Hi I am trying to use cache tiering and read the topic about mapping OSD with pools (http://ceph.com/docs/master/rados/operations/crush-map/#placing-different-pools-on-different-osds). I can't realize why OSDs were splitted on spinner and SSD type on root level of CRUSH map? Is it possible to to use some location type under host level to group OSDs by type and use then it in mapping rules? -- Michael Kolomiets