Thanks everyone, got several good ideas on how to proceed forward. Thanks!!
//adam On Oct 28, 2015 11:55 AM, "Andrew Woodward" <xar...@gmail.com> wrote: > Adam, > > Most deployments use different pools for each type as discussed above. > These pools can then be mapped differently to disks, racks and so on by > updating the CRUSH rules. This controls how pools are distributed in the > cluster. > > On Tue, Oct 27, 2015 at 3:15 AM Warren Wang <war...@wangspeed.com> wrote: > >> There are some cases where it may be easier to run them as separate >> clusters. Like when you start adding tuning changes that don't make sense >> for types of clusters. Like the recent tcmalloc/jemalloc discovery for >> SSDs. I'm not sure that makes sense for spinners, and that is at a library >> level, not config. >> >> It isn't much more overhead to run multi backend cinder, which you kind >> of need to do anyway to guarantee QoS on the default volume for BfV. >> >> -- >> Warren >> >> On Oct 27, 2015, at 12:32 AM, Arne Wiebalck <arne.wieba...@cern.ch> >> wrote: >> >> Hi Adam, >> >> We provide various volume types which differ in >> >> - performance (implemented via different IOPS QoS specifications, not via >> different hardware), >> - service quality (e.g. volumes on a Ceph pool that is on Diesel-backed >> servers, so via separate hardware), >> - a combination of the two, >> - geographical location (with a second Ceph instance in another data >> centre). >> >> I think it is absolutely realistic/manageable to use the same Ceph >> cluster for various use cases. >> >> HTH, >> Arne >> >> On 26 Oct 2015, at 14:02, Adam Lawson <alaw...@aqorn.com> wrote: >> >> Has anyone deployed Ceph and accommodate different disk/performance >> requirements? I.e. Saving ephemeral storage and boot volumes on SSD and >> less important content such as object storage, glance images on SATA or >> something along those lines? >> >> Just looking at it's realistic (or discover best practice) on using the >> same Ceph cluster for both use cases... >> >> //adam >> >> *Adam Lawson* >> >> AQORN, Inc. >> 427 North Tatnall Street >> Ste. 58461 >> Wilmington, Delaware 19801-2230 >> Toll-free: (844) 4-AQORN-NOW ext. 101 >> International: +1 302-387-4660 >> Direct: +1 916-246-2072 >> >> _______________________________________________ >> OpenStack-operators mailing list >> OpenStack-operators@lists.openstack.org >> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators >> >> >> _______________________________________________ >> OpenStack-operators mailing list >> OpenStack-operators@lists.openstack.org >> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators >> >> _______________________________________________ >> OpenStack-operators mailing list >> OpenStack-operators@lists.openstack.org >> http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators >> > -- > > -- > > Andrew Woodward > > Mirantis > > Fuel Community Ambassador > > Ceph Community > > _______________________________________________ > OpenStack-operators mailing list > OpenStack-operators@lists.openstack.org > http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators > >
_______________________________________________ OpenStack-operators mailing list OpenStack-operators@lists.openstack.org http://lists.openstack.org/cgi-bin/mailman/listinfo/openstack-operators