[lm-sensors] hwmon K8 sensor in processor up to revision E.

[lm-sensors] hwmon K8 sensor in processor up to revision E.

[Ângelo Miguel Arrifano]

[-- Attachment #1.1: Type: text/plain, Size: 2173 bytes --]

Hi all,

I have a AMD Athlon64 3500+ socket 754 and reading cpu temperatures using the k8 sensor is totally useful (thanks Rudolf). My ACPI is buggy and reading CPU temperature from it, is a mess.
More information about my processor:

$cat /proc/cpuinfo
processor       : 0
vendor_id       : AuthenticAMD
cpu family      : 15
model           : 4
model name      : AMD Athlon(tm) 64 Processor 3400+
stepping        : 10
cpu MHz         : 800.000
cache size      : 1024 KB
fpu             : yes
fpu_exception   : yes
cpuid level     : 1
wp              : yes
flags           : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 syscall nx mmxext lm 3dnowext 3dnow
bogomips        : 1602.36
TLB size        : 1024 4K pages
clflush size    : 64
cache_alignment : 64
address sizes   : 40 bits physical, 48 bits virtual
power management: ts fid vid ttp

Despite the K8 sensor my ACPI offers me two more sensors.
$cat /proc/acpi/thermal_zone/THRC/temperature
temperature:             55 C
$cat /proc/acpi/thermal_zone/THRS/temperature
temperature:             47 C

Since reading cpu temperature through acpi causes a lot of interrupts. It's near impossible to get a working system with ACPI temperature readouts with high sampling rates (lost ticks).

$cat /proc/acpi/thermal_zone/THRC/temperature && cat /sys/class/hwmon/
hwmon0/device/temp1_input
temperature:             55 C
30000

I readed that:
"Temperature known as TCaseMax was specified for processors up to revision E.
This temperature is defined as temperature between heat-spreader and CPU
case, so the internal CPU temperature supplied by this driver can be higher.
There is no easy way how to measure the temperature which will correlate
with TCaseMax temperature."

So I logged some ACPI VS K8Sensor:
"ACPI","K8"
51,28
52,28
53,28
54,29
55,29
56,30
57,30
58,31
59,32
60,30
61,35
62,35
63,38
64,33
65,35
66,39
68,38
73,48
74,42
75,43
76,43
77,46
78,44
79,44
80,46
81,48
82,48
83,48
84,49
85,50
86,51

It looks like the CPU temperature is more or less twice the K8 sensor temperature (?in my system?).

Thanks all
--
MiKNiX
miknix@gmail.com
http://miknix.homelinux.com

[-- Attachment #1.2: Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] hwmon K8 sensor in processor up to revision E.

[Ângelo Miguel Arrifano]

[-- Attachment #1.1.1: Type: text/plain, Size: 851 bytes --]

Hi there,

> Hello,
>
> Please can you send the dsdt.bin table, output of sensors-detect and lspci?
> Also what is your board manufacturer/model ?

Acer Aspire 1520 WLMi Laptop

Processor (Not original): Athlon64 3400+
Motherboard: VIA K8N800 with nVIDIA AGP

(...)

> > Despite the K8 sensor my ACPI offers me two more sensors.
> > $cat /proc/acpi/thermal_zone/THRC/temperature
> > temperature:             55 C
> > $cat /proc/acpi/thermal_zone/THRS/temperature
> > temperature:             47 C
>
> Hmm this is bit strange. The CPU seems to be totally idle.
Yes! It was totally idle. But what's strange?
Today was a sunny day with high temperatures, my friends were on the beach :)
And this is a laptop with one small fan cooling both cpu and gpu :\

>
> Thanks,
> Rudolf

Thanks for your time
--
MiKNiX
miknix@gmail.com
http://miknix.homelinux.com

[-- Attachment #1.1.2: hwmon-k8-k8n800.tar.bz2 --]
[-- Type: application/x-bzip, Size: 12284 bytes --]

[-- Attachment #1.2: Type: application/pgp-signature, Size: 189 bytes --]

[-- Attachment #2: Type: text/plain, Size: 153 bytes --]

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] hwmon K8 sensor in processor up to revision E.

[Rudolf Marek]

Hello,

Please can you send the dsdt.bin table, output of sensors-detect and lspci?
Also what is your board manufacturer/model ?

do generate the dstd.bin do:

cat /proc/acpi/dsdt > /tmp/dsdt.bin


> Despite the K8 sensor my ACPI offers me two more sensors.
> $cat /proc/acpi/thermal_zone/THRC/temperature
> temperature:             55 C
> $cat /proc/acpi/thermal_zone/THRS/temperature
> temperature:             47 C

Hmm this is bit strange. The CPU seems to be totally idle.

> "Temperature known as TCaseMax was specified for processors up to revision E.
> This temperature is defined as temperature between heat-spreader and CPU
> case, so the internal CPU temperature supplied by this driver can be higher.
> There is no easy way how to measure the temperature which will correlate
> with TCaseMax temperature."


This is something different. Lets find out from sensors-detect and dsdt table 
where does acpi take the infos.

Thanks,
Rudolf

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors

Re: [lm-sensors] hwmon K8 sensor in processor up to revision E.

[Rudolf Marek]

Hello

My conclusion is: ACPI might measure temperature from the other end of the 
heatpipe, so this is possible. I tried to track the DSDT it calls SMM so I cant 
tell how it get the temperature.

Rudolf

_______________________________________________
lm-sensors mailing list
lm-sensors@lm-sensors.org
http://lists.lm-sensors.org/mailman/listinfo/lm-sensors