Resharding, whether dynamic or manual, has not previously clean up the old bucket info objects or shard objects. That has led to an accumulation of unneeded objects that likely impacts performance.
BZ#1627562 addresses one aspect of this issue, and automatically cleans up these objects after both successful and failed reshardings. But for existing clusters that have experienced this accumulation of unneeded objects, we need an administrative tool to clean these up.
Upstream this issue is tracker: http://tracker.ceph.com/issues/24082
The solution is a backport of PR https://github.com/ceph/ceph/pull/24662
Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.
For information on the advisory, and where to find the updated
files, follow the link below.
If the solution does not work for you, open a new bug report.