On 01/15/2014 07:52 AM, NEVEU Stephane wrote:
Hi all,
I have to build a new Ceph storage architecture replicated between
two datacenters (for Disastry Recovery Plan) so basically 2x30 terabits
(2x3.75 terabytes).
I only can buy Dell servers.
I planned to use 2x1gb (LACP) for the replication network and also 2x1gb
(LACP) for production network, so 4 NICs per /server.
I would like a good price/performance ratio of course, that is the main
goal so I’d like to use SSDs for journals only if possible…
Given your requirements and network config I'd skip SSD journals and
stick with doing each disk in a single-disk raid0, and using a
controller that has a BBU and can do WB cache.
Could you please give me some good advices / ideas to start ? I know
this is a quite large question…
What would be a nice OSD /Core / servers / nb of server per datacenter
ratio ?
If I'm understanding correctly, you only need 7.5TB of total capacity
(2x replication, 3.75TB usable)?
I guess I'd probably look at the R520 in an 8 bay configuration with an
E5-2407 and 4 1TB data disks per chassis (along with whatever OS disk
setup you want). That gives you 4 PCIE slots for the extra network
cards, the option for a hardware raid controller, and some expansion
options if you want to add more disks. It's not the densest chassis and
I've never tested performance on it, but it's a fairly straightforward
setup with no expanders to worry about and a cheap/fast CPU.
Any feedbacks, advices, or ideas are welcome of course…
Thank you for your help.
Regards,
_______________________________________________
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
