[slurm-users] Execute parallel commands on all nodes running jobs of a particular user

Ole Holm Nielsen Ole.H.Nielsen at fysik.dtu.dk
Thu Jul 19 02:47:26 MDT 2018


Hi Slurm users,

We have found the need to execute a parallel command on all nodes 
running jobs belonging to a particular user.

I have made a configuration to the excellent ClusterShell tool as 
documented in https://wiki.fysik.dtu.dk/niflheim/SLURM#clustershell

If you add a "slurmuser" section to the 
/etc/clustershell/groups.conf.d/slurm.conf file, you can now run 
commands such as:

$ clush -bw at su:username 'df -Ph /scratch'

$ clush -bw at su:username 'du -s /scratch/username'

I hope that others may find this feature useful.

/Ole



More information about the slurm-users mailing list