summaryrefslogtreecommitdiff
path: root/kernel/sched
diff options
context:
space:
mode:
authorVincent Guittot <vincent.guittot@linaro.org>2019-12-20 12:04:53 +0100
committerPeter Zijlstra <peterz@infradead.org>2020-01-17 10:19:19 +0100
commit5f68eb19b5716f8cf3ccfa833cffd1522813b0e8 (patch)
tree6cfc6190c838f5a254336451b1fa254ce2eecddf /kernel/sched
parentdb5793c5993d265fe6644b6638fcb0758f6b5347 (diff)
sched/fair : Improve update_sd_pick_busiest for spare capacity case
Similarly to calculate_imbalance() and find_busiest_group(), using the number of idle CPUs when there is only 1 CPU in the group is not efficient because we can't make a difference between a CPU running 1 task and a CPU running dozens of small tasks competing for the same CPU but not enough to overload it. More generally speaking, we should use the number of running tasks when there is the same number of idle CPUs in a group instead of blindly select the 1st one. When the groups have spare capacity and the same number of idle CPUs, we compare the number of running tasks to select the busiest group. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/1576839893-26930-1-git-send-email-vincent.guittot@linaro.org
Diffstat (limited to 'kernel/sched')
-rw-r--r--kernel/sched/fair.c14
1 files changed, 9 insertions, 5 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 2d170b5da0e3..35c105759dfa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -8181,14 +8181,18 @@ static bool update_sd_pick_busiest(struct lb_env *env,
case group_has_spare:
/*
- * Select not overloaded group with lowest number of
- * idle cpus. We could also compare the spare capacity
- * which is more stable but it can end up that the
- * group has less spare capacity but finally more idle
+ * Select not overloaded group with lowest number of idle cpus
+ * and highest number of running tasks. We could also compare
+ * the spare capacity which is more stable but it can end up
+ * that the group has less spare capacity but finally more idle
* CPUs which means less opportunity to pull tasks.
*/
- if (sgs->idle_cpus >= busiest->idle_cpus)
+ if (sgs->idle_cpus > busiest->idle_cpus)
return false;
+ else if ((sgs->idle_cpus == busiest->idle_cpus) &&
+ (sgs->sum_nr_running <= busiest->sum_nr_running))
+ return false;
+
break;
}