From 5d4cf996cf134e8ddb4f906b8197feb9267c2b77 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Tue, 17 Dec 2013 09:21:25 +0000 Subject: sched: Assign correct scheduling domain to 'sd_llc' Commit 42eb088e (sched: Avoid NULL dereference on sd_busy) corrected a NULL dereference on sd_busy but the fix also altered what scheduling domain it used for the 'sd_llc' percpu variable. One impact of this is that a task selecting a runqueue may consider idle CPUs that are not cache siblings as candidates for running. Tasks are then running on CPUs that are not cache hot. This was found through bisection where ebizzy threads were not seeing equal performance and it looked like a scheduling fairness issue. This patch mitigates but does not completely fix the problem on all machines tested implying there may be an additional bug or a common root cause. Here are the average range of performance seen by individual ebizzy threads. It was tested on top of candidate patches related to x86 TLB range flushing. 4-core machine 3.13.0-rc3 3.13.0-rc3 vanilla fixsd-v3r3 Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%) Mean 2 0.34 ( 0.00%) 0.10 ( 70.59%) Mean 3 1.29 ( 0.00%) 0.93 ( 27.91%) Mean 4 7.08 ( 0.00%) 0.77 ( 89.12%) Mean 5 193.54 ( 0.00%) 2.14 ( 98.89%) Mean 6 151.12 ( 0.00%) 2.06 ( 98.64%) Mean 7 115.38 ( 0.00%) 2.04 ( 98.23%) Mean 8 108.65 ( 0.00%) 1.92 ( 98.23%) 8-core machine Mean 1 0.00 ( 0.00%) 0.00 ( 0.00%) Mean 2 0.40 ( 0.00%) 0.21 ( 47.50%) Mean 3 23.73 ( 0.00%) 0.89 ( 96.25%) Mean 4 12.79 ( 0.00%) 1.04 ( 91.87%) Mean 5 13.08 ( 0.00%) 2.42 ( 81.50%) Mean 6 23.21 ( 0.00%) 69.46 (-199.27%) Mean 7 15.85 ( 0.00%) 101.72 (-541.77%) Mean 8 109.37 ( 0.00%) 19.13 ( 82.51%) Mean 12 124.84 ( 0.00%) 28.62 ( 77.07%) Mean 16 113.50 ( 0.00%) 24.16 ( 78.71%) It's eliminated for one machine and reduced for another. Signed-off-by: Mel Gorman Signed-off-by: Peter Zijlstra Cc: Alex Shi Cc: Andrew Morton Cc: Fengguang Wu Cc: H Peter Anvin Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20131217092124.GV11295@suse.de Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 19af58f3a261..a88f4a485c5e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -4902,6 +4902,7 @@ DEFINE_PER_CPU(struct sched_domain *, sd_asym); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; + struct sched_domain *busy_sd = NULL; int id = cpu; int size = 1; @@ -4909,9 +4910,9 @@ static void update_top_cache_domain(int cpu) if (sd) { id = cpumask_first(sched_domain_span(sd)); size = cpumask_weight(sched_domain_span(sd)); - sd = sd->parent; /* sd_busy */ + busy_sd = sd->parent; /* sd_busy */ } - rcu_assign_pointer(per_cpu(sd_busy, cpu), sd); + rcu_assign_pointer(per_cpu(sd_busy, cpu), busy_sd); rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); per_cpu(sd_llc_size, cpu) = size; -- cgit v1.2.3 From 757dfcaa41844595964f1220f1d33182dae49976 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Wed, 27 Nov 2013 19:59:13 +0400 Subject: sched/rt: Fix rq's cpupri leak while enqueue/dequeue child RT entities This patch touches the RT group scheduling case. Functions inc_rt_prio_smp() and dec_rt_prio_smp() change (global) rq's priority, while rt_rq passed to them may be not the top-level rt_rq. This is wrong, because changing of priority on a child level does not guarantee that the priority is the highest all over the rq. So, this leak makes RT balancing unusable. The short example: the task having the highest priority among all rq's RT tasks (no one other task has the same priority) are waking on a throttle rt_rq. The rq's cpupri is set to the task's priority equivalent, but real rq->rt.highest_prio.curr is less. The patch below fixes the problem. Signed-off-by: Kirill Tkhai Signed-off-by: Peter Zijlstra CC: Steven Rostedt CC: stable@vger.kernel.org Link: http://lkml.kernel.org/r/49231385567953@web4m.yandex.ru Signed-off-by: Ingo Molnar --- kernel/sched/rt.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'kernel/sched') diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 7d57275fc396..1c4065575fa2 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -901,6 +901,13 @@ inc_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && prio < prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, prio); } @@ -910,6 +917,13 @@ dec_rt_prio_smp(struct rt_rq *rt_rq, int prio, int prev_prio) { struct rq *rq = rq_of_rt_rq(rt_rq); +#ifdef CONFIG_RT_GROUP_SCHED + /* + * Change rq's cpupri only if rt_rq is the top queue. + */ + if (&rq->rt != rt_rq) + return; +#endif if (rq->online && rt_rq->highest_prio.curr != prev_prio) cpupri_set(&rq->rd->cpupri, rq->cpu, rt_rq->highest_prio.curr); } -- cgit v1.2.3