Hi All, I'm working on integrating our new Ceph cluster with our older OpenStack infrastructure. It's going pretty well so far but looking to check my expectations. We're running Firefly on the ceph side and Icehouse on the OpenStack side. I've pulled the recommnded nova branch from https://github.com/angdraug/nova/tree/rbd-ephemeral-clone-stable-icehouse on my test nova nodes and have happily gotten instances booting from CoW clones of images stored in glance's rbd pool. I notice if I take a snapshot of that instance however, rather than making a clone as I'd hoped the hypervisor is pulling down a copy of the instance rbd to local disk then shipping that full sized raw image back to glance to be uploaded back into rbd. Is this expected? Am I misconfiguring some thing (glance and nova are using different pools, which works to launch a cloned instance but maybe doesn't work in reverse)? Is there another patch I need to pull? Thanks, -Jon
 |