Hi Ales, On Sun, 23 Aug 2009, ales...@seznam.cz wrote:
> Hello Sage, > > I have a few questions regarding Ceph. Have not tried Ceph so far, the > cluster I have keeps important data and I do not have spare machines for > testing. Currently I use a different cluster-based filesystem, but I > plan to try Ceph as soon as it is production ready. The roadmap section > on Ceph website does not seem to be updated for a long time. To be more > precise, I am curious about two things: > > 1) roughly, when do you expect first production release of Ceph (I know > it depends on btrfs progress as well)? It is possible that a similar > question appeared on this forum already, but I mean rougly, next year, > in next two years...? It depends on how you define production ready. I hope to deploy it in a semi-production environment (non customer facing machines) by years end, but I also expect there to be problems. Even then I would absolutly not recommend going without regular backups for important data. What is appropriate for your situation really depends on your requirements for availability and durability... > 2) Any plans for pNFS filesystem frontend? I have read all the Ceph and > Rados papers, and the project is very ambitious about performance and > features. But one thing I am missing is multi-platform support. This is > the case for most cluster-based storage solution on the market > (non-parallel workarounds with Samba or NFS heads does not count). Ceph > servers would probably be tightly coupled with btrfs and thus with > Linux, but what about clients? I know there is (was) FUSE based Ceph > client, but pNFS would be more elegant/compatible and it would also > remove the burden of client development from Ceph developers, since pNFS > might become de-facto standard and might be supported on many platforms > including Windows (which, to the best of my knowledge, does not have any > cluster-based filesystem client to date - with the exception of Boxwood > experiment). If that is the case then pNFS (or NFSv4.1 for that matter) > clients might be available from various differrent vendors for various > operating systems and people can take advantage of Ceph on differrent > platforms, not only Linux. There is a fuse client that is fully supported. pNFS is something we've thought about. The problem is that moving to pNFS throws out many of Ceph's architectural advantages. The biggest one is the metadata clustering. AFAICS clustered pNFS metadata servers is in a pretty early state of planning (though I'd love to see pointers to info on pNFS metadata clustering if I'm missing something). The other is that pNFS still keeps NFS's pretty weak consistency semantics. Not knowing more about pNFS metadata clustering, it's hard for me to say how disruptive grafting a pNFS front-end on the mds would be. If someone really wants to use pNFS and just needs the scalable storage backend, the simplest thing might be to write a pNFS storage driver for Ceph's distributed object storage layer (RADOS), and forgo the Ceph MDS entirely. You'd lose Ceph's metadata clustering, embedded inodes, recursive accounting, and directory based snapshots, but it'd be a much simpler system. sage ------------------------------------------------------------------------------ Let Crystal Reports handle the reporting - Free Crystal Reports 2008 30-Day trial. Simplify your report design, integration and deployment - and focus on what you do best, core application coding. Discover what's new with Crystal Reports now. http://p.sf.net/sfu/bobj-july _______________________________________________ Ceph-devel mailing list Ceph-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/ceph-devel
