Commit Graph

12251 Commits

Author SHA1 Message Date
Colin Patrick McCabe
bf31f3f129 logger: Fix DoutStreambuf::create_rank_symlink
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-14 06:20:23 -08:00
Colin Patrick McCabe
4c37719988 cephtool: rename tools files
Rename tools files to be more consistent. For example, the main()
function for ./ceph should be in ceph.cc.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-14 06:13:50 -08:00
Sage Weil
c8d9b20cc5 Merge branch 'sync2' into unstable 2010-12-14 12:47:40 -08:00
Sage Weil
056e91e0ce librados: drop watch_lock
Use the existing lock to do protect all of this.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-14 11:02:12 -08:00
Sage Weil
d4420a8a57 objecter: drop linger_info_mutex
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-14 11:00:19 -08:00
Sage Weil
215f3320fe objecter: simplify linger register
Drop single-use helper; make unregister_linger part of the public
interface.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-14 10:48:57 -08:00
Sage Weil
b60a9abf56 objecter: fix up linger ack/commit to trigger first time only
We only want the user-provided ack/commit callbacks to trigger the first
time we register the lingering op.  Same goes for the eversion_t *objver.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-14 10:47:19 -08:00
Sage Weil
8a75086d5e objecter: clean up linger interface
Put LingerOp on heap.  Use xlist to attach to PGs.  Add in/out bufferlists.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-14 10:35:40 -08:00
Sage Weil
96b32382d0 Merge remote branch 'origin/unstable' into sync2
Conflicts:
	src/auth/Crypto.cc
	src/osd/ReplicatedPG.cc
	src/osd/ReplicatedPG.h
	src/osd/osd_types.h
2010-12-14 09:55:21 -08:00
Vangelis Koukis
a3fcf90898 logging: Fix use-before-access in debug.cc
Signed-off-by: Vangelis Koukis <vkoukis@cslab.ece.ntua.gr>
Signed-off-by: Constantinos Venetsanopoulos <cven@cslab.ece.ntua.gr>
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-14 01:58:14 -08:00
Sage Weil
0e08cb0f6c osd: return ENOSPC for non-mds if full flag is set in osdmap
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-11 13:58:47 -08:00
Sage Weil
239b7677e7 Merge remote branch 'origin/syslog' into unstable
Conflicts:
	src/mon/Paxos.cc
	src/osd/PG.cc
2010-12-11 08:09:17 -08:00
Sage Weil
46242586ed Merge branch 'gceph' into unstable 2010-12-11 08:04:09 -08:00
Colin Patrick McCabe
292414c5fd gceph: Add gceph to rpm, deb
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-10 20:34:49 -08:00
Colin Patrick McCabe
71a19a9432 gceph: run shutdown functions at exit
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-10 20:30:57 -08:00
Colin Patrick McCabe
bb82fd3d19 gceph: fix compile
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-10 20:25:47 -08:00
Colin Patrick McCabe
1a201f85e4 gceph: add -h argument
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-10 20:15:25 -08:00
Colin Patrick McCabe
b4ceb19472 ceph tool: Create gceph
Put the gui into a separate binary.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-10 20:12:56 -08:00
Yehuda Sadeh
4984473848 librados, objecter: fix unwatch operation 2010-12-09 15:57:55 -08:00
Colin Patrick McCabe
346a2aac42 rpm: update changelog
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-09 14:38:08 -08:00
Colin Patrick McCabe
e23d620068 rpm: fix ceph.spec to work with gcephtool
Don't try to package gui_resources unless we are building the GUI.
Get GUI dependencies correct.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-09 14:35:48 -08:00
Yehuda Sadeh
e5769b061b objecter: resend_linger copies ops 2010-12-09 13:55:45 -08:00
Vangelis Koukis
83612ef736 Fix overflow in FileJournal::_open_file()
[ The following text is in the "iso-8859-7" character set. ]
    [ Your display is set for the "iso-8859-1" character set.  ]
    [ Some special characters may be displayed incorrectly. ]

Running the unstable branch, mkcephfs fails when trying to create
a 3GB journal file on the OSDs.

Relevant messages from the osd logfile:

2010-12-09 19:03:54.419737 7fdde4d51720 journal _open_file: unable to extend journal to 18446744072560312320 bytes
2010-12-09 19:03:54.419789 7fdde4d51720 filestore(/osd) mkjournal error creating journal on /osd/journal

The problem is that the calculation of the journal size in bytes
overflows, in FileJournal::_open_file().

Signed-off-by: Vangelis Koukis <vkoukis@cslab.ece.ntua.gr>
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-09 13:45:30 -08:00
Samuel Just
d0fbc30a0a ReplicatedPG.cc: Fixes a bug in snap_trimmer where a pointer to a stack
Cond is left in the mode.waiting_cond list.

Signed-off-by: Samuel Just <samuelj@hq.newdream.net>
2010-12-09 13:09:20 -08:00
Samuel Just
329ae1bc3b ReplicatedPG: snap_trimmer now acquires a read lock on the osd map
before calling share_pg_info.

