This doesn't cover reads from the same objects though, and in fact Ceph deliberately sends all object reads to the primary copy. There are various options (which are variously implemented) to turn this off but turning it into a proper striped reads system or something would take some work. -Greg On Fri, Mar 1, 2013 at 12:44 PM, John Wilkins <john.wilkins@xxxxxxxxxxx> wrote: > I'm not sure about the implications of IB, but Ceph certainly has > striping capability. The following section of the architecture > document explains it. See > http://ceph.com/docs/master/architecture/#how-ceph-clients-stripe-data > > On Fri, Mar 1, 2013 at 9:28 AM, Gandalf Corvotempesta > <gandalf.corvotempesta@xxxxxxxxx> wrote: >> Let's assume a cluster with IB OSD network and 2GB public network (2 >> bonded nic for each storage server) >> >> Public network is used by RGW, MON, MDS and server access. >> With replica set to 3, is ceph smart enough to route read requests for >> the same object to to multiple servers archieving something like 3x2GB >> of aggregated bandwidth? >> _______________________________________________ >> ceph-users mailing list >> ceph-users@xxxxxxxxxxxxxx >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > > > > -- > John Wilkins > Senior Technical Writer > Intank > john.wilkins@xxxxxxxxxxx > (415) 425-9599 > _______________________________________________ > 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
 |