Examining Nodes and Partitions Before Running Jobs

Before launching an application, you can determine the availability and status of the system's nodes and partitions. Node and partition information is useful to have before launching a job so that you can launch the job to properly match the resources that are available on the system.

When invoked with no options, the SLURM sinfo command returns information about node availability and partitions, along with other information:

$ sinfo
PARTITION AVAIL TIMELIMIT NODES  STATE  NODELIST
lsf          up  infinite     4  down*  n[12-15]
slurm*       up   infinite    2  idle   n[10-11]

The previous sinfo output shows that there are two partitions on the system:

The asterisk in the PARTITION column indicates the default partition. An asterisk in the STATE column indicates nodes that are currently not responding.

See Chapter 9 “Using SLURM” for information about using the sinfo command. The SLURM sinfo manpage also provides detailed information about the sinfo command.