On Mon, 7 Nov 2011, Mandell Degerness wrote: > So, does this apply only to Posix, or to RBD mounts as well? If so, I > think we may have to rethink using Ceph in our environment at all.
It applies to RBD too... _if_ the ceph-osd process is calling sync(2). On btrfs it doesn't, and on XFS/extN/etc., it only does on older kernels with older glibc. New kernels (.39+) and new glibc have syncfs(2), which syncs only the fs the ceph-osd is serving up. http://linux.die.net/man/2/syncfs sage > > On Mon, Nov 7, 2011 at 1:45 PM, Tommi Virtanen > <[email protected]> wrote: > > On Mon, Nov 7, 2011 at 11:48, Gregory Farnum > > <[email protected]> wrote: > >> (Hopefully this email still makes sense; I rewrote it several times > >> trying to figure out what was going on with ceph-fuse!) > > > > tl;dr: Don't mount any network filesystem on the box serving that > > filesystem. The virtual memory disk buffer system will deadlock at > > some point. That includes Ceph and NFS. The cost of making that work > > right is so high that in practice it's just not done. > > > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to [email protected] > More majordomo info at http://vger.kernel.org/majordomo-info.html > > -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html
