On Wed, 30 Sep 1998, West, Jeff wrote:
> Jacek:
>
> I downloaded bWatch a few months ago and played with it a bit. I
> now have funding to build a 48 cluster. I will be doing domain
> decomposition CFD on it.
>
> In the process of procuring I have noted that some motherboards have
> the ability to report the board temperature. I think that would be a nice
> addition to bWatch. Do you know how to access this information? The vendor
> I talked to said that he knew of NT programs that could access this info,
> but not Linux programs. He said the chip that reported this info was the
> LM97 chip, sounds like the LM87 performance monitoring chip from Pentium Pro
> discussions.
>
> What do you think/know?
If NT programs can access it, linux certainly CAN access it; the
question is whether it already does for your mobo. There are a couple
of temperature drivers in the kernel source: h8 appears to be for alphas
and pcwd appears to be for a special "watchdog" card, and there is a
/dev/temperature device defined. I don't know of any applications to
read from this device, though, and have no idea where to find any (cpu
temperature isn't in my local /usr/doc/faq/howto/mini).
Current CPU temperature doesn't appear to be in /proc/cpuinfo, even on
my Dell motherboards that do maintain the information, and this seems
like a reasonable place to put it if it were generally available. I can
try contacting Dell to see if there is an API for this -- I would guess
that the information is available through a BIOS call or the PCI bus but
don't know where to look
This is an apropos time to be asking this. I agree that CPU temperature
would be a useful indicator variable, and I also "should" have it
available on our beowulf boxes. I'm working with Jacek writing my own
version of "procd", a daemon that I already have running in alpha that
can provide on demand what amounts to a cat of any (permitted) file in
/proc, all via a TCP connection without the overhead of a shell. The
procd can also lookup or query/build anything accessible in userspace,
e.g. it calculates and returns number of users or local time the hard
way to avoid shell calls to uptime (I'm trying to leave it
unprivileged). I'd be happy to add code to procd to query the CPU
temperatures and serve it out, IF I knew how to do so.
I'm going to cross-post this to linux-smp, because current kernel
development folks there (including Alan Cox, who seems to have worked on
the pcwd driver) might know how to do this or already have plans to add
a current temperature field to /proc/cpuinfo for each CPU (the logical
place, no?). If it is there, I can serve it, and a next-generation
tkperl/procd bWatch Jacek and I are working on or any perl socket or
binary socket code can trivially retrieve the information and act on it
automatically, remotely.
rgb
Robert G. Brown http://www.phy.duke.edu/~rgb/
Duke University Dept. of Physics, Box 90305
Durham, N.C. 27708-0305
Phone: 1-919-660-2567 Fax: 919-660-2525 email:[EMAIL PROTECTED]
