
* The left subtree either is empty or has no eligible
* entity, so check the current node since it is the one
@@ -925,7 +933,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
node = node->rb_right;
}
-
+found:
if (!best || (curr && entity_before(curr, best)))
best = curr;
--
2.37.3
^ permalink raw reply [flat|nested] 7+ messages in thread* [tip: sched/core] sched/eevdf: O(1) fastpath for task selection
2023-11-15 3:36 ` [PATCH v2 3/4] sched/eevdf: O(1) fastpath for task selection Abel Wu
@ 2023-11-15 9:04 ` tip-bot2 for Abel Wu
0 siblings, 0 replies; 7+ messages in thread
From: tip-bot2 for Abel Wu @ 2023-11-15 9:04 UTC (permalink / raw)
To: linux-tip-commits; +Cc: Abel Wu, Peter Zijlstra (Intel), x86, linux-kernel
The following commit has been merged into the sched/core branch of tip:
Commit-ID: ee4373dc902c0a403dd084b254ce70a78f95466f
Gitweb: https://git.kernel.org/tip/ee4373dc902c0a403dd084b254ce70a78f95466f
Author: Abel Wu <wuyun.abel@bytedance.com>
AuthorDate: Wed, 15 Nov 2023 11:36:46 +08:00
Committer: Peter Zijlstra <peterz@infradead.org>
CommitterDate: Wed, 15 Nov 2023 09:57:47 +01:00
sched/eevdf: O(1) fastpath for task selection
Since the RB-tree is now sorted by deadline, let's first try the
leftmost entity which has the earliest virtual deadline. I've done
some benchmarks to see its effectiveness.
All the benchmarks are done inside a normal cpu cgroup in a clean
environment with cpu turbo disabled, on a dual-CPU Intel Xeon(R)
Platinum 8260 with 2 NUMA nodes each of which has 24C/48T.
hackbench: process/thread + pipe/socket + 1/2/4/8 groups
netperf: TCP/UDP + STREAM/RR + 24/48/72/96/192 threads
tbench: loopback 24/48/72/96/192 threads
schbench: 1/2/4/8 mthreads
direct: cfs_rq has only one entity
parity: RUN_TO_PARITY
fast: O(1) fastpath
slow: heap search
(%) direct parity fast slow
hackbench 92.95 2.02 4.91 0.12
netperf 68.08 6.60 24.18 1.14
tbench 67.55 11.22 20.61 0.62
schbench 69.91 2.65 25.73 1.71
The above results indicate that this fastpath really makes task
selection more efficient.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20231115033647.80785-4-wuyun.abel@bytedance.com
---
kernel/sched/fair.c | 14 +++++++++++---
1 file changed, 11 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 31bca05..d3e045d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -878,6 +878,7 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
{
struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node;
+ struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
@@ -886,7 +887,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
* in this cfs_rq, saving some cycles.
*/
if (cfs_rq->nr_running == 1)
- return curr && curr->on_rq ? curr : __node_2_se(node);
+ return curr && curr->on_rq ? curr : se;
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
@@ -898,9 +899,14 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
return curr;
+ /* Pick the leftmost entity if it's eligible */
+ if (se && entity_eligible(cfs_rq, se)) {
+ best = se;
+ goto found;
+ }
+
/* Heap search for the EEVD entity */
while (node) {
- struct sched_entity *se = __node_2_se(node);
struct rb_node *left = node->rb_left;
/*
@@ -913,6 +919,8 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
continue;
}
+ se = __node_2_se(node);
+
/*
* The left subtree either is empty or has no eligible
* entity, so check the current node since it is the one
@@ -925,7 +933,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
node = node->rb_right;
}
-
+found:
if (!best || (curr && entity_before(curr, best)))
best = curr;
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v2 4/4] sched/stats: Add statistics for pick_eevdf()
2023-11-15 3:36 [PATCH v2 0/4] sched/eevdf: Optimize reweight and pick Abel Wu
` (2 preceding siblings ...)
