]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
15 years agologger: fix warning
Sage Weil [Thu, 18 Feb 2010 17:57:15 +0000 (09:57 -0800)]
logger: fix warning

15 years agoworkqueue: behave when multiple threads call drain()
Sage Weil [Thu, 18 Feb 2010 05:47:18 +0000 (21:47 -0800)]
workqueue: behave when multiple threads call drain()

Use a counter, not a bool.

15 years agomds: add support for directory sticky bit
Sage Weil [Thu, 18 Feb 2010 05:24:50 +0000 (21:24 -0800)]
mds: add support for directory sticky bit

Take an rdlock on the directory authlock, so that we can reliably set the
new inode's gid if the directory mode has SGID bit set.

15 years agofilestore: only do btrfs_snap if btrfs
Sage Weil [Thu, 18 Feb 2010 05:11:30 +0000 (21:11 -0800)]
filestore: only do btrfs_snap if btrfs

15 years agoMerge commit 'origin/filestore' into unstable
Sage Weil [Wed, 17 Feb 2010 22:57:31 +0000 (14:57 -0800)]
Merge commit 'origin/filestore' into unstable

Conflicts:

src/os/FileStore.cc
src/os/FileStore.h

15 years agoupdate release checklist
Sage Weil [Wed, 17 Feb 2010 22:55:40 +0000 (14:55 -0800)]
update release checklist

15 years agov0.19 v0.19
Sage Weil [Wed, 17 Feb 2010 21:53:06 +0000 (13:53 -0800)]
v0.19

15 years agomon: disable 'osd setmap'
Sage Weil [Wed, 17 Feb 2010 17:18:16 +0000 (09:18 -0800)]
mon: disable 'osd setmap'

This is dangerous, since it doesn't preserve old pool ids or pool_max, and
will confuse osds and generally wreak havoc.

15 years agoosdmap: fix uninit var warning
Sage Weil [Wed, 17 Feb 2010 03:53:51 +0000 (19:53 -0800)]
osdmap: fix uninit var warning

Harmless, but this shuts it up.

15 years agomon: add 'auth export ]name]' to export a full or partial keyring
Sage Weil [Wed, 17 Feb 2010 00:37:59 +0000 (16:37 -0800)]
mon: add 'auth export ]name]' to export a full or partial keyring

15 years agoqa: fix snaptest1.sh
Sage Weil [Mon, 15 Feb 2010 23:28:02 +0000 (15:28 -0800)]
qa: fix snaptest1.sh

15 years agoosdmap: decode old osdmaps prior to pool_max stuff
Sage Weil [Tue, 16 Feb 2010 23:59:09 +0000 (15:59 -0800)]
osdmap: decode old osdmaps prior to pool_max stuff

15 years agoosdmap: get rid of useless max_pools
Sage Weil [Tue, 16 Feb 2010 23:49:16 +0000 (15:49 -0800)]
osdmap: get rid of useless max_pools

15 years agoosd: pool cleanups
Sage Weil [Tue, 16 Feb 2010 23:07:35 +0000 (15:07 -0800)]
osd: pool cleanups

missed this before:

 - no need to initalize in create_pending(), constructor does that
 - int32_t, not int
 - pool_max while we're at it
 - initialize pool_max in OSDMap constructor

15 years agotodo
Sage Weil [Tue, 16 Feb 2010 22:33:02 +0000 (14:33 -0800)]
todo

15 years agomds: ignore session RENEWCAPS if state not open|stale
Sage Weil [Tue, 16 Feb 2010 22:32:43 +0000 (14:32 -0800)]
mds: ignore session RENEWCAPS if state not open|stale

This avoids breakage where a renewcaps races with a session
being purged, for example.

