Received-SPF: pass (google.com: domain of linux-kernel+bounces-48944-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:40f1:3f00::1 as permitted sender) client-ip=2604:1380:40f1:3f00::1;
Date: Thu, 1 Feb 2024 22:31:29 +0000
From: Qais Yousef <qyousef@layalina.io>
To: Ingo Molnar <mingo@kernel.org>, Peter Zijlstra <peterz@infradead.org>,
	"Rafael J. Wysocki" <rafael@kernel.org>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Vincent Guittot <vincent.guittot@linaro.org>,
	Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
	Lukasz Luba <lukasz.luba@arm.com>, Wei Wang <wvw@google.com>,
	Rick Yiu <rickyiu@google.com>, Chung-Kai Mei <chungkai@google.com>
Subject: Re: [PATCH v2 7/8] sched/schedutil: Add a new tunable to dictate
 response time
Message-ID: <20240201223129.2dgeko4aikkpisqf@airbuntu>
References: <20231208002342.367117-1-qyousef@layalina.io>
 <20231208002342.367117-8-qyousef@layalina.io>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=utf-8
Content-Disposition: inline
In-Reply-To: <20231208002342.367117-8-qyousef@layalina.io>

On 12/08/23 00:23, Qais Yousef wrote:

> +static inline u64 sugov_calc_freq_response_ms(struct sugov_policy *sg_policy)
> +{
> +	int cpu = cpumask_first(sg_policy->policy->cpus);
> +	unsigned long cap = arch_scale_cpu_capacity(cpu);
> +	unsigned int max_freq, sec_max_freq;
> +
> +	max_freq = sg_policy->policy->cpuinfo.max_freq;
> +	sec_max_freq = __resolve_freq(sg_policy->policy,
> +				      max_freq - 1,
> +				      CPUFREQ_RELATION_H);
> +
> +	/*
> +	 * We will request max_freq as soon as util crosses the capacity at
> +	 * second highest frequency. So effectively our response time is the
> +	 * util at which we cross the cap@2nd_highest_freq.
> +	 */
> +	cap = sec_max_freq * cap / max_freq;
> +
> +	return approximate_runtime(cap + 1);

After Linus problem (and more testing) I realize this is not correct. This
value is correct for the biggest core only, for smaller cores I must stretch
time with capacity. I have similar invariance issues that I need to address in
this series and uclamp max aggregation series.