White Papers

12 DELL EMC HPC System for Life Sciences v1.2 | Document ID | version (optional)
HA cluster will failover the storage service to the healthy server with the assistance of the two fence devices;
and also ensure that the failed server does not return to life without the administrator’s knowledge or control.
The test used to evaluate the NSS7.0-HA functionality and performance is shown in Figure 2. The following
configuration was used.
• A 32-node HPC compute cluster (also known as “the clients”) was used to provide I/O network traffic
for the test bed.
• A pair of Dell EMC PowerEdge R730 servers were configured as an active-passive HA pair and
function as a NFS server for the HPC compute cluster.
• Both NFS servers were connected to a shared Dell EMC PowerVault MD3460 storage enclosure
extended with one Dell EMC PowerVault MD3060e storage enclosure (Figure 2 shows a 480 TB
solution with the two PowerVault MD storage arrays) at the back-end. The user data is stored on an
XFS file system created on this storage. The XFS file system was exported to the clients by using
NFS.
• The NFS servers were connected to the clients by using the public network. This network was Intel
OPA.
• For the HA functionality of the NFS servers, a private 1 Gigabit Ethernet network was configured to
monitor server health and heartbeat, and to provide a route for the fencing operations by using a Dell
EMC Networking 3048-ON Gigabit Ethernet switch.
• Power to the NFS servers was provided by two APC switched PDUs on two separate power buses.
Figure 2: NSS7.0-HA test bed