On Wed, Jun 5, 2019 at 1:36 PM Sameh <sameh+ceph-users@xxxxxxxxxxxxxxx> wrote: > > Hello cephers, > > I was trying to reproduce a production situation involving a stuck stale PG. > > While playing with a test cluster, I aggressively removed 3 OSDs at once > from the cluster. One OSD per host. All pools are size 3. > > After re-adding them, I ended up in this situation (PG unfound, or acting on one > OSD, or another, depending on which command you run): > https://rentry.co/6zwof > > I am not sure of the next steps to unblock this. Marking OSD 11 down didn't > help. > > > Cheers, I get this in a lab sometimes, and do ceph osd set noout and reboot the node with the stuck PG. In production, we remove OSDs one by one. -- Alex Gorbachev Intelligent Systems Services Inc. _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com