Scyld: bad scaling

Ivan Rossi ivan at biocomp.unibo.it
Wed Sep 26 01:57:18 PDT 2001


Beowulfers,
   recently i rebuilt our tiny 10 CPUs cluster using Scyld. Before i have been
using RedHat 6.2 + LAM MPI. And i like it, it is easier to mantain.
Unfortunately, after the rebuild, I found a marked performance degradation
with respect to the former installation.  In particular i found a
disappointingly bad scaling for the application we use most, the MD program
Gromacs 2.0.

Now scaling goes almost exactly as the square root of the number of nodes,
that is it takes 4 CPUs to double performance and nine CPUs to triple them.

Since no hardware has been changed, in my opinion it must be either the
pre-compiled Scyld kernel, bpsh or Scyld MPICH. So i hope that some fine
tuning of them should solve the problem.

Do you have any advice about the cause of the problem and about what to do?
I really would like to stay with Scyld.

Thanks in advance

Ivan

PS The cluster is composed by 4 Dual PIII 500, a dual PIII 700 front-end and
an Intel Express 520 switch. RAM is 512MB on each machine. NIC are Intel
eepro100 cards

-- 
Dr. Ivan Rossi - CIRB Biocomputing Unit - University of Bologna (Italy)
e-mail: ivan at biocomp.unibo.it   Web: http://www.biocomp.unibo.it/ivan






More information about the Beowulf mailing list