# v0.47 05/13/2012 * Feature #1937: teuthology: --unlock option for -nuke * Feature #2141: ceph: 'object map ' or similar * Bug #2188: mon: mds rm should be harder to break things with * Bug #2263: obsync: move man page to section 1 * Bug #2275: osd: crash in FileJournal::wrap_read_bl * Feature #2281: build big burnupi cluster for testing * Feature #2290: ObjectCacher: handle read/write errors * Bug #2291: objectcacher perfcounters don't work with test_librbd_fsx * Feature #2305: Moving rbd images between pools * Bug #2307: OSD & Monitor disagree on the contents of pg_temp * Feature #2314: remove localized pgs * Bug #2316: rbd: restart of OSD leeds to stale qem-VM's with "ceph version 0.45-207-g3053e47" * Feature #2317: mon: pause/unpause auto-mark-out * Feature #2318: mon: block osd boot * Feature #2319: mon: block osd mark-down * Feature #2321: osd: investigate memory consumption from peering backlog * Bug #2322: osd/ReplicatedPG.cc: 3832: FAILED assert(!object_contexts.size()) * Feature #2323: osd: limit 'old request' messages generated * Feature #2325: setup new email/etc * Feature #2334: mon: set max mark-out or mark-down * Feature #2335: librbd: write-thru cache mode * Feature #2336: qemu: wire up discard * Bug #2338: mon: adding new monitors simultaneously can allow a new mon to become leader * Bug #2345: mon: users can create both pool snapshots and self-managed snapshots on a single pool * Bug #2348: osd: peer_info_requested not pruned with prior_set.probe * Bug #2350: conf: can't set subsystem settings (debug levels, logging settings) via librados or libcephfs * Bug #2351: osd: bad state machine event * Bug #2352: ceph -s without a conf file doesn't work when it should * Bug #2355: pgs stuck creating (with thrashing) * Feature #2358: throttle: expose via perfcounters * Bug #2361: osd: failed exists() assertion for identify_osd() * Bug #2363: mon: ./ceph-mon -i b --mkfs -c ceph.conf segfaults * Bug #2364: mon: can't specify monitor to join with -m * Bug #2365: osd: don't notice when nodes in probe set are down * Feature #2367: mon: osd crush add should move item if it exists elsewhere * Bug #2372: librbd: unit tests get different error codes * Bug #2373: osd: last_epoch_clean > last_epoch_started * Cleanup #2376: ceph-authtool -C option doesn't work * Bug #2391: librados docs bug * Bug #2396: don't fail on mismatched size CRUSH and OSD maps * Bug #2397: mon: prevent addition of CRUSH items past the max_osd