Ceph deployment

[Mark Shuttleworth]

On 20/11/15 01:12, James Page wrote:
> With that many LXC containers running on a single host, its quite possible
> that it took a while for all of the hook executions to complete and for the
> OSD's to startup.

We'll move Juju to use LXD for 16.04, which together with ZFS will
dramatically cut the typical I/O required for container startup. Machine
containers then become sub-second startups, as opposed to hundreds of
megs of I/O.

Mark