sched/fair: Let asymmetric CPU configurations balance at wake-up
Currently, SD_WAKE_AFFINE always takes priority over wakeup balancing if SD_BALANCE_WAKE is set on the sched_domains. For asymmetric configurations SD_WAKE_AFFINE is only desirable if the waking task's compute demand (utilization) is suitable for the waking CPU and the previous CPU, and all CPUs within their respective SD_SHARE_PKG_RESOURCES domains (sd_llc). If not, let wakeup balancing take over (find_idlest_{group, cpu}()). This patch makes affine wake-ups conditional on whether both the waker CPU and the previous CPU has sufficient capacity for the waking task, or not, assuming that the CPU capacities within an SD_SHARE_PKG_RESOURCES domain (sd_llc) are homogeneous. Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Vincent Guittot <vincent.guittot@linaro.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mike Galbraith <efault@gmx.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: dietmar.eggemann@arm.com Cc: freedom.tan@mediatek.com Cc: keita.kobayashi.ym@renesas.com Cc: mgalbraith@suse.de Cc: sgurrappadi@nvidia.com Cc: yuyang.du@intel.com Link: http://lkml.kernel.org/r/1469453670-2660-10-git-send-email-morten.rasmussen@arm.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
cd92bfd3b8
commit
3273163c67
|
@ -114,6 +114,12 @@ unsigned int __read_mostly sysctl_sched_shares_window = 10000000UL;
|
||||||
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
|
unsigned int sysctl_sched_cfs_bandwidth_slice = 5000UL;
|
||||||
#endif
|
#endif
|
||||||
|
|
||||||
|
/*
|
||||||
|
* The margin used when comparing utilization with CPU capacity:
|
||||||
|
* util * 1024 < capacity * margin
|
||||||
|
*/
|
||||||
|
unsigned int capacity_margin = 1280; /* ~20% */
|
||||||
|
|
||||||
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
|
static inline void update_load_add(struct load_weight *lw, unsigned long inc)
|
||||||
{
|
{
|
||||||
lw->weight += inc;
|
lw->weight += inc;
|
||||||
|
@ -5376,6 +5382,32 @@ static int cpu_util(int cpu)
|
||||||
return (util >= capacity) ? capacity : util;
|
return (util >= capacity) ? capacity : util;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
static inline int task_util(struct task_struct *p)
|
||||||
|
{
|
||||||
|
return p->se.avg.util_avg;
|
||||||
|
}
|
||||||
|
|
||||||
|
/*
|
||||||
|
* Disable WAKE_AFFINE in the case where task @p doesn't fit in the
|
||||||
|
* capacity of either the waking CPU @cpu or the previous CPU @prev_cpu.
|
||||||
|
*
|
||||||
|
* In that case WAKE_AFFINE doesn't make sense and we'll let
|
||||||
|
* BALANCE_WAKE sort things out.
|
||||||
|
*/
|
||||||
|
static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
|
||||||
|
{
|
||||||
|
long min_cap, max_cap;
|
||||||
|
|
||||||
|
min_cap = min(capacity_orig_of(prev_cpu), capacity_orig_of(cpu));
|
||||||
|
max_cap = cpu_rq(cpu)->rd->max_cpu_capacity;
|
||||||
|
|
||||||
|
/* Minimum capacity is close to max, no need to abort wake_affine */
|
||||||
|
if (max_cap - min_cap < max_cap >> 3)
|
||||||
|
return 0;
|
||||||
|
|
||||||
|
return min_cap * 1024 < task_util(p) * capacity_margin;
|
||||||
|
}
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* select_task_rq_fair: Select target runqueue for the waking task in domains
|
* select_task_rq_fair: Select target runqueue for the waking task in domains
|
||||||
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
|
* that have the 'sd_flag' flag set. In practice, this is SD_BALANCE_WAKE,
|
||||||
|
@ -5399,7 +5431,8 @@ select_task_rq_fair(struct task_struct *p, int prev_cpu, int sd_flag, int wake_f
|
||||||
|
|
||||||
if (sd_flag & SD_BALANCE_WAKE) {
|
if (sd_flag & SD_BALANCE_WAKE) {
|
||||||
record_wakee(p);
|
record_wakee(p);
|
||||||
want_affine = !wake_wide(p) && cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
|
want_affine = !wake_wide(p) && !wake_cap(p, cpu, prev_cpu)
|
||||||
|
&& cpumask_test_cpu(cpu, tsk_cpus_allowed(p));
|
||||||
}
|
}
|
||||||
|
|
||||||
rcu_read_lock();
|
rcu_read_lock();
|
||||||
|
|
Loading…
Reference in New Issue