]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Thu, 2 Oct 2008 18:15:21 +0000 (11:15 -0700)]
mds: remove stale proc_message()
Sage Weil [Thu, 2 Oct 2008 18:15:08 +0000 (11:15 -0700)]
mon: allow new arguments to be sent to running mon, mds, osd via cmonctl
Sage Weil [Thu, 2 Oct 2008 16:57:48 +0000 (09:57 -0700)]
todos
Sage Weil [Wed, 1 Oct 2008 22:17:27 +0000 (15:17 -0700)]
kclient: mds reset stub
Get rid of compile warning. Add todo.
Sage Weil [Wed, 1 Oct 2008 22:34:16 +0000 (15:34 -0700)]
msgr: fixed bug in accept
banner[] isn't null terminated
Sage Weil [Wed, 1 Oct 2008 22:03:41 +0000 (15:03 -0700)]
messenger protocol changes
There is now a plaintext banner that is exchanged so that both ends can
verify they are talking to the right software. This string should be
changed each time the wire protocol changes.
There are also mon, osd, and mds specific protocol versions defined, but
these are not yet used.
Yehuda Sadeh [Wed, 1 Oct 2008 20:41:05 +0000 (13:41 -0700)]
kclient: whitespaces
Yehuda Sadeh [Wed, 1 Oct 2008 20:38:26 +0000 (13:38 -0700)]
kclient: can supply multiple monitor ips on mount
Yehuda Sadeh [Mon, 29 Sep 2008 20:33:02 +0000 (13:33 -0700)]
kclient: adding unmaskable debug flag
Sage Weil [Wed, 1 Oct 2008 19:00:53 +0000 (12:00 -0700)]
makefile update
Sage Weil [Wed, 1 Oct 2008 18:53:38 +0000 (11:53 -0700)]
v0.4, todos
Sage Weil [Wed, 1 Oct 2008 18:41:00 +0000 (11:41 -0700)]
Merge branch 'master' into unstable
Sage Weil [Wed, 1 Oct 2008 18:40:48 +0000 (11:40 -0700)]
config: comment
Sage Weil [Wed, 1 Oct 2008 18:39:42 +0000 (11:39 -0700)]
mds: fix file recovery
Make state bits distinct. Duh.
Also, if an inode is queued for recovery, and doesn't need it later, unqueue it
(clear the bit, drop auth pin).
Sage Weil [Wed, 1 Oct 2008 17:50:51 +0000 (10:50 -0700)]
kclient: fix pending cap_snap checks, queuing
Add new cap_snaps to the _tail_ of the list.
Also, use a helper to check for pending (write in progress) check, and be
sure to check the list tail in that case.
Sage Weil [Wed, 1 Oct 2008 17:50:46 +0000 (10:50 -0700)]
client: fix queued cap_snap write-in-progress checks
Sage Weil [Tue, 30 Sep 2008 19:59:27 +0000 (12:59 -0700)]
kclient: be more paranoid in prepare_pages
It's theoretically possible to get racing incoming osd_op_replies. Make sure we only give the pages away once.
Sage Weil [Tue, 30 Sep 2008 19:58:17 +0000 (12:58 -0700)]
kclient: fix bad pointer arithmetic in messenger
This was causing intermittent slab corruption when TCP fragmented the stream in unusual ways.
Sage Weil [Mon, 29 Sep 2008 23:30:54 +0000 (16:30 -0700)]
kclient: don't include pages in read requests; some osdc cleanup
Sage Weil [Mon, 29 Sep 2008 22:25:07 +0000 (15:25 -0700)]
kclient: switch to sync writes when NEARFULL osdmap flag set; ENOSPC on FULL flag
Sage Weil [Mon, 29 Sep 2008 20:52:28 +0000 (13:52 -0700)]
todos
Sage Weil [Mon, 29 Sep 2008 20:31:24 +0000 (13:31 -0700)]
kclient: default to safe writeback
Now that async writepages is working, we can wait for data to be fully committed without the higher latency affecting writeback throughput.
