Re: Abysmal scheduler performance in Linus' tree?

[Peter Zijlstra <peterz@infradead.org>]

On Wed, Sep 06, 2017 at 12:44:20PM +0200, Peter Zijlstra wrote:
> > > +       /* if this cache has capacity, come here */
> > > +       if (this_stats.has_capacity && this_stats.nr_running < prev_stats.nr_running+1)
> > > +               return true;
> > 
> > This is still not working as intended, it should be 
> > 
> > 	if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
> > 		return true;
> > 
> > to fix the regression.
> 
> Argh, you're quite right. Let me do a patch for that.

---
Subject: sched/fair: Fix wake_affine_llc() balance rules
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed Sep  6 12:45:45 CEST 2017

Chris reported that the SMT balance rules got the +1 on the wrong
side, resulting in a bias towards the current LLC; which the
load-balancer would then try and undo.

Reported-by: Chris Wilson <chris@chris-wilson.co.uk>
Fixes: 90001d67be2f ("sched/fair: Fix wake_affine() for !NUMA_BALANCING")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
---
 kernel/sched/fair.c |    2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5435,7 +5435,7 @@ wake_affine_llc(struct sched_domain *sd,
 		return false;
 
 	/* if this cache has capacity, come here */
-	if (this_stats.has_capacity && this_stats.nr_running < prev_stats.nr_running+1)
+	if (this_stats.has_capacity && this_stats.nr_running+1 < prev_stats.nr_running)
 		return true;
 
 	/*