Cascading Failover in a Continentalclusters, December 2005

3. Split the local mirror (device B’) from the primary replication group in the secondary disk

array.

4. Re-establish the recovery replication group between the recovery disk array and the

secondary disk array. Note, the data is copied from the recovery disk array (device C) to the

secondary disk array (device B’).

5. Check the data copy from the devices in the recovery disk array to the local devices of the

recovery replication group in the secondary disk array.

6. Once the data copy completes, split the replication link between secondary disk array and

recovery disk array.

7. Re-establish the local mirror devices (device B’) in the secondary disk array as mirrors to the

primary replication group devices (device B). Restore the data from the local mirror devices

to the devices in the primary replication group.

8. Check the data restore from the local mirror to the devices in the primary replication group.

9. Once the data restore completes, split the local mirror devices from the primary replication

group.

10. Set the primary replication group such that the devices (device B) on the secondary disk are

read write-able.

11. For LVM, since the recovery cluster has a different cluster ID, the data restored from the

recovery disk array to the secondary disk array also copies the recovery cluster’s ID to the

secondary disk array. Do the following to change the cluster’s ID on each cluster aware

volume group in the secondary disk array before starting the application package:

# vgchange -c n /dev/<vg_name>

# vgchange -c y /dev/<vg_name>

For VxVM, the disk group needs to be imported with a force flag in order to clear the hostid

of a node from the recovery site. Perform the following command on each disk group on a

node in the primary cluster:

# vxdg –tfC <disk_group_name>

12. Start the package application at the primary site. Issue the following command for all hosts in

the primary cluster that may run this package:

# cmmodpkg -e -n <host_name> <package_name>

13. Start the package with the following command:

# cmmodpkg -e <package_name>

14. Start the Continentalclusters monitor package on the recovery cluster.

15. Check the primary replication group between the primary disk array and the secondary disk

array and make sure data replication is established.

16. Re-establish the local mirror devices (device B’) in the secondary disk array to the primary

replication group.