I am running a simple workload (just 1 client and 1 file) of random writings on Ceph FS and I noticed that approximately 3% of the operations (well spread over time) show latencies higher than the other 97% (100 ms x 10 ms). Is there any reason for this to happen? - I'm using fio with O_DIRECT to avoid cache buffer, so it is expected that the operations will only be completed after writing to the disk. - My WAL is also disabled, so there is no reason for ceph to be doing deferred writing. - I performed the same workload on the gluster fs and the latencies were uniform over time.