-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1
Hello,
There is an option in kernel configuration (2.6.3):
CONFIG_THERM_WINDTUNNEL=m
How does G4 Windtunnel thermal support work? Does it make an ability to change
fans speed by the OS or maybe something other/else?
Greetings,
- --
Micha? Roszka
[email protected]
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.2.4 (GNU/Linux)
iD8DBQFAWU4ENyoZJvl7/4kRAqlMAJ9+nP8FgPU0Toa3ylEl8Ae0uRRcaQCeI2xy
JajBj0nto2kKfSxgxFqNv1g=
=SrIH
-----END PGP SIGNATURE-----
On Thu, 18 Mar 2004, [iso-8859-2] Micha? Roszka wrote:
> There is an option in kernel configuration (2.6.3):
> CONFIG_THERM_WINDTUNNEL=m
> How does G4 Windtunnel thermal support work? Does it make an ability to change
> fans speed by the OS or maybe something other/else?
Yes, it works. It controls the speed of the CPU fan according to the
temperature. Do not forget to load the i2c_keywest module.
--
Giuliano.
On Thu, Mar 18, 2004 at 10:16:28AM +0100, Giuliano Pochini wrote:
> > How does G4 Windtunnel thermal support work? Does it make
> > an ability to change fans speed by the OS or maybe something
> > other/else?
>
> Yes, it works. It controls the speed of the CPU fan according to the
> temperature. Do not forget to load the i2c_keywest module.
Nice to see that this driver has made it into the kernel tree :-).
I've been thinking about adding proper sysfs and make things
somewhat customable from userspace. I'm not quite sure the working
point is optimal for all machines (the ambient temperature is also
a factor).
Btw, I would like to get reports about how well this driver works
with respect to noise reduction. I'm in particular interested
in the dual 1.4 GHz model...
/Samuel
On Thu, 18 Mar 2004, Samuel Rydh wrote:
> Btw, I would like to get reports about how well this driver works
> with respect to noise reduction. I'm in particular interested
> in the dual 1.4 GHz model...
The author has a dual-1.2 and I tested it on another dual-1.2. I don't
know if it has been tested on other mathines. The driver writes in
the system logs the temperature and the fan speed every time they change,
so you can check what it's doing (and you can unload the module if you
see it does something wrong).
--
Giuliano.
Giuliano Pochini, wiadomo?? z dnia: czw 18. marca 2004 12:27
> The author has a dual-1.2 and I tested it on another dual-1.2. I don't
> know if it has been tested on other mathines.
I also have a dual-1.25 and I do not know anybody with Linux on the Power Mac
Dual :(.
--
Micha? Roszka
[email protected]
On Thu, Mar 18, 2004 at 12:27:28PM +0100, Giuliano Pochini wrote:
> On Thu, 18 Mar 2004, Samuel Rydh wrote:
>
> > Btw, I would like to get reports about how well this driver works
> > with respect to noise reduction. I'm in particular interested
> > in the dual 1.4 GHz model...
>
> The author has a dual-1.2 and I tested it on another dual-1.2. I don't
> know if it has been tested on other mathines. The driver writes in
> the system logs the temperature and the fan speed every time they change,
> so you can check what it's doing (and you can unload the module if you
> see it does something wrong).
Yes I know... I wrote it :-)
It should be perfectly safe to use. It contains a (very conservative)
fail safe; if the temperature exceeds the working point by a few
degrees, the hardware overheat protection is programmed to turn
on the fans 100%. This works even if the kernel has locked up
solidly.
I'm mostly concerned that the working point is set too low for
the 1.4 Ghz machine. If it is, then there might be some unnecessary
noise. When the temperature is going down towards the working point,
the fan speed is increased to remove the last extra heat.
The assumption is that some temporary heat generating operation
has finished (like a CPU intensive calculation or heavy usage of
the graphics card). This is a good strategy if the working point
is correct but not-so-good if the working point is higher than
expected (cyclic fan behavior might occur).
In all cases, it should be an improvement compared to the firmware
setting which is incredibly noisy and usually causes short period
fan speed cycling.
