Child pages
  • What is running on cluster, where? interpreting slurmtop
Skip to end of metadata
Go to start of metadata

The program slurmtop, available on the login nodes, shows which jobs are currently running on which nodes and cores of a cluster.

Jobs belonging to a single user can be highlighted by launching slurmtop with the -u switch:

slurmtop -u <NetID>

(of course, replace <NetID> with your NYU NetID). Or, you can use the alias "me":

slurmtop -u me 

When you start slurmtop you see something like the annotated screenshot below. You might need to resize your terminal to make it all fit: 

Exercise

Start slurmtop and find your interactive session.

 You'll probably need to use 'slurmtop -u me' to identify your job amongst all the colors.                                                       

You'll probably also need to increase the size of your terminal window and decrease the font size so it all fits!

What hardware is available?

You can use slurmtop to see which nodes are busy and which are free. Knowing what resources are available on a given node can help in estimating how busy is that part of the cluster that your job needs.

Node types we have, and where they appear in slurmtop, are:


  • No labels