15 years agoosdmap/mon: Be more defensive about highest_pool_num usage
Greg Farnum [Tue, 16 Feb 2010 22:15:12 +0000 (14:15 -0800)]
osdmap/mon: Be more defensive about highest_pool_num usage

15 years agorados tool: mkpool/rmpool commands now available
Greg Farnum [Tue, 16 Feb 2010 20:39:46 +0000 (12:39 -0800)]
rados tool: mkpool/rmpool commands now available

15 years agomon: can now delete pools via 'ceph osd pool delete foo'
Greg Farnum [Tue, 16 Feb 2010 17:22:32 +0000 (09:22 -0800)]
mon: can now delete pools via 'ceph osd pool delete foo'

15 years agorgw: actually delete pools when using rados!
Greg Farnum [Fri, 12 Feb 2010 22:54:56 +0000 (14:54 -0800)]
rgw: actually delete pools when using rados!

15 years agorados/objecter: can now delete pools!
Greg Farnum [Fri, 12 Feb 2010 22:54:37 +0000 (14:54 -0800)]
rados/objecter: can now delete pools!

15 years agomon/msg: MPoolOp can carry POOL_OP_DELETE; OSDMon puts pool in incre old_pools
Greg Farnum [Fri, 12 Feb 2010 22:25:57 +0000 (14:25 -0800)]
mon/msg: MPoolOp can carry POOL_OP_DELETE; OSDMon puts pool in incre old_pools

15 years agolibrados: init PoolCtx properly -- was always setting snap_seq to CEPH_NOSNAP
Greg Farnum [Fri, 12 Feb 2010 22:12:22 +0000 (14:12 -0800)]
librados: init PoolCtx properly -- was always setting snap_seq to CEPH_NOSNAP

15 years agoosd: Deal with pools being removed from OSDMap.
Greg Farnum [Fri, 12 Feb 2010 21:21:22 +0000 (13:21 -0800)]
osd: Deal with pools being removed from OSDMap.

This potentially has issues, since pools are not removed from the map
until after all the PGs are removed (which is threaded, not inline with
map delivery). But Sage thinks it's okay and the system keeps working
even if you delete a pool while benchmarking on it with rados.

15 years agoOSDMap: get_pg_pool now returns a pointer
Greg Farnum [Fri, 12 Feb 2010 00:57:23 +0000 (16:57 -0800)]
OSDMap: get_pg_pool now returns a pointer
This lets us return NULL if the pool isn't in the map, which is
needed functionality for pool deletion. Meanwhile, code which
expects the pool to exist will continue to cause a crash if it doesn't.

15 years agorados: fix seg fault on cleanup of a failed pool open
Greg Farnum [Tue, 16 Feb 2010 17:21:32 +0000 (09:21 -0800)]
rados: fix seg fault on cleanup of a failed pool open

15 years agomds: infer 'follows' in journal_dirty_inode on non-head inodes
Sage Weil [Mon, 15 Feb 2010 21:47:41 +0000 (13:47 -0800)]
mds: infer 'follows' in journal_dirty_inode on non-head inodes

There are lots of callers to journal_dirty_inode that may
unwittingly be dealing with a non-head inode (e.g.
check_file_max).  If the provided inode is snapped, infer an
appropriate follows values so as not to cow_inode() again.

15 years agomds: clear cap->issued on flushsnap
Sage Weil [Mon, 15 Feb 2010 21:27:01 +0000 (13:27 -0800)]
mds: clear cap->issued on flushsnap

This allows _do_cap_update to clear out the client_range.

Kill (now) unused/unnecessary 'wanted' arg to _do_cap_update.

Also delay cap removal until after _do_cap_update (whcih takes
a Capability*).  This probably needs further cleanup.

15 years agomds: don't croak on null dentries in cache during reconnect/rejoin
Sage Weil [Mon, 15 Feb 2010 19:40:20 +0000 (11:40 -0800)]
mds: don't croak on null dentries in cache during reconnect/rejoin

They're created when we replay unlink events from the log.

