From b0367629acf62a78404c467cd09df447c2fea804 Mon Sep 17 00:00:00 2001 From: Waiman Long Date: Wed, 2 Dec 2015 13:41:49 -0500 Subject: [PATCH] sched/fair: Move the cache-hot 'load_avg' variable into its own cacheline If a system with large number of sockets was driven to full utilization, it was found that the clock tick handling occupied a rather significant proportion of CPU time when fair group scheduling and autogroup were enabled. Running a java benchmark on a 16-socket IvyBridge-EX system, the perf profile looked like: 10.52% 0.00% java [kernel.vmlinux] [k] smp_apic_timer_interrupt 9.66% 0.05% java [kernel.vmlinux] [k] hrtimer_interrupt 8.65% 0.03% java [kernel.vmlinux] [k] tick_sched_timer 8.56% 0.00% java [kernel.vmlinux] [k] update_process_times 8.07% 0.03% java [kernel.vmlinux] [k] scheduler_tick 6.91% 1.78% java [kernel.vmlinux] [k] task_tick_fair 5.24% 5.04% java [kernel.vmlinux] [k] update_cfs_shares In particular, the high CPU time consumed by update_cfs_shares() was mostly due to contention on the cacheline that contained the task_group's load_avg statistical counter. This cacheline may also contains variables like shares, cfs_rq & se which are accessed rather frequently during clock tick processing. This patch moves the load_avg variable into another cacheline separated from the other frequently accessed variables. It also creates a cacheline aligned kmemcache for task_group to make sure that all the allocated task_group's are cacheline aligned. By doing so, the perf profile became: 9.44% 0.00% java [kernel.vmlinux] [k] smp_apic_timer_interrupt 8.74% 0.01% java [kernel.vmlinux] [k] hrtimer_interrupt 7.83% 0.03% java [kernel.vmlinux] [k] tick_sched_timer 7.74% 0.00% java [kernel.vmlinux] [k] update_process_times 7.27% 0.03% java [kernel.vmlinux] [k] scheduler_tick 5.94% 1.74% java [kernel.vmlinux] [k] task_tick_fair 4.15% 3.92% java [kernel.vmlinux] [k] update_cfs_shares The %cpu time is still pretty high, but it is better than before. The benchmark results before and after the patch was as follows: Before patch - Max-jOPs: 907533 Critical-jOps: 134877 After patch - Max-jOPs: 916011 Critical-jOps: 142366 Signed-off-by: Waiman Long Signed-off-by: Peter Zijlstra (Intel) Cc: Ben Segall Cc: Douglas Hatch Cc: Linus Torvalds Cc: Mike Galbraith Cc: Morten Rasmussen Cc: Paul Turner Cc: Peter Zijlstra Cc: Scott J Norton Cc: Thomas Gleixner Cc: Yuyang Du Link: http://lkml.kernel.org/r/1449081710-20185-3-git-send-email-Waiman.Long@hpe.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 10 +++++++--- kernel/sched/sched.h | 7 ++++++- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index d591db1..aa3f978 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7370,6 +7370,9 @@ int in_sched_functions(unsigned long addr) */ struct task_group root_task_group; LIST_HEAD(task_groups); + +/* Cacheline aligned slab cache for task_group */ +static struct kmem_cache *task_group_cache __read_mostly; #endif DECLARE_PER_CPU(cpumask_var_t, load_balance_mask); @@ -7427,11 +7430,12 @@ void __init sched_init(void) #endif /* CONFIG_RT_GROUP_SCHED */ #ifdef CONFIG_CGROUP_SCHED + task_group_cache = KMEM_CACHE(task_group, 0); + list_add(&root_task_group.list, &task_groups); INIT_LIST_HEAD(&root_task_group.children); INIT_LIST_HEAD(&root_task_group.siblings); autogroup_init(&init_task); - #endif /* CONFIG_CGROUP_SCHED */ for_each_possible_cpu(i) { @@ -7712,7 +7716,7 @@ static void free_sched_group(struct task_group *tg) free_fair_sched_group(tg); free_rt_sched_group(tg); autogroup_free(tg); - kfree(tg); + kmem_cache_free(task_group_cache, tg); } /* allocate runqueue etc for a new task group */ @@ -7720,7 +7724,7 @@ struct task_group *sched_create_group(struct task_group *parent) { struct task_group *tg; - tg = kzalloc(sizeof(*tg), GFP_KERNEL); + tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO); if (!tg) return ERR_PTR(-ENOMEM); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 472cd14..a5a6b3e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -248,7 +248,12 @@ struct task_group { unsigned long shares; #ifdef CONFIG_SMP - atomic_long_t load_avg; + /* + * load_avg can be heavily contended at clock tick time, so put + * it in its own cacheline separated from the fields above which + * will also be accessed at each tick. + */ + atomic_long_t load_avg ____cacheline_aligned; #endif #endif -- 2.7.4