On Mon, 26 Oct 2020 16:42:14 +0100 Vincent Guittot <vincent.guit...@linaro.org> wrote: > On Mon, 26 Oct 2020 at 16:04, Rik van Riel <r...@surriel.com> wrote:
> > Could utilization estimates be off, either lagging or > > simply having a wrong estimate for a task, resulting > > in no task getting pulled sometimes, while doing a > > migrate_task imbalance always moves over something? > > task and cpu utilization are not always up to fully synced and may lag > a bit which explains that sometimes LB can fail to migrate for a small > diff OK, running with this little snippet below, I see latencies improve back to near where they used to be: Latency percentiles (usec) runtime 150 (s) 50.0th: 13 75.0th: 31 90.0th: 69 95.0th: 90 *99.0th: 761 99.5th: 2268 99.9th: 9104 min=1, max=16158 I suspect the right/cleaner approach might be to use migrate_task more in !CPU_NOT_IDLE cases? Running a task to an idle CPU immediately, instead of refusing to have the load balancer move it, improves latencies for fairly obvious reasons. I am not entirely clear on why the load balancer should need to be any more conservative about moving tasks than the wakeup path is in eg. select_idle_sibling. diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 35bdc0cccfa6..60acf71a2d39 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7415,7 +7415,7 @@ static int detach_tasks(struct lb_env *env) case migrate_util: util = task_util_est(p); - if (util > env->imbalance) + if (util > env->imbalance && env->idle == CPU_NOT_IDLE) goto next; env->imbalance -= util;