summaryrefslogtreecommitdiff
path: root/src/TODO
Commit message (Collapse)AuthorAgeFilesLines
* update TODOSage Weil2010-09-161-494/+1
|
* Merge branch 'msgr' into unstableSage Weil2010-04-231-0/+210
|\ | | | | | | | | | | | | | | | | Conflicts: src/TODO src/mds/Server.cc src/msg/SimpleMessenger.cc src/msg/SimpleMessenger.h src/osd/OSD.cc
| * msg: Add MClassAck to Message.cc so it will decode properlyGreg Farnum2010-03-311-0/+2
| |
* | todo: move bugs to trackerSage Weil2010-04-091-183/+0
| |
* | librados: clean up object listing apiSage Weil2010-04-081-0/+1
| |
* | todo: mdsSage Weil2010-04-061-0/+2
| |
* | mds: journal oldest client tidSage Weil2010-04-061-1/+1
| | | | | | | | | | | | | | | | Journal the client's safe tid with new requests. This keeps the client completed_requests list trimmed, so that we don't build up a ginormous list of all requests over the entire journal. Forward rolling mds format change.
* | todo: updatesSage Weil2010-04-061-17/+4
| |
* | todo: updatesSage Weil2010-03-311-81/+14
| |
* | todo: kclient snap bugSage Weil2010-03-301-0/+2
| |
* | Merge branch 'mds' into unstableSage Weil2010-03-301-4/+2
|\ \
| * | mds: todo rejoin bugSage Weil2010-03-301-4/+1
| | |
| * | Merge branch 'unstable' into mdsSage Weil2010-03-261-1/+120
| |\ \ | | |/ | | | | | | | | | Conflicts: src/TODO
| * | todo mds bugSage Weil2010-03-231-0/+2
| | |
| * | mds: fix up client session importingSage Weil2010-03-231-2/+1
| | | | | | | | | | | | | | | | | | Keep import counter for each session, for overlapping imports. Prevent a session close or kill during an import.
* | | todo: kclient bugSage Weil2010-03-301-0/+54
| |/ |/|
* | todoSage Weil2010-03-241-0/+3
| |
* | todoSage Weil2010-03-231-0/+116
|/
* mds: don't kick clients if we've been laggy ourselvesSage Weil2010-03-221-1/+0
|
* todo fixed some bugsSage Weil2010-03-221-67/+0
|
* mds: fix resolve stageSage Weil2010-03-181-3/+1
| | | | This was recently broken by b818f5bc.
* todoSage Weil2010-03-181-0/+3
|
* todo: more kclient bugsSage Weil2010-03-171-10/+17
|
* todo kclient osd_client bugSage Weil2010-03-161-16/+8
|
* mds: detach mdsdir inode from hierarchySage Weil2010-03-111-0/+3
| | | | | | | | | | | | | | | | Attaching mdsdir to the root hierarchy means that random mds X can't push replicas of everything needed for mds Y to reach a stray item, because Y may not have the /.ceph/mds# dentries and inode. So detach myin from the hierarchy. This simplifies startup/mkfs somewhat because non-root mds's don't have to traverse through /.ceph. We can still make it reachable via /.ceph/mds# with a remote dentry (although we haven't done that yet). MDS stopping is currently broken, since we can't export the stray dir any more (it's auth mds fixed).
* todo multi-mds issueSage Weil2010-03-111-1/+15
|
* todo bugsSage Weil2010-03-081-0/+69
|
* decay: separate fixed DecayRate from DecayCounterSage Weil2010-03-081-6/+0
| | | | Avoid eating a double per instance.
* todoSage Weil2010-03-031-15/+0
|
* todoSage Weil2010-03-021-0/+14
|
* mds: put forced open sessions in OPENING then OPENSage Weil2010-03-011-0/+2
| | | | | | | | | | | | | | | We use OPENING state to indicate sessions that are being imported. Fix get_or_add_open_session() to NOT set the session state (except to STATE_NEW if new) so that the caller can do the right thing. Otherwise, the prepare_force_open_sessions() can't tell if it just forced open a session (and needs it to be OPENING) or if it was already open. Subsequently cap migrations weren't working if the client didn't already have a session open. There is still a bug: if the import aborts, we have an OPENING session with no actual open client_session message queued. Maybe we should have a different state instead of OPENING... IMPORTING?
* todoSage Weil2010-03-011-3/+2
|
* mds: fix file purge raceSage Weil2010-02-231-20/+0
| | | | | | | | | | Handle the case where a new inode ref appears while we are purging an inode. If so, we just truncate it to 0, so that next time we go through purge_stray() we don't have to do the work over again. This can happen if a client goes snooping in the stray dir (or who knows what else!).
* todoSage Weil2010-02-221-2/+0
|
* Merge commit 'origin/filestore' into unstableSage Weil2010-02-171-0/+7
|\ | | | | | | | | | | | | Conflicts: src/os/FileStore.cc src/os/FileStore.h
| * Merge branch 'unstable' into filestoreSage Weil2010-02-051-44/+5
| |\ | | | | | | | | | | | | | | | | | | Conflicts: src/authtool.cc src/config.cc
| * | todoSage Weil2010-02-021-2/+2
| | |
| * | Merge commit 'origin/unstable' into filestoreSage Weil2010-01-291-8/+6
| |\ \
| * | | filestore: queue_transaction and generic C_DeleteTransactionSage Weil2010-01-271-0/+3
| | | |
| * | | osd: simplify pg write mode transitionsSage Weil2010-01-261-0/+3
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is no reason to track client on the per-pg AccessMode, since we only care about read/write races on a per-object state, and need to track that per-object anyway due to the new async commit/apply model. (Though this is semi-broken even without that...) Currently we will move from delayed to rmw, but there is no rmw->delayed transition, since the logic for that is a bit more complex.. it'll be difficult to determine when it is really a win. In general, though, RMW is probably a better all around policy!
| * | | filestore: preliminary support for parallel journalingSage Weil2010-01-251-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | - fixed issue with normal write-behind journal (op_seq wasn't updated inside the fs transaction) - reworked journal interface to support write-behind, parallel, write-ahead (hopefully)
* | | | mon: disable 'osd setmap'Sage Weil2010-02-171-2/+0
| | | | | | | | | | | | | | | | | | | | This is dangerous, since it doesn't preserve old pool ids or pool_max, and will confuse osds and generally wreak havoc.
* | | | todoSage Weil2010-02-161-32/+10
| | | |
* | | | todoSage Weil2010-02-111-1/+6
| |_|/ |/| |
* | | todoSage Weil2010-02-031-44/+5
| |/ |/|
* | TODO: mark bugs completedGreg Farnum2010-01-291-4/+2
| |
* | todo: Slightly out of dateGreg Farnum2010-01-291-4/+4
|/
* todoSage Weil2010-01-141-6/+6
|
* TODOGreg Farnum2010-01-081-0/+3
|
* todoSage Weil2010-01-081-4/+2
|
View Lorry Controller Status