Re: [PATCH 5/5] sched: make fix_small_imbalance work with asymmetric packing
From: Peter Zijlstra <peterz@infradead.org>
Date: 2010-04-13 12:29:39
Also in:
lkml
On Fri, 2010-04-09 at 16:21 +1000, Michael Neuling wrote:
With the asymmetric packing infrastructure, fix_small_imbalance is causing idle higher threads to pull tasks off lower threads. =20 =20 This is being caused by an off-by-one error. =20 =20 Signed-off-by: Michael Neuling <redacted> --- I'm not sure this is the right fix but without it, higher threads pull tasks off the lower threads, then the packing pulls it back down, etc etc and tasks bounce around constantly.
Would help if you expand upon the why/how it manages to get pulled up. I can't immediately spot anything wrong with the patch, but then that isn't my favourite piece of code either.. Suresh, any comments?
--- =20 kernel/sched_fair.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) =20 Index: linux-2.6-ozlabs/kernel/sched_fair.c =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D= =3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
quoted hunk ↗ jump to hunk
--- linux-2.6-ozlabs.orig/kernel/sched_fair.c +++ linux-2.6-ozlabs/kernel/sched_fair.c@@ -2652,7 +2652,7 @@ static inline void fix_small_imbalance(s * SCHED_LOAD_SCALE; scaled_busy_load_per_task /=3D sds->busiest->cpu_power;=20 - if (sds->max_load - sds->this_load + scaled_busy_load_per_task >=3D + if (sds->max_load - sds->this_load + scaled_busy_load_per_task > (scaled_busy_load_per_task * imbn)) { *imbalance =3D sds->busiest_load_per_task; return;