Overnight, the iscsi service became unresponsive again, which caused a
lot of services to go down/become unresponsive.  I was able to manually
restore the service and the VMs should be back and running as normal.

I'm still investigating changes to the iscsi configuration to allow
failover to happen more-gracefully (perhaps at all) that may make such
temporary service failures easier to handle.
_______________________________________________
Sepia mailing list -- sepia@ceph.io
To unsubscribe send an email to sepia-leave@ceph.io