2023-11-15 3:36 ` [PATCH v2 3/4] sched/eevdf: O(1) fastpath for task selection Abel Wu
@ 2023-11-15 3:36 ` Abel Wu
3 siblings, 0 replies; 7+ messages in thread
From: Abel Wu @ 2023-11-15 3:36 UTC (permalink / raw)
To: Peter Zijlstra, Ingo Molnar, Vincent Guittot, Dietmar Eggemann,
Valentin Schneider
Cc: Barry Song, Benjamin Segall, Chen Yu, Daniel Jordan,
Gautham R . Shenoy, Joel Fernandes, K Prateek Nayak,
Mike Galbraith, Qais Yousef, Tim Chen, Yicong Yang,
Youssef Esmat, linux-kernel, Abel Wu
For statistical purpose only, not intended to upstream.
Signed-off-by: Abel Wu <wuyun.abel@bytedance.com>
---
kernel/sched/fair.c | 12 ++++++++++--
kernel/sched/sched.h | 5 +++++
kernel/sched/stats.c | 6 ++++--
3 files changed, 19 insertions(+), 4 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4197258b76ab..94d9318ac484 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -881,13 +881,16 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
struct sched_entity *se = __pick_first_entity(cfs_rq);
struct sched_entity *curr = cfs_rq->curr;
struct sched_entity *best = NULL;
+ struct rq *rq = rq_of(cfs_rq);
/*
* We can safely skip eligibility check if there is only one entity
* in this cfs_rq, saving some cycles.
*/
- if (cfs_rq->nr_running == 1)
+ if (cfs_rq->nr_running == 1) {
+ schedstat_inc(rq->pick_direct);
return curr && curr->on_rq ? curr : se;
+ }
if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
curr = NULL;
@@ -896,15 +899,20 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
* Once selected, run a task until it either becomes non-eligible or
* until it gets a new slice. See the HACK in set_next_entity().
*/
- if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline)
+ if (sched_feat(RUN_TO_PARITY) && curr && curr->vlag == curr->deadline) {
+ schedstat_inc(rq->pick_parity);
return curr;
+ }
/* Pick the leftmost entity if it's eligible */
if (se && entity_eligible(cfs_rq, se)) {
+ schedstat_inc(rq->pick_fast);
best = se;
goto found;
}
+ schedstat_inc(rq->pick_slow);
+
/* Heap search for the EEVD entity */
while (node) {
struct rb_node *left = node->rb_left;
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 539c7e763f15..85a79990a698 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1105,6 +1105,11 @@ struct rq {
/* try_to_wake_up() stats */
unsigned int ttwu_count;
unsigned int ttwu_local;
+
+ unsigned int pick_direct;
+ unsigned int pick_parity;
+ unsigned int pick_fast;
+ unsigned int pick_slow;
#endif
#ifdef CONFIG_CPU_IDLE
diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
index 857f837f52cb..4b862c798989 100644
--- a/kernel/sched/stats.c
+++ b/kernel/sched/stats.c
@@ -133,12 +133,14 @@ static int show_schedstat(struct seq_file *seq, void *v)
/* runqueue-specific stats */
seq_printf(seq,
- "cpu%d %u 0 %u %u %u %u %llu %llu %lu",
+ "cpu%d %u 0 %u %u %u %u %llu %llu %lu %u %u %u %u",
cpu, rq->yld_count,
rq->sched_count, rq->sched_goidle,
rq->ttwu_count, rq->ttwu_local,
rq->rq_cpu_time,
- rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount);
+ rq->rq_sched_info.run_delay, rq->rq_sched_info.pcount,
+ rq->pick_direct, rq->pick_parity,
+ rq->pick_fast, rq->pick_slow);
seq_printf(seq, "\n");
--
2.37.3
^ permalink raw reply [flat|nested] 7+ messages in thread