Sage Weil [Mon, 29 Sep 2008 20:30:35 +0000 (13:30 -0700)]
mds: choose new mon only if beacons are delayed, and switch to mon that sends up beacons
This streamlines the mds <-> mon beacon interaction a bit.
Sage Weil [Mon, 29 Sep 2008 19:57:55 +0000 (12:57 -0700)]
kclient: some async writeback cleanup
Sage Weil [Mon, 29 Sep 2008 18:48:56 +0000 (11:48 -0700)]
kclient: async writepages
Yehuda Sadeh [Mon, 29 Sep 2008 18:08:36 +0000 (11:08 -0700)]
kclient: using special protocol mask for mds requests
Yehuda Sadeh [Mon, 29 Sep 2008 16:57:32 +0000 (09:57 -0700)]
kclient: added missing file
Yehuda Sadeh [Mon, 29 Sep 2008 16:54:42 +0000 (09:54 -0700)]
kclient: mask to enable/disable debug messages
Sage Weil [Mon, 22 Sep 2008 21:37:18 +0000 (14:37 -0700)]
journal: fix off-by-one bug in committed_thru callbacks
Sage Weil [Mon, 22 Sep 2008 18:21:44 +0000 (11:21 -0700)]
journal: avoid queueing null context
Sage Weil [Tue, 16 Sep 2008 22:39:49 +0000 (15:39 -0700)]
kclient: writepage noop should be kswapd
Sage Weil [Sat, 20 Sep 2008 22:02:04 +0000 (15:02 -0700)]
osdmaptool: print osdmap
Sage Weil [Sat, 20 Sep 2008 22:01:51 +0000 (15:01 -0700)]
osdmap: set ctime+mtime on creation
Sage Weil [Sat, 20 Sep 2008 21:11:03 +0000 (14:11 -0700)]
kclient: writeback cleanups (use filemap_write_and_wait)
Sage Weil [Sat, 20 Sep 2008 20:51:12 +0000 (13:51 -0700)]
kclient: time out mds session close on umount. messily.
This at least won't hang, but it will leave inodes pinned after umount, so it still needs some real work.
Sage Weil [Sat, 20 Sep 2008 20:37:11 +0000 (13:37 -0700)]
kclient: fix up safe/unsafe writeback flags
Sage Weil [Sat, 20 Sep 2008 20:34:11 +0000 (13:34 -0700)]
kclient: unify mount timeouts
Make both mon map and mount messages and mds session, root inode open time out. Previously the mon interaction would time out but we could hang on a non-responsive (e.g., not active) mds.
Sage Weil [Thu, 18 Sep 2008 22:39:54 +0000 (15:39 -0700)]
todos
Sage Weil [Thu, 18 Sep 2008 21:30:47 +0000 (14:30 -0700)]
psim: test localized placement groups
Sage Weil [Thu, 18 Sep 2008 21:30:01 +0000 (14:30 -0700)]
crush: fix forcefeeding for forceleaf
Sage Weil [Thu, 18 Sep 2008 21:26:57 +0000 (14:26 -0700)]
osdmaptool: lpg_bits specifiable
Sage Weil [Thu, 18 Sep 2008 20:44:29 +0000 (13:44 -0700)]
set bl length in buffer::read_file
Sage Weil [Thu, 18 Sep 2008 20:43:51 +0000 (13:43 -0700)]
osdmaptool: fix crush import
Sage Weil [Thu, 18 Sep 2008 20:10:14 +0000 (13:10 -0700)]
crushtool: fix chooseleaf compilation/decompilation
Sage Weil [Thu, 18 Sep 2008 18:38:33 +0000 (11:38 -0700)]
Merge commit '
c43adbe5d679e4920791f4cf4baa294eab36ccfa '
Conflicts:
src/kernel/osd_client.c
Sage Weil [Wed, 17 Sep 2008 21:37:45 +0000 (14:37 -0700)]
