On Sunday 23 August 2009 07:10:11 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...?
This has been asked in the irc channel, maybe I should add it to the FAQ or somewhere else in the wiki. Sage has stated that he'd like to see people start using it by the end of the year. quote: 00:26 < sage> i'm aiming for something pretty usable by end of year, but i wouldn't skip regular backups for a long time after that! > > 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. Ceph has a pretty limited developer base at the moment. I'd prefer they expended their efforts on improving ceph and the kernel client now. Maybe that's a project someone else can take on when the developer base grows or if someone outside the project wanted to step up to do that. FWIW, I can't imagine there being a huge difference code wise between writing ceph drivers for other popular OSes and and writing a pnfs frontend to ceph's backend. I don't know of any open source pnfs backends/servers or pnfs fs drivers for more than linux/openslowaris, so code is going to have to be written either way. I'd guess it's up to whoever is going to write said code to determine which way they want to go. > > Thanks for your answers > > Ales Blaha > > --------------------------------------------------------------------------- > --- 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 > ------------------------------------------------------------------------------ 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
