Re: [REGRESSION] Re: [PATCH 00/24] Complete EEVDF

[Peter Zijlstra <peterz@infradead.org>]

On Mon, Jan 06, 2025 at 06:04:55PM +0100, Peter Zijlstra wrote:
> On Mon, Jan 06, 2025 at 05:59:32PM +0100, Peter Zijlstra wrote:
> > On Mon, Jan 06, 2025 at 07:01:34AM -0800, Doug Smythies wrote:
> > 
> > > > What is the easiest 100% load you're seeing this with?
> > > 
> > > Lately, and specifically to be able to tell others, I have been using:
> > > 
> > > yes > /dev/null &
> > > 
> > > On my Intel i5-10600K, with 6 cores and 2 threads per core, 12 CPUs,
> > > I run 12 of those work loads.
> > 
> > On my headless ivb-ep 2 sockets, 10 cores each and 2 threads per core, I
> > do:
> > 
> > for ((i=0; i<40; i++)) ; do yes > /dev/null & done
> > tools/power/x86/turbostat/turbostat --quiet --Summary --show Busy%,Bzy_MHz,IRQ,PkgWatt,PkgTmp,TSC_MHz --interval 1
> > 
> > But no so far, nada :-( I've tried with full preemption and voluntary,
> > HZ=1000.
> > 
> 
> And just as I send this, I see these happen:
> 
> 100.00  3100    2793    40302   71      195.22
> 100.00  3100    2618    40459   72      183.58
> 100.00  3100    2993    46215   71      209.21
> 100.00  3100    2789    40467   71      195.19
> 99.92   3100    2798    40589   71      195.76
> 100.00  3100    2793    40397   72      195.46
> ...
> 100.00  3100    2844    41906   71      199.43
> 100.00  3100    2779    40468   71      194.51
> 99.96   3100    2320    40933   71      163.23
> 100.00  3100    3529    61823   72      245.70
> 100.00  3100    2793    40493   72      195.45
> 100.00  3100    2793    40462   72      195.56
> 
> They look like funny little blips. Nowhere near as bad as you had
> though.

Anyway, given you've confirmed disabling DELAY_DEQUEUE fixes things,
could you perhaps try the below hackery for me? Its a bit of a wild
guess, but throw stuff at wall, see what sticks etc..

---
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 84902936a620..fa4b9891f93a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3019,7 +3019,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag
 	} else {
 
 		if (!is_migration_disabled(p)) {
-			if (task_on_rq_queued(p))
+			if (task_on_rq_queued(p) && !p->se.sched_delayed)
 				rq = move_queued_task(rq, rf, p, dest_cpu);
 
 			if (!pending->stop_pending) {
@@ -3776,28 +3776,30 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
  */
 static int ttwu_runnable(struct task_struct *p, int wake_flags)
 {
-	struct rq_flags rf;
-	struct rq *rq;
-	int ret = 0;
+	CLASS(__task_rq_lock, rq_guard)(p);
+	struct rq *rq = rq_guard.rq;
 
-	rq = __task_rq_lock(p, &rf);
-	if (task_on_rq_queued(p)) {
-		update_rq_clock(rq);
-		if (p->se.sched_delayed)
-			enqueue_task(rq, p, ENQUEUE_NOCLOCK | ENQUEUE_DELAYED);
-		if (!task_on_cpu(rq, p)) {
-			/*
-			 * When on_rq && !on_cpu the task is preempted, see if
-			 * it should preempt the task that is current now.
-			 */
-			wakeup_preempt(rq, p, wake_flags);
+	if (!task_on_rq_queued(p))
+		return 0;
+
+	update_rq_clock(rq);
+	if (p->se.sched_delayed) {
+		int queue_flags = ENQUEUE_NOCLOCK | ENQUEUE_DELAYED;
+		if (!is_cpu_allowed(p, cpu_of(rq))) {
+			dequeue_task(rq, p, DEQUEUE_SLEEP | queue_flags);
+			return 0;
 		}
-		ttwu_do_wakeup(p);
-		ret = 1;
+		enqueue_task(rq, p, queue_flags);
 	}
-	__task_rq_unlock(rq, &rf);
-
-	return ret;
+	if (!task_on_cpu(rq, p)) {
+		/*
+		 * When on_rq && !on_cpu the task is preempted, see if
+		 * it should preempt the task that is current now.
+		 */
+		wakeup_preempt(rq, p, wake_flags);
+	}
+	ttwu_do_wakeup(p);
+	return 1;
 }
 
 #ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 65fa64845d9f..b4c1f6c06c18 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1793,6 +1793,11 @@ task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 	raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
 }
 
+DEFINE_LOCK_GUARD_1(__task_rq_lock, struct task_struct,
+		    _T->rq = __task_rq_lock(_T->lock, &_T->rf),
+		    __task_rq_unlock(_T->rq, &_T->rf),
+		    struct rq *rq; struct rq_flags rf)
+
 DEFINE_LOCK_GUARD_1(task_rq_lock, struct task_struct,
 		    _T->rq = task_rq_lock(_T->lock, &_T->rf),
 		    task_rq_unlock(_T->rq, _T->lock, &_T->rf),