]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Thu, 12 Nov 2009 22:17:18 +0000 (14:17 -0800)]
put testing ceph.conf's in git
Sage Weil [Thu, 12 Nov 2009 22:16:31 +0000 (14:16 -0800)]
osd: print useful mode wait message
Sage Weil [Thu, 12 Nov 2009 22:16:17 +0000 (14:16 -0800)]
filestore: skip sync_file_range if the full commit has started
Presumably btrfs commit_transaction is more effective than our per-file
flushing. And we don't want to fight each other.
Greg Farnum [Thu, 12 Nov 2009 20:06:57 +0000 (12:06 -0800)]
rados: fix usage() and -p option checking
Sage Weil [Thu, 12 Nov 2009 18:45:54 +0000 (10:45 -0800)]
mds: warn, don't crash, on rfiles/rsubdirs underflow
This doesn't fix the bug, but lets the mds at least start up.
Sage Weil [Thu, 12 Nov 2009 00:10:14 +0000 (16:10 -0800)]
uclient: increase cache size
Sage Weil [Thu, 12 Nov 2009 00:09:52 +0000 (16:09 -0800)]
filestore: flusher thread; commit snaps (disabled)
Sage Weil [Wed, 11 Nov 2009 18:20:12 +0000 (10:20 -0800)]
osd: avoid truncate, remove ops we know will fail
Now that we check return codes, these cause problems.
Sage Weil [Wed, 11 Nov 2009 18:19:28 +0000 (10:19 -0800)]
osd: don't requeue pg removal if already removing
Sage Weil [Wed, 11 Nov 2009 23:52:10 +0000 (15:52 -0800)]
todo
Sage Weil [Wed, 11 Nov 2009 23:47:28 +0000 (15:47 -0800)]
mds: force rdlock on any snapped inodes
When the client has an excl lock on an inode, and it's
stating a snapped version of it, we can't expect it to
put 2 and 2 together and look at it's head metadata. If
the cap does not follow the snapid we're trying to stat, do
the full rdlock to force the snapped values back to the
mds so we can do the cow.
If there is nothing cow, the cap will get reissued with an
accurate follows value, and we won't have to do this again.
Greg Farnum [Wed, 11 Nov 2009 00:44:07 +0000 (16:44 -0800)]
sessionmap is an object, not a pointer
Sage Weil [Wed, 11 Nov 2009 00:32:01 +0000 (16:32 -0800)]
mds: fix typo; also only suicide if we have clients
If we are the last MDS and have no clients we should be
able to stop cleanly....
Sage Weil [Wed, 11 Nov 2009 00:26:44 +0000 (16:26 -0800)]
mds: underwater is function of _loaded_ version, not in core version
We may load a dir version off disk that is older than the
in-core version (because we got newer data from the
journal, say). When marking underwater items clean, do
so based on the _loaded_ version, not out in-core version.
Sage Weil [Mon, 9 Nov 2009 21:32:07 +0000 (13:32 -0800)]
todo
Greg Farnum [Wed, 11 Nov 2009 00:02:04 +0000 (16:02 -0800)]
mds: If last MDS, suicide on stop rather than entering infinite requeue loop
Sage Weil [Tue, 10 Nov 2009 22:51:20 +0000 (14:51 -0800)]
osd: do not apply_transaction in finish_recovery
finish_recovery needs to set up a callback for when the current set of
changes commit to disk (to kickstart cleanup of strya replicas etc). We
can't call apply_transaction this deep inside the call chain without
causing problems. So, pass a list of completion contexts all the way down
so that we can set up the completion callback.
Sage Weil [Tue, 10 Nov 2009 22:51:33 +0000 (14:51 -0800)]
filestore: don't croak on 0 op usertrans error
Sage Weil [Tue, 10 Nov 2009 21:12:33 +0000 (13:12 -0800)]
filestore: check return values
Sage Weil [Tue, 10 Nov 2009 16:23:38 +0000 (08:23 -0800)]
test_trans
Sage Weil [Tue, 10 Nov 2009 16:09:18 +0000 (08:09 -0800)]
filestore: fix usertrans setxattr, print it out nicely
Sage Weil [Tue, 10 Nov 2009 15:51:44 +0000 (07:51 -0800)]
filestore: clean up btrfs ioctls; use actual btrfs ioctl.h
Sage Weil [Tue, 10 Nov 2009 15:37:56 +0000 (07:37 -0800)]
sample.ceph.conf: include usertrans flag
Sage Weil [Tue, 10 Nov 2009 15:37:45 +0000 (07:37 -0800)]
filestore: make FileStore btrfs ioctl tests more readable
Sage Weil [Mon, 9 Nov 2009 21:17:29 +0000 (13:17 -0800)]
osd: log misdirected ops; reply with -ENXIO
This is more helpful than assert(0). It's still bad (it means the client
and osd calculated different pg mappings) though, but this makes it easier
to identify and fix.
