HP XC System Software Installation Guide Version 3.2

Do one of the following:
• To install LSF, enter y or press the Enter key.
— If you elected to install SLURM in step 14, proceed to step 17 to choose the type of
LSF to install.
— If you did not elect to install SLURM, you cannot choose the type of LSF to install,
and standard LSF is installed automatically. Proceed to step 19.
• If you intend to install another job management system, such as PBS Professional (see
Chapter 9) or the Maui Scheduler (see Chapter 10) enter n. Proceed to step 22.
If at a future time you want to install LSF, rerun the cluster_config utility, and
answer y to this question.
The remainder of this procedure does not describe how to install any other job
management system other than LSF-HPC with SLURM or standard LSF.
17. Decide what type of LSF to install:
There are two types of LSF available to install:
1. Standard LSF: the standard Load Sharing Facility product.
2. LSF-HPC integrated with SLURM: the LSF High Performance
Computing solution integrated with SLURM for XC.
Which LSF product would you like to install (1/2)? [2]:
Table 3-8 lists the features of LSF-HPC with SLURM and standard LSF to help you decide
the type of LSF to install.
Table 3-8 LSF-HPC with SLURM and Standard LSF Features
Standard LSFLSF-HPC with SLURM
• Ideal for serial jobs because it is a load-based
scheduler
• Finds the free resource that is the least loaded and
dispatches the job to that node.
• Sufficient for sites that do not need the type of
parallel job support provided by LSF-HPC with
SLURM.
• Parallel support (through SLURM) for:
— Accounting
— Signal propagation
— I/O
— Job launching
• Designed to ensure that parallel jobs (MPI jobs)
achieve the best performance by dedicating whole
nodes to parallel jobs. This works well for systems
with 2 processor and 4 processor nodes where jobs
are expected to span across nodes.
• Exclusive node allocation with exclusive user access
control.
• Presents the entire system as a single, large SMP
host rather than a large system of many hosts. This
simplifies system status commands because
information is shown for one host, which makes it
desirable for large-scale systems.
18. If you are installing LSF-HPC with SLURM, your first decision is where to assign the primary
LSF node; this decision is not required for standard LSF.
• If more than one node has the resource_management role, you are prompted to
identify the primary LSF node, as follows:
Here is the set of nodes from which to select the Primary
XC LSF-HPC node: n[15-16]
Enter the Primary XC LSF-HPC node [n16] : n16
• If only one node has the resource_management role, the following appears:
n16 is the only node with the Resource Management role,
and it is the Primary LSF-HPC node.
96 Configuring and Imaging the System