[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <002401d90108$93a831e0$baf895a0$@telus.net>
Date: Fri, 25 Nov 2022 12:00:32 -0800
From: "Doug Smythies" <dsmythies@...us.net>
To: "'Rafael J. Wysocki'" <rafael@...nel.org>,
"'Kajetan Puchalski'" <kajetan.puchalski@....com>
Cc: <daniel.lezcano@...aro.org>, <lukasz.luba@....com>,
<Dietmar.Eggemann@....com>, <yu.chen.surf@...il.com>,
<linux-pm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
"Doug Smythies" <dsmythies@...us.net>
Subject: RE: [RFC PATCH v3 2/2] cpuidle: teo: Introduce util-awareness
On 2022.11.25 10:27 Rafael wrote:
> On Mon, Oct 31, 2022 at 1:14 PM Kajetan wrote:
... [delete some] ...
>> +}
>> +
>> /**
>> * teo_update - Update CPU metrics after wakeup.
>> * @drv: cpuidle driver containing state data.
>> @@ -303,7 +359,9 @@ static int teo_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
>> int i;
>>
>> if (dev->last_state_idx >= 0) {
>> - teo_update(drv, dev);
>> + /* don't update metrics if the cpu was utilized during the last sleep */
>
> Why?
>
> The metrics are related to idle duration and cpu_data->utilized
> indicates whether or not latency should be reduced. These are
> different things.
>
> Moreover, this is just one data point and there may not be any direct
> connection between it and the decision made in this particular cycle.
Hi Rafael,
Yes, agreed. And version 4 of this patch set deleted this stuff.
See also my similar feedback, with accompanying test data
that verified the issue in [1].
[1] https://lore.kernel.org/linux-pm/CAAYoRsUgm6KyJCDowGKFVuMwJepnVN8NFEenjd3O-FN7+BETSw@mail.gmail.com/
... Doug
Powered by blists - more mailing lists