Sage Weil [Mon, 9 Nov 2009 21:01:08 +0000 (13:01 -0800)]
sample.ceph.conf: fix btrfs mountoptions
Sage Weil [Sun, 8 Nov 2009 17:21:16 +0000 (09:21 -0800)]
osdmap: clear out old hash distribution code
This screws up linkage because not everything that #Includes osdmap.h
links crush.
Sage Weil [Sun, 8 Nov 2009 05:06:27 +0000 (21:06 -0800)]
osd: make pgids sort on (pool, preferred, ps)
This makes pg dump output easier to read, mainly.
Sage Weil [Sun, 8 Nov 2009 05:05:32 +0000 (21:05 -0800)]
crushtool: small fix
Sage Weil [Sun, 8 Nov 2009 04:49:37 +0000 (20:49 -0800)]
Revert "crush: use spirit classic headers"
This reverts commit
28ac4441b87907713ddaf1fe1dee62350f947cf3 .
Sage Weil [Sat, 7 Nov 2009 23:27:08 +0000 (15:27 -0800)]
hash: small cleanup
Sage Weil [Sun, 8 Nov 2009 04:12:21 +0000 (20:12 -0800)]
crush: hrm fix up builder too
fix
Sage Weil [Sun, 8 Nov 2009 03:59:42 +0000 (19:59 -0800)]
crush: use spirit classic headers
This makes the 'deprecated' warnings go away.
Sage Weil [Sun, 8 Nov 2009 03:59:05 +0000 (19:59 -0800)]
crush: make hash function selectable
Sage Weil [Sat, 7 Nov 2009 05:36:43 +0000 (21:36 -0800)]
osd: make object hash a pg_pool parameter
Sage Weil [Sat, 7 Nov 2009 00:48:38 +0000 (16:48 -0800)]
osdmaptool: test-map-object
Sage Weil [Sat, 7 Nov 2009 00:43:47 +0000 (16:43 -0800)]
osd: use stronger hash function for mapping objects -> pgs
The old hash (from linux dcache) was very weak, such that
least sig bits may not change and you could get lots of
consecutive objects on the same osds (because lsbits of the
pg weren't changing).
This is Robert Jenkin's hash and is quite strong. Public
domain.
Rev osd disk format, protocol, since we're totally changing
object placement here.
Sage Weil [Fri, 6 Nov 2009 23:37:01 +0000 (15:37 -0800)]
crush: no more static inline
Greg Farnum [Fri, 6 Nov 2009 23:27:23 +0000 (15:27 -0800)]
osd: This logic is slightly less confusing without the always-true 'full' param
Sage Weil [Fri, 6 Nov 2009 21:54:53 +0000 (13:54 -0800)]
mon: don't delete stats when sending osdmap incremental
send_latest will delete m, and/or wait. Instead call send_incremental
directly only when we know paxos is_readable.
Sage Weil [Fri, 6 Nov 2009 20:12:24 +0000 (12:12 -0800)]
qa: test subdir mounts
Sage Weil [Fri, 6 Nov 2009 06:22:27 +0000 (22:22 -0800)]
init-ceph: tell user we're mounting btrfs
Sage Weil [Fri, 6 Nov 2009 21:36:32 +0000 (13:36 -0800)]
osd: send single osd_boot on startup
Sage Weil [Fri, 6 Nov 2009 21:36:25 +0000 (13:36 -0800)]
mon: don't log dup osd boot msgs
Sage Weil [Fri, 6 Nov 2009 21:35:08 +0000 (13:35 -0800)]
msgr: leave off ss_family when printing
Sage Weil [Fri, 6 Nov 2009 06:21:22 +0000 (22:21 -0800)]
todo
Sage Weil [Fri, 6 Nov 2009 21:09:58 +0000 (13:09 -0800)]
ppc: do not copy_in unencoded __u32
Fixes big endian bugs.
