We can go with 8 OSD nodes. We just can't afford cluster not available events.
Also, since we will be using CephFS to mount storage data on client nodes, so having 2 dedicated servers with mds daemon running on each will provide more protection. Correct? Thanks On Tue, 22 Apr, 2025, 10:16 pm Anthony D'Atri, <anthony.da...@gmail.com> wrote: > It’s the same protection, really, just a matter of flexibility. > > With 4+2 EC, 7+ hosts are ideal for multiple reasons. You would likely be > fine with 6 hosts, so long as you have the ability to quickly repair a host > if/when it fails. > > > > > > On Apr 22, 2025, at 12:03 PM, gagan tiwari < > gagan.tiw...@mathisys-india.com> wrote: > > > > Hi Janne, > > Thanks for your advice. > > > > So, you mean with with K=4 M =2 EC, we need 8 OSD nodes to have better > > protection > > > > Thanks, > > Gagan > > > > > > > > On Tue, 22 Apr, 2025, 7:22 pm Janne Johansson, <icepic...@gmail.com> > wrote: > > > >>> So, I need to know what will be data safely level with the above > set-up ( > >>> i.e. 6 OSDs with 4X2 EC ). How many OSDs ( disks ) and nodes > failure , > >>> above set-up can withstand. > >> > >> With EC N+2 you can lose one drive or host, and the cluster will go on > >> with degraded mode until it has been able to recreate the missing data > >> on another OSD, if you lose two drives or hosts, I believe the EC pool > >> with go readonly, again until it has rebuilt copies elsewhere. > >> > >> Still, if you have EC 4+2 and only 6 OSD hosts, this means if a host > >> dies, the cluster can not recreate data anywhere without violating > >> "one copy per host" default placement, so the cluster will be degraded > >> until this host comes back or another one replaces it. For a N+M EC > >> cluster, I would suggest having N+M+1 or even +2 number of hosts, so > >> that you can do maintenance on a host or lose a host and still be able > >> to recover without visiting the server room. > >> > >> -- > >> May the most significant bit of your life be positive. > >> > > _______________________________________________ > > ceph-users mailing list -- ceph-users@ceph.io > > To unsubscribe send an email to ceph-users-le...@ceph.io > > _______________________________________________ ceph-users mailing list -- ceph-users@ceph.io To unsubscribe send an email to ceph-users-le...@ceph.io
