Serviceguard Extension for RAC Version A.11.19 Release Notes, October 2009 (T1907-90051)

Before You Start
IMPORTANT: If you need to upgrade Oracle software, a non-rolling upgrade may be
required; consult the Oracle documentation.
Make sure you plan sufficient system capacity to allow moving the packages from
node to node during the process without an unacceptable loss of performance.
Make sure you have read and understood the “Restrictions for DRD Upgrades”
(page 17), and that your cluster meets the prerequisites.
If you are upgrading from a qualifying A.11.18 version, make sure you have
implemented the workaround for defect QXCR1000906197 as described under
“Restrictions for DRD Upgrades” (page 17).
Make sure that you have downloaded the latest DRD software and are thoroughly
familiar with the DRD documentation. See “Rolling Upgrade Using DRD” (page 16)
for more information.
There are some restrictions on where the install depot can reside. Make sure you
will be upgrading the clone disk from a supported location; see “Restrictions for
DRD Upgrades” (page 17).
Running the Rolling Upgrade
1. On the node you want to upgrade, edit /etc/rc.config.d/cmcluster to
include the following line:
AUTOSTART_CMCLD = 0
This value will be replicated on the clone root disk and will keep the upgraded
node from automatically rejoining the cluster when it reboots.
2. Create a clone root disk for the node you want to upgrade.
3. Upgrade the clone disk to the new HP-UX release (if necessary), including
Serviceguard (using drd runcmd update-ux), or upgrade Serviceguard alone
(using drd runcmd swinstall).
4. Upgrade the clone disk to the new SGeRAC release.
5. Halt Oracle (RAC, CRS, Clusterware, OPS) on the node.
6. Halt the node. You can do this in Serviceguard Manager, or use the cmhaltnode
(1m) command. This will cause the node’s packages to start up on an adoptive
node.
7. Reboot the node from the updated clone root disk.
8. Edit the /etc/rc.config.d/cmcluster file to include the following line:
AUTOSTART_CMCLD = 1
9. Restart the cluster on the upgraded node, using Serviceguard Manager or
cmrunnode (1m).
10. Restart Oracle (RAC, CRS, Clusterware, OPS) on the upgraded node.
Compatibility Information and Installation 23