Re: [patch v7 05/21] sched: log the cpu utilization at rq

[Paul Turner <pjt@google.com>]

On Wed, Apr 3, 2013 at 7:00 PM, Alex Shi <alex.shi@intel.com> wrote:
> The cpu's utilization is to measure how busy is the cpu.
>         util = cpu_rq(cpu)->avg.runnable_avg_sum * SCHED_POEWR_SCALE
>                 / cpu_rq(cpu)->avg.runnable_avg_period;
>
> Since the util is no more than 1, we scale its value with 1024, same as
> SCHED_POWER_SCALE and set the FULL_UTIL as 1024.
>
> In later power aware scheduling, we are sensitive for how busy of the
> cpu. Since as to power consuming, it is tight related with cpu busy
> time.
>
> BTW, rq->util can be used for any purposes if needed, not only power
> scheduling.
>
> Signed-off-by: Alex Shi <alex.shi@intel.com>

Hmm, rather than adding another variable to struct rq and another
callsite where we open code runnable-scaling we should consider at
least adding a wrapper, e.g.

/* when to_scale is a load weight callers must pass "scale_load(value)" */
static inline u32 scale_by_runnable_avg(struct sched_avg *avg, u32 to_scale) {
  u32 result = se->avg.runnable_avg_sum * to_scale;
  result /= (se->avg.runnable_avg_period + 1);
  return result;
}

util can then just be scale_by_runnable_avg(&rq->avg, FULL_UTIL) and
if we don't need it frequently, it's now simple enough that we don't
need to cache it.

> ---
>  include/linux/sched.h | 2 +-
>  kernel/sched/debug.c  | 1 +
>  kernel/sched/fair.c   | 5 +++++
>  kernel/sched/sched.h  | 4 ++++
>  4 files changed, 11 insertions(+), 1 deletion(-)
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 5a4cf37..226a515 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -793,7 +793,7 @@ enum cpu_idle_type {
>  #define SCHED_LOAD_SCALE       (1L << SCHED_LOAD_SHIFT)
>
>  /*
> - * Increase resolution of cpu_power calculations
> + * Increase resolution of cpu_power and rq->util calculations
>   */
>  #define SCHED_POWER_SHIFT      10
>  #define SCHED_POWER_SCALE      (1L << SCHED_POWER_SHIFT)
> diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
> index 75024a6..f5db759 100644
> --- a/kernel/sched/debug.c
> +++ b/kernel/sched/debug.c
> @@ -311,6 +311,7 @@ do {                                                                        \
>
>         P(ttwu_count);
>         P(ttwu_local);
> +       P(util);
>
>  #undef P
>  #undef P64
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 2e49c3f..7124244 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -1495,8 +1495,13 @@ static void update_cfs_rq_blocked_load(struct cfs_rq *cfs_rq, int force_update)
>
>  static inline void update_rq_runnable_avg(struct rq *rq, int runnable)
>  {
> +       u32 period;
>         __update_entity_runnable_avg(rq->clock_task, &rq->avg, runnable);
>         __update_tg_runnable_avg(&rq->avg, &rq->cfs);
> +
> +       period = rq->avg.runnable_avg_period ? rq->avg.runnable_avg_period : 1;
> +       rq->util = (u64)(rq->avg.runnable_avg_sum << SCHED_POWER_SHIFT)
> +                               / period;
>  }
>
>  /* Add the load generated by se into cfs_rq's child load-average */
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 804ee41..8682110 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -351,6 +351,9 @@ extern struct root_domain def_root_domain;
>
>  #endif /* CONFIG_SMP */
>
> +/* full cpu utilization */
> +#define FULL_UTIL      SCHED_POWER_SCALE
> +
>  /*
>   * This is the main, per-CPU runqueue data structure.
>   *
> @@ -482,6 +485,7 @@ struct rq {
>  #endif
>
>         struct sched_avg avg;
> +       unsigned int util;
>  };
>
>  static inline int cpu_of(struct rq *rq)
> --
> 1.7.12
>
a