[GRASSLIST:1701] GRASS on clusters

[Lars Bromley]

Hi List,
I'd like to reopen Dr. Rich Shepard's
year old message (see below) to this
list, regarding using GRASS with a
cluster.  I have a big project coming up
and am hoping to set up a cluster to
help speed up the workload. Have any of
you experimented further with GRASS and
clusters? Messages to the listserv
indicate that it is indeed possible, but
I didn't see if anyone had actually
tried it. If anyone has, would they mind
giving me a clue as to how it might turn
out? Does it speed things up, or is it
more hassle than its worth? I am using
linux as my OS and will be using Beowulf
as my clustering software, and have six
pentiums to start with.

Thanks for any input, feedback, and
comments!

Lars

Lars Bromley
IT Guy
American Association for
  the Advancement of Science

PS Someone on the ERDAS list got flamed
today for referring to GIS folks as
'toadies', he said it was cuz that's
what he learned to call them in the
military. Does anyone on this list know
the appropriate military response for
Image Analysts? ;)

              To: grasslist at baylor.edu
              Subject:
SMP/Cluster-GRASS: closure
              From: Rich Shepard
<rshepard at appl-ecosys.com>
              Date: Sat, 22 Apr 2000
09:46:16 -0700 (PDT)
              Sender:
owner-GRASSLIST at baylor.edu


            I've dug more deeply into
requirements for running GRASS on a
          multiprocessor or cluster
system (such as a beowulf cluster). What
I've
          learned are:

            1) It can be done.

            2) It is too expensive to be
practical for us.

            Apparently, The Portland
Group is one of a few compiler/tool
developers
          out there (NAG being another
one). A 2-developer license for their
cluster
          development kit (CDK) costs
$2,500 plus $500/year for minor upgrades
and
          technical assistance. Since
I'm the only developer here, that's much
to much
          money to spend on a single
project for a single user.

            Ergo, while it was a nice
concept, it's not for us. For a team
using the
          tools for more than one
project, or with more than one
developer, it may be
          a very practical approach.

          'Nuff said,

          Rich

          Dr. Richard B. Shepard,
President

                                 Applied
Ecosystem Services, Inc. (TM)
                        Making
environmentally-responsible mining
happen. (SM)

--------------------------------
                      2404 SW 22nd
Street | Troutdale, OR 97060-1247 |
U.S.A.
           + 1 503-667-4517 (voice) | +
1 503-667-8863 (fax) |
rshepard at appl-ecosys.com