On Fri, Aug 5, 2016 at 3:42 AM, Wido den Hollander <wido@xxxxxxxx> wrote: > >> Op 4 augustus 2016 om 18:17 schreef Shain Miley <smiley@xxxxxxx>: >> >> >> Hello, >> >> I am thinking about setting up a second Ceph cluster in the near future, >> and I was wondering about the current status of rbd-mirror. >> > > I don't have all the answers, but I will give it a try. > >> 1)is it production ready at this point? >> > > Yes, but rbd-mirror is a single process at the moment. So mirroring a very large number of images might become a bottleneck at some point. I don't know where that point it. Production ready could mean different things to different people. We haven't had any reports of data corruption or similar issues. The forthcoming 10.2.3 release will include several rbd-mirror daemon stability and performance improvements (especially in terms of memory usage) that were uncovered during heavy stress testing beyond our normal automated test cases. It is not currently HA nor horizontally scalable, but we have a design blueprint in place to start addressing this for the upcoming Kraken release. It is also missing a "deep scrub"-like utility to periodically verify that your replicated images match your primary images, which I am hoping to include in the Luminous release. Finally, we are tweaking for performance issues with the default journal settings, but in the meantime setting the "rbd_journal_object_flush_age" config setting to a non-zero value (in seconds), will improve IOPS noticeably when journaling is enabled. >> 2)can it be used when you have a cluster with existing data in order to >> replicate onto a new cluster? >> > > iirc, images need the fast-diff feature enable to be able to support mirroring, more on that in the docs: http://docs.ceph.com/docs/master/rbd/rbd-mirroring/ > > The problem is, if you have old RBD images, maybe even format 1, you will not be able to mirror those. > > Some rbd format 2 images neither, since they don't have the journal and don't have the fast-diff. > > So per image it will depend if the mirroring is able to run. Yes, it will automatically "bootstrap" existing images to the new cluster by performing a full, deep copy of the images. The default setting is to synchronize a maximum of 5 images concurrently, but for huge images you may want to tweak that setting down. This requires only the exclusive-lock and journaling features on the images -- which can be dynamically enabled/disabled on existing v2 images if needed. >> 3)we have some rather large rbd images at this point..several in the >> 90TB range...would there be any concern using rbd-mirror given the size >> of our images? >> > > The initial sync might be slow and block the single rbd-mirror process. Afterwards, if fast-diff is enabled it shouldn't be a real problem. Agreed -- the initial sync will take the longest. By default it copies up to 10 backing object blocks concurrently for each syncing image, but if your cluster has enough capacity you can adjust that up using the "rbd_concurrent_management_ops" config setting to increase the transfer throughput. While the initial sync is in-progress, the journal will continue to grow since the remote rbd-mirror process won't be able to replay events until after the sync is complete. As with any new feature or release of Ceph, I would recommend first playing around with it on non-production workloads. Since RBD mirroring is configured on a per-pool and per-image basis, there is a potentially lower barrier for testing. > Wido > >> Thanks, >> >> Shain >> >> -- >> NPR | Shain Miley | Manager of Infrastructure, Digital Media | >> smiley@xxxxxxx | 202.513.3649 >> >> _______________________________________________ >> 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 -- Jason _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com