The MDS requests the clients to release caps to trim caches when there is cache pressure or it might proactively request the client to release caps in some cases. But the client is failing to release the caps soon enough in your case. Few questions: 1. Have you tuned MDS cache configurations? If so please share. 2. Is this kernel client or fuse client? 3. Could you please share 'session ls' output? 4. Also share the MDS/Client logs. Sometimes dropping the caches (echo 3 > /proc/sys/vm/drop_caches if it's kclient) or unmount and mounting the problematic client could fix the issue if it's acceptable. Thanks and Regards, Kotresh H R On Thu, Dec 29, 2022 at 4:35 PM Amudhan P <amudhan83@xxxxxxxxx> wrote: > Hi, > > Suddenly facing an issue with Ceph cluster I am using ceph version 16.2.6. > I couldn't find any solution for the issue below. > Any suggestions? > > > health: HEALTH_WARN > 1 clients failing to respond to capability release > 1 clients failing to advance oldest client/flush tid > 1 MDSs are read only > 1 MDSs report slow requests > 1 MDSs behind on trimming > > services: > mon: 3 daemons, quorum strg-node1,strg-node2,strg-node3 (age 9w) > mgr: strg-node1.ivkfid(active, since 9w), standbys: strg-node2.unyimy > mds: 1/1 daemons up, 1 standby > osd: 32 osds: 32 up (since 9w), 32 in (since 5M) > > data: > volumes: 1/1 healthy > pools: 3 pools, 321 pgs > objects: 13.19M objects, 45 TiB > usage: 90 TiB used, 85 TiB / 175 TiB avail > pgs: 319 active+clean > 2 active+clean+scrubbing+deep > _______________________________________________ > 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
 |