I've been evaluating ceph as a solution for persistent block in our kubrenetes clusters for low-iops requirement applications. It doesn't do too terribly bad with 32k workloads even though it's object storage under the hood.
However it seems this is a very high maintenance solution requiring you to be on top of it at every minute of the day coupled with impeccable monitoring and alert response times.
Also how stable/reliable are erasure coded pools?
Thx
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
