Description of problem: Quiesce op when started on 5 pre-upgrade subvolumes and with IO in-progress, results in MDS slowness. Could not create snapshots when subvolumes were quiesced. No ceph fs commands could be processed. Ceph status reports '1 MDSs report slow requests' Version-Release number of selected component (if applicable): ceph version 18.2.1-40.el9cp (a842b5916501030e0c0be773e91c33daf38fd65f) reef (stable) How reproducible: Steps to Reproduce: 1. Setup 6.1 ceph cluster.Create 5 subvolumes across default and non-default subvolumegroups 2. Add Dataset to all subvolumes, create snapshots. 3. Upgrade Ceph to 7.1 4. Run IO on subvolumes. Start Quiesce on 5 existing subvolumes created in step1. 5. While in QUIESCED state, Create snapshot on subvolumes Actual results: Snapshot create request doesn't proceed, remains hung. Ceph status reports '1 MDSs report slow requests' No ceph fs cmds gets processed. Expected results: Snapshot creation should succeed. Additional info:
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 (Critical: Red Hat Ceph Storage 7.1 security, enhancements, and bug fix update), 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://access.redhat.com/errata/RHSA-2024:3925