linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH] sched/fair: ensure tasks spreading in LLC during LB
@ 2020-11-02 10:24 Vincent Guittot
  2020-11-02 13:31 ` Rik van Riel
                   ` (3 more replies)
  0 siblings, 4 replies; 5+ messages in thread
From: Vincent Guittot @ 2020-11-02 10:24 UTC (permalink / raw)
  To: mingo, peterz, juri.lelli, dietmar.eggemann, rostedt, bsegall,
	mgorman, linux-kernel, riel, clm
  Cc: hannes, Vincent Guittot

schbench shows latency increase for 95 percentile above since:
  commit 0b0695f2b34a ("sched/fair: Rework load_balance()")

Align the behavior of the load balancer with the wake up path, which tries
to select an idle CPU which belongs to the LLC for a waking task.

calculate_imbalance() will use nr_running instead of the spare
capacity when CPUs share resources (ie cache) at the domain level. This
will ensure a better spread of tasks on idle CPUs.

Running schbench on a hikey (8cores arm64) shows the problem:

tip/sched/core :
schbench -m 2 -t 4 -s 10000 -c 1000000 -r 10
Latency percentiles (usec)
	50.0th: 33
	75.0th: 45
	90.0th: 51
	95.0th: 4152
	*99.0th: 14288
	99.5th: 14288
	99.9th: 14288
	min=0, max=14276

tip/sched/core + patch :
schbench -m 2 -t 4 -s 10000 -c 1000000 -r 10
Latency percentiles (usec)
	50.0th: 34
	75.0th: 47
	90.0th: 52
	95.0th: 78
	*99.0th: 94
	99.5th: 94
	99.9th: 94
	min=0, max=94

Fixes: 0b0695f2b34a ("sched/fair: Rework load_balance()")
Reported-by: Chris Mason <clm@fb.com>
Suggested-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
---
 kernel/sched/fair.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aa4c6227cd6d..210b15f068a6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9031,7 +9031,8 @@ static inline void calculate_imbalance(struct lb_env *env, struct sd_lb_stats *s
 	 * emptying busiest.
 	 */
 	if (local->group_type == group_has_spare) {
-		if (busiest->group_type > group_fully_busy) {
+		if ((busiest->group_type > group_fully_busy) &&
+		    !(env->sd->flags & SD_SHARE_PKG_RESOURCES)) {
 			/*
 			 * If busiest is overloaded, try to fill spare
 			 * capacity. This might end up creating spare capacity
-- 
2.17.1


^ permalink raw reply related	[flat|nested] 5+ messages in thread

end of thread, other threads:[~2020-11-12 12:35 UTC | newest]

Thread overview: 5+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2020-11-02 10:24 [PATCH] sched/fair: ensure tasks spreading in LLC during LB Vincent Guittot
2020-11-02 13:31 ` Rik van Riel
2020-11-10 12:55 ` Peter Zijlstra
2020-11-11  8:23 ` [tip: sched/urgent] sched/fair: Ensure " tip-bot2 for Vincent Guittot
2020-11-12 12:34 ` [PATCH] sched/fair: ensure " Mel Gorman

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).