15 years agoobjectcacher: use trimtrunc read/write ops
Yehuda Sadeh [Fri, 12 Feb 2010 22:32:11 +0000 (14:32 -0800)]
objectcacher: use trimtrunc read/write ops

15 years agoosdc: clean up some mess
Yehuda Sadeh [Fri, 12 Feb 2010 22:23:57 +0000 (14:23 -0800)]
osdc: clean up some mess

15 years agoobjecter: add read_trunc, write_trunc
Yehuda Sadeh [Fri, 12 Feb 2010 22:05:42 +0000 (14:05 -0800)]
objecter: add read_trunc, write_trunc

15 years agomkmonfs: rm -rf, so that we kill 0600 admin_keyring.bin
Sage Weil [Fri, 12 Feb 2010 22:54:01 +0000 (14:54 -0800)]
mkmonfs: rm -rf, so that we kill 0600 admin_keyring.bin

15 years agoosd: fix recovery requeue race
Sage Weil [Fri, 12 Feb 2010 22:45:02 +0000 (14:45 -0800)]
osd: fix recovery requeue race

If a recovery op finished right as another recovery op was
begin started, we could get into start_recovery_ops() and get
max = 0 and not start anything.  Since the PG wasn't being
requeued for later, it would never recover.  So, requeue if we
race and get max == 0.

15 years agoinit-ceph: print 'already started' instead of failing to start
Sage Weil [Fri, 12 Feb 2010 22:20:02 +0000 (14:20 -0800)]
init-ceph: print 'already started' instead of failing to start

15 years agomsgr: more conservative locking, thread join asserts
Sage Weil [Fri, 12 Feb 2010 21:38:38 +0000 (13:38 -0800)]
msgr: more conservative locking, thread join asserts

We caught a bunch of crashes like this:

10.02.11 17:01:01.600660 7f87070c3950 -- 10.3.14.134:6800/8203 >> 10.3.14.130:6800/18914 pipe(0x7fc2be2cebe0 sd=36 pgs=2409 cs=1 l=0).do_sendmsg error Broken pipe
10.02.11 17:01:01.600700 7f87070c3950 -- 10.3.14.134:6800/8203 >> 10.3.14.130:6800/18914 pipe(0x7fc2be2cebe0 sd=36 pgs=2409 cs=1 l=0).writer error sending 0x7fc27da1c570, 32: Broken pipe
10.02.11 17:01:01.600796 7f87070c3950 -- 10.3.14.134:6800/8203 >> 10.3.14.130:6800/18914 pipe(0x7fc2be2cebe0 sd=-1 pgs=2409 cs=1 l=0).fault initiating reconnect
...
./common/Thread.h: In function 'int Thread::join(void**)':
./common/Thread.h:66: FAILED assert(0)
 1: (Thread::join(void**)+0x73) [0x64fcd3]
 2: (SimpleMessenger::Pipe::join_reader()+0x68) [0x6555a2]
 3: (SimpleMessenger::Pipe::connect()+0xf5) [0x645be9]
 4: (SimpleMessenger::Pipe::writer()+0x157) [0x64793d]
 5: (SimpleMessenger::Pipe::Writer::entry()+0x19) [0x63e107]
 6: (Thread::_entry_func(void*)+0x20) [0x64e816]
 7: /lib/libpthread.so.0 [0x7fc2c3bbdfc7]
 8: (clone()+0x6d) [0x7fc2c2e005ad]

that look a bit like multiple procs were racing into
join_reader().  Add an assert to catch that if it happens again,
and also wrap thread starts in pipe_lock to ensure we keep the
_running flags in sync with reality.  Add in a few other
sanity checks too.

15 years agomon: note mds beacon times more carefully
Sage Weil [Fri, 12 Feb 2010 21:35:57 +0000 (13:35 -0800)]
mon: note mds beacon times more carefully

We need to update the beacon timestamp even when we are updating
the mds state.  Otherwise we can get caught in a busy loop
between marking an mds laggy and !laggy because the beacon stamp
never updates.

So even if we are updating, and the reply will be slow, update
our timestamp, so we don't mark the mds laggy.

