HP XC System Software Administration Guide Version 3.1

The Nagios infrastructure contains a module that monitors the LSF-HPC with SLURM virtual IP. If it
detects a problem with the virtual IP (for example, the inability to ping it), the monitoring code assumes
the node is down and chooses a new LSF execution host from the backup candidate nodes on which to
set up the virtual IP and restart LSF-HPC with SLURM.
See “LSF-HPC with SLURM Failover” (page 189) for more information.
15.3 Switching 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-HPC 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. Log in as superuser (root) on the head node.
2. Rerun the cluster_config utility. Proceed through the process until you reach the LSF section.
3. When you are prompted to configure LSF, enter yes.
4. When prompted, select the type of LSF you want to install:
• Standard LSF-HPC is choice 1.
• LSF-HPC with SLURM is choice 2, the default.
5. When prompted, enter d to delete the existing LSF installation.
6. Answer the remainder of the questions as appropriate for your system. The cluster_config updates
the golden image.
7. Propagate the new golden image to all nodes. See Chapter 10 (page 129) for more information.
15.4 LSF-HPC with SLURM Installation
When selected, LSF-HPC with SLURM is automatically installed during cluster_config execution.
This installation is optimized for operational scalability and efficiency within the HP XC system, and is a
very good solution for the HP XC system. Depending how you manage your overall LSF cluster file system,
this installation is sufficient for adding the HP XC system to an existing LSF cluster. For more information,
see “Installing LSF-HPC with SLURM into an Existing Standard LSF Cluster ” (page 251).
The LSF-HPC with SLURM tar files to be installed are located in the /opt/hptc/lsf/files directory.
Before the installation begins, you are prompted for the following information:
• Primary LSF administrator
This user account is necessary for establishing ownership of the LSF-HPC with SLURM configuration
file. If the lsfadmin user account does not exist, it will be created locally within HP XC. You can
configure other LSF administrators after the installation has completed. For more information, see
Administering Platform LSF on the HP XC Documentation CD.
• The name of the LSF cluster
This name must be unrelated to any network host name. This name must be unique unless the intent
is to add the HP XC system to an existing LSF cluster. In such a case, the name must match the name
of the existing LSF cluster.
The default name is hptclsf.
After these values are obtained and verified, the LSF-HPC with SLURM installation runs installing the
appropriate files under /opt/hptc/lsf/top/. On completion, the following post-installation procedures
are performed:
• LSF-HPC with SLURM directories are relocated to take advantage of the HP XC file system hierarchy.
The location of the LSF-HPC with SLURM installation is /opt/hptc/lsf/top, which contains four
directories:
conf The conf directory is moved to /hptc_cluster/lsf/conf; it is linked through a soft link
to /opt/hptc/lsf/top/conf.
182 Managing LSF