Hi all,
I've setup a 2 node cluster (1 headnode + 1 client), each with 2 processors,
using Fedora Core 5.
In a previous mail I've managed to solve some of my OSCAR/MPI problems by using
"lamboot -ssi boot rsh". however, this seems to cause a deficient communication
between MPI and TORQUE. Namely, If I use "mpirun -np 4" he launches 4 processes
but assumes I'm using 1 processor (see below).
laminfo output:
Queue: workq
queue_type = Execution
total_jobs = 2
state_count = Transit:0 Queued:0 Held:0 Waiting:0 Running:1 Exiting:0
resources_max.cput = 10000:00:00
resources_max.ncpus = 4
resources_max.nodect = 2
resources_max.walltime = 10000:00:00
resources_min.cput = 00:00:01
resources_min.ncpus = 1
resources_min.nodect = 1
resources_min.walltime = 00:00:01
resources_default.cput = 10000:00:00
resources_default.ncpus = 1
resources_default.nodect = 1
resources_default.walltime = 10000:00:00
resources_available.nodect = 1
resources_assigned.ncpus = 1
resources_assigned.nodect = 1
enabled = True
started = True
Going through the LAMMPI web page, there is an SSI boot module especially for
PBS: the "tm". I've installed OSCAR with the remote repository option but the
LAMMPI distribution available from Fedora repos doesn't support this SSI
module.
I was thinking if I could keep using Fedora repos but use the original LAMMPI
distribution instead. Can I use both (the original LAMMPI rpms and the remote
repos)? Which one will OSCAR use first?
thanks in adv,
FG
-------------------------------------------------------------------------
This SF.net email is sponsored by: Splunk Inc.
Still grepping through log files to find problems? Stop.
Now Search log events and configuration files using AJAX and a browser.
Download your FREE copy of Splunk now >> http://get.splunk.com/
_______________________________________________
Oscar-users mailing list
Oscar-users@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/oscar-users
