[lm-sensors] k8temp on K8 rev.F and rev.G: Testers wanted

Hans de Goede hdegoede at redhat.com
Sun Jan 11 10:45:42 CET 2009

Hi all,

Jean Delvare wrote:
> Hi all,
> I am done reviewing and testing Andreas' k8temp patches. After some
> reorganization I came up with the following stack:
> http://khali.linux-fr.org/devel/linux-2.6/jdelvare-hwmon/hwmon-k8temp-01-warn-about-errata.patch
> http://khali.linux-fr.org/devel/linux-2.6/jdelvare-hwmon/hwmon-k8temp-02-fix-wrong-sensor-selection-for-revf-revg.patch
> http://khali.linux-fr.org/devel/linux-2.6/jdelvare-hwmon/hwmon-k8temp-03-fix-temperature-reporting-for-most-revg.patch
> These are in linux-next at the moment, and I'd like to push them to
> Linus quickly. But I do not own any rev.F nor rev.G CPU myself, so I
> couldn't really test the patches, other than ensure that they do not
> cause a regression on earlier K8 CPUs.
> So this is a call to owners of rev.F and rev.G K8 CPUs, to try these
> patches and report how they are doing. There's also a standalone
> version of the updated driver at:
>   http://jdelvare.pck.nerim.net/sensors/k8temp/
> if it is easier for you.


I've just tested this on my x2 5000, I did so with 2 loaded cores to also 
answer the questions about the 2 per core temps being pretty far apart when idle:

Loaded for about a minute:
Adapter: PCI adapter
Core0 Temp:  +52.0°C
Core0 Temp:  +51.0°C
Core1 Temp:  +54.0°C
Core1 Temp:  +47.0°C

And after being loaded for some minutes:
Adapter: PCI adapter
Core0 Temp:  +56.0°C
Core0 Temp:  +56.0°C
Core1 Temp:  +58.0°C
Core1 Temp:  +52.0°C

The readings loook much saner now then with the driver in 2.6.28 (the +21 
degrees helps!)

cpu revision info:
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 107
model name      : AMD Athlon(tm) 64 X2 Dual Core Processor 5000+
stepping        : 2

I also get:
k8temp 0000:00:18.3: Temperature readouts might be wrong - check erratum #141



More information about the lm-sensors mailing list