[Bioclusters] self-built clusters and red hat

Andrew Fant bioclusters@bioinformatics.org
Tue, 17 Dec 2002 15:42:45 -0500 (EST)


Afternoon all.
     I'm in the process of completing the spec for a new cluster we are
building.  In the course of the design review, the issue of the linux
distribution to be used has come up repeatedly.  I am strongly
disinclined to use Red Hat for it for both technical and personal reasons
that I would rather not delve into here (email me off-list if you really
want to talk about it).  The question has been raised as to why we are
doing something differently from everyone else who builds clusters.  I
know people do use other distros for beowulf-style clusters, but proot is
always useful.  If there are people out there who are running production
services on beowulf-like clusters with a non-redhat based distribution
(meaning a customized red-hat image like rocks or the old VALinux distro,
not mandrake),  I would really appreciate a note about it.  If you
migrated to something else from redhat, and care to tell me why you did it
and how it went, that would even be more helpful.  I don't have anything
to offer for the stories, but if any of you are near boston, or I end up
near your location, I will gladly buy contributors a drink of their choice
8-).

Thanks in advance,
		Andy

P.S.  I also mailed this query to the beowulf lift, so if you see it there
too, you are not loosing it.

Andrew Fant      |   This    |  "If I could walk THAT way...
Molecular Geek   |   Space   |     I wouldn't need the talcum powder!"
fant@pobox.com   |    For    |          G. Marx (apropos of Aerosmith)
Boston, MA USA   |   Hire    |    http://www.pharmawulf.com