On Dec 18, 2019, at 1:48 PM, eric(a)lapsus.org wrote:
That sounds very similar to what I described there:
https://tracker.ceph.com/issues/43364
I would agree that they're quite similar if not the same thing! Now that you mention
it I see the thread is named mgr-fin in 'top -H' as well. I don't have really
high queue length like you do though, but it does bounce around between 0 and 200, so
maybe I'm right at the edge for cluster size before it starts growing out of control?
Thanks,
Bryan