aboutsummaryrefslogtreecommitdiff
path: root/kernel/sched/fair.c
diff options
context:
space:
mode:
authorVincent Guittot <vincent.guittot@linaro.org>2020-07-10 17:24:26 +0200
committerPeter Zijlstra <peterz@infradead.org>2020-07-16 23:19:48 +0200
commit01cfcde9c26d8555f0e6e9aea9d6049f87683998 (patch)
tree1e14dfeca6f69e6c3ce3b0c3f46f2742c7678432 /kernel/sched/fair.c
parentce3614daabea8a2d01c1dd17ae41d1ec5e5ae7db (diff)
downloadlinux-01cfcde9c26d8555f0e6e9aea9d6049f87683998.tar.gz
sched/fair: handle case of task_h_load() returning 0
task_h_load() can return 0 in some situations like running stress-ng mmapfork, which forks thousands of threads, in a sched group on a 224 cores system. The load balance doesn't handle this correctly because env->imbalance never decreases and it will stop pulling tasks only after reaching loop_max, which can be equal to the number of running tasks of the cfs. Make sure that imbalance will be decreased by at least 1. misfit task is the other feature that doesn't handle correctly such situation although it's probably more difficult to face the problem because of the smaller number of CPUs and running tasks on heterogenous system. We can't simply ensure that task_h_load() returns at least one because it would imply to handle underflow in other places. Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Valentin Schneider <valentin.schneider@arm.com> Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com> Cc: <stable@vger.kernel.org> # v4.4+ Link: https://lkml.kernel.org/r/20200710152426.16981-1-vincent.guittot@linaro.org
Diffstat (limited to 'kernel/sched/fair.c')
-rw-r--r--kernel/sched/fair.c15
1 files changed, 13 insertions, 2 deletions
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 658aa7a2ae6f..04fa8dbcfa4d 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4039,7 +4039,11 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
return;
}
- rq->misfit_task_load = task_h_load(p);
+ /*
+ * Make sure that misfit_task_load will not be null even if
+ * task_h_load() returns 0.
+ */
+ rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
}
#else /* CONFIG_SMP */
@@ -7638,7 +7642,14 @@ static int detach_tasks(struct lb_env *env)
switch (env->migration_type) {
case migrate_load:
- load = task_h_load(p);
+ /*
+ * Depending of the number of CPUs and tasks and the
+ * cgroup hierarchy, task_h_load() can return a null
+ * value. Make sure that env->imbalance decreases
+ * otherwise detach_tasks() will stop only after
+ * detaching up to loop_max tasks.
+ */
+ load = max_t(unsigned long, task_h_load(p), 1);
if (sched_feat(LB_MIN) &&
load < 16 && !env->sd->nr_balance_failed)