On 12/28/2014 02:12 PM, Max Power wrote: > Hi, my cluster setup would be much easier if I use cephfs on it (instead of a > block device with ocfs2 or something else). But its said everywhere that it is > not ready for production-use at this time. I wonder what this is all about? > > Does it mean that there are a few features missing or is the code full of bugs? > I want to use cephfs fuse drivers (v0.90) with a 3.18.1 kernel. Can I give my > data to such a configuration without destroying? Or will there be tears and > scrambled files? I heard that the fuse driver is more stable than the kernel > driver? > If you are going to be using FUSE you don't need a new kernel, you don't use the kernel driver for that. I've been running tests with CephFS on v0.89 lately and I haven't been able to break it, but a couple of recommendations: - Active/Standby MDS - Stay away from CephFS snapshots With that setup it worked just fine for me. I've been hammering it, restarting and killing MDSes and it recovered all the time. If you are able to create backups of your data I'd say it's pretty useable now. > It looks like we are getting closer to a v1.00 - will cephfs be production ready > at this point? Is it possible to say "production ready" at any time anyway? > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > -- Wido den Hollander 42on B.V. Ceph trainer and consultant Phone: +31 (0)20 700 9902 Skype: contact42on _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |