From a426f99c91d1036767a7819aaaba6bd3191b7f06 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 25 Nov 2015 14:09:38 -0500 Subject: sched/fair: Avoid redundant idle_cpu() call in update_sg_lb_stats() Part of the responsibility of the update_sg_lb_stats() function is to update the idle_cpus statistical counter in struct sg_lb_stats. This check is done by calling idle_cpu(). The idle_cpu() function, in turn, checks a number of fields within the run queue structure such as rq->curr and rq->nr_running. With the current layout of the run queue structure, rq->curr and rq->nr_running are in separate cachelines. The rq->curr variable is checked first followed by nr_running. As nr_running is also accessed by update_sg_lb_stats() earlier, it makes no sense to load another cacheline when nr_running is not 0 as idle_cpu() will always return false in this case. This patch eliminates this redundant cacheline load by checking the cached nr_running before calling idle_cpu(). Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Cc: Douglas Hatch Cc: Linus Torvalds Cc: Mike Galbraith Cc: Peter Zijlstra Cc: Scott J Norton Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1448478580-26467-2-git-send-email-Waiman.Long@hpe.com Signed-off-by: Ingo Molnar --- kernel/sched/fair.c | 10 +++++++--- 1 file changed, 7 insertions(+), 3 deletions(-) (limited to 'kernel/sched') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index efd664c4926e..4b0e8b8700fd 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6398,7 +6398,7 @@ static inline void update_sg_lb_stats(struct lb_env *env, bool *overload) { unsigned long load; - int i; + int i, nr_running; memset(sgs, 0, sizeof(*sgs)); @@ -6415,7 +6415,8 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->group_util += cpu_util(i); sgs->sum_nr_running += rq->cfs.h_nr_running; - if (rq->nr_running > 1) + nr_running = rq->nr_running; + if (nr_running > 1) *overload = true; #ifdef CONFIG_NUMA_BALANCING @@ -6423,7 +6424,10 @@ static inline void update_sg_lb_stats(struct lb_env *env, sgs->nr_preferred_running += rq->nr_preferred_running; #endif sgs->sum_weighted_load += weighted_cpuload(i); - if (idle_cpu(i)) + /* + * No need to call idle_cpu() if nr_running is not 0 + */ + if (!nr_running && idle_cpu(i)) sgs->idle_cpus++; } -- cgit v1.2.3