Sage Weil [Fri, 6 Nov 2009 21:09:26 +0000 (13:09 -0800)]
buffer: only define _XOPEN_SOURCE ifndef
Sage Weil [Fri, 6 Nov 2009 07:03:59 +0000 (23:03 -0800)]
todo
Sage Weil [Fri, 6 Nov 2009 06:25:30 +0000 (22:25 -0800)]
mon: make initial monmap epoch match paxos version
Sage Weil [Fri, 6 Nov 2009 06:24:19 +0000 (22:24 -0800)]
mkmonfs: use common_init and parse regular args
Sage Weil [Fri, 6 Nov 2009 05:53:15 +0000 (21:53 -0800)]
don't forget -standalone.git in release checklist
Greg Farnum [Wed, 4 Nov 2009 00:43:53 +0000 (16:43 -0800)]
uclient: set NAME_MAX = PAGE_SIZE
Greg Farnum [Thu, 5 Nov 2009 20:58:29 +0000 (12:58 -0800)]
Hadoop: Update JavaDoc and put in new patch file
Greg Farnum [Wed, 4 Nov 2009 22:14:41 +0000 (14:14 -0800)]
Hadoop: Numerous fixes.
Set bufUsed=0 on a flush to avoid bad rewrites of data
Downgrade a warning in IOStream since Hadoop apparently checks for EOF by reading until a read returns -1.
Remove some leftover if checks that don't do anything.
TODO: Remove something Sage did already.
Yehuda Sadeh [Thu, 5 Nov 2009 18:00:19 +0000 (10:00 -0800)]
mount: fix hint initialization for getaddrinfo
Sage Weil [Thu, 5 Nov 2009 05:43:47 +0000 (21:43 -0800)]
filestore: oops less noisy
Sage Weil [Thu, 5 Nov 2009 00:21:20 +0000 (16:21 -0800)]
osdmap: fix pps calc for preferred pgs
Sage Weil [Thu, 5 Nov 2009 00:09:32 +0000 (16:09 -0800)]
osd: nicer debug output on misdirected requests
Sage Weil [Wed, 4 Nov 2009 23:22:54 +0000 (15:22 -0800)]
mds: mark scatterlocks with dirty rstat/fragstat during replay
This ensures we propagate this info back toward the root
after we've replayed and gone active.
Sage Weil [Wed, 4 Nov 2009 23:22:11 +0000 (15:22 -0800)]
mds: use fnode when replaying journal
We weren't actually pulling the fnode from the journal. I'm
surprised anything worked.
This fixes a crash when untaring, restarting mds, and then
rm -r'ing the dir. Previously the rstat would roll
negative and assert.
Sage Weil [Wed, 4 Nov 2009 21:27:06 +0000 (13:27 -0800)]
debian: gracefully replace lib packages prior to '1' suffix
Sage Weil [Wed, 4 Nov 2009 20:24:39 +0000 (12:24 -0800)]
osd: kill int <-> pg_t conversions
These are messy and asking for trouble. And a cleaner
coll_t paves the way for real named coll_t's down the
line.
Sage Weil [Wed, 4 Nov 2009 19:37:41 +0000 (11:37 -0800)]
osd: convert ceph_pg union to struct
This simplifies/fixes endian conversions.
Sage Weil [Tue, 3 Nov 2009 23:15:22 +0000 (15:15 -0800)]
msgr: encode sockaddr.ss_family big endian in ceph_entity_addr
The ss_family field is normally host endianness, but we
want to exchange ceph_entity_addr across the wire and store
it on disk. So, encode ss_family in big endian (to match
the other sockaddr field endianness).
Rev disk and wire protocols to match.
Sage Weil [Tue, 3 Nov 2009 20:31:40 +0000 (12:31 -0800)]
filestore: close btrfs transactions cleanly
Don't just close the fd. We may add a mount option that makes a messy
transaction close wedge the fs instead of committing partial results.
Sage Weil [Tue, 27 Oct 2009 15:39:02 +0000 (08:39 -0700)]
default pid file /var/run/ceph/$type.$id.pid
Greg Farnum [Tue, 3 Nov 2009 00:37:38 +0000 (16:37 -0800)]
Hadoop: Don't use the local pg by default.
Greg Farnum [Mon, 2 Nov 2009 04:18:29 +0000 (20:18 -0800)]
Now passes all unit tests!
Changes made to rename and between error codes/exception throwing.
Greg Farnum [Sat, 31 Oct 2009 01:39:48 +0000 (18:39 -0700)]
Hadoop: Don't throw IOExceptions on extra calls to close
Greg Farnum [Fri, 30 Oct 2009 22:37:06 +0000 (15:37 -0700)]
Hadoop: f5 e3
Greg Farnum [Fri, 30 Oct 2009 20:53:54 +0000 (13:53 -0700)]
Hadoop: Behavioral fixes to CephFileSystem
Greg Farnum [Fri, 30 Oct 2009 20:50:30 +0000 (13:50 -0700)]
Hadoop: Various changes to CephFaker; not completed.
