Hey all, It's a bit of a broken record, but we are again trying to kickstart CephFS development going forward. To that end, I've created one blueprint for the next CDS on CephFS "Forward Scrub" (https://wiki.ceph.com/Planning/Blueprints/Submissions/CephFS%3A_Forward_Scrub) based off discussions on the mailing last early last year (it still seems to apply). Other blueprints I'm mulling over: *) beginning to gather requirements and discuss possible implementations of multiple FSes within a single RADOS cluster *) changes we may want to make to backtraces (having clients write them, optionally storing authoritative copies in the metadata pool, or anything else of interest) *) implementing file locking in the userspace client *) an expansion on MDS dupability (https://wiki.ceph.com/Planning/Sideboard/mds%3A_dumpability) which also includes options to "kick" blocked parts of the tree *) better methods for synchronizing CephFS clocks (for purposes of mtime/atime/et al) across a cluster.
And I'm missing some other ideas I had earlier today. If you'd like to see one of these, or some other blueprint, on the agenda for CephFS discussion please let me know! -Greg Software Engineer #42 @ http://inktank.com | http://ceph.com -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
