# v0.80.11 * Backport #11542: Change variable length array of std::strings (not legal in C++) to std::vector * Tasks #11644: firefly v0.80.11 * Backport #11699: Objecter: resend linger ops on split * Backport #11700: make the all osd/filestore thread pool suicide timeouts separately configurable * Backport #11703: objecter: can get stuck in redirect loop if osdmap epoch == last_force_op_resend * Backport #11705: PGLog: split divergent priors as well * Backport #11707: Client admin socket leaks file descriptors * Backport #11708: Malformed JSON command output when non-ASCII strings are present * Backport #11711: use a new disk as journal disk,ceph-disk prepare fail * Backport #11713: src/ceph-disk : "disk zap" sgdisk invocation * Backport #11714: ceph_argparse_flag has no regular 3rd parameter * Backport #11715: utf8 and old gcc breakage on RHEL6.5 * Backport #11718: RGW doesn't return 'x-timestamp' in header which is used by 'View Details' of OpenStack * Backport #11721: Keystone PKI token expiration is not enforced * Backport #11726: delete bucket does not remove .bucket.meta file * Backport #11728: rgw: quota not respected in POST object * Backport #11729: rgw: leak of bucket meta objects on bucket re-creation * Backport #11731: Objectcacher setting max object counts too low * Backport #11741: crush: take crashes due to invalid arg * Backport #11745: object creation by write cannot use an offset on an erasure coded pool * Backport #11754: Object copy bug * Backport #11759: ceph-disk: get_partition_type fails on /dev/cciss... * Backport #11761: REJECTED: rgw: fcgi connections are not closed when using mod-proxy-fcgi * Backport #11769: librbd: aio calls may block * Backport #11799: REJECTED mon/OSDMonitor: require mon_allow_pool_delete = true to remove pools * Backport #11801: Make it more difficult to delete pools in firefly * Backport #11852: librbd: new config option for legacy blocking aio behavior * Backport #11871: RGW does not send Date HTTP header when civetweb frontend is used * Backport #11873: Bucket header is enclosed by quotes * Backport #11875: ceph-post-file fails on rhel7 * Backport #11878: Clock skew causes missing summary and confuses Calamari * Backport #11961: Cleanup boost optionals for boost 1.56 * Backport #11980: MDSMonitor: handle MDSBeacon messages properly * Backport #12007: Objecter: pg listing can deadlock when throttling is in use * Backport #12011: PG stuck with remapped * Backport #12014: osd: cache tier: avoid promotion on first read * Backport #12015: LibRadosTwoPools[EC]PP.PromoteSnap failure * Backport #12016: osd cache full mode still skips young objects * Backport #12027: mon: osd featuers aren't updated correctly * Backport #12039: RGW Swift API: response for PUT on /container does not contain the mandatory Content-Length header when FCGI is used * Backport #12045: rgw/logrotate.conf calls service with wrong init script name * Backport #12074: RGW logfile does not get chowned properly * Backport #12097: kernel_untar_build fails on EL7 * Backport #12202: ceph fails to compile with boost 1.58 * Backport #12240: librbd/internal.cc: 1967: FAILED assert(watchers.size() == 1) * Backport #12244: Civetweb RGW appears to report full size of object as downloaded when only partially downloaded * Backport #12247: RadosModel assertion failure * Backport #12266: ceph.spec.in: 50-rbd.rules conditional is wrong * Backport #12268: ceph-common needs python-argparse on older distros, but doesn't require it * Backport #12289: mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2 * Backport #12304: ceph.spec.in running fdupes unnecessarily * Backport #12310: read on chunk-aligned xattr not handled * Backport #12312: mon: adding exsting pool as tier with --force-nonempty clobbers removed_snaps * Backport #12389: PGLog::proc_replica_log: correctly handle case where entries between olog.head and log.tail were split out * Backport #12391: EC pools are not allowed as cache pools, disallow in the mon * Backport #12393: Memory leak in Mutex.cc, pthread_mutexattr_init without pthread_mutexattr_destroy * Backport #12395: register_new_pgs() should check ruleno instead of its index * Backport #12418: ceph-disk: sometimes the journal symlink is not created * Backport #12447: ceph.spec.in: useless %py_requires breaks SLE11-SP3 build * Backport #12484: mon: MonitorDBStore iterator's get_next_key() returns wrong keys * Backport #12485: mon: leaked Messenger, MLog on shutdown * Backport #12490: buffer: critical bufferlist::zero bug * Backport #12492: the output is wrong when runing "ceph osd reweight" * Backport #12495: pgmonitor: wrong "at/near target max“ reporting * Backport #12497: get pools health'info have error * Backport #12503: rgw/logrotate.conf calls service with wrong init script name * Backport #12519: Log::reopen_log_file() must take the flusher lock to avoid closing an fd ::_flush() is still using * Backport #12584: OSD crash creating/deleting pools * Backport #12586: FileStore calls syncfs(2) even it is not supported * Backport #12633: rgw: shouldn't return content-type: application/xml if content length is 0 * Backport #12635: swift smoke test fails on TestAccountUTF8 * Backport #12752: kvm die with assert(m_seed < old_pg_num) * Backport #12816: build_incremental() could take 40678 ms to finish * Backport #12837: WBThrottle::clear_object: signal on cond when we reduce throttle values * Backport #12838: Mutex Assert from PipeConnection::try_get_pipe * Backport #12840: recursive lock of md_config_t (0) * Backport #12842: is_new_interval: size change should cause new interval * Backport #12845: osd/PGLog.cc: 732: FAILED assert(log.log.size() == log_keys_debug.size()) * Backport #12879: COPYing an old object onto itself produces a truncated object * Backport #12882: cache agent is idle although one object is left in the cache * Backport #12889: RGW returns requested bucket name raw in "Bucket" response header * Backport #12942: RGW returns requested bucket name raw in "Bucket" response header * Backport #12945: osd mkfs fails when zeroing journal * Backport #12982: /etc/init.d/radosgw restart does not work correctly * Backport #13038: hit set clear repops fired in same epoch as map change -- segfault since they fall into the new interval even though the repops are cleared * Backport #13041: common/Thread:pthread_attr_destroy(thread_attr) when done with it * Backport #13043: ThreadPool add/remove work queue methods not thread safe * Backport #13048: Content-Type header should have correct initial capitals * Backport #13168: upstart: configuration is too generous on restarts * Backport #13169: update docs to point to download.ceph.com * Backport #13178: rgw: content length parsing calls strtol() instead of strtoll() * Backport #13244: client nonce collision due to unshared pid namespaces * Backport #13252: mon: does not check for IO errors on every transaction * Backport #13255: Increase globalid default for firefly (improves mon responsiveness) * Backport #13360: RGW Swift API: responses for several request types don't contain mandatory Content-Type header * Backport #13361: RGW Swift API: response for GET on Swift account doesn't contain mandatory Content-Length header * Backport #13362: testGetContentType and testHead failed * Backport #13413: fedora21 has junit, not junit4 * Backport #13417: Fix -Wno-format and -Werror=format-security options clash * Backport #13551: qemu workunit refers to apt-mirror.front.sepia.ceph.com * Bug #13613: radosgw problems concurrent downloads