Re: [R] rmpi/snow/sge/openmpi help

2008-11-07 Thread jk jk
Forgive the spam.  Let me try that e-mail again.


I'm trying to get snow working with openmpi and sge.  Everything
appears to work, except the program only runs on 1 node.  If i tell
snow to run on 5 nodes, it spawns 5 processes on a single node, 6
nodes = 6 procs on 1 node and so on.  I'm at a loss for ideas.  Any
help would be appreciated.

Setup:  Rocks Cluster, OpenMPI, R 2.8.0, Snow, Rmpi.


Please ask for specifics.  Thanks in advance.

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.


Re: [R] rmpi/snow/sge/openmpi help

2008-11-07 Thread Markus Schmidberger
Hi,

there is a new mailing list for R and HPC: [EMAIL PROTECTED]
This is probably a better list for your question. Do not forgett, first
of all you have to register: https://stat.ethz.ch/mailman/listinfo/r-sig-hpc

Did you tried to run openmpi and R without SGE?
Like this: orterun -n 1 R --no-save

I think openmpi / orterun do not get the correct hostfile. Therefore it
starts with a default hostfile and this is only for the local machine!
So all nodes are at the same machine.
It normally works like this that SGE creates a hostfile and puts the
path of the hostfile to a special (environment) variable. Now you have
to  make sure that the correct hostfile will be used. So SGE should call
something like this:
ortrun -n 1 --hostfile $PATH_TO_HOSTFILE R --so-save

Best
Markus




jk jk wrote:
 Forgive the spam.  Let me try that e-mail again.
 
 
 I'm trying to get snow working with openmpi and sge.  Everything
 appears to work, except the program only runs on 1 node.  If i tell
 snow to run on 5 nodes, it spawns 5 processes on a single node, 6
 nodes = 6 procs on 1 node and so on.  I'm at a loss for ideas.  Any
 help would be appreciated.
 
 Setup:  Rocks Cluster, OpenMPI, R 2.8.0, Snow, Rmpi.
 
 
 Please ask for specifics.  Thanks in advance.
 
 __
 R-help@r-project.org mailing list
 https://stat.ethz.ch/mailman/listinfo/r-help
 PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
 and provide commented, minimal, self-contained, reproducible code.


-- 
Dipl.-Tech. Math. Markus Schmidberger

Ludwig-Maximilians-Universität München
IBE - Institut für medizinische Informationsverarbeitung,
Biometrie und Epidemiologie
Marchioninistr. 15, D-81377 Muenchen
URL: http://www.ibe.med.uni-muenchen.de
Mail: Markus.Schmidberger [at] ibe.med.uni-muenchen.de
Tel: +49 (089) 7095 - 4599

__
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.