Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 31 Dec 1999 15:38:17 -0500
From:      Ted Sikora <tsikora@home.com>
To:        "freebsd-stable@FreeBSD.ORG" <freebsd-stable@FreeBSD.ORG>, Brad Knowles <blk@skynet.be>, David Schwartz <davids@webmaster.com>
Subject:   Re: Temperature Findings
Message-ID:  <386D1439.D9AC45BB@home.com>
References:  <000101bf53c4$1cf9c690$021d85d1@youwant.to>

Next in thread | Previous in thread | Raw E-Mail | Index | Archive | Help
David Schwartz wrote:
> 
> > At 10:27 PM -0800 1999/12/30, Mike Smith wrote:
> >
> > >  The difference has already been explained as a different
> > instruction mix.
> > >  This should be obvious to anyone that has been in the industry for as
> > >  long as you have.

I am not a kernel programmer and relatively new to FreeBSD (since
3.0-RC) and nobody explained this previously.

> >
> >       It seems to me that you guys are all talking past each other:
Giant understatement!

> >
> >               1.  He's mentioned that he runs the same instruction mix
> > (i.e., two seti@home clients) under both Linux and FreeBSD
> 
>         Yes, Linux before he overclocked and overvoltaged and FreeBSD before.
> 
> >               2.  He's mentioned that he's run FreeBSD in both
> > uniprocessor
> > and SMP modes
> 
>         Yes, UP uses HLT, SMP doesn't. With FreeBSD's SMP kernel, both processors
> are always running full bore.
> 
> >               3.  He's mentioned that he's run FreeBSD SMP with
> > 3.3 without problems
YES 3.3 runs cool w/ or w/o a SMP kernel.

> 
>         Before he overclocked and overvoltaged. Possibly also before his fan's
> capacity decreased due to bearing failure or similar.

The fan's are fine. The case is a custom server design *with* a panel
mounted digital display for the TEMP readings from the Winbond
W83782D/W83783S IC mounted on the motherboard. The readings are taken
right from the systems MB routed through the systems bios. It is
independant of the OS installed. I had a technician verify the voltage
readings and case temperature before I posted with this problem. I
verified it again myself after being accused of presenting false or
inaccurate data. 

> 
> >               4.  He's mentioned that the overclocking is a recent
> > introduction to the issue and the system was overheating before then

I only overclocked it 3 days prior. The increase in temp was nominal
only 3-5 degrees so really it had no bearing on this. 

> 
>         So he has cooling problems even at normal CPU voltages and frequencies.
No problems just much higher than before or compared to Linux SMP.
The FreeBSD Uni kernel is fine. It is only with the SMP kernel in 3.4.


> Obviously, he either has inadequate cooling or he has some defective
> component in his system that is creating too much heat.
> 
> >               5.  He's also mentioned that this is a chipset which we now
> > know is not directly supported by the measurement interface, and
> > therefore the temperature multiples might (or might not) be off
There are no multiples I was not using the OS measurement tools.
I was using the MB/case display and the system bios for readings.
I only used lmmon after I was told to.

> 
>         Okay, so we can't even trust his data as correctly indicating a temperature
> problems. So, perhaps we know nothing at all.
> 
> [snip]
> >       Of course, the fact that everyone is talking past each other is
> > not surprising, seeing as many of the correspondents are spread
> > around the globe.
> 
>         There's nothing to explain or analyze. Much of his data comes from
> unsupported (and unsupportable) configurations.
> 
> >       If I might make a suggestion based on my own recent introduction
> > to this mailing list -- it really helps if the new poster provides as
> > much detail as possible and doesn't make any assumptions about how
> > much they know about the problem based on their decade-plus (or more)
> > experience, and it really helps if the other people involved give the
> > guy at least half a break while he tries to explain what weirdo
> > whacked out thing he's seeing.
> 
>         Seeing an overclocked, overvoltaged SMP system overheat is not exactly
> weird or whacked out. It's specifically the reason most people do not
> recommend overclocking or overvoltaging.
> 
That had nothing to do with the issue at hand. (Whether overclocked or
normal it's hotter.)

I wanted to know if you (FreeBSD) was aware that the SMP kernel runs
quite a bit hotter than normal and that the Linux SMP kernel 
is cooler(Why?). Is this normal or a problem?

That's all I wanted to know.(and everyone went for the juggler.)

Regards,
--
Ted Sikora
Jtl Development Group 
tsikora@powerusersbbs.com


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <http://docs.FreeBSD.org/cgi/mid.cgi?386D1439.D9AC45BB>