Note that you *can* disable teh journal if you use btrfs, but your write latency will tend to be pretty terrible. This is only viable for bulk-storage use cases where throughput trumps all and latency is not an issue at all (it may be seconds). We are planning on eliminating the double-write for at least large writes when using btrfs by cloning data out of the journal and into the target file. This is not a hugely complex task (although it is non-trivial) but it hasn't made it to the top of the priority list yet. sage On Thu, 11 Jul 2013, Mark Nelson wrote: > Hi Ker, > > Unfortunately no. Ceph uses the journal for internal consistency and > atomicity and it can't use the XFS journal for it. On the BTRFS side, we've > been investigating allowing the Ceph journal to be on the same disk as the OSD > and doing a clone() operation to effectively reduce the journal write penalty, > but that feature hasn't been implemented yet. > > Mark > > On 07/11/2013 08:12 PM, ker can wrote: > > Hi, > > > > Is it possible to turn off ceph journaling if I switch to xfs ? > > For using it as a storage layer for hadoop we're concerned about the > > additional requirements for separate SSDs ($$) etc. In our testing > > we're seeing a performance hit when using the same disk for both journal > > + data ... so we're investigating the possibility of being able to turn > > it off completely, since xfs is already a journaled FS. > > > > thanks > > kc > > > > > > > > _______________________________________________ > > ceph-users mailing list > > ceph-users@xxxxxxxxxxxxxx > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |