Re: [BProc] Re: ANNOUNCE: New Clustermatic

[Erik A. H. <er...@he...>]

On Fri, Aug 09, 2002 at 10:33:55AM -0400, Mike Snitzer wrote:
> On Mar 25, 2002 Erik Arjan Hendriks (er...@he...) said:
> 
> > A new version of the clustermatic CD was placed on
> > www.clustermatic.org today.  The diff looks like this:
> > 
> >  * Updated BProc (3.1.9): fewer bugs, remote exec hacks, etc.
> > 
> >  * Updated Beoboot (lanl 1.2): minor changes.
> <snip>
> > The MPICH hacks which I've mentioned are included on the CD in the
> > mpirun-0.1 tar ball in the tarballs directory.  We used those hacks to
> > run a 396 process job on Chiba city at Argonne National Lab the other
> > day.  This clustermatic also survived some boot time torture testing
> > on about 200 nodes there.  (Thanks guys!)  The load spike on the front
> > end is severe when they all boot at once but all the nodes we started
> > with came up.  We've got a guy working on that problem here.
> > Hopefully beoboot lanl 1.3 will mostly eliminate that problem.
> 
> Has there been any progress on beoboot lanl 1.3 development?

Yup.  Lots.  It's gotten a bit more complicated than I had in mind but
it's actually started working (as of a few days ago).  I'm planning on
cleaning up a bit and throwing it up "soon".  I expect next week.
It's looking good right now.  I setup 100 nodes (with 40MB of
libraries) in 12 seconds yesterday.  There's basically no more load
spike though 12 seconds isn't really long enough to tell via the usual
mechanisms.

- Erik