Yes, this is expected. Bluestore’s internal design differs a great deal from filestore, and it doesn’t have a distinction between the journaled and readable data the way filestore does with its separate journal and then normal xfs filesystem. -Greg On Tue, Jan 30, 2018 at 11:05 AM Shawn Edwards <[email protected]> wrote:
> When I run 'ceph osd perf' on my cluster (12.2.2), for bluestore osd, the > commit latency and apply latency are always equal. This is not the case on > filestore osd; the commit is lower or equal to apply. Are the bluestore > numbers expected behavior? > _______________________________________________ > ceph-users mailing list > [email protected] > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
