Hi, I have my monitors running on three out of my eight OSD servers (I know the docs recommend separate hardware but I don't think that makes sense for a small/dense cluster like this). I noticed that when I reboot the server that hosts the primary monitor, the OSDs on that server are not gracefully marked down and I end up with warnings about blocked ops until the server comes back up. This is the only server it happens on. Digging deeper I noticed the monitor service was getting shutdown before (or at least at the same time as) the OSD service. This is on Ubuntu 16.04, so I am using systemd.
I went ahead and modified /lib/systemd/system/ceph-osd@.service to include "ceph-mon.target" on the "AFTER" and "WANTS" lines and that appears to have solved the issue for me. Shall I open a ticket to include this change? Thanks, Brendan
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
