Re: [PATCH v3 10/13] sched/fair: Compute task/cpu utilization at wake-up more correctly

[Wanpeng Li]

2016-08-18 18:24 GMT+08:00 Morten Rasmussen <morten.rasmussen@xxxxxxx>:
> On Thu, Aug 18, 2016 at 09:40:55AM +0100, Morten Rasmussen wrote:
>> On Mon, Aug 15, 2016 at 04:42:37PM +0100, Morten Rasmussen wrote:
>> > On Mon, Aug 15, 2016 at 04:23:42PM +0200, Peter Zijlstra wrote:
>> > > But unlike that function, it doesn't actually use __update_load_avg().
>> > > Why not?
>> >
>> > Fair question :)
>> >
>> > We currently exploit the fact that the task utilization is _not_ updated
>> > in wake-up balancing to make sure we don't under-estimate the capacity
>> > requirements for tasks that have slept for a while. If we update it, we
>> > loose the non-decayed 'peak' utilization, but I guess we could just
>> > store it somewhere when we do the wake-up decay.
>> >
>> > I thought there was a better reason when I wrote the patch, but I don't
>> > recall right now. I will look into it again and see if we can use
>> > __update_load_avg() to do a proper update instead of doing things twice.
>>
>> AFAICT, we should be able to synchronize the task utilization to the
>> previous rq utilization using __update_load_avg() as you suggest. The
>> patch below is should work as a replacement without any changes to
>> subsequent patches. It doesn't solve the under-estimation issue, but I
>> have another patch for that.
>
> And here is a possible solution to the under-estimation issue. The patch
> would have to go at the end of this set.
>
> ---8<---
>
> From 5bc918995c6c589b833ba1f189a8b92fa22202ae Mon Sep 17 00:00:00 2001
> From: Morten Rasmussen <morten.rasmussen@xxxxxxx>
> Date: Wed, 17 Aug 2016 15:30:43 +0100
> Subject: [PATCH] sched/fair: Track peak per-entity utilization
>
> When using PELT (per-entity load tracking) utilization to place tasks at
> wake-up using the decayed utilization (due to sleep) leads to
> under-estimation of true utilization of the task. This could mean
> putting the task on a cpu with less available capacity than is actually
> needed. This issue can be mitigated by using 'peak' utilization instead
> of the decayed utilization for placement decisions, e.g. at task
> wake-up.
>
> The 'peak' utilization metric, util_peak, tracks util_avg when the task
> is running and retains its previous value while the task is
> blocked/waiting on the rq. It is instantly updated to track util_avg
> again as soon as the task running again.

Maybe this will lead to disable wake affine due to a spike peak value
for a low average load task.

Regards,
Wanpeng Li

>
> cc: Ingo Molnar <mingo@xxxxxxxxxx>
> cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
>
> Signed-off-by: Morten Rasmussen <morten.rasmussen@xxxxxxx>
> ---
>  include/linux/sched.h |  2 +-
>  kernel/sched/fair.c   | 18 ++++++++++++++----
>  2 files changed, 15 insertions(+), 5 deletions(-)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 4e0c47af9b05..40e427d1d378 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1281,7 +1281,7 @@ struct load_weight {
>  struct sched_avg {
>         u64 last_update_time, load_sum;
>         u32 util_sum, period_contrib;
> -       unsigned long load_avg, util_avg;
> +       unsigned long load_avg, util_avg, util_peak;
>  };
>
>  #ifdef CONFIG_SCHEDSTATS
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 11b250531ed4..8462a3d455ff 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -692,6 +692,7 @@ void init_entity_runnable_average(struct sched_entity *se)
>          * At this point, util_avg won't be used in select_task_rq_fair anyway
>          */
>         sa->util_avg = 0;
> +       sa->util_peak = 0;
>         sa->util_sum = 0;
>         /* when this task enqueue'ed, it will contribute to its cfs_rq's load_avg */
>  }
> @@ -744,6 +745,7 @@ void post_init_entity_util_avg(struct sched_entity *se)
>                 } else {
>                         sa->util_avg = cap;
>                 }
> +               sa->util_peak = sa->util_avg;
>                 sa->util_sum = sa->util_avg * LOAD_AVG_MAX;
>         }
>
> @@ -2806,6 +2808,9 @@ __update_load_avg(u64 now, int cpu, struct sched_avg *sa,
>                 sa->util_avg = sa->util_sum / LOAD_AVG_MAX;
>         }
>
> +       if (running || sa->util_avg > sa->util_peak)
> +               sa->util_peak = sa->util_avg;
> +
>         return decayed;
>  }
>
> @@ -5174,7 +5179,7 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p,
>         return 1;
>  }
>
> -static inline int task_util(struct task_struct *p);
> +static inline int task_util_peak(struct task_struct *p);
>  static int cpu_util_wake(int cpu, struct task_struct *p);
>
>  static unsigned long capacity_spare_wake(int cpu, struct task_struct *p)
> @@ -5257,10 +5262,10 @@ find_idlest_group(struct sched_domain *sd, struct task_struct *p,
>         } while (group = group->next, group != sd->groups);
>
>         /* Found a significant amount of spare capacity. */
> -       if (this_spare > task_util(p) / 2 &&
> +       if (this_spare > task_util_peak(p) / 2 &&
>             imbalance*this_spare > 100*most_spare)
>                 return NULL;
> -       else if (most_spare > task_util(p) / 2)
> +       else if (most_spare > task_util_peak(p) / 2)
>                 return most_spare_sg;
>
>         if (!idlest || 100*this_load < imbalance*min_load)
> @@ -5423,6 +5428,11 @@ static inline int task_util(struct task_struct *p)
>         return p->se.avg.util_avg;
>  }
>
> +static inline int task_util_peak(struct task_struct *p)
> +{
> +       return p->se.avg.util_peak;
> +}
> +
>  /*
>   * cpu_util_wake: Compute cpu utilization with any contributions from
>   * the waking task p removed.
> @@ -5455,7 +5465,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu)
>         /* Bring task utilization in sync with prev_cpu */
>         sync_entity_load_avg(&p->se);
>
> -       return min_cap * 1024 < task_util(p) * capacity_margin;
> +       return min_cap * 1024 < task_util_peak(p) * capacity_margin;
>  }
>
>  /*
> --
> 1.9.1
>



-- 
Regards,
Wanpeng Li