On 1/7/22 16:49, Marc wrote:
Where else can I look to find out why the managed block storage isn't
accessible anymore?
ceph -s ? I guess it is not showing any errors, and there is probably nothing with ceph, you can do an rbdmap and see if you can just map an image.
Then try mapping an image with the user credentials ovirt is using, maybe some auth key has been deleted.
Finally figured out the problem. A routing change on our core switch
was preventing the OSDs from being able to talk to the ovirg engine.
For some reason I thought the engine delegated all disk creation/attach
operations to the ovirt hosts, but it seems that the engine still needs
to be able to reach the OSDs.
Access to the rbd images from the hosts was working fine, but access to
the rbd images (and OSDs) from the engine was failing.
After adding back the missing route, I'm able to create and attach new
ceph rbd volumes.
Thanks for the nudge in the right direction,
--Mike
_______________________________________________
ceph-users mailing list -- ceph-users@xxxxxxx
To unsubscribe send an email to ceph-users-leave@xxxxxxx
