Hello Alex, We have a similar design. Two Datacenters at short distance (sharing the same level 2 network) and one Datacenter at long range (more than 100km) for our Ceph cluster. Let's call these sites A1, A2 and B. We set 2 Mons on A1, 2 Mons on A2 and 1 Mon on B. A1 and A2 shared a same level 2 network. We need routing to connect to B. We set a HSRP Gateway on A1 & A2 to reach the B site. Let's call them GwA1 and GwA2 with default to GwA1 We set a HSRP Gateway on site B. Let's call them GwB1 and GwB2 with default to GwB1. GwB1 connected to A1 and A2 via GwA1, GwB2 connected to A1 and A2 via GwA2. We set an simple LACP between GwB1 and GwA1 ports and an other between GwB2 and GwA2 ports. (If GwA1 port is going down then GwB1 port will go down too) So if everything is OK, the Mon on site B can see every OSDs and Mons on both sites A1 & A2 via GwB1, then GwA1. Quorum is reached and Ceph is healthy if B1 site is down, the Mon on site B can see every OSDs and Mons on site A1 via GwB1, then GwA1. Quorum is reached and Ceph is available If A1 site is down, both HSRPs will change. The Mon on site B will see Mons and OSDs of the A2 site via GwB2 then GwA2. Quorum is reached and Ceph is still available if the L2 links between A1 & B2 are cut, the B2 site will be isolated. The Mon on site B can see every OSDs and Mons on A1 via GwB1, then GwA1 but cannot see Mons and OSDs of the A2 site because of the link failure. The quorum will be reached only on A1 site with 3 Mons and Ceph will still be available I hope i have been enough clear. Tell me _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |