Hi,
Am 23.09.16 um 05:55 schrieb Zhongyan Gu: from my (still limited) POV, one main aspect is: how reliabel is your hardware if you think off this? How often will a disk break, a server crash, a datacenter burn down, a networkswitch fail? And if there is a failure, how fast could that broken part be replaced or how fast is your availabel hardware to replicate the lost OSD to the remaining system. I dont have numbers, but for our first initial cluster we go as well with a repl size of 2 and I dont have bad feelings yet when i look at the server and network infrastrukture we got. Others with more experiacne will give some other hints and may be numbers. I never found some sort of calculator which can say "Oh you get this hardware? Than a repl size of x y z is what you need." HTH a bit . Regards . Götz |
Attachment:
smime.p7s
Description: S/MIME Cryptographic Signature
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com