That sounds a bit strange to me, because all clusters we adopted so
far successfully converted the previous systemd-units into systemd
units targeting the pods. This process also should have been logged
(stdout, probably in the cephadm.log as well), resulting in "enabled"
systemd units. Can you paste the output of 'systemctl status
ceph-<FSID>@mon.<MON>'? If you have it, please also share the logs
from the adoption process.
What I did notice in a test cluster a while ago was that I had to
reboot a node where I had to "play around" a bit with removed and
redeployed osd containers. At some point they didn't react to
systemctl commands anymore, but a reboot fixed that. But I haven't
seen that in a production cluster yet, so some more details would be
useful.
Zitat von Boris Behrens <bb@xxxxxxxxx>:
Hi,
is there a way to have the pods start again after reboot?
Currently I need to start them by hand via ceph orch start mon/mgr/osd/...
I imagine this will lead to a lot of headache when the ceph cluster gets a
powercycle and the mon pods will not start automatically.
I've spun up a test cluster and there the pods start very fast. On the
legacy test cluster, which got adopted to cephadm, it does not.
Cheers
Boris
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
