HP XC System Software Administration Guide Version 3.2

2. Use the following command to stop LSF-HPC with SLURM:
# controllsf stop
3. Use the following command to restart LSF-HPC with SLURM on another node; this example
starts LSF-HPC with SLURM on node n18:
# ssh n18 controllsf start here
16.15 Moving SLURM and LSF Daemons to Their Backup Nodes
It may be necessary to move SLURM and LSF daemons from their primary node to their backup
node. One reason for this is to perform maintenance on the primary node.
Follow this procedure to move the SLURM and LSF daemons from their primary node:
1. Log in to the backup node as superuser (root).
2. Shut down the backup slurmctld daemon:
# pkill slurmctld
3. Use the text editor of your choice to edit the /hptc_cluster/slurm/etc/slurm.conf
file
a. Change the value of the ControlMachine attribute to the backup node.
b. Comment out or change the value of the BackupController.
c. Save the file and exit the text editor.
4. Take the appropriate precautions before shutting down LSF on the primary node. You can
warn users or close the LSF queues and wait for all jobs to finish.
5. Shut down LSF on the primary node.
NOTE: You do not have to be logged into the primary node to do this.
Shutting down LSF on the primary node will not affect batch jobs, but it will end interactive
LSF jobs, that is, jobs submitted with the bsub -I option.
# controllsf stop
6. Log in to the primary SLURM node and shut down the primary slurmctld daemon:
# pkill slurmctld
7. On the backup SLURM node, start the primary slurmctld controller:
# slurmctld
8. Start LSF locally on the backup node:
# controllsf start here
9. Enter the following command if you want to make the backup node the primary node for
LSF:
# controllsf set primary backup_nodename
If you set another node to be the BackupController for SLURM, you can log into that node
and run the slurmctld command. This new backup node requires the resource_management
role to be assigned to it for this configuration to persist after future runs of the cluster_config
command.
To move LSF and SLURM back to the original primary node, follow the same procedure with
the assumption that the original primary node is now the backup node, and the original backup
node is now the primary node.
206 Managing LSF