HP XC System Software Installation Guide Version 3.0
8 Node Roles, Services, and the Default Configuration
This chapter addresses the following topics:
• Default Node Role Assignments (page 91)
• Special Considerations for Modifying Default Node Role Assignments (page 91)
• Role Definitions (page 92)
Default Node Role Assignments
Table 8-1 lists the default role assignments. The default assignments are based on the number of total nodes
in your system.
Table 8-1 Default Role Assignments Based on System Size
Systems with 64 or More NodesSystems with 63 or Fewer Nodes
•• The resource_management role (containing LSF and SLURM) is located
on an exclusive node.
All roles, and thus all services, are located on the
head node.
• All nodes, including the head node, are compute
nodes.
• Nodes configured with roles that are not essential for computation, including
the head node and the node configured with the resource_management
role, are not compute nodes; every other node is a compute node.
• Compute nodes are assigned with only the compute role; no other roles
are configured on these nodes to keep them as free as practical of services
not needed for computation.
Special Considerations for Modifying Default Node Role Assignments
This section presents information you need to consider before accepting the default role assignments made
by the cluster_config utility. After reading this information, you may decide to modify the default
assignments. Appendix F (page 117) describes how to modify and verify node role assignments.
• General Considerations (page 91)
• Considerations for Systems with 63 or Fewer Nodes (page 92)
• Considerations for Systems with 64 or More Nodes (page 92)
General Considerations
Before deciding whether or not you want to accept the default configuration, consider the following:
• By default only one node is configured with the resource_management role. The
resource_management role consists of one or more SLURM controller daemons and the LSF XC
execution host. If only one node has the resource_management role, both SLURM and LSF controller
daemons run on that node, and no failover of these components is possible.
HP recommends that you configure at least two nodes with the resource_management role to
distribute the work of these components and provide for failover configuration.
• If you expect LSF to be accessible from outside the HP XC system, all nodes with the
resource_management role must also be configured with the external role and have the
appropriate hardware and wiring to directly access the external network.
• If standard LSF is selected, the node or nodes with the resource_management role are configured
first, and the first node listed is the LSF Master Host.
• You must assign the disk_io role to any node that is exporting SAN storage.
• No nodes are configured with the login role. Assigning a login role to a node enables the LVS
director service. You must assign a login role to each node on which you expect users to be able to
log in and use the system.
Default Node Role Assignments 91