So, did the cluster have 5 nodes, and one is now down? That would explain it.
CRUSH needs 5 failure domains to place shards, so if you only have 4, it has nowhere to place the fifth shard. You need to get that node up, or a replacement. I think reducing min_size to 3 — assuming it’s 4 now — would unblock, but I’ve never taken that risky step on an EC pool and would ask for corroboration first. Why is the down node still down? > On Jul 10, 2025, at 7:20 PM, Devender Singh <deven...@netskrt.io> wrote: > > Sorry ! > Yes its 3+2, Now I remember still one is not yet replaced which went down… > > > Regards > Dev > >> On Jul 10, 2025, at 3:51 PM, Peter Eisch <pe...@boku.net> wrote: >> >> ill likely be juggling % to get you > > _______________________________________________ > 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
