diff options
| author | Peter Zijlstra <peterz@infradead.org> | 2013-07-04 12:56:46 +0800 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2013-07-23 12:22:06 +0200 |
| commit | 7d9ffa8961482232d964173cccba6e14d2d543b2 (patch) | |
| tree | 80fd615fb64b1bd82e0de0e5d1e8be2bae8cb06d /kernel/sched | |
| parent | 62470419e993f8d9d93db0effd3af4296ecb79a5 (diff) | |
| download | linux-7d9ffa8961482232d964173cccba6e14d2d543b2.tar.gz linux-7d9ffa8961482232d964173cccba6e14d2d543b2.tar.bz2 linux-7d9ffa8961482232d964173cccba6e14d2d543b2.zip | |
sched: Micro-optimize the smart wake-affine logic
Smart wake-affine is using node-size as the factor currently, but the overhead
of the mask operation is high.
Thus, this patch introduce the 'sd_llc_size' percpu variable, which will record
the highest cache-share domain size, and make it to be the new factor, in order
to reduce the overhead and make it more reasonable.
Tested-by: Davidlohr Bueso <davidlohr.bueso@hp.com>
Tested-by: Michael Wang <wangyun@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Michael Wang <wangyun@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Link: http://lkml.kernel.org/r/51D5008E.6030102@linux.vnet.ibm.com
[ Tidied up the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'kernel/sched')
| -rw-r--r-- | kernel/sched/core.c | 7 | ||||
| -rw-r--r-- | kernel/sched/fair.c | 2 | ||||
| -rw-r--r-- | kernel/sched/sched.h | 1 |
3 files changed, 8 insertions, 2 deletions
diff --git a/kernel/sched/core.c b/kernel/sched/core.c index b7c32cb7bfeb..6df0fbe53767 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -5083,18 +5083,23 @@ static void destroy_sched_domains(struct sched_domain *sd, int cpu) * two cpus are in the same cache domain, see cpus_share_cache(). */ DEFINE_PER_CPU(struct sched_domain *, sd_llc); +DEFINE_PER_CPU(int, sd_llc_size); DEFINE_PER_CPU(int, sd_llc_id); static void update_top_cache_domain(int cpu) { struct sched_domain *sd; int id = cpu; + int size = 1; sd = highest_flag_domain(cpu, SD_SHARE_PKG_RESOURCES); - if (sd) + if (sd) { id = cpumask_first(sched_domain_span(sd)); + size = cpumask_weight(sched_domain_span(sd)); + } rcu_assign_pointer(per_cpu(sd_llc, cpu), sd); + per_cpu(sd_llc_size, cpu) = size; per_cpu(sd_llc_id, cpu) = id; } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 860063a8c849..f237437446e5 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3175,7 +3175,7 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu, static int wake_wide(struct task_struct *p) { - int factor = nr_cpus_node(cpu_to_node(smp_processor_id())); + int factor = this_cpu_read(sd_llc_size); /* * Yeah, it's the switching-frequency, could means many wakee or diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 5e129efb84ce..4c1cb8029feb 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -594,6 +594,7 @@ static inline struct sched_domain *highest_flag_domain(int cpu, int flag) } DECLARE_PER_CPU(struct sched_domain *, sd_llc); +DECLARE_PER_CPU(int, sd_llc_size); DECLARE_PER_CPU(int, sd_llc_id); struct sched_group_power { |