Difference between revisions of "Grid5000"
From HCL
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