todo
Sage Weil [Wed, 17 Sep 2008 21:37:39 +0000 (14:37 -0700)]
crush: chooseleaf
Sage Weil [Tue, 16 Sep 2008 21:44:43 +0000 (14:44 -0700)]
kclient: remove extraneous dput in fill_trace
Sage Weil [Mon, 15 Sep 2008 23:01:30 +0000 (16:01 -0700)]
osd: push/pull data_subset, clone_subsets
Sage Weil [Mon, 15 Sep 2008 23:01:07 +0000 (16:01 -0700)]
objectstore: clonerange, list->vector encoding
Yehuda Sadeh [Mon, 15 Sep 2008 18:25:47 +0000 (11:25 -0700)]
kclient: lowered debug level on some message
Sage Weil [Fri, 12 Sep 2008 22:09:34 +0000 (15:09 -0700)]
kclient: fix mds reconnect message encoding; include snaprealms
Sage Weil [Fri, 12 Sep 2008 20:30:14 +0000 (13:30 -0700)]
filejournal: typo, fixes callbacks
Sage Weil [Fri, 12 Sep 2008 19:51:10 +0000 (12:51 -0700)]
journal: remove some dead code
Sage Weil [Fri, 12 Sep 2008 19:46:43 +0000 (12:46 -0700)]
kclient: fill in kstatfs f_fsid
Sage Weil [Fri, 12 Sep 2008 19:46:31 +0000 (12:46 -0700)]
paxosservice: reset propose timer when election is called
Sage Weil [Fri, 12 Sep 2008 18:44:23 +0000 (11:44 -0700)]
filestore: constrain ObjectStore interface, simplify journaling, update commit_op_seq on each transaction
Sage Weil [Fri, 12 Sep 2008 16:51:31 +0000 (09:51 -0700)]
filejournal: noop is committed_thru is same seq
Sage Weil [Fri, 12 Sep 2008 16:46:37 +0000 (09:46 -0700)]
kclient: fix bug in mdsc check_new_map
Sage Weil [Fri, 12 Sep 2008 16:36:45 +0000 (09:36 -0700)]
filestore: serialize journal entries
Yehuda Sadeh [Fri, 12 Sep 2008 16:23:14 +0000 (09:23 -0700)]
kclient: dirfrag access using mutex and not inode's spinlock
Sage Weil [Thu, 11 Sep 2008 23:57:37 +0000 (16:57 -0700)]
kclient: fix random mds selection bug
Sage Weil [Thu, 11 Sep 2008 23:40:51 +0000 (16:40 -0700)]
ebofs: maintain an op seq count, and use that for the journal
Sage Weil [Thu, 11 Sep 2008 17:56:16 +0000 (10:56 -0700)]
journal: journal rewrite
Sage Weil [Thu, 11 Sep 2008 17:41:57 +0000 (10:41 -0700)]
use vector or deque in place of list<Context*> in finisher, ebofs
Yehuda Sadeh [Thu, 11 Sep 2008 17:59:02 +0000 (10:59 -0700)]
kclient: removing of virutal xattr is not allowed
Yehuda Sadeh [Thu, 11 Sep 2008 17:55:19 +0000 (10:55 -0700)]
kclient: setxattr for virtual xattr is not allowed
Yehuda [Thu, 11 Sep 2008 17:36:29 +0000 (10:36 -0700)]
kclient: mount default without DIRSTAT
Yehuda [Thu, 11 Sep 2008 17:29:33 +0000 (10:29 -0700)]
kclient: no need to check for mount with dir stat (xattr)
Yehuda [Thu, 11 Sep 2008 00:22:24 +0000 (17:22 -0700)]
kclient: remove whitespace
Yehuda [Thu, 11 Sep 2008 00:21:03 +0000 (17:21 -0700)]
kclient: xattr show dir extended data
Sage Weil [Wed, 10 Sep 2008 23:30:29 +0000 (16:30 -0700)]
startnew.sh: sudo if btrfs
Sage Weil [Wed, 10 Sep 2008 23:30:13 +0000 (16:30 -0700)]
