Sorry for the two typos! I cannot for the life of me explain the "plural apostrophe" on the title slide, and my colleague's name is properly spelled "João" instead. If you've got any feedback, please reach out to me by email so I can continue improving the talk! I'm also happy to answer any questions or follow-ups.
TOTALLY agree! Nothing out there I have looked at is even close to as decent as CEPH. I have tried quite a few, the best part is rook-ceph works very well in the cloud on bare metal!
Is 3 node ceph cluster(with let's say 5 OSDs per node) ok for production? Or is it significantly better to have 5 nodes with 3 OSD per node? I only care about the performance.
It is better to go wide (more nodes less osds) deep (less nodes more osds) but it may not be worth it because of the overhead the additional nodes bring.
![[UNCUT] เก็บ "สจ.โต้ง" เอี่ยวมาเฟีย รู้ตัวคนบงการ ก่อนสั่งลั่นไก I คนดังนั่งเคลียร์ I 13 ธ.ค.67](http://i.ytimg.com/vi/o-J_p62D40w/mqdefault.jpg)
Sorry for the two typos! I cannot for the life of me explain the "plural apostrophe" on the title slide, and my colleague's name is properly spelled "João" instead. If you've got any feedback, please reach out to me by email so I can continue improving the talk!
I'm also happy to answer any questions or follow-ups.
Was a great presentation, much appreciated.
The availability aspect of ceph is unbeatable. I'd hate to go back to drdb. That's why I run rook/ceph in my 4 node k8s cluster. The future is now
TOTALLY agree! Nothing out there I have looked at is even close to as decent as CEPH. I have tried quite a few, the best part is rook-ceph works very well in the cloud on bare metal!
Is 3 node ceph cluster(with let's say 5 OSDs per node) ok for production? Or is it significantly better to have 5 nodes with 3 OSD per node? I only care about the performance.
It is better to go wide (more nodes less osds) deep (less nodes more osds) but it may not be worth it because of the overhead the additional nodes bring.