HP XC System Software Release Notes for Version 3.0

To verify the change, submit an interactive job similar to the following:

[lsfadmin@n16 ~]$hostname

n16

[lsfadmin@n16 ~]$ bsub -Is -n8 /bin/bash -i

Job <261> is submitted to the default queue <interactive>.

<<Waiting for dispatch ...>>

<<Starting on lsf.localdomain>>

[lsfadmin@n4 ~]$ hostname

[lsfadmin@n4 ~]$ srun hostname

[lsfadmin@n4 ~]$ exit

exit

[lsfadmin@n16 ~]$ hostname

n16

[lsfadmin@n16 ~]$

9.1.2 How To Switch the Type of LSF Installed

The HP XC system installation process offers a choice of two different types of LSF. The default

choice is LSF-HPC with SLURM. This choice requires that SLURM is installed and configured

when you run the cluster_config utility. Standard LSF is the second type of LSF that is

available to install, and it does not interact with SLURM.

If you made the wrong LSF selection while running the cluster_config utility, perform the

following procedure to remove the current type of LSF installed and install the other type of

LSF:

1. As root on the head node, rerun the cluster_config utility. Proceed through the process

until you reach the LSF section.

2. When you are prompted to configure LSF, enter yes.

3. When prompted, select the type of LSF you want to install. Standard LSF is choice 1, and

LSF-HPC with SLURM is choice 2 (choice 2 is the default).

4. When prompted, enter d to delete the existing LSF installation.

5. Answer the remainder of the questions as appropriate for your system. The

cluster_config updates the golden image.

6. Propagate the new golden image to all nodes.

9.1.3 Node Reboot May Result in Inconclusive Job Termination

If a node that is running a job under LSF-HPC with SLURM is rebooted (with the reboot

command), SLURM may recognize the node as unresponsive and attempt to terminate the job.

However, some remnants of the job may remain, which will cause LSF to report the job as still

running.

This issue has been seen with large jobs using in excess of 100 nodes.

If the node power is turned off instead of rebooted, however, LSF-HPC with SLURM reports the

status as EXIT, and the node is released back to the pool of idle nodes.

52 Load Sharing Facility and Job Management Notes