# v0.43

02/25/2012



* Feature #1412: qa: spec out messenger testing
* Bug #1765: osd: 'call' op can return data even if op is modifying
* Bug #1820: deprecate "ceph stop"
* Feature #1932: mon: before accepting a new crushmap, monitor should validate and test some inputs
* Feature #2005: mon: track timestamps on pg states
* Feature #2006: osd: report what is blocking peering completion
* Feature #2007: osd: enumerate unfound, lost objects, possible locations
* Feature #2015: osd: dump in-flight ops via admin socket
* Cleanup #2021: fix signal handlers
* Feature #2028: qa: allocate disks to btrfs on new hardware
* Feature #2030: osd: clean up mark_unfound api
* Feature #2034: osd: refactor push code
* Feature #2054: teuthology: run radosgw through valgrind
* Bug #2056: osd: unfound object during backfill qa test
* Feature #2058: ceph: query pg state
* Bug #2061: osd: scrub mismatch
* Bug #2062: filestore: idempotent test failed
* Bug #2068: osd: FAILED assert(infoevt.info.history.last_epoch_started >= pg->info.history.same_interval_since)
* Bug #2070: osd/ReplicatedPG.cc: 3627: FAILED assert(is_active()) 
* Feature #2074: teuthology: remove old kernel packages
* Bug #2075: osd: recover_got assert
* Bug #2076: ceph fails to build with gcc 4.7 
* Bug #2077: mon: assert in Paxos::is_consistent
* Bug #2090: mon: assertion failed on shutdown
* Bug #2091: corrupt v5 inc osdmap
* Bug #2094: osd: pgs remapped to down+out osd
* Bug #2095: osd: need feature bit for v0.42 osdmap encoding change
* Bug #2104: teuthology: wait_for_clean doesn't wait for last_epoch_started to propagate
* Bug #2107: teuthology: lost_unfound fails pg state assert