On Thu, Mar 21, 2019 at 05:20:17PM -0400, Julien Desfossez wrote:
> On further investigation, we could see that the contention is mostly in the
> way rq locks are taken. With this patchset, we lock the whole core if
> cpu.tag is set for at least one cgroup. Due to this, __schedule() is more or
> less serialized for the core and that attributes to the performance loss
> that we are seeing. We also saw that newidle_balance() takes considerably
> long time in load_balance() due to the rq spinlock contention. Do you think
> it would help if the core-wide locking was only performed when absolutely
> needed ?
Something like that could be done, but then you end up with 2 locks,
something which I was hoping to avoid.
Basically you keep rq->lock as it exists today, but add something like
rq->core->core_lock, you then have to take that second lock (nested
under rq->lock) for every scheduling action involving a tagged task.
It makes things complicatd though; because now my head hurts thikning
about pick_next_task().
(this can obviously do away with the whole rq->lock wrappery)
Also, completely untested..
---
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -146,6 +146,8 @@ void sched_core_enqueue(struct rq *rq, s
if (!p->core_cookie)
return;
+ raw_spin_lock(&rq->core->core_lock);
+
node = &rq->core_tree.rb_node;
parent = *node;
@@ -161,6 +163,8 @@ void sched_core_enqueue(struct rq *rq, s
rb_link_node(&p->core_node, parent, node);
rb_insert_color(&p->core_node, &rq->core_tree);
+
+ raw_spin_unlock(&rq->core->core_lock);
}
void sched_core_dequeue(struct rq *rq, struct task_struct *p)
@@ -170,7 +174,9 @@ void sched_core_dequeue(struct rq *rq, s
if (!p->core_cookie)
return;
+ raw_spin_lock(&rq->core->core_lock);
rb_erase(&p->core_node, &rq->core_tree);
+ raw_spin_unlock(&rq->core->core_lock);
}
/*
@@ -181,6 +187,8 @@ struct task_struct *sched_core_find(stru
struct rb_node *node = rq->core_tree.rb_node;
struct task_struct *node_task, *match;
+ lockdep_assert_held(&rq->core->core_lock);
+
/*
* The idle task always matches any cookie!
*/
@@ -206,6 +214,8 @@ struct task_struct *sched_core_next(stru
{
struct rb_node *node = &p->core_node;
+ lockdep_assert_held(&rq->core->core_lock);
+
node = rb_next(node);
if (!node)
return NULL;
@@ -3685,6 +3695,8 @@ pick_next_task(struct rq *rq, struct tas
* If there were no {en,de}queues since we picked (IOW, the task
* pointers are all still valid), and we haven't scheduled the last
* pick yet, do so now.
+ *
+ * XXX probably OK without ->core_lock
*/
if (rq->core->core_pick_seq == rq->core->core_task_seq &&
rq->core->core_pick_seq != rq->core_sched_seq) {
@@ -3710,6 +3722,20 @@ pick_next_task(struct rq *rq, struct tas
if (!rq->nr_running)
newidle_balance(rq, rf);
+ if (!rq->core->core_cookie) {
+ for_each_class(class) {
+ next = pick_task(rq, class, NULL);
+ if (next)
+ break;
+ }
+
+ if (!next->core_cookie) {
+ set_next_task(rq, next);
+ return next;
+ }
+ }
+
+ raw_spin_lock(&rq->core->core_lock);
cpu = cpu_of(rq);
smt_mask = cpu_smt_mask(cpu);
@@ -3849,6 +3875,7 @@ next_class:;
trace_printk("picked: %s/%d %lx\n", next->comm, next->pid,
next->core_cookie);
done:
+ raw_spin_unlock(&rq->core->core_lock);
set_next_task(rq, next);
return next;
}
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -966,6 +966,7 @@ struct rq {
struct rb_root core_tree;
/* shared state */
+ raw_spinlock_t core_lock;
unsigned int core_task_seq;
unsigned int core_pick_seq;
unsigned long core_cookie;
@@ -1007,9 +1008,6 @@ static inline bool sched_core_enabled(st
static inline raw_spinlock_t *rq_lockp(struct rq *rq)
{
- if (sched_core_enabled(rq))
- return &rq->core->__lock;
-
return &rq->__lock;
}
