11.2.1
------

* In previous versions, if a client sent an op to the wrong OSD, the OSD
  would reply with ENXIO.  The rationale here is that the client or OSD is
  clearly buggy and we want to surface the error as clearly as possible.
  We now only send the ENXIO reply if the osd_enxio_on_misdirected_op option
  is enabled (it's off by default).  This means that a VM using librbd that
  previously would have gotten an EIO and gone read-only will now see a
  blocked/hung IO instead.

* There was a bug introduced in Jewel (#19119) that broke the mapping behavior
  when an "out" OSD that still existed in the CRUSH map was removed with 'osd rm'.
  This could result in 'misdirected op' and other errors.  The bug is now fixed,
  but the fix itself introduces the same risk because the behavior may vary between
  clients and OSDs.  To avoid problems, please ensure that all OSDs are removed
  from the CRUSH map before deleting them.  That is, be sure to do::

     ceph osd crush rm osd.123

  before::

     ceph osd rm osd.123

* This release greatly improves control and throttling of the snap trimmer. It
  introduces the "osd max trimming pgs" option (defaulting to 2), which limits
  how many PGs on an OSD can be trimming snapshots at a time. And it restores
  the safe use of the "osd snap trim sleep" option, wihch defaults to 0 but
  otherwise adds the given number of seconds in delay between every dispatch
  of trim operations to the underlying system.
