Hello folks. Regarding rgw dynamic bucket resharding, I've read somewhat contradictory reports in the documentation that it should be a transparent process to the user, but other documents mention that writes are disabled to the bucket while the resharding is taking place. In: https://docs.ceph.com/en/latest/radosgw/dynamicresharding/#rgw-dynamic-bucket-index-resharding <https://docs.ceph.com/en/latest/radosgw/dynamicresharding/#rgw-dynamic-bucket-index-resharding> "This process is transparent to the user. Write I/Os to the target bucket are blocked and read I/Os are not during resharding process." Recently this happened to one of our buckets and in fact we could not write to it. Can anyone confirm that this is the expected behaviour? This post seems to indicate that we can still write to the bucket during the resharding: https://www.redhat.com/en/blog/ceph-rgw-dynamic-bucket-sharding-performance-investigation-and-guidance <https://www.redhat.com/en/blog/ceph-rgw-dynamic-bucket-sharding-performance-investigation-and-guidance> Another question that I have is around multisite. According to the documentation dynamic resharding is not available in a multisite envinronment. Even though we only run one Ceph cluster, we do have a realm (+zonegroup+zone) defined. Does this turn the deployment into a multisite configuration? Thank you and best regards, André _______________________________________________ ceph-users mailing list -- ceph-users@xxxxxxx To unsubscribe send an email to ceph-users-leave@xxxxxxx
 |