Re: [PATCH 1/3] sched/fair: Prepare variables for increased precision of EAS estimated energy

From: Dietmar Eggemann <dietmar.eggemann@arm.com>
To: Lukasz Luba <lukasz.luba@arm.com>,
	Vincent Guittot <vincent.guittot@linaro.org>
Cc: linux-kernel <linux-kernel@vger.kernel.org>,
	Chris Redpath <Chris.Redpath@arm.com>,
	Morten Rasmussen <morten.rasmussen@arm.com>,
	Quentin Perret <qperret@google.com>,
	"open list:THERMAL" <linux-pm@vger.kernel.org>,
	Peter Zijlstra <peterz@infradead.org>,
	"Rafael J. Wysocki" <rjw@rjwysocki.net>,
	Viresh Kumar <viresh.kumar@linaro.org>,
	Ingo Molnar <mingo@redhat.com>,
	Juri Lelli <juri.lelli@redhat.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	segall@google.com, Mel Gorman <mgorman@suse.de>,
	Daniel Bristot de Oliveira <bristot@redhat.com>,
	CCj.Yeh@mediatek.com
Subject: Re: [PATCH 1/3] sched/fair: Prepare variables for increased precision of EAS estimated energy
Date: Wed, 7 Jul 2021 11:45:00 +0200	[thread overview]
Message-ID: <9b0ea7bc-934a-43bd-7dd8-9fe33dec97bc@arm.com> (raw)
In-Reply-To: <2f43b211-da86-9d48-4e41-1c63359865bb@arm.com>

On 07/07/2021 10:23, Lukasz Luba wrote:
>  
> On 7/7/21 9:00 AM, Vincent Guittot wrote:
>> On Wed, 7 Jul 2021 at 09:49, Lukasz Luba <lukasz.luba@arm.com> wrote:
>>>
>>>
>>>
>>> On 7/7/21 8:07 AM, Vincent Guittot wrote:
>>>> On Fri, 25 Jun 2021 at 17:26, Lukasz Luba <lukasz.luba@arm.com> wrote:

[...]

>>>> Could you explain why 32bits results are not enough and you need to
>>>> move to 64bits ?
>>>>
>>>> Right now the result is in the range [0..2^32[ mW. If you need more
>>>> precision and you want to return uW instead, you will have a result in
>>>> the range  [0..4kW[ which seems to be still enough
>>>>
>>>
>>> Currently we have the max value limit for 'power' in EM which is
>>> EM_MAX_POWER 0xffff (64k - 1). We allow to register such big power
>>> values ~64k mW (~64Watts) for an OPP. Then based on 'power' we
>>> pre-calculate 'cost' fields:
>>> cost[i] = power[i] * freq_max / freq[i]
>>> So, for max freq the cost == power. Let's use that in the example.
>>>
>>> Then the em_cpu_energy() calculates as follow:
>>> cost * sum_util / scale_cpu
>>> We are interested in the first part - the value of multiplication.
>>
>> But all these are internal computations of the energy model. At the
>> end, the computed energy that is returned by compute_energy() and
>> em_cpu_energy(), fits in a long
> 
> Let's take a look at existing *10000 precision for x CPUs:
> cost * sum_util / scale_cpu =
> (64k *10000) * (x * 800) / 1024
> which is:
> x * ~500mln
> 
> So to be close to overflowing u32 the 'x' has to be > (?=) 8
> (depends on sum_util).

I assume the worst case is `x * 1024` (max return value of
effective_cpu_util = effective_cpu_util()) so x ~ 6.7.

I'm not aware of any arm32 b.L. systems with > 4 CPUs in a PD.