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 <waiman.l...@hpe.com>
---
kernel/sched/core.c | 36 ++++++++++++++++++++++++++++++++++--
kernel/sched/sched.h | 7 ++++++-
2 files changed, 40 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 4d568ac..e39204f 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7331,6 +7331,11 @@ int in_sched_functions(unsigned long addr)
*/
struct task_group root_task_group;
LIST_HEAD(task_groups);
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
+/* Cacheline aligned slab cache for task_group */
+static struct kmem_cache *task_group_cache __read_mostly;
+#endif
#endif
DECLARE_PER_CPU(cpumask_var_t, load_balance_mask);
@@ -7356,6 +7361,7 @@ void __init sched_init(void)
root_task_group.cfs_rq = (struct cfs_rq **)ptr;
ptr += nr_cpu_ids * sizeof(void **);
+ task_group_cache = KMEM_CACHE(task_group, SLAB_HWCACHE_ALIGN);
#endif /* CONFIG_FAIR_GROUP_SCHED */
#ifdef CONFIG_RT_GROUP_SCHED
root_task_group.rt_se = (struct sched_rt_entity **)ptr;
@@ -7668,12 +7674,38 @@ void set_curr_task(int cpu, struct task_struct *p)
/* task_group_lock serializes the addition/removal of task groups */
static DEFINE_SPINLOCK(task_group_lock);
+/*
+ * Make sure that the task_group structure is cacheline aligned when
+ * fair group scheduling is enabled.
+ */
+#ifdef CONFIG_FAIR_GROUP_SCHED
+static inline struct task_group *alloc_task_group(void)
+{
+ return kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
+}
+
+static inline void free_task_group(struct task_group *tg)
+{
+ kmem_cache_free(task_group_cache, tg);
+}
+#else /* CONFIG_FAIR_GROUP_SCHED */
+static inline struct task_group *alloc_task_group(void)
+{
+ return kzalloc(sizeof(struct task_group), GFP_KERNEL);
+}
+
+static inline void free_task_group(struct task_group *tg)
+{
+ kfree(tg);
+}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
static void free_sched_group(struct task_group *tg)
{
free_fair_sched_group(tg);
free_rt_sched_group(tg);
autogroup_free(tg);
- kfree(tg);
+ free_task_group(tg);
}
/* allocate runqueue etc for a new task group */
@@ -7681,7 +7713,7 @@ struct task_group *sched_create_group(struct task_group
*parent)
{
struct task_group *tg;
- tg = kzalloc(sizeof(*tg), GFP_KERNEL);
+ tg = alloc_task_group();
if (!tg)
return ERR_PTR(-ENOMEM);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index efd3bfc..e679895 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
--
1.7.1
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
