HP XC System Software Administration Guide Version 3.0

LSF_RSH=ssh
e. Save the file and exit the text editor.
5. Optional: Configure any special HP XC-specific queues.
XC V2.1 recommends the use of a JOB_STARTER script to be configured for all queues on a HP XC
system. The default installation of LSF on the HP XC system provides default queue configurations which
can be found here: /opt/hptc/lsf/etc/configdir/lsb.queues. The JOB_STARTER script
and its helper scripts can be found in /opt/hptc/lsf/bin/ and may need to be moved to a shared
location depending on how they are configured for use. If they are moved, be sure to edit the
job_starter.sh script and update the loc definition, which provides the location of the helper
scripts.
The intent of the JOB_STARTER script is to handle the case in which a job is launched on a non-HP
XC system node with minimal impact, so it can be configured on all queues. Use good judgement in
employing this script on your system.
6. Optional: Adjust the LSF environment files if necessary
When a new or different version of LSF is installed, it renames the old profile.lsf and cshrc.lsf
files before replacing them with the files from the most recent installation.
Ensure that these files are consistent with the HP XC default LSF environment files as configured above.
Configuring the LSF Alias
Now that LSF has been installed, log out and log back into the HP XC system to establish the proper LSF
environment.
The next step is to configure the LSF alias on the HP XC system. An alias is used on the HP XC system to
prevent hard-wiring LSF to any one node, so that the LSF node in HP XC can fail over to another node if the
current node becomes compromised (hung or crashed). HP XC provides infrastructure to monitor the LSF
node and fail over the LSF daemons to another node if necessary.
The selected IP and host name must not be in use but must be known on the external network. Our example
is using xclsf with an IP address of '16.32.2.140', and the head node for the HP XCsystem is xc-head.
Use the ping command to verify that the selected external host name is not currently in use:
$ ping xclsf
PING xclsf.lab.mycorp.com (16.32.2.140) 56(84) bytes of data.
From xc128.lab.mycorp.com (16.32.2.128) icmp_seq=0
Destination Host Unreachable
Next configure controllsf (which manages LSF setup on HP XC) with the new alias:
$ controllsf set virtual hostname xclsf
Confirm that the alias is set:
$ controllsf show
LSF is currently shut down, and assigned to node .
Failover is disabled.
Head node is preferred.
The primary LSF host node is xc128.
SLURM affinity is enabled.
The virtual hostname is "xclsf".
Starting LSF on the HP XC System
At this point lsadmin reconfig followed by badmin reconfig can be run within the existing LSF
cluster (on plain in our example) to update LSF with the latest configuration changes. A subsequent lshosts
or bhosts should display the new HP XC "node", although it will be UNKNOWN and unavailable, respectively.
LSF can now be started on XC:
$ controllsf start
This command sets up the virtual LSF alias on the appropriate node and then starts the LSF daemons. It will
also create a $LSF_ENVDIR/hosts file (in our example $LSF_ENVDIR = /shared/lsf/conf). This
hosts file is used by LSF to map the LSF alias to the actual host name of the node in HP XC system running
LSF. See the Platform LSF documentation for information on hosts files.
Configuring the LSF Alias 179