It would help if people could include which release of Linux they are
using and the type/speed of network.
We have a cluster of 25 PIII/500MHz/128Mb connected to a Cisco switch
full-duplex 100Mbit/s, we should have more information to share over
the next few weeks (comparative genomics using psi-blast), but so far
the bottleneck seems to be the speed the local ide disk and not the
network/NFS. We are running RH 6.1 and I've been told that NFS has
been much improved/rewritten (I need to check on that though).
Just my $.02
M.
Steffen Schmidt <schmidt at embl-heidelberg.de> writes:
[...]
> We are running BLAST searches on Linux based PentiumIII-Servers - we
> have severe problems (i.e. the server crashes) when we use e.g. blastpgp
> and a database which is accessed via NFS. This is a known bug to Linux
> as far as I know (If someone knows better please answer). So the best
> way to use BLAST is by using locally stored databases and everything is
> fine!
--
Marcel Turcotte Biomolecular Modelling Laboratory
M.Turcotte at icrf.icnet.uk Imperial Cancer Research Fund
[44|0]-171-269-3348/3258 Phone/Fax PO Box 123, 44 Lincoln's Inn Fields
http://www.bmm.icnet.uk/people/turcotte London WC2A 3PX, England