Greg Farnum [Thu, 29 Oct 2009 22:06:12 +0000 (15:06 -0700)]
HadooP: CephFaker now properly sanitizes input filenames.
Greg Farnum [Thu, 29 Oct 2009 01:36:22 +0000 (18:36 -0700)]
Hadoop: Update constructor/initialize usage a bit
Greg Farnum [Wed, 28 Oct 2009 21:04:58 +0000 (14:04 -0700)]
Simplify CephInputStream so that it actually works
Greg Farnum [Tue, 27 Oct 2009 20:57:29 +0000 (13:57 -0700)]
Hadoop: Simplify CephOutputStream so that it actually works.
Greg Farnum [Tue, 27 Oct 2009 20:02:30 +0000 (13:02 -0700)]
Hadoop: Reorder a few things for better safety and fix compile bugs
Sage Weil [Mon, 2 Nov 2009 01:51:51 +0000 (17:51 -0800)]
crush: always return a value from crush_bucket_choose
Sage Weil [Thu, 29 Oct 2009 23:24:40 +0000 (16:24 -0700)]
todo
Sage Weil [Wed, 28 Oct 2009 22:32:07 +0000 (15:32 -0700)]
todo
Sage Weil [Wed, 28 Oct 2009 22:31:50 +0000 (15:31 -0700)]
Makefile: fix lib dependencies
libceph and librados should link libcrush. Users of
libceph|librados need not link libcrush.
Sage Weil [Wed, 28 Oct 2009 21:47:08 +0000 (14:47 -0700)]
makefile: don't link libm and libpthread with crush
Sage Weil [Wed, 28 Oct 2009 21:05:27 +0000 (14:05 -0700)]
debian: fix copyright to avoid lintian check
possible-gpl-code-linked-with-openssl
Sage Weil [Wed, 28 Oct 2009 20:16:34 +0000 (13:16 -0700)]
debian: fix -dbg packages
Sage Weil [Wed, 28 Oct 2009 19:13:48 +0000 (12:13 -0700)]
debian: warn on no args to build script
Sage Weil [Wed, 28 Oct 2009 19:08:54 +0000 (12:08 -0700)]
radosgw: fix man page names, include in package
Sage Weil [Wed, 28 Oct 2009 18:56:55 +0000 (11:56 -0700)]
debian: strip, put debug binaries in usr/lib/debug
Yehuda Sadeh [Wed, 28 Oct 2009 18:51:46 +0000 (11:51 -0700)]
rgw: man page for rgw_admin
Yehuda Sadeh [Wed, 28 Oct 2009 18:16:17 +0000 (11:16 -0700)]
rgw: radosgw man page continued
Sage Weil [Wed, 28 Oct 2009 18:06:36 +0000 (11:06 -0700)]
radosgw: rename binaries rgw -> radosgw
Sage Weil [Wed, 28 Oct 2009 18:03:11 +0000 (11:03 -0700)]
debian: remove rgw_aclparser from package
It's a unit test
Sage Weil [Wed, 28 Oct 2009 17:54:01 +0000 (10:54 -0700)]
rgw: initial man page
Sage Weil [Wed, 28 Oct 2009 17:48:39 +0000 (10:48 -0700)]
debian: override openssl warning on radosgw
Sage Weil [Wed, 28 Oct 2009 17:37:19 +0000 (10:37 -0700)]
debian: update package descriptions, sections
Sage Weil [Wed, 28 Oct 2009 17:26:35 +0000 (10:26 -0700)]
debian: make lib package versions match SONAMES
Sage Weil [Wed, 28 Oct 2009 17:13:52 +0000 (10:13 -0700)]
Makefile: make all lib versions 1:0:0, fix libcrush
Sage Weil [Wed, 28 Oct 2009 17:10:52 +0000 (10:10 -0700)]
debian: some lintian fixes
Note that I'm moving some library SONAME version backwards!
Otherwise we'd have to rename libceph to libceph1, etc. And
that's lame.
Sage Weil [Tue, 27 Oct 2009 18:46:38 +0000 (11:46 -0700)]
mount.ceph: only return INET addr when doing lookup
Greg Farnum [Mon, 26 Oct 2009 22:18:33 +0000 (15:18 -0700)]
mon: Move full OSD test logic around