lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <6f5fad13-d570-a923-ff40-45071709c296@gmail.com>
Date:   Mon, 5 Oct 2020 17:29:51 +0300
From:   Dmitry Osipenko <digetx@...il.com>
To:     Peter Geis <pgwipeout@...il.com>
Cc:     Rob Herring <robh+dt@...nel.org>,
        Thierry Reding <thierry.reding@...il.com>,
        Jonathan Hunter <jonathanh@...dia.com>,
        Matt Merhar <mattmerhar@...tonmail.com>,
        Stephen Warren <swarren@...dotorg.org>,
        Bob Ham <rah@...trans.net>,
        Leonardo Bras <leobras.c@...il.com>,
        Michael Brougham <jusplainmike@...il.com>,
        linux-tegra@...r.kernel.org, devicetree@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: Re: [PATCH v3 1/3] ARM: tegra: Add device-tree for Ouya

05.10.2020 17:22, Peter Geis пишет:
> On Mon, Oct 5, 2020 at 10:02 AM Dmitry Osipenko <digetx@...il.com> wrote:
>>
>> 04.10.2020 16:31, Peter Geis пишет:
>>> +     thermal-zones {
>>> +             cpu_thermal: cpu-thermal {
>>> +                     polling-delay = <5000>;
>>> +                     polling-delay-passive = <5000>;
>>> +
>>> +                     thermal-sensors = <&cpu_temp 1>;
>>> +
>>> +                     trips {
>>> +                             cpu_alert0: cpu-alert0 {
>>> +                                     temperature = <50000>;
>>> +                                     hysteresis = <10000>;
>>
>> Hello, Peter!
>>
>> A day ago I was tuning thermal zones for Nexus 7 because found that the
>> current variant is a bit too unpractical. In particular temperature
>> hysteresis should be small, otherwise cpufreq could get throttled
>> enormously to the point that device becomes unusable. This is an
>> active-cooling zone, but it looks to me that hysteresis is a bit too
>> high and should make Ouya much noisier than it could be.
>>
>> I suggest to try to set hysteresis to 0.2C here, i.e. hysteresis = <200>.
>>
>> I also suggest to bump the temperature threshold to 55C in order to
>> ignore temporal temperature spikes because CPU temp should be about 40C
>> during idle and then it may raise quickly for a brief moments during
>> average usage.
> 
> Good Morning,
> 
> The Ouya has a rather large heatsink with poor conductivity and a
> single stage fan.
> The fan is not terribly loud, as it runs at a rather low rpm.
> The temperature at the cpu tends to be much higher than observed at
> the heatsink.
> I've found that a low hysteresis value leads to a situation where the
> fan is constantly toggling on and off.
> I actually burned out the power transistor driving the fan on my first
> Ouya this way.
> The high hysteresis value provides a good balance of fan on/off time
> under most loads.
> The temperature threshold was chosen for this as well.
> 
>>
>>> +                                     type = "active";
>>> +                             };
>>> +                             cpu_alert1: cpu-alert1 {
>>> +                                     temperature = <70000>;
>>> +                                     hysteresis = <5000>;
>>> +                                     type = "passive";
>>> +                             };
>>
>> And here to 0.2C as well.
> 
> This value was chosen to protect the CPU in case of fan failure.
> Again, with the large heatsink and poor conductivity we need to
> maintain throttling for longer.
> Otherwise the cpu temp will overshoot and risk thermal shutdown before
> throttling can prevent it.

Alright! Then I don't have any more comments for now, thanks :)

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