15 years agoosd: bail out of interval loop completely
Sage Weil [Fri, 12 Feb 2010 21:27:49 +0000 (13:27 -0800)]
osd: bail out of interval loop completely

We're going backwards, so once this test fails, it always fails,
and we can break instead of continue.  Any skipped intervals will
be pruned shortly anyway.

15 years agoosd: always update up_thru if pg changes before going active
Sage Weil [Fri, 12 Feb 2010 21:26:19 +0000 (13:26 -0800)]
osd: always update up_thru if pg changes before going active

We already required this if prior PG members were down, so this
affected the 'failure' case.  We now also require it for
non-failure PG changes (expansion, migration).

This fixes our maybe_went_rw calculation for prior PG intervals,
which is based on up_thru.  If maybe_went_rw is false when the
pg actually went rw, we can lose (and have lost) data.  But it is
not practical to calculate without up_thru being consistently
updated, because determining whether a pg would have been able to
go active depends on knowing last_epoch_started at a previous
point in time, which then determines how many prior intervals
may have been considered, which in turn determines whether
up_thru would have been updated, etc.  Much simpler to update it
all the time.

This should not impose a significantly greater cost, since we
already need it for the failure case.  And in general the
migration/expansion/whatever case is no more common nor critical
than the failure case.

15 years agoosd: simplify, and version, pg attrs
Sage Weil [Fri, 12 Feb 2010 20:52:18 +0000 (12:52 -0800)]
osd: simplify, and version, pg attrs

15 years agoosd: remove some dead code from build_prior
Sage Weil [Fri, 12 Feb 2010 20:45:15 +0000 (12:45 -0800)]
osd: remove some dead code from build_prior

Not sure what any_up_now used to be for, but it's not used now.

15 years agoosd: fail startup if store is in use (before we fork)
Sage Weil [Fri, 12 Feb 2010 19:20:30 +0000 (11:20 -0800)]
osd: fail startup if store is in use (before we fork)

15 years agoosd: set heartbeat addr properly
Sage Weil [Fri, 12 Feb 2010 19:07:20 +0000 (11:07 -0800)]
osd: set heartbeat addr properly

This was broken by the osd startup change in 8538efc

15 years agoosd: fix memset transposed params
Sage Weil [Thu, 11 Feb 2010 23:41:09 +0000 (15:41 -0800)]
osd: fix memset transposed params

15 years agoosd: don't block on mon negotiation on startup
Sage Weil [Fri, 12 Feb 2010 00:18:54 +0000 (16:18 -0800)]
osd: don't block on mon negotiation on startup

That means we don't check for monmap vs ondisk fsid checks and
such.  They're mostly useless anyway.

15 years agomkcephfs: fix up permissions, ownership on temp keyrings
Sage Weil [Fri, 12 Feb 2010 00:10:26 +0000 (16:10 -0800)]
mkcephfs: fix up permissions, ownership on temp keyrings

15 years agoceph_common: sudo su, not su
Sage Weil [Thu, 11 Feb 2010 23:37:27 +0000 (15:37 -0800)]
ceph_common: sudo su, not su

15 years agomkcephfs: always clobber, since we don't support not clobbering anyway
Sage Weil [Thu, 11 Feb 2010 23:32:45 +0000 (15:32 -0800)]
mkcephfs: always clobber, since we don't support not clobbering anyway

15 years agomkmonfs: require '-c conf' to avoid accidents; stash admin keyring
Sage Weil [Thu, 11 Feb 2010 23:31:40 +0000 (15:31 -0800)]
mkmonfs: require '-c conf' to avoid accidents; stash admin keyring

15 years agocauthtool: mode 0600 for keyrings
Sage Weil [Thu, 11 Feb 2010 23:31:14 +0000 (15:31 -0800)]
cauthtool: mode 0600 for keyrings

15 years agomkcephfs: put admin keyring in mon_data, for safe keeping
Sage Weil [Thu, 11 Feb 2010 23:21:27 +0000 (15:21 -0800)]
mkcephfs: put admin keyring in mon_data, for safe keeping

