HP Application Recovery Manager software A.06.10 Administrator's guide (March 2008)

1. On the backup system, set ZDB_VOLUMESCAN_RETRIES and
ZDB_POST_RESCAN_DELAY omnirc variables to moderately higher values
(defaults are 5 retries and 30 seconds delay time).
2. Restart the backup session.
Problem
Application Recovery Manager fails to delete a replica from the replica rotation set
in a cluster environment
A backup session reports the following major error and then normal message:
[Major]
Resolving of storage volume 'target_volume_ID' has failed.
...
[Normal]
Some disks are still in use. They will be moved in purge bucket.
This error may appear in a cluster environment with backup system as a virtual server.
In this case, after failover, new backup sessions cannot rotate out the replicas on the
active node because the presentations match the passive node. The replicas to be
removed are marked with the purge flag in the SMISDB and it is recommended to
delete such replicas.
Action
To delete the replicas with the purge flag from the disk array and SMISDB, perform
one of the following actions:
• Manually delete all storage volumes that are marked for purging by running:
omnidbsmis –purge [-force] –host hostname
where hostname is the name of the node on which you want to perform the
purge operation.
Use the –force option to remove the volumes marked for purging even if they
are presented to the systems.
• Perform manual failover and run another backup. The backup will delete all the
volumes marked for purging on the new active node.
Troubleshooting60