[torqueusers] Success setting up a new Torque Environment in University

Coyle, James J [ITACD] jjc at iastate.edu
Fri Sep 16 09:21:07 MDT 2011


Guilherme Rocha,


  To add to the options Bas van der Vlies sent to you, I suggest users also add the -V option to qsub.
Make sure to add all the -lnodes=...,walltime=...  options to the command line sinceyou are not submitting a script.

E.g.

qsub -V -I  -X  -l nodes=5:ppn=16,walltime=3:00:00


  Also, clustallw and OpenMPI must be installed on all nodes for this to work.
I use (and recommend) a common network mounted (e.g. NFS)   /opt  directory
which is hosted from my head node so that I keep a consistent set of binaries
and libraries on all nodes.




Why I did it this way:
------------------------
  I did this because early on in cluster computing, I was a user on a cluster which had locally
mounted non-system libraries.  I had lots of jobs fail because one node in the set that my
job ran on did not have the latest version of some   libxxx.so library.  This wasted lots of
time for both me and the sysadmin, especially because I was running from several time
zones away, making real-time responses nearly impossible, and because the jobs did not run
immediately, so I would not know that the job failed until the next day.



James Coyle, PhD
High Performance Computing Group
 Iowa State Univ.
web: http://jjc.public.iastate.edu/<http://www.public.iastate.edu/~jjc>




From: torqueusers-bounces at supercluster.org [mailto:torqueusers-bounces at supercluster.org] On Behalf Of Bas van der Vlies
Sent: Friday, September 16, 2011 8:34 AM
To: Torque Users Mailing List
Cc: rbzucoloto at gmail.com; vitorvilas at gmail.com
Subject: Re: [torqueusers] Success setting up a new Torque Environment in University


On 16 sep 2011, at 13:34, Guilherme Rocha wrote:





Hello folks,



thanks a lot for all answers, I'm doing a troubleshooting now, considering your answers, in order to get my target acquired.
Thanks a lot once more.

I already start to research how to use MPI, in fact we have the clustalw-mpi installed on the head node,
but no in the nodes (yet), I will try to do your recommendations now.

We alson have open-mpi installed.


We are using Debian, all software installed via #aptitude.


I have this question from my teacher, the lab coordinator

 *   Is possible to run X programs (like clustalx)  interactivelly under Torque?

qsub - I -X

-I: interactively
-X: X11 forwarding

You get a shell prompt:
 * xcalc

PS) man qsub





2011/9/2 Coyle, James J [ITACD] <jjc at iastate.edu<mailto:jjc at iastate.edu>>
  You'll need and MPI application to use multiple nodes.

  Perhaps this application would be  Clustalw-MPI .
It looks like this is available at:
http://www.bii.a-star.edu.sg/achievements/applications/clustalw/download.php
Information on this can be found at:
http://www.bii.a-star.edu.sg/docs/software/README.clustalw-mpi


  Torque just reserves node, you need something like MPi and program written in MPI to use
multiple nodes.

  If you need a suggestion on MPI,  I use OpenMPI because it installs easily and can use
multiple network interconnects, it also works well with Torque.

Ethernet works, but is slow, however, that is likely what you have.
We use Infiniband and Myrinet networks in addition to Ethernet. They give much better
performance for our workloads, but the cards and switches are very expensive.


From: torqueusers-bounces at supercluster.org<mailto:torqueusers-bounces at supercluster.org> [mailto:torqueusers-bounces at supercluster.org<mailto:torqueusers-bounces at supercluster.org>] On Behalf Of Guilherme Rocha
Sent: Friday, September 02, 2011 4:18 AM
To: torqueusers at supercluster.org<mailto:torqueusers at supercluster.org>

Subject: [torqueusers] Success setting up a new Torque Environment in University


Hello folks,



My name is Guilherme and this is my first post here.
Thanks for this great project.

We're setting-up a Torque Cluster with 23 nodes and will be used to bioinformatics tasks.

I'm completely newbie to all of this, so after hard steps of troubleshooting, we finally
received good news in logs.  We did a small alginment using clustalw.

But we have some doubts about how to use a program in parallel, like:


Question 1)  I need to have clustalw (or the script programs installed in all nodes?)
Clustalw is only installed  in head node by now.

Question 2:  Can we use/open GUI program's interfaces to work  using torque?

Question 3: When I submit a job, even requesting 10 nodes, clustal are being runned
only in one node. What can be wrong?


thanks in advance

thanks in advance,


--
--
Guilherme Rocha
GF7 Doc & Systems - Soluções Tecnológicas
Pesquisa e Desenvolvimento - World Wide
R. João Goulart, 170  - Rio Pardo - RS - CEP 96640-000
Mobile:  +55 51 81400360<tel:%2B55%2051%2081400360> - Home Page:   http://www.gf7.com.br<http://www.gf7.com.br/>


_______________________________________________
torqueusers mailing list
torqueusers at supercluster.org<mailto:torqueusers at supercluster.org>
http://www.supercluster.org/mailman/listinfo/torqueusers



--
--
Guilherme Rocha
GF7 Doc & Systems - Soluções Tecnológicas
Pesquisa e Desenvolvimento - World Wide
R. João Goulart, 170  - Rio Pardo - RS - CEP 96640-000
Mobile:  +55 51 81400360 - Home Page:   http://www.gf7.com.br<http://www.gf7.com.br/>

<ATT00001..txt>

--
Bas van der Vlies
basv at sara.nl<mailto:basv at sara.nl>



-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20110916/9e16fef7/attachment-0001.html 


More information about the torqueusers mailing list