15 years agomkcephfs: --clobber, not --clobber_old_data
Sage Weil [Thu, 11 Feb 2010 23:21:14 +0000 (15:21 -0800)]
mkcephfs: --clobber, not --clobber_old_data

15 years agoqa: +x snaptest1.sh
Sage Weil [Thu, 11 Feb 2010 21:32:42 +0000 (13:32 -0800)]
qa: +x snaptest1.sh

15 years agoobjectcacher: use ObjectSet container instead of inodeno_t hash_maps
Sage Weil [Thu, 11 Feb 2010 23:11:23 +0000 (15:11 -0800)]
objectcacher: use ObjectSet container instead of inodeno_t hash_maps

Caller provides an ObjectSet* to group objects into.
Later we can put other info here, like truncate_seq and
truncate_size.

15 years agocephx: adjust auth ticket renewal encoding a bit
Sage Weil [Thu, 11 Feb 2010 19:39:06 +0000 (11:39 -0800)]
cephx: adjust auth ticket renewal encoding a bit

This simplifies the code slightly, esp in the kclient.

15 years agoqa: fix up runallonce.sh
Sage Weil [Thu, 11 Feb 2010 18:36:45 +0000 (10:36 -0800)]
qa: fix up runallonce.sh

15 years agodebian: fix init script hackery
Sage Weil [Thu, 11 Feb 2010 18:36:38 +0000 (10:36 -0800)]
debian: fix init script hackery

Copy src/init-ceph to debian/ceph.init _after_ we make, so that
the autoconf paths are substituted in properly.

15 years agotodo
Sage Weil [Thu, 11 Feb 2010 18:03:06 +0000 (10:03 -0800)]
todo

15 years agomon: print caps to debug log
Sage Weil [Thu, 11 Feb 2010 17:25:59 +0000 (09:25 -0800)]
mon: print caps to debug log

15 years agocephx: nicer debug output in service handler
Sage Weil [Thu, 11 Feb 2010 17:25:15 +0000 (09:25 -0800)]
cephx: nicer debug output in service handler

15 years agocephx: use 'next' key for ticketes when 'current' is expired
Sage Weil [Thu, 11 Feb 2010 17:24:42 +0000 (09:24 -0800)]
cephx: use 'next' key for ticketes when 'current' is expired

When generating tickets for clients, use next key if the current
is expired.  That ensures they will renew before their ticket
times out.

15 years agocsyn: print something on mount failure
Sage Weil [Thu, 11 Feb 2010 17:06:18 +0000 (09:06 -0800)]
csyn: print something on mount failure

15 years agocephx: return expires service keys from rotatingkeyring
Sage Weil [Thu, 11 Feb 2010 17:04:25 +0000 (09:04 -0800)]
cephx: return expires service keys from rotatingkeyring

Otherwise there's no point in keeping around old service tickets.

To prevent really old tickets from working, we need to rotate
keys.  We want slightly old ones to still work, though.. that's
why we keep 3.

15 years agocephx: fix negotiation on reconnect
Sage Weil [Thu, 11 Feb 2010 17:00:10 +0000 (09:00 -0800)]
cephx: fix negotiation on reconnect

Don't send another request after initial handshake if we don't
need an auth ticket.

15 years agomonclient: renew service tickets a bit after the current expires
Sage Weil [Thu, 11 Feb 2010 15:54:12 +0000 (07:54 -0800)]
monclient: renew service tickets a bit after the current expires

This ensures the monitor will actually ahve generated a newer
one to give us, avoiding a busy loop.

