On Tue, Apr 12, 2016 at 1:33 PM, Jan Schermer <j...@schermer.cz> wrote: > Still the answer to most of your points from me is "but who needs that?" > Who needs to have exactly the same data in two separate objects (replicas)? > Ceph needs it because "consistency"?, but the app (VM filesystem) is fine > with whatever version because the flush didn't happen (if it did the contents > would be the same).
This isn't something that can happen quickly due to the fundamental designs of the RADOS architecture (I think we've discussed this before?), built to underlie a posix filesystem and expecting all object operations to be latency-sensitive. However, figuring out a roadmap to reduce the correspondence of rbd cache-too-full flushes to latency-sensitive disk hits is something that's been tickling my brain for a while, and I think it's on the mind of some other contributors as well. Many Ceph developers will be seeing each other at conferences over the next couple of weeks and this will be a topic of discussion. Assuming I figure out it's even possible, and manage to persuade a few others, you should start hearing things about it in the Ceph Dev Monthlies. :) -Greg _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
