Technically this was tested in community 10.2.1/10.2.2, but the "problem" likely exists in downstream as well as no references to this issue have been found other than another reported instance in the community mailing list. Description of problem: An RBD with the object-map feature enabled will experience extremely poor performance with discard operations. Version-Release number of selected component (if applicable): Jewel How reproducible: 100% Steps to Reproduce: 1. Attempt to create a filesystem on an RBD device that has object-map enabled Actual results: Takes approximately 21 seconds to complete on a 10G image Expected results: should take < .5s on a 10G image Additional info:
https://www.mail-archive.com/ceph-users@lists.ceph.com/msg29984.html
Upstream, master branch PR: https://github.com/ceph/ceph/pull/10332
working as expected.(not taking too much time) hence moving to verified
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. https://rhn.redhat.com/errata/RHSA-2016-2815.html