15 years agoosd: don't update object size if didn't write anything
Yehuda Sadeh [Thu, 11 Feb 2010 01:17:45 +0000 (17:17 -0800)]
osd: don't update object size if didn't write anything

15 years agocmon: suggest mkcephfs when 'whoami' not in monfs
Sage Weil [Wed, 10 Feb 2010 22:51:18 +0000 (14:51 -0800)]
cmon: suggest mkcephfs when 'whoami' not in monfs

15 years agocephx: fix up key rotation
Sage Weil [Wed, 10 Feb 2010 22:51:08 +0000 (14:51 -0800)]
cephx: fix up key rotation

15 years agocephx: nicer keyserver debug output
Sage Weil [Wed, 10 Feb 2010 19:57:04 +0000 (11:57 -0800)]
cephx: nicer keyserver debug output

15 years agoosd: write op updates trancation sequence if not already set
Yehuda Sadeh [Wed, 10 Feb 2010 22:34:09 +0000 (14:34 -0800)]
osd: write op updates trancation sequence if not already set

15 years agomsgr: Update 'documentation'.
Greg Farnum [Wed, 10 Feb 2010 20:02:42 +0000 (12:02 -0800)]
msgr: Update 'documentation'.

15 years agoinit-ceph, mkcephfs: fix ETCDIR
Sage Weil [Wed, 10 Feb 2010 19:33:23 +0000 (11:33 -0800)]
init-ceph, mkcephfs: fix ETCDIR

15 years agomds: behave when we pipeline session updates to journal
Sage Weil [Tue, 9 Feb 2010 18:03:12 +0000 (10:03 -0800)]
mds: behave when we pipeline session updates to journal

15 years agomsg: union sockaddr_storage to hush strict aliasing warnings and clean up code
Greg Farnum [Wed, 10 Feb 2010 00:26:18 +0000 (16:26 -0800)]
msg: union sockaddr_storage to hush strict aliasing warnings and clean up code

15 years agoinit-ceph: Required-start: $remote_fs
Sage Weil [Tue, 9 Feb 2010 18:27:08 +0000 (10:27 -0800)]
init-ceph: Required-start: $remote_fs

This ensures /usr is mounted before ceph daemons start.  It seems like
this may be problematic for hosts that act as both servers and clients,
but nfs-kernel-server does the same, so whatev!

15 years agodebian: do not include var/run/ceph in package; mkdir -p dirname unconditionally
Sage Weil [Tue, 9 Feb 2010 18:20:20 +0000 (10:20 -0800)]
debian: do not include var/run/ceph in package; mkdir -p dirname unconditionally

15 years agorados man page; include rados in ceph package
Sage Weil [Tue, 9 Feb 2010 18:19:57 +0000 (10:19 -0800)]
rados man page; include rados in ceph package

15 years agodebian: include cauthtool
Sage Weil [Tue, 9 Feb 2010 18:14:13 +0000 (10:14 -0800)]
debian: include cauthtool

15 years agorename authtool -> cauthtool
Sage Weil [Tue, 9 Feb 2010 18:14:04 +0000 (10:14 -0800)]
rename authtool -> cauthtool

15 years agomds: behave when we pipeline session updates to journal
Sage Weil [Tue, 9 Feb 2010 18:03:12 +0000 (10:03 -0800)]
mds: behave when we pipeline session updates to journal

15 years agoworkqueue: make drain() wait for processing AND queue
Sage Weil [Tue, 9 Feb 2010 18:02:41 +0000 (10:02 -0800)]
workqueue: make drain() wait for processing AND queue

15 years agomutex: fix file mode
Sage Weil [Tue, 9 Feb 2010 17:58:54 +0000 (09:58 -0800)]
mutex: fix file mode

15 years agoosd: take ondisk_read_lock if pushing object to peer
Sage Weil [Tue, 9 Feb 2010 17:03:51 +0000 (09:03 -0800)]
osd: take ondisk_read_lock if pushing object to peer

15 years agofilestore: return 0 for no-op transaction
Sage Weil [Wed, 3 Feb 2010 19:11:17 +0000 (11:11 -0800)]
filestore: return 0 for no-op transaction

15 years agodebian: fixups to build inside pbuilder
Sage Weil [Tue, 9 Feb 2010 16:24:57 +0000 (08:24 -0800)]
debian: fixups to build inside pbuilder

