Dear all, to give some closure here: I was missing the "admin" service in my "rgw" deployment. I had "s3" and "s3website" explicitly configured in my cephadm deployment which turned out to be the mistake. Once the admin service was deployed, the dashboard created the bucket and necessary entries on its own. Kind regards, Manuel On Tue, Jan 2, 2024 at 8:29 AM Manuel Holtgrewe <zyklenfrei@gmail.com> wrote:
Hello,
I have an issue with a Ceph 17.2.6 cluster. The dashboard says "The Object Gateway Service is not configured" when trying to access the Object Gateway section. It used to work before.
One interesting symptom: the "admin" bucket exists in the output of "radosgw-admin bucket list" but it does not exist in "radosgw-admin bucket stats". Rather, I get a number of "ERROR: could not decode buffer info, caught buffer::error" messages from the "radosgw-admin bucket stats" command. Also, I cannot remove the "admin" bucket because I also get the same error (I thought about starting fresh with the admin bucket).
Could someone help me debug this further and eventually resolve the issue?
There is no critical data in the radosgw buckets (the cluster is primarily accessed via an CephFS cluster), so clearing all radosgw buckets is an option. Ideally, I could repair this, however.
Kind regards, Manuel