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

11
There are several points to consider prior to using either toolkit to create Serviceguard packages:
It is highly recommended that the VM guest to be packaged should be tested by first starting it on each VM host node
in the cluster to ensure that its backing stores are accessible from all cluster nodes.
The toolkit commands expect the VM guest to be running in order to identify all required backing stores and their
mount points for the package configuration file it creates.
After executing the toolkit commands, it is important to review the generated package configuration file to ensure the
correct logical volumes and mount points have been identified and are included in the configuration.
Integrity virtual machines as Serviceguard nodes
In the previously described VM as Serviceguard package model, Serviceguard provided high availability for VM
guests encapsulated within Serviceguard packages. In the virtual machines as Serviceguard nodes (or, VMs as nodes)
model, HP-UX VM guests are used as actual Serviceguard cluster nodes to provide the same HA failover capabilities
found in traditional Serviceguard cluster configurations. Essentially, Integrity VM can be used to consolidate
Serviceguard clusters on to VMs. VMs as HP-UX Node cluster configurations can span across:
VMs and separate physical nodes or vPars
VMs on separate VM hosts
A combination of the above
VMs on the same VM host (cluster in a box”)
Linux guests running as Serviceguard nodes are supported starting with Integrity VM A.03.00 and Serviceguard for
Linux version A.11.18 (with a required patch).
Note:
Serviceguard Linux clusters can only contain all physical Linux servers or all
Linux VM guests as nodes in the cluster.
In an HPVM environment, using physical Linux nodes with Linux VM guest nodes in the same cluster is not supported
due to the differences in how physical I/O to shared storage is handled between a Linux guest using virtual I/O on
an HP-UX host and a physical Linux server using a Linux I/O stack.
The following are several examples of VMs-as-nodes configurations that are currently supported.
In figure 4, a Serviceguard 2-node cluster is formed using a VM guest serving as one node and a physical system as
the second node.
Figure 4: Serviceguard cluster using a VM guest and physical node
In this configuration, Serviceguard provides high availability in the event of a VM guest or application failure.
A failed application can either be restarted within the same VM guest or failed over to the physical node.
VM Host
Physical Node
VM Guest
Serviceguard Package Failover
Serviceguard Cluster
VM Host
Physical Node
VM Guest
Serviceguard Package Failover
Serviceguard Cluster