15 years agoceph: fix manpages so they are only installed once
Josef Bacik [Tue, 9 Feb 2010 16:24:23 +0000 (08:24 -0800)]
ceph: fix manpages so they are only installed once

While creating a spec file for CEPH, rpmbuild was complaining because make
install was copying the manpages in, and then copying them in again.  This is
because man_MANS and dist_man_MANS are supposed to be two seperate lists that do
not overlap.  So make install would install all the man pages in the man_MANS
list and the dist_man_MANS list.  This patch kills the dist_man_MANS thing to
keep this from happening.  This made rpmbuild happy, which makes me happy :).
Thanks,

Signed-off-by: Josef Bacik <josef@redhat.com>
15 years agoMerge branch 'unstable' into filestore
Sage Weil [Tue, 9 Feb 2010 16:15:31 +0000 (08:15 -0800)]
Merge branch 'unstable' into filestore

15 years agoosd: count objects degraded due to degraded pg
Sage Weil [Tue, 9 Feb 2010 16:08:12 +0000 (08:08 -0800)]
osd: count objects degraded due to degraded pg

15 years agoosd: prevent do_waiters() while _dispatch() is running
Sage Weil [Tue, 9 Feb 2010 16:06:35 +0000 (08:06 -0800)]
osd: prevent do_waiters() while _dispatch() is running

Fixes race between handle_osd_map and tick() requeuing ops.

15 years agoceph: wait for monmap
Sage Weil [Mon, 8 Feb 2010 19:15:03 +0000 (11:15 -0800)]
ceph: wait for monmap

15 years agoosd: btrfs_snap by default
Sage Weil [Tue, 9 Feb 2010 16:07:47 +0000 (08:07 -0800)]
osd: btrfs_snap by default

15 years agoosd: carry ondisk_read_lock if prepare_transaction may_read()
Sage Weil [Mon, 8 Feb 2010 22:59:33 +0000 (14:59 -0800)]
osd: carry ondisk_read_lock if prepare_transaction may_read()

15 years agoosd: order rmdir in remove_collection after deleting dir contents
Sage Weil [Mon, 8 Feb 2010 19:57:52 +0000 (11:57 -0800)]
osd: order rmdir in remove_collection after deleting dir contents

15 years agofilestore: fix old clobbering of commit_op_seq
Sage Weil [Mon, 8 Feb 2010 19:32:26 +0000 (11:32 -0800)]
filestore: fix old clobbering of commit_op_seq

Update only at commit.  And add a newline.

15 years agoosd: fix lock inversion with ondisk_write_unlock
Sage Weil [Mon, 8 Feb 2010 19:29:25 +0000 (11:29 -0800)]
osd: fix lock inversion with ondisk_write_unlock

Drop write lock before taking pg lock.

15 years agoosd: store local osd magic, whoami, and other static bits outside of ObjectStore
Sage Weil [Tue, 9 Feb 2010 04:29:09 +0000 (20:29 -0800)]
osd: store local osd magic, whoami, and other static bits outside of ObjectStore

These values are immutable, and we also want to look at them prior to
forking and 'mounting' the ObjectStore.  Just keep them in separate files
for simplicity.

This avoids the double filestore startup cost paid on cosd startup.

15 years agoosd: print truncate_size signed, and only print at all if _seq > 0
Sage Weil [Mon, 8 Feb 2010 20:47:17 +0000 (12:47 -0800)]
osd: print truncate_size signed, and only print at all if _seq > 0

15 years agodebian: updated debian build scripts, changelog
Sage Weil [Mon, 8 Feb 2010 18:27:27 +0000 (10:27 -0800)]
debian: updated debian build scripts, changelog

15 years agomkcephfs: warn on missing keyring for mds, osd
Sage Weil [Mon, 8 Feb 2010 17:57:17 +0000 (09:57 -0800)]
mkcephfs: warn on missing keyring for mds, osd

15 years agoauthtool: add -a/--add-key command
Sage Weil [Mon, 8 Feb 2010 17:57:05 +0000 (09:57 -0800)]
authtool: add -a/--add-key command