Signed-off-by: Samuel Just <samuelj@hq.newdream.net>
2010-12-09 13:09:20 -08:00
Colin Patrick McCabe
f68e6e7d38 rpm: don't try to package radosacl
radosacl is just a test binary, so unless we build with --with-debug, we
won't get it.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-09 11:18:33 -08:00
Colin Patrick McCabe
6722b0c85d rpm: add pkgconfig to BuildRequires
You can't build without pkgconfig.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-09 11:18:32 -08:00
Colin Patrick McCabe
9df18d1984 rpm: set files-attr for radosgw
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-09 10:28:39 -08:00
Sage Weil
b4264fbbdc filejournal: reset last_commited_seq if we find journal to be invalid
If we read an event that's later than our expected entry, we set read_pos
to -1 and discard the journal.  If that happens we also need to reset
last_committed_seq to avoid a crash like

2010-12-08 17:04:39.246950 7f269d138910 journal commit_finish thru 16904
2010-12-08 17:04:39.246961 7f269d138910 journal committed_thru 16904 < last_committed_seq 37778589
os/FileJournal.cc: In function 'virtual void FileJournal::committed_thru(uint64_t)':
os/FileJournal.cc:854: FAILED assert(seq >= last_committed_seq)
 ceph version 0.24~rc (commit:fe10300317383ec29948d7dbe3cb31b3aa277e3c)
 1: (FileJournal::committed_thru(unsigned long)+0xad) [0x588e7d]
 2: (JournalingObjectStore::commit_finish()+0x8c) [0x57f2ec]
 3: (FileStore::sync_entry()+0xcff) [0x5764cf]
 4: (FileStore::SyncThread::entry()+0xd) [0x506d9d]
 5: (Thread::_entry_func(void*)+0xa) [0x4790ba]
 6: /lib/libpthread.so.0 [0x7f26a2f8373a]
 7: (clone()+0x6d) [0x7f26a1c2569d]

Fixes #631

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-08 18:10:49 -08:00
Yehuda Sadeh
cc78bbf16e objecter: create a new op for resending lingering requests 2010-12-08 16:02:52 -08:00
Colin Patrick McCabe
027d5bfdca logger: tweak cmon log output a bit
Make the output of cmon on stderr a little bit less verbose.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-08 13:51:00 -08:00
Colin Patrick McCabe
fdc7414ecd logging: DoutStreambuf: handle daemonizing better
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-08 12:25:17 -08:00
Yehuda Sadeh
5cba1e6333 objecter: a few lingering fixes 2010-12-08 11:36:18 -08:00
Sage Weil
a9c098df47 mon: use helper for clock drift check; log relative instead of absolute time
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-08 11:12:51 -08:00
Colin Patrick McCabe
986c2af4ae logging: debug.h: use DoutStreambuf
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-08 10:54:51 -08:00
Colin Patrick McCabe
c53ffafb5c logging: Remove _dout_check_log
_dout_check_log is unneeded, since every invocation of dout makes the
same check.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 23:27:19 -08:00
Colin Patrick McCabe
8fdd0f44a5 logging: debug.h: minor cleanup
Don't put std::ostream into the global namespace. Copyright update.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 23:17:48 -08:00
Colin Patrick McCabe
aeba6bca5d logging: eliminate dbeginl
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 22:52:21 -08:00
Colin Patrick McCabe
0f0cb46ad7 logging: Implement rank symlinks
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 19:09:18 -08:00
Colin Patrick McCabe
6c4a7d5810 logging: Support isym_path
Support instance symlinks, which are activated when we are using
g_conf.log_per_instance.

Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:54:03 -08:00
Colin Patrick McCabe
e597d02d42 logging: rename_output_file -> handle_pid_change
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:51:35 -08:00
Colin Patrick McCabe
116478a3be logging: _calculate_opath: use g_conf.log_dir
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:49:14 -08:00
Colin Patrick McCabe
ea3414d4dd logging: DoutStreambuf: better debug output
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:47:28 -08:00
Colin Patrick McCabe
627399f760 logging: create_symlink:sometimes use rel symlinks
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:45:21 -08:00
Colin Patrick McCabe
b00baab159 logging: implement get_dirname, move get_basename
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:43:49 -08:00
Colin Patrick McCabe
ef22366455 logging: fix normalize_relative
Signed-off-by: Colin McCabe <colinm@hq.newdream.net>
2010-12-07 18:41:23 -08:00
Sage Weil
fe10300317 mds: sync->mix replica state is sync->mix(2)
When auth first moves to sync->mix,
 - auth sends AC_MIX to replicas
 - replicas go to sync->mix
 - replicas finish gather, send AC_SYNCACK, move to sync->mix(2)
 - auth gets all acks, sends AC_MIX again
 - replica moves to MIX

So any new replica should just get sync->mix(2), so that it is not confused
by the second AC_MIX.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-07 16:44:19 -08:00
Sage Weil
2000f69e99 mds: no not choose lock state on replicas
The lock state has already been set during rejoin.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-07 16:44:19 -08:00
Sage Weil
3825c4b87b mds: small rejoin cleanup
Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-07 16:44:18 -08:00
Sage Weil
9b9b86935e mds: rev mds cluster internal protocol
The lock encoding changed with the dirty bit on scatterlocks.

Signed-off-by: Sage Weil <sage@newdream.net>
2010-12-07 16:44:18 -08:00