From 6efdb105d392da3ad5cb4ef951aed373cd049813 Mon Sep 17 00:00:00 2001 From: Byungchul Park Date: Thu, 20 Aug 2015 20:21:59 +0900 Subject: [PATCH] sched/fair: Fix switched_to_fair()'s per entity load tracking Where switched_from_fair() will remove the entity's load from the runqueue, switched_to_fair() does not currently add it back. This means that when a task leaves the fair class for a short duration; say because of PI; we loose its load contribution. This can ripple forward and disturb the load tracking because other operations (enqueue, dequeue) assume its factored in. Only once the runqueue empties will the load tracking recover. When we add it back in, age the per entity average to match up with the runqueue age. This has the obvious problem that if the task leaves the fair class for a significant time, the load will age to 0. Employ the normal migration rule for inter-runqueue moves in task_move_group_fair(). Again, there is the obvious problem of the task migrating while not in the fair class. The alternative solution would be to to omit the chunk in attach_entity_load_avg(), which would effectively reset the timestamp and use whatever avg there was. Signed-off-by: Byungchul Park [ Rewrote the changelog and comments. ] Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Thomas Gleixner Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1440069720-27038-5-git-send-email-byungchul.park@lge.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 23 +++++++++++++++++++++++ 1 file changed, 23 insertions(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 1e1fe7f796e9..5143ea0cb55b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -2712,6 +2712,20 @@ static inline void update_load_avg(struct sched_entity *se, int update_tg) static void attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { + /* + * If we got migrated (either between CPUs or between cgroups) we'll + * have aged the average right before clearing @last_update_time. + */ + if (se->avg.last_update_time) { + __update_load_avg(cfs_rq->avg.last_update_time, cpu_of(rq_of(cfs_rq)), + &se->avg, 0, 0, NULL); + + /* + * XXX: we could have just aged the entire load away if we've been + * absent from the fair class for too long. + */ + } + se->avg.last_update_time = cfs_rq->avg.last_update_time; cfs_rq->avg.load_avg += se->avg.load_avg; cfs_rq->avg.load_sum += se->avg.load_sum; @@ -7945,6 +7959,9 @@ static void switched_to_fair(struct rq *rq, struct task_struct *p) se->depth = se->parent ? se->parent->depth + 1 : 0; #endif + /* Synchronize task with its cfs_rq */ + attach_entity_load_avg(cfs_rq_of(&p->se), &p->se); + if (!task_on_rq_queued(p)) { /* @@ -8044,6 +8061,12 @@ static void task_move_group_fair(struct task_struct *p, int queued) /* Synchronize task with its prev cfs_rq */ detach_entity_load_avg(cfs_rq, se); set_task_rq(p, task_cpu(p)); + +#ifdef CONFIG_SMP + /* Tell se's cfs_rq has been changed -- migrated */ + p->se.avg.last_update_time = 0; +#endif + se->depth = se->parent ? se->parent->depth + 1 : 0; cfs_rq = cfs_rq_of(se); if (!queued) -- 2.20.1