This is a mechanism to set the next task_pick target,
'buddy' is too ambiguous and refers to a historic feature we
don't have anymore.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
kernel/sched/fair.c | 28 +++++++++++++---------------
1 file changed, 13 insertions(+), 15 deletions(-)
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 93ea653065f5..fe730f232ffd 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3200,7 +3200,16 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
hrtick_update(rq);
}
-static void set_next_buddy(struct sched_entity *se);
+static void set_next_pick(struct sched_entity *se)
+{
+ for_each_sched_entity(se) {
+ if (SCHED_WARN_ON(!se->on_rq))
+ return;
+ if (se_is_idle(se))
+ return;
+ cfs_rq_of(se)->next = se;
+ }
+}
/*
* The dequeue_task method is called before nr_running is
@@ -3240,7 +3249,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
* p is sleeping when it is within its sched_slice.
*/
if (task_sleep && se && !throttled_hierarchy(cfs_rq))
- set_next_buddy(se);
+ set_next_pick(se);
break;
}
flags |= DEQUEUE_SLEEP;
@@ -4631,17 +4640,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
#endif /* CONFIG_SMP */
-static void set_next_buddy(struct sched_entity *se)
-{
- for_each_sched_entity(se) {
- if (SCHED_WARN_ON(!se->on_rq))
- return;
- if (se_is_idle(se))
- return;
- cfs_rq_of(se)->next = se;
- }
-}
-
/*
* Preempt the current task with a newly woken task if needed:
*/
@@ -4769,7 +4767,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
goto simple;
/*
- * Because of the set_next_buddy() in dequeue_task_fair() it is rather
+ * Because of the set_next_pick() in dequeue_task_fair() it is rather
* likely that a next task is from the same cgroup as the current.
*
* Therefore attempt to avoid putting and setting the entire cgroup
@@ -4957,7 +4955,7 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
return false;
/* Tell the scheduler that we'd really like se to run next. */
- set_next_buddy(se);
+ set_next_pick(se);
yield_task_fair(rq);
--
2.40.1On Sun, Apr 07, 2024 at 10:43:19AM +0200, Ingo Molnar wrote:
> This is a mechanism to set the next task_pick target,
> 'buddy' is too ambiguous and refers to a historic feature we
> don't have anymore.
>
> Signed-off-by: Ingo Molnar <mingo@kernel.org>
> ---
> kernel/sched/fair.c | 28 +++++++++++++---------------
> 1 file changed, 13 insertions(+), 15 deletions(-)
>
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 93ea653065f5..fe730f232ffd 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -3200,7 +3200,16 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
> hrtick_update(rq);
> }
>
> -static void set_next_buddy(struct sched_entity *se);
> +static void set_next_pick(struct sched_entity *se)
> +{
> + for_each_sched_entity(se) {
> + if (SCHED_WARN_ON(!se->on_rq))
> + return;
> + if (se_is_idle(se))
> + return;
> + cfs_rq_of(se)->next = se;
> + }
> +}
>
> /*
> * The dequeue_task method is called before nr_running is
> @@ -3240,7 +3249,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
> * p is sleeping when it is within its sched_slice.
> */
> if (task_sleep && se && !throttled_hierarchy(cfs_rq))
> - set_next_buddy(se);
> + set_next_pick(se);
> break;
> }
> flags |= DEQUEUE_SLEEP;
> @@ -4631,17 +4640,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
> static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
> #endif /* CONFIG_SMP */
>
> -static void set_next_buddy(struct sched_entity *se)
> -{
> - for_each_sched_entity(se) {
> - if (SCHED_WARN_ON(!se->on_rq))
> - return;
> - if (se_is_idle(se))
> - return;
> - cfs_rq_of(se)->next = se;
> - }
> -}
> -
Hurmmm.. afaict the only actual user of cfs_rq->next left is task_hot(),
no? Is that thing worth it?
That is, should we not totally nuke the thing?
> /*
> * Preempt the current task with a newly woken task if needed:
> */
> @@ -4769,7 +4767,7 @@ pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf
> goto simple;
>
> /*
> - * Because of the set_next_buddy() in dequeue_task_fair() it is rather
> + * Because of the set_next_pick() in dequeue_task_fair() it is rather
> * likely that a next task is from the same cgroup as the current.
> *
So, given you killed the ->next consideration in pick, isn't this
comment 'misleading' at best?
* Peter Zijlstra <peterz@infradead.org> wrote:
> On Sun, Apr 07, 2024 at 10:43:19AM +0200, Ingo Molnar wrote:
> > This is a mechanism to set the next task_pick target,
> > 'buddy' is too ambiguous and refers to a historic feature we
> > don't have anymore.
