Hello, On Tue, 29 Sep 2015 10:21:00 +0200 Raluca Halalai wrote: > In my understanding, the deployment you suggested (local Ceph clusters + > Rados Gateways) would imply giving up strong consistency guarantees. In > that case, it is not what we are aiming for. > Indeed, there is another planned project to replicate Ceph clusters on a RBD level (not rados-gw), but with similar constraints. Personally, I'd be happy with a slightly lagging replication like that. A WAN storage without quantum entanglement data links will always be slower than what most Ceph users are able to accept. Christian > Thank you for your replies. > > On Tue, Sep 29, 2015 at 10:02 AM, Robert Sander < > r.sander@xxxxxxxxxxxxxxxxxxx> wrote: > > > On 29.09.2015 09:54, Raluca Halalai wrote: > > > What do you want to prove with such a setup? > > > > > > > > > It's for research purposes. We are trying different storage systems > > > in a WAN environment. > > > > Then Ceph can be ticked off the list of candidates. > > Its purpose is not to be a WAN storage system. > > > > It would be different if you setup local Ceph clusters and have Rados > > Gateways (S3 Interfaces) interact with them (geo replication with the > > radosgw agent). > > > > Regards > > -- > > Robert Sander > > Heinlein Support GmbH > > Schwedter Str. 8/9b, 10119 Berlin > > > > http://www.heinlein-support.de > > > > Tel: 030 / 405051-43 > > Fax: 030 / 405051-19 > > > > Zwangsangaben lt. §35a GmbHG: > > HRB 93818 B / Amtsgericht Berlin-Charlottenburg, > > Geschäftsführer: Peer Heinlein -- Sitz: Berlin > > > > > > _______________________________________________ > > ceph-users mailing list > > ceph-users@xxxxxxxxxxxxxx > > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > > > -- Christian Balzer Network/Systems Engineer chibi@xxxxxxx Global OnLine Japan/Fusion Communications http://www.gol.com/ _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |