Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]
Groups > linux.kernel > #1209664
| From | byungchul.park@lge.com |
|---|---|
| Newsgroups | linux.kernel |
| Subject | [PATCH v3 3/5] sched: sync a se with prev cfs_rq when changing cgroup |
| Date | 2015-08-19 08:50 +0200 |
| Message-ID | <pZ5ma-6uL-17@gated-at.bofh.it> (permalink) |
| References | <pZ5m9-6uL-1@gated-at.bofh.it> |
| Organization | linux.* mail to news gateway |
From: Byungchul Park <byungchul.park@lge.com> current code is wrong with cfs_rq's average load when changing a task's cfs_rq to another. i tested with "echo pid > cgroup" and found that e.g. cfs_rq->avg.load_avg became larger and larger whenever changing cgroup to another again and again. we have to sync se's average load with both *prev* cfs_rq and next cfs_rq when changing its cgroup. Signed-off-by: Byungchul Park <byungchul.park@lge.com> --- kernel/sched/fair.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 191d9be..1be042a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -8040,8 +8040,14 @@ static void task_move_group_fair(struct task_struct *p, int queued) if (!queued && (!se->sum_exec_runtime || p->state == TASK_WAKING)) queued = 1; + cfs_rq = cfs_rq_of(se); if (!queued) - se->vruntime -= cfs_rq_of(se)->min_vruntime; + se->vruntime -= cfs_rq->min_vruntime; + +#ifdef CONFIG_SMP + /* synchronize task with its prev cfs_rq */ + detach_entity_load_avg(cfs_rq, se); +#endif set_task_rq(p, task_cpu(p)); se->depth = se->parent ? se->parent->depth + 1 : 0; cfs_rq = cfs_rq_of(se); -- 1.7.9.5 -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread
[PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it byungchul.park@lge.com - 2015-08-19 08:50 +0200
[PATCH v3 2/5] sched: make task_move_group_fair adjust cfs_rq's load in case of queued byungchul.park@lge.com - 2015-08-19 08:50 +0200
[PATCH v3 5/5] sched: add two functions for att(det)aching a task to(from) a cfs_rq byungchul.park@lge.com - 2015-08-19 08:50 +0200
[PATCH v3 1/5] sched: add two functions adjusting cfs_rq's load when att(det)aching a se byungchul.park@lge.com - 2015-08-19 08:50 +0200
[PATCH v3 3/5] sched: sync a se with prev cfs_rq when changing cgroup byungchul.park@lge.com - 2015-08-19 08:50 +0200
[PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class byungchul.park@lge.com - 2015-08-19 08:50 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Peter Zijlstra <peterz@infradead.org> - 2015-08-19 19:20 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Yuyang Du <yuyang.du@intel.com> - 2015-08-20 06:10 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Byungchul Park <byungchul.park@lge.com> - 2015-08-20 08:20 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Peter Zijlstra <peterz@infradead.org> - 2015-08-20 23:20 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Byungchul Park <byungchul.park@lge.com> - 2015-08-21 02:00 +0200
Re: [PATCH v3 4/5] sched: sync a se with its cfs_rq when switching sched class to fair class Byungchul Park <byungchul.park@lge.com> - 2015-08-20 07:30 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Byungchul Park <byungchul.park@lge.com> - 2015-08-19 09:10 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Peter Zijlstra <peterz@infradead.org> - 2015-08-20 03:20 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Byungchul Park <byungchul.park@lge.com> - 2015-08-20 07:30 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Byungchul Park <byungchul.park@lge.com> - 2015-08-20 10:40 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Byungchul Park <byungchul.park@lge.com> - 2015-08-20 12:50 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Peter Zijlstra <peterz@infradead.org> - 2015-08-20 23:20 +0200
Re: [PATCH v3 0/5] sync a se with its cfs_rq when att(det)aching it Byungchul Park <byungchul.park@lge.com> - 2015-08-21 02:10 +0200
csiph-web