v0.6
/- fold observer into cmonctl/ceph?
/- osd scrub
/- async metadata

v0.7
/- smart osd sync
/- osd bug fixes
/- fast truncate
/- updated debian package
/- improved start/stop scripts
/- proc -> sysfs cleanup

v0.7.1
/- O_DIRECT
/- dentry lease renewal

v0.7.2
/- make kclient handle osd ack + sync properly
/- make fill_trace handle short traces; return short traces from mds
/- rdcap renewal
/- some mds clustering fixes
/- sysfs -> debugfs
/- queue delayed check upon receipt of unwanted, un-EXPIREABLE caps
/- init/mkfs fixes
/- warn on cmon startup if monmap doesn't match .conf
/- make kclient timeouts tunable

v0.7.3
/- clean up path_traverse interface, esp the usages in Server.cc
/- piggyback lease/cap release on client_request?
/- store metadata format version on disk...
/- async xattr
/- dcache readdir
/- confutils memory leaks
/- osd re-up attempt when marked down

v0.8
- bug fixes?
- mount error reporting
- fix mds file size/mtime recovery
- changes for 2.6.30
- mds cap fixes
- crush fixes

v0.9
- make mds exhert memory pressure on client caps, leases
- optionally separate osd interfaces (ips) for clients and osds (replication, peering, etc.)

later
- client reconnect after long eviction; and slow delayed reconnect
- ENOSPC
  - space reservation in ObjectStore, redeemed by Transactions?
  - reserved as PG goes active; reservation canceled when pg goes inactive
  - something similar during recovery
  - ?
- repair
- mds security enforcement
- client, user authentication
- cas
- osd failure declarations
- rename over old files should flush data, or revert back to old contents

repair
- are we concerned about
  - scrubbing
  - reconstruction after loss of subset of cdirs
  - reconstruction after loss of md log
- data object 
  - path backpointers?
  - parent dir pointer?
- cdir objects
  - parent dir pointer
    - update on rename?  or on cdir store?
      on cdir store is sufficient if mdlog survives...
  - or what the hell, full trace?
- mds scrubbing


kernel client
- fix up mds selection, and ESTALE handling
- make cap import/export efficient
- simplify mds auth tracking?
  - use caps instead?
- unwind writeback start error in addr.c (see fixme)... by redirtying pages?
- flock, fnctl locks
- ACLs
- make writepages maybe skip pages with errors?
  - EIO, or ENOSPC?
  - ... writeback vs ENOSPC vs flush vs close()... hrm...
- set mapping bits for ENOSPC, EIO?
- should we try to ref CAP_PIN on special inodes that are open?  
- fix readdir vs fragment race by keeping a separate frag pos, and ignoring dentries below it
- reconnect after being disconnected from the mds
- inotify for updates from other clients?

vfs issues
- real_lookup() race:
  1- hash lookup find no dentry
  2- real_lookup() takes dir i_mutex, but then finds a dentry
  3- drops mutex, then calld d_revalidate.  if that fails, we return ENOENT (instead of looping?)
- vfs_rename_dir()
- a getattr mask would be really nice

filestore
- make min sync interval self-tuning (ala xfs, ext3?)
- get file csum?

btrfs
- clone compressed inline extents
- ioctl to pull out data csum?


userspace client
- handle session STALE
- time out caps, wake up waiters on renewal
  - link caps with mds session
- validate dn leases
- fix lease validation to check session ttl
- clean up ll_ interface, now that we have leases!
- clean up client mds session vs mdsmap behavior?
- stop using mds's inode_t?
- fix readdir vs fragment race by keeping a separate frag pos, and ignoring dentries below it

mds
- fix client op replay
  - ordering
  - should to set caps/lock states so that ops can proceed without revoking from client
  - need to make sure replayed ops finish before new ops proceed.  globally across the cluster.  ick.
- fix up *_RDCACHE vs FILE_RDCACHE semantics
  - ability to read attribute value is distinct from being able to hold cached pages?
- file recovery maybe needs to scan entire file range for a truncation event?  (and object attr maybe needs file offset, not object offset, or original truncation?)
- on replay, but dirty scatter replicas on lists so that they get flushed?  or does rejoin handle that?
- take some care with replayed client requests vs new requests
- linkage vs cdentry replicas and remote rename....
- make recovery work with early replies
  - purge each session's unused preallocated inodes
- file size recovery gives (wrong) 4MB-increment results?
- hard link backpointers
  - anchor source dir
  - build snaprealm for any hardlinked file
  - include snaps for all (primary+remote) parents
- how do we properly clean up inodes when doing a snap purge?
  - when they are mid-recover?  see 136470cf7ca876febf68a2b0610fa3bb77ad3532
- what if a recovery is queued, or in progress, and the inode is then cowed?  can that happen?  
- proper handling of cache expire messages during rejoin phase?
  -> i think cache expires are fine; the rejoin_ack handler just has to behave if rejoining items go missing
- add an up:shadow mode?
  - tail the mds log as it is written
  - periodically check head so that we trim, too
- rename: importing inode... also journal imported client map?
- rerun destro trace against latest, with various journal lengths
- cap/lease length heuristics
  - mds lock last_change stamp?
- handle slow client reconnect (i.e. after mds has gone active)
- fix reconnect/rejoin open file weirdness
- anchor_destroy needs to xlock linklock.. which means it needs a Mutation wrapper?
  - ... when it gets a caller.. someday..
- FIXME how to journal/store root and stray inode content? 
  - in particular, i care about dirfragtree.. get it on rejoin?
  - and dir sizes, if i add that... also on rejoin?
- add FILE_CAP_EXTEND capability bit
- return extra inode(s) in reply (namely, unlink)?


journaler
- fix up for large events (e.g. imports)
- should we pad with zeros to avoid splitting individual entries?
  - make it a g_conf flag?
  - have to fix reader to skip over zeros (either <4 bytes for size, or zeroed sizes)
- need to truncate at detected (valid) write_pos to clear out any other partial trailing writes


mon
- paxos need to clean up old states.
  - default: simple max of (state count, min age), so that we have at least N hours of history, say?
  - osd map: trim only old maps < oldest "in" osd up_from

osdmon
- monitor needs to monitor some osds...

pgmon
/- include osd vector with pg state
  - check for orphan pgs
- monitor pg states, notify on out?
- watch osd utilization; adjust overload in cluster map

crush
- allow forcefeed for more complicated rule structures.  (e.g. make force_stack a list< set<int> >)

osd
- pg split should be a work queue
- generalize ack semantics?  or just change ack from memory to journal?  memory/journal/disk...
- rdlocks
- optimize remove wrt recovery pushes

simplemessenger
- close idle connections?

objectcacher
- read locks?
- maintain more explicit inode grouping instead of wonky hashes

cas
- chunking.  see TTTD in
   ESHGHI, K.
   A framework for analyzing and improving content-based chunking algorithms.
   Tech. Rep. HPL-2005-30(R.1), Hewlett Packard Laboratories, Palo Alto, 2005. 