On 13/09/2019 16.25, Hector Martin wrote:
> Is this expected for CephFS? I know data deletions are asynchronous, but
> not being able to delete metadata/directories without an undue impact on
> the whole filesystem performance is somewhat problematic.
I think I'm getting a feeling for who the cu
I was able to repeat this issue locally by restarting the primary OSD
for the "rbd_mirroring" object. It seems that a regression was
introduced w/ the introduction of Ceph msgr2 in that upon reconnect,
the connection type for the client switches from ANY to V2 -- but only
for the watcher session an
Dear Jason,
Am 15.09.19 um 00:03 schrieb Jason Dillaman:
> I was able to repeat this issue locally by restarting the primary OSD
> for the "rbd_mirroring" object. It seems that a regression was
> introduced w/ the introduction of Ceph msgr2 in that upon reconnect,
> the connection type for the cli
