Ok, thanks for confirming. On Thu, Mar 23, 2017 at 7:32 PM, Gregory Farnum <gfar...@redhat.com> wrote:
> Nope. This is a theoretical possibility but would take a lot of code > change that nobody has embarked upon yet. > -Greg > On Wed, Mar 22, 2017 at 2:16 PM Sergio A. de Carvalho Jr. < > scarvalh...@gmail.com> wrote: > >> Hi all, >> >> Is it possible to create a pool where the minimum number of replicas for >> the write operation to be confirmed is 2 but the minimum number of replicas >> to allow the object to be read is 1? >> >> This would be useful when a pool consists of immutable objects, so we'd >> have: >> * size 3 (we always keep 3 replicas of all objects) >> * min size for write 2 (write is complete once 2 replicas are created) >> * min size for read 1 (read is allowed even if only 1 copy of the object >> is available) >> >> Thanks, >> >> Sergio >> _______________________________________________ >> ceph-users mailing list >> ceph-users@lists.ceph.com >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com