[Beowulf] newbie's dilemma
Don R. Baker
donb at eps.mcgill.ca
Tue Feb 28 18:04:55 PST 2006
I am another newbie seeking more basic advice. And from reading this
list over the past months I realize how little I have learned about
Beowulf systems from my readings and my few experiments with Parallel
Knoppix. Nevertheless, let me get on with my question and stop wasting
I am performing embarrassingly parallel, Monte Carlo calculations, some
using integers and some using floating points (some written in C and
some written in FORTRAN), and I am tired of waiting for 4 months for my
dual Xeon 2.0 machine to finish a calculation. So, I want to start off
with a dedicated COW (perhaps running OpenMosix or Sun's free Grid
software or something else) and later move to a true Beowulf system once
I learn to properly write parallel software. I have been a linux user
for 8 years, but consider myself to still be a beginner. I have a room
with 4, 15 amp circuits and a 20 000 btu air conditioning unit installed
that I can use for the next 2 years, but after that I may need to find
another home for the system.
My dilemma is that for my budget I can buy one of the following
A custom built "personal cluster" with 8 dual core processors either
Xeons or Opterons (16 cores and 16 GB of memory) with all the software
installed, read to go.
I can buy 16 workstations, each with Dual Core Athlon X64 4400+
processors (32 cores and 32 GB of memory) upon which I will probably
install either Warewulf or Oscar.
I can buy 32 HP or Dell "mass market" desktops running dual core chips
(64 cores and 64 GB memory) upon which I will probably install either
Warewulf or Oscar. (Note that I read the discussion this past November
on "cheap PCs this christmas")
Obviously, I get more computing power in the last two solutions, but at
what cost in terms of time and upkeep? Once the system is up and
running I can dedicate about 5 hours per week, and probably no more, and
CAD$ ~500 per year for maintenance.
Do any of you have some sage advice? Have any of you used a "personal
cluster"? Any thoughts you may have will be very much appreciated.
Thank you all for your time.
Wishing you the best from a cool Montreal,
"Melting rocks today for a better tomorrow . . . "
Don R. Baker, Professor of Geochemistry, Earth and Planetary Sciences,
McGill University 3450 rue University, Montreal, QC Canada H3A 2A7 514-398-7485
More information about the Beowulf