Re: [PATCH 1/2] sched/fair: Add cfs bandwidth burst statistics

[Benjamin Segall]

Huaixin Chang <changhuaixin@xxxxxxxxxxxxxxxxx> writes:

> Two new statistics are introduced to show the internal of burst feature
> and explain why burst helps or not.
>
> nr_bursts:  number of periods bandwidth burst occurs
> burst_time: cumulative wall-time (in nanoseconds) that any cpus has
> 	    used above quota in respective periods
>
> Co-developed-by: Shanpei Chen <shanpeic@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Shanpei Chen <shanpeic@xxxxxxxxxxxxxxxxx>
> Co-developed-by: Tianchen Ding <dtcccc@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Tianchen Ding <dtcccc@xxxxxxxxxxxxxxxxx>
> Signed-off-by: Huaixin Chang <changhuaixin@xxxxxxxxxxxxxxxxx>

Reviewed-by: Ben Segall <bsegall@xxxxxxxxxx>

I know there's some worry about the overhead of a constantly increasing
amount of statistics, but as far as the implementation of this goes, it
looks good to me.

> ---
>  kernel/sched/core.c  | 13 ++++++++++---
>  kernel/sched/fair.c  |  9 +++++++++
>  kernel/sched/sched.h |  3 +++
>  3 files changed, 22 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 20ffcc044134..d00b92712253 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -10068,6 +10068,9 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
>  		seq_printf(sf, "wait_sum %llu\n", ws);
>  	}
>  
> +	seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst);
> +	seq_printf(sf, "burst_time %llu\n", cfs_b->burst_time);
> +
>  	return 0;
>  }
>  #endif /* CONFIG_CFS_BANDWIDTH */
> @@ -10164,16 +10167,20 @@ static int cpu_extra_stat_show(struct seq_file *sf,
>  	{
>  		struct task_group *tg = css_tg(css);
>  		struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
> -		u64 throttled_usec;
> +		u64 throttled_usec, burst_usec;
>  
>  		throttled_usec = cfs_b->throttled_time;
>  		do_div(throttled_usec, NSEC_PER_USEC);
> +		burst_usec = cfs_b->burst_time;
> +		do_div(burst_usec, NSEC_PER_USEC);
>  
>  		seq_printf(sf, "nr_periods %d\n"
>  			   "nr_throttled %d\n"
> -			   "throttled_usec %llu\n",
> +			   "throttled_usec %llu\n"
> +			   "nr_bursts %d\n"
> +			   "burst_usec %llu\n",
>  			   cfs_b->nr_periods, cfs_b->nr_throttled,
> -			   throttled_usec);
> +			   throttled_usec, cfs_b->nr_burst, burst_usec);
>  	}
>  #endif
>  	return 0;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 44c452072a1b..464371f364f1 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4655,11 +4655,20 @@ static inline u64 sched_cfs_bandwidth_slice(void)
>   */
>  void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
>  {
> +	s64 runtime;
> +
>  	if (unlikely(cfs_b->quota == RUNTIME_INF))
>  		return;
>  
>  	cfs_b->runtime += cfs_b->quota;
> +	runtime = cfs_b->runtime_snap - cfs_b->runtime;
> +	if (runtime > 0) {
> +		cfs_b->burst_time += runtime;
> +		cfs_b->nr_burst++;
> +	}
> +
>  	cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
> +	cfs_b->runtime_snap = cfs_b->runtime;
>  }
>  
>  static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 14a41a243f7b..80e4322727b4 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -367,6 +367,7 @@ struct cfs_bandwidth {
>  	u64			quota;
>  	u64			runtime;
>  	u64			burst;
> +	u64			runtime_snap;
>  	s64			hierarchical_quota;
>  
>  	u8			idle;
> @@ -379,7 +380,9 @@ struct cfs_bandwidth {
>  	/* Statistics: */
>  	int			nr_periods;
>  	int			nr_throttled;
> +	int			nr_burst;
>  	u64			throttled_time;
> +	u64			burst_time;
>  #endif
>  };