Hello Christopher,
We had something similar on Pacific multi-site.
The problem was in leftover bucket metadata in our case, and was solved
by "radosgw-admin metadata list ..." and "radosgw-admin metadata rm
..." on master, for a non-existent bucket.
Best regards,
Konstantin
On Tue, 2024-04-30 at 21:42 +0000, Christopher Durham wrote:
>
> Hi,
> I have a reef cluster 18.2.2 on Rocky 8.9. This cluster has been
> upgraded from pacific->quincy->reef over the past few years. It is a
> multi site with one other cluster that works fine with s3/radosgw on
> both sides, with proper bidirectional data replication.
> On one of the master cluster's radosgw logs, I noticed a sync request
> regarding a deleted bucket. I am not sure when this error started,
> but I know that the bucket in question was deleted a long time before
> the upgrade to reef. Perhapsthis error existed prior to reef, I do
> not know. Here is the error in the radosgw log:
> :get_bucket_index_log_status ERROR:
> rgw_read_bucket_full_sync_status() on pipe{s={b=BUCKET_NAME:CLUSTERID
> ..., z=...., az= ...},d={b=..,az=...}} returned ret=-2
> My understanding:
> s=source, d=destination, each of which is a tuple with the
> appropriate info necessary....
>
> This happens for BUCKET_NAME every few minutes. Said bucket does not
> exist on either side of the multisite, but did in the past.
> Any way I can force radosgw to stop trying to replicate?
> Thanks
> -Chris
> _______________________________________________
> 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
