Yehuda Sadeh
5e8a6096b3
rbd: modify header, add utility to ease sync with qemu tree
2010-05-24 15:55:58 -07:00
Sage Weil
0d98fc6ffd
osd: keep recovery ops in sync with pull
...
Call start_recovery_op from pull() instead of fixing every caller (some
were wrong). This keeps the recovery state in sync with pulling state,
even when pull() has to pull something different (head, snapdir) first.
Fixes this crash:
osd/PG.cc: In function 'void PG::finish_recovery_op(const sobject_t&, bool)':
osd/PG.cc:1842: FAILED assert(recovering_oids.count(soid))
1: (PG::finish_recovery_op(sobject_t const&, bool)+0x14e) [0x74caf6]
2: (ReplicatedPG::sub_op_push(MOSDSubOp*)+0x1da8) [0x669292]
3: (ReplicatedPG::do_sub_op(MOSDSubOp*)+0x109) [0x671a73]
4: (OSD::dequeue_op(PG*)+0x23c) [0x6bda00]
5: (OSD::OpWQ::_process(PG*)+0x21) [0x7387c9]
6: (ThreadPool::WorkQueue<PG>::_void_process(void*)+0x28) [0x6f5e12]
7: (ThreadPool::worker()+0x23a) [0x7f2404]
8: (ThreadPool::WorkThread::entry()+0x19) [0x73b783]
9: (Thread::_entry_func(void*)+0x20) [0x64f92a]
10: /lib/libpthread.so.0 [0x7f7a12cf473a]
11: (clone()+0x6d) [0x7f7a11f1e69d]
2010-05-24 14:00:43 -07:00
Sage Weil
a9b494c444
mon: no need for 'whoami' file in store
...
The monitor rank is provided during startup. No need to verify it against
the monitor store, especially since the stores are otherwise identical.
This makes it simpler to restore/duplicate/wahtever a monitor.. just copy
the files.
2010-05-24 14:00:43 -07:00
Greg Farnum
56c4043acc
reword blacklisted output so it's clearly discussing MDSes and not OSDs
2010-05-23 15:13:33 -07:00
Sage Weil
f7708dea1f
uclient: don't unlink null dentry when getting null linkage in mds reply
...
This broke semi-recently when the mds started returning null linkages (and
associated leases).
2010-05-22 09:56:27 -07:00
Sage Weil
bf1cb87d25
mon: trim pgmap states even when we don't have a full quorum
2010-05-21 16:17:48 -07:00
Sage Weil
357aa03344
paxos: recover using stashed latest when state histories don't overlap
...
If we don't have incremental states to catch up, jump to the latest.
2010-05-21 16:17:34 -07:00
Sage Weil
51c5823472
mds: anchor multiversion inode before unlinking it
...
If we are going to create a remote dentry linking to a multiversion inode
we're unlinking, make sure it's anchored!
This is a bit fugly because it mirrors the logic in journal_cow_dentry. No
obvious way to use a generic helper for that though.
2010-05-21 14:55:38 -07:00
Yehuda Sadeh
fbbff74304
librados.h: add other TMAP definitions
...
also add a comment in rados.h about the defines in librados.h
2010-05-21 13:44:40 -07:00
Sage Weil
929048f98f
mds: fix readdir pingpong on snapped dir with multiple mds
...
Our traverse helper will follow the auth if we're looking at snapped
metadata, but we _don't_ want that for readdir because we check auth
ourselves, and want the dir's auth, not the inode's.
Signed-off-by: Sage Weil <sage@newdream.net>
2010-05-21 12:08:35 -07:00
Sage Weil
cd1b071011
monc: pick a different mon when repicking
2010-05-21 12:08:35 -07:00
Sage Weil
3ec4605977
monc: hunting by default
...
Otherwise if we fail to connect to the first mon we try, we never retry.
2010-05-21 12:08:35 -07:00
Yehuda Sadeh
16ab067c75
librados: update librados to define CEPH_OSD_TMAP_SET
2010-05-20 16:19:01 -07:00
Sage Weil
0050dd84d8
mon: fix mon injectargs, and simplify
2010-05-20 11:14:41 -07:00
Sage Weil
9e4e53e073
osd: simplify --mkjournal, add --flush-journal
2010-05-20 10:58:56 -07:00
Sage Weil
41b260600c
Merge branch 'osd_snapdir' into unstable
2010-05-20 10:39:57 -07:00
Sage Weil
1d9ab261ba
osd: nicer debug output
2010-05-20 10:39:47 -07:00
Sage Weil
f3ab812ba0
interval_set: fix union_of _size accounting; optimize ==
2010-05-20 10:33:55 -07:00
Sage Weil
e162aab360
mds: fix interval_set copy of projected_free
2010-05-19 16:43:02 -07:00
Sage Weil
155efe24dc
mds: fix interval_set copy of projected_free
2010-05-19 16:42:34 -07:00
Sage Weil
f6c4827483
osd: use blank reqid for snapdir events, too
...
