Skip site navigation (1)Skip section navigation (2)
Date:      Sun, 15 Jun 2014 14:43:56 +1000 (EST)
From:      Ian Smith <smithi@nimnet.asn.au>
To:        sbruno@freebsd.org
Cc:        "freebsd-acpi@freebsd.org" <freebsd-acpi@freebsd.org>, Eric Neblock <cen5848@louisiana.edu>
Subject:   Re: Missing: hw.acpi.thermal.tz%d._HOT
Message-ID:  <20140615133533.A609@sola.nimnet.asn.au>
In-Reply-To: <1402769262.1120.5.camel@bruno>
References:  <1402412054.2426.13.camel@canpc36.cacs.louisiana.edu> <20140611011810.V10629@sola.nimnet.asn.au> <1402414819.17836.2.camel@canpc36.cacs.louisiana.edu> <CALCpEUEFmg4twoiDC1czEAXOanmLbR9DarvRcg9h8o=Xc3dwjg@mail.gmail.com> <20140614013631.J10629@sola.nimnet.asn.au> <CALCpEUGzi1h=25DLA7xeP%2B_SpfAib-dWeb6Jx45UjKK4xTOJNA@mail.gmail.com> <CALCpEUGi0EtonwUOx3wS65aOrGNngO%2BTnPetPO2i%2BAQ5r%2BEDKg@mail.gmail.com> <1402769262.1120.5.camel@bruno>

next in thread | previous in thread | raw e-mail | index | archive | help
On Sat, 14 Jun 2014 11:07:41 -0700, Sean Bruno wrote:

 > > Just for curious minds:
 > > 
 > > Afternoon and evenings bring direct sunlight to where the machine is.
 > > And I guess that is showing? probably?
 > > # sysctl dev.cpu | grep temp
 > > dev.cpu.0.temperature: 16.8C
 > > dev.cpu.1.temperature: 16.8C
 > > dev.cpu.2.temperature: 16.8C
 > > dev.cpu.3.temperature: 16.8C
 > > dev.cpu.4.temperature: 16.8C
 > > dev.cpu.5.temperature: 16.8C
 > > dev.cpu.6.temperature: 16.8C
 > > dev.cpu.7.temperature: 16.8C
 > 
 > 
 > I have an FX-8150 based system similar, but a bit older that this one:
 > Base Board Information
 >         Manufacturer: ASUSTeK Computer INC.
 >         Product Name: M5A88-M
 > 
 > Processor Information
 >         Socket Designation: AM3R2
 >         Type: Central Processor
 >         Family: FX
 >         Manufacturer: AMD              
 >         ID: 12 0F 60 00 FF FB 8B 17
 >         Version: AMD FX(tm)-8150 Eight-Core Processor   

Which family, model, stepping is that?

 > At idle, the machine reports pretty low temps:
 > dev.amdtemp.0.%desc: AMD CPU On-Die Thermal Sensors
 > dev.amdtemp.0.%driver: amdtemp
 > dev.amdtemp.0.%parent: hostb4
 > dev.amdtemp.0.sensor_offset: 0
 > dev.amdtemp.0.core0.sensor0: 16.2C

Is it water-cooled?  Roughly, what's the ambient temperature where it 
lives?  Short of forced water cooling, with the watertank feeling cool 
to the touch, I can't see how any electronic equipment can run anything 
like that cool.  If you touch the heatsink, is it cooler than ambient?

 > But when doing builds with all the cpus firing:
 > dev.amdtemp.0.core0.sensor0: 49.5C
 > ...
 > dev.amdtemp.0.core0.sensor0: 52.3C
 > ...
 > dev.cpu.0.temperature: 53.0C
 > 
 > 
 > Seems legit to me.

I don't think so.  Maybe becaus we use Centigrade here.  16C is ~62F, 
I'd have a wooly jumper on.  50C ~= 120F, we get days that hot outback.
  
There's mention in amdtemp.c of some models having a -28C offset:
#define AMDTEMP_FLAG_ALT_OFFSET 0x04 /* CurTmp starts at -28C. */

and later:

535 	mask = (sc->sc_flags & AMDTEMP_FLAG_CT_10BIT) != 0 ? 0x3ff : 0x3fc;
536 	offset = (sc->sc_flags & AMDTEMP_FLAG_ALT_OFFSET) != 0 ? 28 : 49;
537 	temp = pci_read_config(dev, AMDTEMP_THERMTP_STAT, 4);
538 	temp = ((temp >> 14) & mask) * 5 / 2;
539 	temp += AMDTEMP_ZERO_C_TO_K + (sc->sc_offset - offset) * 10;

I'm not claiming to follow that through the masking, shift and factor, 
and it's returned in Kelvin anyway, but there's clearly a 21 $something 
difference in offset for some models, and see the XXX comments there.

16C + 21C = 37C, which is believable at idle.  53C + 21C = 74C, which is 
quite believable for 8 busy cores, assuming a good h/s & fan.  You can 
leave your finger, for a good while anyway, on a heatsink at 53C.  74C 
will burn you quite quickly; here anyway, most home hot water systems 
are set to deliver between 60 and 70C, which will scald before long.

Touch test?

cheers, Ian



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20140615133533.A609>