# v12.1.0



* Tasks #16784: RADOSGW feature requires FCGI which no longer has an upstream source
* Feature #19109: Use data pool's 'df' for statfs instead of global stats, if there is only one data pool
* Bug #19635: Deadlock on two ceph-fuse clients accessing the same file
* Feature #19657: An EIO from a single device should not be a client-visible failure.
* Fix #19691: Remove journaler_allow_split_entries option
* Bug #20109: src/common/crc32c_ppc_asm.s ppc64le build break
* Documentation #20119: Documentation of Python RBD API does not say that aio_* functions call their callbacks in DIFFERENT (dummy) thread
* Bug #20288: armhf build fail
* Fix #20330: msg : tcp backlog parameter increase
* Bug #20334: I/O become slowly when multi mds which subtree root has replica
* Bug #20415: dashboard: Health is not updated
* Bug #20426: some generic options can not be passed by rbd-nbd
* Bug #20435: `ceph -s` repeats some health details in Luminous RC release
* Bug #20484: snap can be removed while it is been using by rbd-nbd device
* Bug #20525: ceph osd replace problem with osd out
* Bug #20545: erasure coding = crashes
* Bug #20583: mds: improve wording when mds respawns due to mdsmap removal
* Bug #20595: mds: export_pin should be included in `get subtrees` output
* Bug #20612: radosgw ceases responding to list requests
* Bug #20659: MDSMonitor: assertion failure if two mds report same health warning
* Bug #20663: Segmentation fault when exporting rgw bucket in nfs-ganesha
* Bug #20677: mds: abrt during migration
* Bug #20680: osd: FAILED assert(num_unsent <= log_queue.size())
* Bug #20683: mon: HealthMonitor.cc: 216: FAILED assert(store_size > 0)
* Bug #20745: Error on create-initial with --cluster 
* Bug #20746: dashboard: usage graph is getting more and mor big
* Bug #20755: radosgw  crash when service is restarted during lifecycle processing
* Bug #20756: radosgw daemon crash when service is restarted during lifecycle processing
* Feature #20760: mds: add perf counters for all mds-to-mds  messages
* Bug #20765: bluestore: mismatched uuid in bdev_label after unclean shutdown
* Bug #20767: Zabbix plugin assumes legacy compat mode for health json
* Bug #20787: the bucket created by swift can not be used by s3
* Feature #20801: ability to rebuild BlueStore WAL journals is missing
* Bug #20807: Error in boot.log - Failed to start Ceph disk activation - Luminous
* Bug #20856: osd: luminous osd bluestore crashes with jemalloc enabled on debian 9
* Bug #20861: Object data  loss in RGW when multipart upload completion times out