filestore: no rmdir in mkfs
Sage Weil [Wed, 10 Sep 2008 22:53:00 +0000 (15:53 -0700)]
osd: some snap_trimmer fixes
Sage Weil [Wed, 10 Sep 2008 22:52:39 +0000 (15:52 -0700)]
mds: purge stray files immediately; only keep snapped directories around
Sage Weil [Wed, 10 Sep 2008 22:33:07 +0000 (15:33 -0700)]
mds: optimize open_snaprealm() for stray and/or non-dirs
Sage Weil [Wed, 10 Sep 2008 20:01:36 +0000 (13:01 -0700)]
kclient: some todos
Sage Weil [Wed, 10 Sep 2008 19:52:27 +0000 (12:52 -0700)]
kclient: rename __ceph_get_frag -> __get_or_create_frag
Sage Weil [Wed, 10 Sep 2008 19:15:56 +0000 (12:15 -0700)]
mds: recover file size for all affected snapshots, not just the head
Sage Weil [Wed, 10 Sep 2008 17:14:31 +0000 (10:14 -0700)]
mds: adjust TABLE_OP namespaces; fix prepare journal event
Sage Weil [Wed, 10 Sep 2008 14:10:33 +0000 (07:10 -0700)]
filer: snapid should be nonzero on all reads
Sage Weil [Tue, 9 Sep 2008 23:31:53 +0000 (16:31 -0700)]
kclient: allocate xattr buffer outside of i_lock
Sage Weil [Tue, 9 Sep 2008 23:11:30 +0000 (16:11 -0700)]
msgr: relax seq checking on lossy channels (incomplete fix)
Sage Weil [Tue, 9 Sep 2008 23:10:32 +0000 (16:10 -0700)]
mds: write objects directory, avoid filer
Sage Weil [Tue, 9 Sep 2008 23:03:56 +0000 (16:03 -0700)]
osd: typo
Sage Weil [Tue, 9 Sep 2008 23:03:48 +0000 (16:03 -0700)]
mds: read mds objects with CEPH_NOSNAP
Sage Weil [Tue, 9 Sep 2008 22:42:11 +0000 (15:42 -0700)]
synclient: loff_t in write_file
Sage Weil [Tue, 9 Sep 2008 22:42:02 +0000 (15:42 -0700)]
objectcacher: off_t -> loff_t
Sage Weil [Tue, 9 Sep 2008 21:53:09 +0000 (14:53 -0700)]
osdmaptool: require num_osd > 0 when creating new osdmap
Sage Weil [Tue, 9 Sep 2008 21:24:22 +0000 (14:24 -0700)]
mon: verify osdmap fsid in 'setmap'
Sage Weil [Tue, 9 Sep 2008 21:26:40 +0000 (14:26 -0700)]
osd: fix _finish_recovery locking, refcounting
Sage Weil [Tue, 9 Sep 2008 20:51:57 +0000 (13:51 -0700)]
osd: prevent _finish_recovery from going off after primary changes
Sage Weil [Tue, 9 Sep 2008 20:51:38 +0000 (13:51 -0700)]
fix coll_t != comparator
Sage Weil [Tue, 9 Sep 2008 20:51:21 +0000 (13:51 -0700)]
ebofs: use correct remove in alloc_dec (so that btree remains balanced)
Sage Weil [Tue, 9 Sep 2008 18:32:55 +0000 (11:32 -0700)]
todos
Sage Weil [Tue, 9 Sep 2008 14:53:41 +0000 (07:53 -0700)]
kclient: use truncate_inode_pages instead of vmtruncate
Sage Weil [Tue, 9 Sep 2008 14:53:18 +0000 (07:53 -0700)]
kclient: fix revocation races
Sage Weil [Tue, 9 Sep 2008 14:52:37 +0000 (07:52 -0700)]
mds: fix lock ordering
Yehuda [Tue, 9 Sep 2008 17:41:36 +0000 (10:41 -0700)]
another fix for kernel 2.6.26
Yehuda [Tue, 9 Sep 2008 00:10:12 +0000 (17:10 -0700)]
some changes for work collaboration