/Samuel
On Thursday 18 of March 2004 10:16, Giuliano Pochini wrote:
> Yes, it works. It controls the speed of the CPU fan according to the
> temperature. Do not forget to load the i2c_keywest module.
Should I also compile something from Processor / Thermal Management Support?
--
Micha? Roszka
[email protected]
Hi!
> > > Btw, I would like to get reports about how well this driver works
> > > with respect to noise reduction. I'm in particular interested
> > > in the dual 1.4 GHz model...
> >
> > The author has a dual-1.2 and I tested it on another dual-1.2. I don't
> > know if it has been tested on other mathines. The driver writes in
> > the system logs the temperature and the fan speed every time they change,
> > so you can check what it's doing (and you can unload the module if you
> > see it does something wrong).
>
> Yes I know... I wrote it :-)
>
> It should be perfectly safe to use. It contains a (very conservative)
> fail safe; if the temperature exceeds the working point by a few
> degrees, the hardware overheat protection is programmed to turn
> on the fans 100%. This works even if the kernel has locked up
> solidly.
Is it actually possible to set that hardware to self-destruct?
[ACPI notebooks have very simple hardware failsafe: if temperature
exceeds some hard limit, power is simply cut.]
Pavel
--
When do you have a heart between your knees?
[Johanka's followup: and *two* hearts?]
On Wed, Mar 24, 2004 at 01:18:28AM +0100, Pavel Machek wrote:
> Is it actually possible to set that hardware to self-destruct?
>
> [ACPI notebooks have very simple hardware failsafe: if temperature
> exceeds some hard limit, power is simply cut.]
Well, I'm not sure.
I know that the hardware which controls the fan (a separate temperature
sensor and a combined sensor/controller) is not connected to any death
switch; the available overheat pin serves as a 100% fan override. There
might very well be a safety mechanism in the UniNorth bridge though.
Something like a forced power off if interrupts are not handled in
a timely manner. I'm pretty sure I have seen references to this behavior
in conjunction with the PowerBook G4. The dual G4 architecture is not all
that different...
It would be interesting to see what happens if one disables the overheat
protection and stops the fan. Anybody volunteering? At least one
has an excellent reason why one need one of those new G5 machines
if things start to smoke :-).
/Samuel
Hi!
> > Is it actually possible to set that hardware to self-destruct?
> >
> > [ACPI notebooks have very simple hardware failsafe: if temperature
> > exceeds some hard limit, power is simply cut.]
>
> Well, I'm not sure.
>
> I know that the hardware which controls the fan (a separate temperature
> sensor and a combined sensor/controller) is not connected to any death
> switch; the available overheat pin serves as a 100% fan override. There
> might very well be a safety mechanism in the UniNorth bridge though.
> Something like a forced power off if interrupts are not handled in
> a timely manner. I'm pretty sure I have seen references to this behavior
> in conjunction with the PowerBook G4. The dual G4 architecture is not all
> that different...
ACPI design seems to have aditional benefit: if your fan fails, you
can still operate machine safely. You just have to be clever with
throttling etc :-). [Assuming vendor did set shutdown threshold
right. HP Omnibook XE3 will kill power at 83C. If you leave it running
at ~82C for ten hours, you'll fry the disk. Oops.]
Funniest machine in this regard was 300MHz P2 toshiba. On extreme
overheat (95C), it went to 40MHz no matter what os did. At that point
it was able to cool itself even without fan. [But I was pretty puzzled
when I saw that behaviour].
> It would be interesting to see what happens if one disables the overheat
> protection and stops the fan. Anybody volunteering? At least one
> has an excellent reason why one need one of those new G5 machines
> if things start to smoke :-).
Well, its enough to end the test when CPU starts doing errors. Usually
CPU stops working at some temperature, and is only physically damaged
after that. Or you can get datasheets from CPU manufacturer, and call
the machine's design broken when it exceeds CPU design limits by
5C... This should be testable without letting magic smoke out.
Pavel
--
When do you have a heart between your knees?
[Johanka's followup: and *two* hearts?]