Re: measuring system wide CPU usage ignoring idle process

[Arnaldo Carvalho de Melo <acme@kernel.org>]

Em Thu, Nov 23, 2017 at 04:15:36PM +0100, Peter Zijlstra escreveu:
> On Thu, Nov 23, 2017 at 11:42:20AM -0300, Arnaldo Carvalho de Melo wrote:
> > What is wrong with perf_event_attr.exclude_idle? :-)
> 
> Neither task- nor cpu-clock actually implement that..
> 
> Something like the _completely_untested_ below might cure that for
> cpu-clock. I have the nagging feeling we actually already account the
> idle time _somewhere_, but I couldn't remember and was too lazy to go
> find -- but someone should if this were to become an actual patch.
> 

Stephane, this was the thread,

- Arnaldo
 
> ---
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index a59fe11558a4..5386d551b373 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -8900,6 +8908,10 @@ static void cpu_clock_event_update(struct perf_event *event)
>  	u64 now;
>  
>  	now = local_clock();
> +
> +	if (event->attr.exclude_idle)
> +		now -= idle_task(event->oncpu)->se.sum_exec_runtime;
> +
>  	prev = local64_xchg(&event->hw.prev_count, now);
>  	local64_add(now - prev, &event->count);
>  }
> diff --git a/kernel/sched/idle_task.c b/kernel/sched/idle_task.c
> index d518664cce4f..419c620510c6 100644
> --- a/kernel/sched/idle_task.c
> +++ b/kernel/sched/idle_task.c
> @@ -27,9 +27,14 @@ static void check_preempt_curr_idle(struct rq *rq, struct task_struct *p, int fl
>  static struct task_struct *
>  pick_next_task_idle(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
>  {
> +	struct task_struct *idle = rq->idle;
> +
>  	put_prev_task(rq, prev);
>  	update_idle_core(rq);
>  	schedstat_inc(rq->sched_goidle);
> +
> +	idle->se.exec_start = rq_clock_task(rq);
> +
>  	return rq->idle;
>  }
>  
> @@ -48,6 +53,17 @@ dequeue_task_idle(struct rq *rq, struct task_struct *p, int flags)
>  
>  static void put_prev_task_idle(struct rq *rq, struct task_struct *prev)
>  {
> +	struct task_struct *idle = rq->idle;
> +	u64 delta, now;
> +
> +	now = rq_clock_task(rq);
> +	delta = now - idle->se.exec_start;
> +	if (unlikely((s64)delta < 0))
> +		delta = 0;
> +
> +	idle->se.sum_exec_runtime += delta;
> +	idle->se.exec_start = now;
> +
>  	rq_last_tick_reset(rq);
>  }
>  
> @@ -57,6 +73,9 @@ static void task_tick_idle(struct rq *rq, struct task_struct *curr, int queued)
>  
>  static void set_curr_task_idle(struct rq *rq)
>  {
> +	struct task_struct *idle = rq->idle;
> +
> +	idle->se.exec_start = rq_clock_task(rq);
>  }
>  
>  static void switched_to_idle(struct rq *rq, struct task_struct *p)