I had several kernel mapped rbds as well as ceph-fuse mounted CephFS clients when I upgraded from Jewel to Luminous. I rolled out the client upgrades over a few weeks after the upgrade. I had tested that the client use cases I had would be fine running Jewel connecting to a Luminous cluster so there weren't any surprised for me when I did it in production.
On Tue, Apr 3, 2018, 11:21 PM Konstantin Shalygin <k0...@k0ste.ru> wrote: > > The VMs are XenServer VMs with virtual Disk saved at the NFS Server > which has the RBD mounted … So there is nor migration from my POV as there > is no second storage to migrate to ... > > > > All your pain is self-inflicted. > > Just FYI clients are not interrupted when you upgrade ceph. Client will > be interrupted only when update, so if you (suddenly) change crush > tunables, minimum_required_version for example (for this reason clients > must be upgraded before cluster). > > > > > k > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com