Re: [RFC PATCH v3] sched/fair: select idle cpu from idle cpumask for task wakeup

["Li, Aubrey" <aubrey.li@linux.intel.com>]

On 2020/11/6 15:58, Vincent Guittot wrote:
> On Wed, 21 Oct 2020 at 17:05, Aubrey Li <aubrey.li@linux.intel.com> wrote:
>>
>> From: Aubrey Li <aubrey.li@intel.com>
>>
>> Added idle cpumask to track idle cpus in sched domain. When a CPU
>> enters idle, its corresponding bit in the idle cpumask will be set,
>> and when the CPU exits idle, its bit will be cleared.
>>
>> When a task wakes up to select an idle cpu, scanning idle cpumask
>> has low cost than scanning all the cpus in last level cache domain,
>> especially when the system is heavily loaded.
>>
>> v2->v3:
>> - change setting idle cpumask to every idle entry, otherwise schbench
>>   has a regression of 99th percentile latency.
>> - change clearing idle cpumask to nohz_balancer_kick(), so updating
>>   idle cpumask is ratelimited in the idle exiting path.
>> - set SCHED_IDLE cpu in idle cpumask to allow it as a wakeup target.
>>
>> v1->v2:
>> - idle cpumask is updated in the nohz routines, by initializing idle
>>   cpumask with sched_domain_span(sd), nohz=off case remains the original
>>   behavior.
>>
>> Cc: Mel Gorman <mgorman@suse.de>
>> Cc: Vincent Guittot <vincent.guittot@linaro.org>
>> Cc: Qais Yousef <qais.yousef@arm.com>
>> Cc: Valentin Schneider <valentin.schneider@arm.com>
>> Cc: Jiang Biao <benbjiang@gmail.com>
>> Cc: Tim Chen <tim.c.chen@linux.intel.com>
>> Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
>> ---
>>  include/linux/sched/topology.h | 13 ++++++++++
>>  kernel/sched/fair.c            | 45 +++++++++++++++++++++++++++++++++-
>>  kernel/sched/idle.c            |  1 +
>>  kernel/sched/sched.h           |  1 +
>>  kernel/sched/topology.c        |  3 ++-
>>  5 files changed, 61 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
>> index fb11091129b3..43a641d26154 100644
>> --- a/include/linux/sched/topology.h
>> +++ b/include/linux/sched/topology.h
>> @@ -65,8 +65,21 @@ struct sched_domain_shared {
>>         atomic_t        ref;
>>         atomic_t        nr_busy_cpus;
>>         int             has_idle_cores;
>> +       /*
>> +        * Span of all idle CPUs in this domain.
>> +        *
>> +        * NOTE: this field is variable length. (Allocated dynamically
>> +        * by attaching extra space to the end of the structure,
>> +        * depending on how many CPUs the kernel has booted up with)
>> +        */
>> +       unsigned long   idle_cpus_span[];
>>  };
>>
>> +static inline struct cpumask *sds_idle_cpus(struct sched_domain_shared *sds)
>> +{
>> +       return to_cpumask(sds->idle_cpus_span);
>> +}
>> +
>>  struct sched_domain {
>>         /* These fields must be setup */
>>         struct sched_domain __rcu *parent;      /* top domain must be null terminated */
>> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
>> index 6b3b59cc51d6..088d1995594f 100644
>> --- a/kernel/sched/fair.c
>> +++ b/kernel/sched/fair.c
>> @@ -6023,6 +6023,38 @@ void __update_idle_core(struct rq *rq)
>>         rcu_read_unlock();
>>  }
>>
>> +static DEFINE_PER_CPU(bool, cpu_idle_state);
>> +/*
>> + * Update cpu idle state and record this information
>> + * in sd_llc_shared->idle_cpus_span.
>> + */
>> +void update_idle_cpumask(struct rq *rq, bool idle_state)
>> +{
>> +       struct sched_domain *sd;
>> +       int cpu = cpu_of(rq);
>> +
>> +       /*
>> +        * No need to update idle cpumask if the state
>> +        * does not change.
>> +        */
>> +       if (per_cpu(cpu_idle_state, cpu) == idle_state)
>> +               return;
>> +
>> +       per_cpu(cpu_idle_state, cpu) = idle_state;
>> +
>> +       rcu_read_lock();
>> +
>> +       sd = rcu_dereference(per_cpu(sd_llc, cpu));
>> +       if (!sd || !sd->shared)
>> +               goto unlock;
>> +       if (idle_state)
>> +               cpumask_set_cpu(cpu, sds_idle_cpus(sd->shared));
>> +       else
>> +               cpumask_clear_cpu(cpu, sds_idle_cpus(sd->shared));
>> +unlock:
>> +       rcu_read_unlock();
>> +}
>> +
>>  /*
>>   * Scan the entire LLC domain for idle cores; this dynamically switches off if
>>   * there are no idle cores left in the system; tracked through
>> @@ -6136,7 +6168,12 @@ static int select_idle_cpu(struct task_struct *p, struct sched_domain *sd, int t
>>
>>         time = cpu_clock(this);
>>
>> -       cpumask_and(cpus, sched_domain_span(sd), p->cpus_ptr);
>> +       /*
>> +        * sched_domain_shared is set only at shared cache level,
>> +        * this works only because select_idle_cpu is called with
>> +        * sd_llc.
>> +        */
>> +       cpumask_and(cpus, sds_idle_cpus(sd->shared), p->cpus_ptr);
>>
>>         for_each_cpu_wrap(cpu, cpus, target) {
>>                 if (!--nr)
>> @@ -10070,6 +10107,12 @@ static void nohz_balancer_kick(struct rq *rq)
>>         if (unlikely(rq->idle_balance))
>>                 return;
>>
>> +       /* The CPU is not in idle, update idle cpumask */
>> +       if (unlikely(sched_idle_cpu(cpu))) {
>> +               /* Allow SCHED_IDLE cpu as a wakeup target */
>> +               update_idle_cpumask(rq, true);
>> +       } else
>> +               update_idle_cpumask(rq, false);
> 
> update_idle_cpumask(rq, sched_idle_cpu(cpu)); ?

This looks much better, thanks! :)