> >
> > Signed-off-by: Ingo Molnar <mingo@kernel.org>
> > ---
> > kernel/sched/fair.c | 28 +++++++++++++---------------
> > 1 file changed, 13 insertions(+), 15 deletions(-)
> >
> > diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> > index 93ea653065f5..fe730f232ffd 100644
> > --- a/kernel/sched/fair.c
> > +++ b/kernel/sched/fair.c
> > @@ -3200,7 +3200,16 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
> > hrtick_update(rq);
> > }
> >
> > -static void set_next_buddy(struct sched_entity *se);
> > +static void set_next_pick(struct sched_entity *se)
> > +{
> > + for_each_sched_entity(se) {
> > + if (SCHED_WARN_ON(!se->on_rq))
> > + return;
> > + if (se_is_idle(se))
> > + return;
> > + cfs_rq_of(se)->next = se;
> > + }
> > +}
> >
> > /*
> > * The dequeue_task method is called before nr_running is
> > @@ -3240,7 +3249,7 @@ static void dequeue_task_fair(struct rq *rq, struct task_struct *p, int flags)
> > * p is sleeping when it is within its sched_slice.
> > */
> > if (task_sleep && se && !throttled_hierarchy(cfs_rq))
> > - set_next_buddy(se);
> > + set_next_pick(se);
> > break;
> > }
> > flags |= DEQUEUE_SLEEP;
> > @@ -4631,17 +4640,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
> > static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
> > #endif /* CONFIG_SMP */
> >
> > -static void set_next_buddy(struct sched_entity *se)
> > -{
> > - for_each_sched_entity(se) {
> > - if (SCHED_WARN_ON(!se->on_rq))
> > - return;
> > - if (se_is_idle(se))
> > - return;
> > - cfs_rq_of(se)->next = se;
> > - }
> > -}
> > -
>
> Hurmmm.. afaict the only actual user of cfs_rq->next left is task_hot(),
> no? Is that thing worth it?
Yeah, so:
1)
While you are correct in the context of my patch, I think that might be a
bug - the yield_to() methods are intending to use ->next:
/* Tell the scheduler that we'd really like se to run next. */
set_next_buddy(se);
yield_task_fair(rq);
... and yield_to() would rather fundamentally rely on ->next overriding the
next-task-pick selection, but it won't due to NEXT_BUDDY being false:
static struct sched_entity *
pick_next_entity(struct cfs_rq *cfs_rq)
{
/*
* Enabling NEXT_BUDDY will affect latency but not fairness.
*/
if (sched_feat(NEXT_BUDDY) &&
cfs_rq->next && entity_eligible(cfs_rq, cfs_rq->next))
return cfs_rq->next;
> That is, should we not totally nuke the thing?
I don't think we want to nuke it - there's 3 users:
- yield()
- CFS bandwidth
- wakeup
I think the yield() and CFS bandwidth ones are genuine, but non-working due
to NEXT_BUDDY at 0. Wakeup was the original intended NEXT_BUDDY logic, but
it got turned off due to some performance or latency considerations that
might or might not be valid & relevant today.
2)
Even the task_hot() use of ->next isn't spurious: if a task has been marked
as run-next, then presumably the current task is descheduling and we should
probably not tear its ->next away in load-balancing.
3)
Side note: a set rq->next should probably reduce a candidate runqueue's
weight both in periodic load-balancing and in idle-balancing, by rq->curr's
weight or so?
So what I think we should do is to keep ->next and fix all its intended
uses, and make it all unconditional by removing both NEXT_BUDDY and
CACHE_HOT_BUDDY. I can cook up a series if you agree in principle.
Thanks,
Ingo
On Tue, Apr 09, 2024 at 10:32:59AM +0200, Ingo Molnar wrote: > I don't think we want to nuke it - there's 3 users: > > - yield() > - CFS bandwidth > - wakeup > > I think the yield() and CFS bandwidth ones are genuine, but non-working due > to NEXT_BUDDY at 0. Wakeup was the original intended NEXT_BUDDY logic, but > it got turned off due to some performance or latency considerations that > might or might not be valid & relevant today. > > 2) > > Even the task_hot() use of ->next isn't spurious: if a task has been marked > as run-next, then presumably the current task is descheduling and we should > probably not tear its ->next away in load-balancing. > > 3) > > Side note: a set rq->next should probably reduce a candidate runqueue's > weight both in periodic load-balancing and in idle-balancing, by rq->curr's > weight or so? > > So what I think we should do is to keep ->next and fix all its intended > uses, and make it all unconditional by removing both NEXT_BUDDY and > CACHE_HOT_BUDDY. I can cook up a series if you agree in principle. So yes on fixing those yield_to() and cfs_bandwidth thingies, but put then under a new knob -- if the fix regresses we can simply flip it. Ack on removing the current knobs, for them not having been changed in forever.
© 2016 - 2026 Red Hat, Inc.