Make reqid_is_indexed() less weird.
2010-05-19 16:11:10 -07:00
Sage Weil
8dfe74f66f
osd: do not index by reqid if reqid not defined
2010-05-19 16:10:14 -07:00
Sage Weil
4ed3acb08a
osd: update purged_snaps in PG::Info on trim completion; and replicate
2010-05-19 15:42:50 -07:00
Yehuda Sadeh
9149dfa1ba
rbd: fix snap_seq type in rbd_header
2010-05-19 13:17:32 -07:00
Sage Weil
99690f63cf
initscripts: remove 'flushoncommit' from default btrfs mount options
2010-05-19 11:49:27 -07:00
Sage Weil
46891dd0e9
osd: trim snaps via replicated osd ops
2010-05-19 10:53:32 -07:00
Sage Weil
ff94c3a4f5
osd: make build_removed_snaps, is_removed_snap consistent
2010-05-19 10:42:20 -07:00
Greg Farnum
e0315485c0
rados: update documentation to mention mkpool and rmpool
2010-05-19 10:35:28 -07:00
Sage Weil
ee218a1e81
osd: fix peer_info updates on active primary
2010-05-18 15:04:17 -07:00
Sage Weil
a7769755c1
automake: some clean up
2010-05-18 08:01:23 -07:00
Yehuda Sadeh
1ea0f858fe
poolop: fix MPoolOpReply decoding
2010-05-17 16:29:50 -07:00
Sage Weil
736d837e88
throttle: allow large items if we're under our max
...
Normally we stay under max, but for large items, take it as long as we're
currently below max. This avoids deadlock.
2010-05-17 14:53:59 -07:00
Sage Weil
d006ae9331
osd: purged_snaps in PG::Info, queue snap trim on primary
2010-05-15 20:55:44 -07:00
Sage Weil
47ba928ba9
osd: include snapdir objects in pg log for proper replication, recovery
2010-05-14 14:18:21 -07:00
Sage Weil
ffd72a98fb
strings: clean up pool op names
2010-05-14 11:36:41 -07:00
Sage Weil
d1c78fcbfe
mds: allow readdir result limit in bytes
...
This will allow the client to bound the size of the reply it gets
2010-05-14 11:32:51 -07:00
Sage Weil
7be27f435d
debian: put proper distribution in debian changelog
2010-05-14 09:43:31 -07:00
Sage Weil
33bf1a2bc2
version: use next version ~rc for unstable branch
...
This makes unstable always sort after stable, testing releases:
0.21~rc-unstable... > 0.20.1-testing...
2010-05-14 09:14:00 -07:00
Sage Weil
0e177d2824
radosgw_admin: die after first bad argument
2010-05-13 13:28:46 -07:00
Sage Weil
c54d6cde61
objecter: separately track pgmap, osdmap state machine version
...
Mixing these up can make our request hang on the monitor indefinitely.
2010-05-13 10:47:33 -07:00
Sage Weil
52e544bf45
mon: return correct state machine epoch in replies
2010-05-13 10:47:07 -07:00
Sage Weil
ecc4f68679
testrados: fix aio api usage
2010-05-13 10:46:47 -07:00
Sage Weil
c3a8adaa57
librados: implement rados_stat_pool()
2010-05-13 10:46:38 -07:00
Sage Weil
4ee1e26125
Merge branch 'unstable' of ceph.newdream.net:git/ceph into unstable
2010-05-12 16:13:36 -07:00
Sage Weil
e741d43fdf
rados: fix typo
2010-05-12 16:13:03 -07:00
Sage Weil
342fc87191
osd: add CEPH_PG_MAX_SIZE to header
2010-05-12 16:06:56 -07:00
Sage Weil
7f43cf8a87
filestore: update btrfs ioctl.h
2010-05-12 16:06:52 -07:00
Sage Weil
856bdf2f21
client: un-"fix" u64 types in client/ioctl.h
2010-05-12 16:06:49 -07:00
Sage Weil
c9b1aee18e
msgr: fix possible overflow when sending seq
2010-05-12 16:06:45 -07:00
Sage Weil
65074e5a6b
msgr: print message encoding version to aid debugging
2010-05-12 16:06:41 -07:00