[Gllug] Re: CPU exerciser?

[Jan Kokoska]

On Mon, 2004-10-25 at 15:28 +0100, John Hearns wrote:
> On Mon, 2004-10-25 at 12:54, David Abbishaw wrote:
> > I have a little script for testing how much a machine can take, never seems
> > to fail to bring the machine down.
> > 
> Not wishing to be rude, honestly,
> but I'm not after a CPU or disk stresstester - we have these.
> We monitor temperatures using sensors and Ganglia. 
> This problem CPU doesn't seem to be getting to a higher
> temperature than any other nodes in the cluster. 

For purposes less specific than yours, I usually use cpuburn:
burnBX, burnK6, burnK7, burnMMX, burnP5, burnP6. Nevertheless, the man
page says they don't test every single instruction and are optimized for
stress tests and heat production. And you surely know about cpuburn
anyway :)

And more specific, oh well, I would see if there is an
instruction-monitoring plugin for Valgrind, which is a x86
debugger/profiler (and indeed has a number of plugins for quite specific
purposes). I remember the (very apt) developers were not too worried
about implementing every single MMX/SSE/whatever instruction and rather
waited for people to post their complaints into list.. the new one
always appeared immediately in CVS head. You would need to valgrind your
HPL test program and find what it does on that place.. then try and
reproduce it. Would end up in coding, I am afraid I don't know anything
cooked already. Overkill IMHO.

It seems to me like you just need a good excuse to thow it back at your
distributor, right? Saying it freezes with HPL should do, they can see
themselves. Just swap it it through a few boxes to make sure it's the
cpu.. I am sure you have *lots* of those ;)

--
Jan

-- 
Gllug mailing list  -  Gllug at gllug.org.uk
http://lists.gllug.org.uk/mailman/listinfo/gllug