Designing High Availability Solutions with HP Serviceguard and HP Integrity Virtual Machines

15
An example of a storage configuration used by an HP-UX VM as Serviceguard node configuration is shown in
figure 10a, and a Linux VM as Serviceguard node configuration in figure 10b.
Figure 10b: Linux VM as Serviceguard node storage configuration
The primary difference between the HP-UX and Linux VM as Serviceguard package storage configurations is that the
Linux configuration can only use Linux VM nodes in the cluster, whereas the HP-UX configuration can use either HP-UX
physical or VM cluster nodes.
Dynamic memory allocation
A capability starting with the Integrity VM A.03.00 release is the ability to dynamically allocate memory used by an
HP-UX VM guest. The intended use case for this feature is for VM hosts acting as consolidated standby servers using
multiple VM guests as Serviceguard nodes that can run Serviceguard packages when a failover occurs (an example
of this configuration is shown in figure 7). In this configuration, the VM guests functioning as Serviceguard standby
servers use a minimum amount of VM host memory resources until they are required to use additional memory to run
a Serviceguard failover package. In this way, the VM host does not have to be configured with the full amount of
memory required to support all failover packages at a single time. Note that the total memory currently allocated to
all running VMs must be less than or equal to the physical memory on the VM host system minus the memory needed
for the VM host itself. In addition, VM guest control of dynamic memory must be enabled using the “hpvmmodify –
P [VM name] –x dynamic_memory_control=1” command in order to use this capability. The advantages to
this configuration are cost savings through the reduction of hardware systems and memory traditionally used by
individual standby servers. Note that the guest management software kit must be installed on the VM guest to enable
this feature.
Figure 11 shows an example of how dynamic memory allocation is used in a failover situation. In step 1 of the figure,
the VM is initially started with the maximum amount of memory required to run its HP-UX guest operating system and
any failover application packages to help prevent memory fragmentation. Once started, the VM will then release an
amount of its initially allocated memory to a “comfortable minimum” level that is required only to run the guest
operating system.
VM Host
VM Host
Application
Data
VM
Backing
Store
Whole Disk Volume Group or CFS
VM Guest
VM Guest
VM
Backing
Store
Whole Disk
Failover
Serviceguard Cluster
VM Host
VM Host
Application
Data
VM
Backing
Store
Whole Disk
VM
Backing
Store
Whole Disk Volume Group or CFS
VM Guest
VM Guest
VM
Backing
Store
Whole Disk
VM
Backing
Store
Whole Disk
Failover
Serviceguard Cluster