Hi Federico,

Hi Max,

On Feb 28, 2018, at 10:06 AM, Max Cuttins <m...@phoenixweb.it> wrote:

This is true, but having something that just works in order to have minimum 
compatibility and start to dismiss old disk is something you should think about.
You'll have ages in order to improve and get better performance. But you should 
allow Users to cut-off old solutions as soon as possible while waiting for a 
better implementation.
I like your thinking, but I wonder why doesn’t a locally-mounted kRBD volume 
meet this need? It seems easier than iSCSI and I would venture would show twice 
the performance at least in some cases.

Simple because it's not possible.
XenServer is closed. You cannot add RPM (so basically install ceph) without hack the distribution by removing the limitation to YUM.
And this is what we do here: https://github.com/rposudnevskiy/RBDSR

In order to let live migration works it's needed to rewrite the VHD/VDI driver (because this driver it's monolitich fused with iSCSI and HBA). So any implementation it's just something more than just a plugin or a class extension. It's an entire rewrite of the SR manager.
Is it working? ....yes.
Is this suitable for production? .... I think should not.

ceph-users mailing list

Reply via email to