Scyld: bad scaling
ivan at biocomp.unibo.it
Wed Sep 26 01:57:18 PDT 2001
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
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
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
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