Difference between revisions of "Grid5000"

From HCL
Jump to: navigation, search
Line 6: Line 6:
 
* There is no access to Internet from computing nodes (external IPs should be registered on proxy), therefore, download/update your stuff at the access nodes.
 
* There is no access to Internet from computing nodes (external IPs should be registered on proxy), therefore, download/update your stuff at the access nodes.
 
* Each site has a separate NFS, therefore, to run an application on several sites at once, you need to copy it '''scp, sftp, rsync''' between access or frontend nodes.
 
* Each site has a separate NFS, therefore, to run an application on several sites at once, you need to copy it '''scp, sftp, rsync''' between access or frontend nodes.
* Jobs are run from the frondend nodes, using a PBS-like system [https://www.grid5000.fr/mediawiki/index.php/Cluster_experiment-OAR2 OAR]. Basic commands:
+
* Jobs are run from the frondend nodes, using a [http://en.wikipedia.org/wiki/OpenPBS PBS]]-like system [https://www.grid5000.fr/mediawiki/index.php/Cluster_experiment-OAR2 OAR]. Basic commands:
 
** '''oarstat''' - queue status
 
** '''oarstat''' - queue status
 
** '''oarsub''' - job submission
 
** '''oarsub''' - job submission
Line 18: Line 18:
 
$ oarsub BATCH_FILE -t allow_classic_ssh -l [/cluster=N/]nodes=N,walltime=HH[:MM[:SS]] [-p 'PROPERTY="VALUE"']
 
$ oarsub BATCH_FILE -t allow_classic_ssh -l [/cluster=N/]nodes=N,walltime=HH[:MM[:SS]] [-p 'PROPERTY="VALUE"']
 
</source>
 
</source>
 +
* The image to deploy can be created with help of a [http://wiki.systemimager.org/index.php/Main_Page Systemimager]-like system [https://www.grid5000.fr/mediawiki/index.php/Deploy_environment-OAR2 Kadeploy]
 +
* Running MPI applications is described [https://www.grid5000.fr/mediawiki/index.php/Run_MPI_On_Grid%275000 here]

Revision as of 08:49, 21 April 2010

https://www.grid5000.fr/mediawiki/index.php/Grid5000:Home

Usage

  • Select sites and cluters for experiments, using information on the Grid5000 network
  • Access is provided via access nodes: access.SITE.grid5000.fr. As soon as you are on one of the sites, you can directly ssh frontend node of any other site: frontend.SITE2.
  • There is no access to Internet from computing nodes (external IPs should be registered on proxy), therefore, download/update your stuff at the access nodes.
  • Each site has a separate NFS, therefore, to run an application on several sites at once, you need to copy it scp, sftp, rsync between access or frontend nodes.
  • Jobs are run from the frondend nodes, using a PBS]-like system OAR. Basic commands:
    • oarstat - queue status
    • oarsub - job submission
    • oardel - job removal

Interactive job on deployed images:

$ oarsub -I -t deploy -l [/cluster=N/]nodes=N,walltime=HH[:MM[:SS]] [-p 'PROPERTY="VALUE"']

Batch job on installed images:

$ oarsub BATCH_FILE -t allow_classic_ssh -l [/cluster=N/]nodes=N,walltime=HH[:MM[:SS]] [-p 'PROPERTY="VALUE"']
  • The image to deploy can be created with help of a Systemimager-like system Kadeploy
  • Running MPI applications is described here