Description of problem (please be detailed as possible and provide log snippests): I observed mds pods continuously switched from "Active --> Standby-Replay" and "Standby-replay --> Active" without pod restart. This is observed only after enabling debug mode in mds "ceph config set mds debug_mds 25". Version of all relevant components (if applicable): versions used: ceph version 17.2.6-194.el9cp (d9f4aedda0fc0d99e7e0e06892a69523d2eb06dc) quincy (stable) odf: 4.15.0-126 ocp: 4.15.0-0.nightly-2024-01-31-032716 Does this issue impact your ability to continue to work with the product (please explain in detail what is the user impact)? Is there any workaround available to the best of your knowledge? Rate from 1 - 5 the complexity of the scenario you performed that caused this bug (1 - very simple, 5 - very complex)? Can this issue reproducible? Can this issue reproduce from the UI? If this is a regression, please provide more details to justify this: Steps to Reproduce: 1.Set debug mode in ceph tools using cmd "ceph config set mds debug_mds 25" 2.Run file operations[creation, modification..etc] IO on cephfs continuously to reach MDS cache utilisation 100% of its limit. 3.mds pods continuously switched from "Active --> Standby-Replay" and "Standby-replay --> Active" without pod restart Actual results: mds pods continuously switched from "Active --> Standby-Replay" and "Standby-replay --> Active" without pod restart Expected results: MSD should not switch between Active and s-r continuously without any failures to the pods. Additional info:
I'm closing this BZ since the issue isn't seen when debug_mds is set to default. There is a lack of debug data when the MDS gets restarted with debug_mds-25. Please reopen with debug detail captured if necessary.
The needinfo request[s] on this closed bug have been removed as they have been unresolved for 120 days