Re: [PATCH v5 10/14] sched/cpufreq: Refactor the utilization aggregation method

[skannan@codeaurora.org]

On 2018-07-24 05:25, Quentin Perret wrote:
> Schedutil aggregates the PELT signals of CFS, RT, DL and IRQ in order
> to decide which frequency to request. Energy Aware Scheduling (EAS)
> needs to be able to predict those requests to assess the energy impact
> of scheduling decisions. However, the PELT signals aggregation is only
> done in schedutil for now, hence making it hard to synchronize it with
> EAS.
> 
> To address this issue, introduce schedutil_freq_util() to perform the
> aforementioned aggregation and make it available to other parts of the
> scheduler. Since frequency selection and energy estimation still need
> to deal with RT and DL signals slightly differently, 
> schedutil_freq_util()
> is called with a different 'type' parameter in those two contexts, and
> returns an aggregated utilization signal accordingly.
> 
> Cc: Ingo Molnar <mingo@redhat.com>
> Cc: Peter Zijlstra <peterz@infradead.org>
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Signed-off-by: Quentin Perret <quentin.perret@arm.com>
> ---
>  kernel/sched/cpufreq_schedutil.c | 86 +++++++++++++++++++++-----------
>  kernel/sched/sched.h             | 14 ++++++
>  2 files changed, 72 insertions(+), 28 deletions(-)
> 
> diff --git a/kernel/sched/cpufreq_schedutil.c 
> b/kernel/sched/cpufreq_schedutil.c
> index 810193c8e4cd..af86050edcf5 100644
> --- a/kernel/sched/cpufreq_schedutil.c
> +++ b/kernel/sched/cpufreq_schedutil.c
> @@ -198,15 +198,15 @@ static unsigned int get_next_freq(struct
> sugov_policy *sg_policy,
>   * based on the task model parameters and gives the minimal 
> utilization
>   * required to meet deadlines.
>   */
> -static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
> +unsigned long schedutil_freq_util(int cpu, unsigned long util_cfs,
> +				  enum schedutil_type type)
>  {
> -	struct rq *rq = cpu_rq(sg_cpu->cpu);
> +	struct rq *rq = cpu_rq(cpu);
>  	unsigned long util, irq, max;
> 
> -	sg_cpu->max = max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
> -	sg_cpu->bw_dl = cpu_bw_dl(rq);
> +	max = arch_scale_cpu_capacity(NULL, cpu);
> 
> -	if (rt_rq_is_runnable(&rq->rt))
> +	if (type == frequency_util && rt_rq_is_runnable(&rq->rt))
>  		return max;
> 
>  	/*
> @@ -224,20 +224,33 @@ static unsigned long sugov_get_util(struct
> sugov_cpu *sg_cpu)
>  	 * utilization (PELT windows are synchronized) we can directly add 
> them
>  	 * to obtain the CPU's actual utilization.
>  	 */
> -	util = cpu_util_cfs(rq);
> +	util = util_cfs;
>  	util += cpu_util_rt(rq);
> 
> -	/*
> -	 * We do not make cpu_util_dl() a permanent part of this sum because 
> we
> -	 * want to use cpu_bw_dl() later on, but we need to check if the
> -	 * CFS+RT+DL sum is saturated (ie. no idle time) such that we select
> -	 * f_max when there is no idle time.
> -	 *
> -	 * NOTE: numerical errors or stop class might cause us to not quite 
> hit
> -	 * saturation when we should -- something for later.
> -	 */
> -	if ((util + cpu_util_dl(rq)) >= max)
> -		return max;
> +	if (type == frequency_util) {
> +		/*
> +		 * For frequency selection we do not make cpu_util_dl() a
> +		 * permanent part of this sum because we want to use
> +		 * cpu_bw_dl() later on, but we need to check if the
> +		 * CFS+RT+DL sum is saturated (ie. no idle time) such
> +		 * that we select f_max when there is no idle time.
> +		 *
> +		 * NOTE: numerical errors or stop class might cause us
> +		 * to not quite hit saturation when we should --
> +		 * something for later.
> +		 */
> +
> +		if ((util + cpu_util_dl(rq)) >= max)
> +			return max;
> +	} else {
> +		/*
> +		 * OTOH, for energy computation we need the estimated
> +		 * running time, so include util_dl and ignore dl_bw.
> +		 */
> +		util += cpu_util_dl(rq);
> +		if (util >= max)
> +			return max;
> +	}

If it's going to be a different aggregation from what's done for 
frequency guidance, I don't see the point of having this inside 
schedutil. Why not keep it inside the scheduler files? Also, it seems 
weird to use a governor's code when it might not actually be in use. 
What if someone is using ondemand, conservative, performance, etc?

> 
>  	/*
>  	 * There is still idle time; further improve the number by using the
> @@ -252,17 +265,34 @@ static unsigned long sugov_get_util(struct
> sugov_cpu *sg_cpu)
>  	util /= max;
>  	util += irq;
> 
> -	/*
> -	 * Bandwidth required by DEADLINE must always be granted while, for
> -	 * FAIR and RT, we use blocked utilization of IDLE CPUs as a 
> mechanism
> -	 * to gracefully reduce the frequency when no tasks show up for 
> longer
> -	 * periods of time.
> -	 *
> -	 * Ideally we would like to set bw_dl as min/guaranteed freq and util 
> +
> -	 * bw_dl as requested freq. However, cpufreq is not yet ready for 
> such
> -	 * an interface. So, we only do the latter for now.
> -	 */
> -	return min(max, util + sg_cpu->bw_dl);
> +	if (type == frequency_util) {
> +		/*
> +		 * Bandwidth required by DEADLINE must always be granted
> +		 * while, for FAIR and RT, we use blocked utilization of
> +		 * IDLE CPUs as a mechanism to gracefully reduce the
> +		 * frequency when no tasks show up for longer periods of
> +		 * time.
> +		 *
> +		 * Ideally we would like to set bw_dl as min/guaranteed
> +		 * freq and util + bw_dl as requested freq. However,
> +		 * cpufreq is not yet ready for such an interface. So,
> +		 * we only do the latter for now.
> +		 */
> +		util += cpu_bw_dl(rq);
> +	}

Instead of all this indentation, can't you just return early without 
doing the code inside the if?

> +
> +	return min(max, util);
> +}
> +
> +static unsigned long sugov_get_util(struct sugov_cpu *sg_cpu)
> +{
> +	struct rq *rq = cpu_rq(sg_cpu->cpu);
> +	unsigned long util = cpu_util_cfs(rq);
> +
> +	sg_cpu->max = arch_scale_cpu_capacity(NULL, sg_cpu->cpu);
> +	sg_cpu->bw_dl = cpu_bw_dl(rq);
> +
> +	return schedutil_freq_util(sg_cpu->cpu, util, frequency_util);
>  }
> 
>  /**
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 6d08ccd1e7a4..51e7f113ee23 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -2185,7 +2185,15 @@ static inline void cpufreq_update_util(struct
> rq *rq, unsigned int flags) {}
>  # define arch_scale_freq_invariant()	false
>  #endif
> 
> +enum schedutil_type {
> +	frequency_util,
> +	energy_util,
> +};

Please don't use lower case for enums. It's extremely confusing.

Thanks,
Saravana