Task 8: Modify SLURM Characteristics (Optional)

Compute node characteristics

Initially, all nodes with the compute role are listed as SLURM compute nodes, and these nodes are configured statically with a processor count of two.

A sample default compute node entry in the slurm.conf file looks like this:

NodeName=n[1-64] Procs=2

SLURM provides the ability to set several other compute node characteristics. At a minimum, you should ensure that the processor count is accurate. You should also set the RealMemory and TmpDisk characteristics so that SLURM can monitor those values on the nodes and users can submit jobs that request specific values.

A sample updated entry might look like this:

NodeName=n[1-59]  Procs=2 RealMemory=2048 TmpDisk=9036
NodeName=n[60-64] Procs=4 RealMemory=4096 TmpDisk=16384 Weight=2

For more information about setting compute node characteristics, see slurm.conf(5) .

Compute node partition layout

Initially, all nodes are placed into one partition for exclusive management by LSF. To set aside some nodes for non-LSF use, you must configure a second partition for those nodes.

A sample default partition entry in the slurm.conf file looks like this:

PartitionName=lsf RootOnly=YES Shared=FORCE Nodes=n[1-64]

An updated partition configuration to create a second partition for direct SLURM use by users might look like this:

PartitionName=lsf RootOnly=YES Shared=FORCE Nodes=n[10-64]
PartitionName=srun Default=YES Nodes=n[1-9]

For more information on configuring partitions, see slurm.conf(5) .