zfs discuss - Sep 2010 - stmf corruption and dealing with dynamic lun mapping

I am running Nexenta NCP 3.0 (134f).

My stmf configuration was corrupted.  I was getting errors like in
/var/adm/messages:

Sep  1 10:32:04 llift-zfs1 svc-stmf[378]: [ID 130283 user.error] get
property view_entry-0/all_hosts failed - entity not found
Sep  1 10:32:04 llift-zfs1 svc.startd[9]: [ID 652011 daemon.warning]
svc:/system/stmf:default: Method "/lib/svc/method/svc-stmf start"
failed
with exit status 1

In the /var/adm/system-stmf\:default.log

[ Sep  1 10:32:05 Executing start method ("/lib/svc/method/svc-stmf
start").
]
svc-stmf: Unable to load the configuration. See /var/adm/messages for
details
svc-stmf: For information on reverting the stmf:default instance to a
previously running configuration see the man page for svccfg(1M)
svc-stmf: After reverting the instance you must clear the service
maintenance state. See the man page for svcadm(1M)


I fixed it by going into the svccfg and reverted to the previous
"running"
snap. 

We have a lab management system which continuously creates and deletes LUNs
as virtual machines are built and destroyed.  When I recovered to the
previous running state we had a mismatch between what the LUNs should be and
what they were.  

Is there a backup "configuration" somewhere, or a way to
"re-read" the LUN
configuration? 

If not, I set the LUN for each volume in the custom zfs properties.  I may
just need to build a "sanitizer" script to rebuild the LUN mappings in
the
event of catastrophic failure.

BTW, I am running this system inside a VMWare Server vm, which has caused
some instability, but I guess it is good to be prepared. 

Thanks,

Geoff