i want to raise your attention to the tracker ticket of https://tracker.ceph.com/issues/48909. and discuss with you for a better solution.

some context first, back in https://github.com/ceph/ceph/pull/18614, changes were made so the slow requests were reported to mgr to move the burden from monitor to mgr. with that change, all health related reports are sent to mgr, and the aggregated version is composed by mgr, and sent to monitor. i think, that'd help to improve the scalability of a Ceph cluster. moreover, IIUC, to let mgr take part of the load of the monitor was one of the reasons why mgr was introduced in the first place. 

in https://tracker.ceph.com/issues/43975, it's reported that the slow ops were no longer recorded in cluster log anymore since mimic. as a fix, https://github.com/ceph/ceph/pull/33328 was created to send slow ops and their types to cluster log.

in https://tracker.ceph.com/issues/43975, it's noticed that this fix even worsen the performance  of a cluster suffering from slow ops by adding more load to monitor. hence https://github.com/ceph/ceph/pull/39199 was created to throttle this.

i am wondering if we can make better use of the health reporting machinery instead of pouring the health warnings to clog when slow ops are observed?

what do you think?

cheers,