On Wed, Feb 28, 2018 at 2:56 PM, Brady Deetz <bdeetz@xxxxxxxxx> wrote: > Great. We are read heavy. I assume the journals do not replicate reads. Is > that correct? Correct -- only writes (plus discards, snapshots, etc) are replicated. > On Wed, Feb 28, 2018 at 1:50 PM, Jason Dillaman <jdillama@xxxxxxxxxx> wrote: >> >> On Wed, Feb 28, 2018 at 2:42 PM, Brady Deetz <bdeetz@xxxxxxxxx> wrote: >> > I'm considering doing one-way rbd mirroring to a DR site. The >> > documentation >> > states that my link to the DR site should have sufficient throughput to >> > support replication. >> > >> > Our write activity is bursty. As such, we tend to see moments of high >> > throughput 4-6gbps followed by long bouts of basically no activity. >> > >> > 1) how sensitive is rbd mirroring to latency? >> >> It's not sensitive at all -- at the worse case, your journals will >> expand during the burst period and shrink again during the idle >> period. >> >> > 2) how sensitive is rbd mirroring to falling behind on replication and >> > having to catch up? >> >> It's designed to be asynchronous replication w/ consistency so it >> doesn't matter to rbd-mirror if it's behind. In fact, you can even >> configure it to always be X hours behind if you want to have a window >> for avoiding accidents from propagating to the DR site. >> >> > >> > _______________________________________________ >> > ceph-users mailing list >> > ceph-users@xxxxxxxxxxxxxx >> > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> > >> >> >> >> -- >> Jason > > -- Jason _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |