]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
15 years agomds: check myin, not stray, in rejoin_send_acks
Sage Weil [Tue, 23 Mar 2010 18:46:49 +0000 (11:46 -0700)]
mds: check myin, not stray, in rejoin_send_acks

15 years agotodo mds bug
Sage Weil [Tue, 23 Mar 2010 23:47:59 +0000 (16:47 -0700)]
todo mds bug

15 years agomds: fix up client session importing
Sage Weil [Tue, 23 Mar 2010 21:54:13 +0000 (14:54 -0700)]
mds: fix up client session importing

Keep import counter for each session, for overlapping imports.

Prevent a session close or kill during an import.

15 years agomds: importing, ugh
Sage Weil [Tue, 23 Mar 2010 20:39:38 +0000 (13:39 -0700)]
mds: importing, ugh

15 years agomds: clean up kill_session()
Sage Weil [Tue, 23 Mar 2010 20:32:58 +0000 (13:32 -0700)]
mds: clean up kill_session()

15 years agomds: possible session 'importing' state
Sage Weil [Tue, 23 Mar 2010 20:20:12 +0000 (13:20 -0700)]
mds: possible session 'importing' state

15 years agomds: drop purge step when closing client sessions
Sage Weil [Tue, 23 Mar 2010 20:15:58 +0000 (13:15 -0700)]
mds: drop purge step when closing client sessions

The purge step when closing client sessions is pointless.  If the
MDS is alive, we know which inos were used and which weren't.  It
is only the _journal_ that doesn't necessarily know which have
been recently allocated: any cleanup needs to happen on journal
replay during mds recovery.

Also clean up session states some more.

15 years agomds: combine new, closed states; few small fixes
Sage Weil [Tue, 23 Mar 2010 17:26:54 +0000 (10:26 -0700)]
mds: combine new, closed states; few small fixes

Still need to audit all state changes.

15 years agomds: style fixes (from cppcheck)
Martin Ettl [Mon, 22 Mar 2010 20:50:30 +0000 (13:50 -0700)]
mds: style fixes (from cppcheck)

15 years agoosd: warn on no osd journal
Sage Weil [Mon, 22 Mar 2010 20:44:44 +0000 (13:44 -0700)]
osd: warn on no osd journal

15 years agomds: don't kick clients if we've been laggy ourselves
Sage Weil [Mon, 22 Mar 2010 20:39:40 +0000 (13:39 -0700)]
mds: don't kick clients if we've been laggy ourselves

15 years agomds: no early complete from scatter_nudge after partial work
Sage Weil [Mon, 22 Mar 2010 19:08:25 +0000 (12:08 -0700)]
mds: no early complete from scatter_nudge after partial work

Do not complete the Context if we only accomplish partial work.
Instead, keep going until we block.

15 years agotodo fixed some bugs
Sage Weil [Thu, 18 Mar 2010 23:02:37 +0000 (16:02 -0700)]
todo fixed some bugs

15 years agomsgr: no more forward_message()
Sage Weil [Mon, 22 Mar 2010 17:18:04 +0000 (10:18 -0700)]
msgr: no more forward_message()

15 years agomds: re-send, do not forward, mds messages
Sage Weil [Mon, 22 Mar 2010 16:14:36 +0000 (09:14 -0700)]
mds: re-send, do not forward, mds messages

15 years agomds: encode source mds in MDirUpdate
Sage Weil [Mon, 22 Mar 2010 16:12:10 +0000 (09:12 -0700)]
mds: encode source mds in MDirUpdate

Not that it's actually used, but just in case.

15 years agomds: encode source mds in MExportDirDiscover explicitly
Sage Weil [Mon, 22 Mar 2010 16:09:21 +0000 (09:09 -0700)]
mds: encode source mds in MExportDirDiscover explicitly

This removes any dependency on the message 'source', which will
let us remove the forward hackery.

15 years agomds: rev mds internal protocol
Sage Weil [Mon, 22 Mar 2010 16:15:25 +0000 (09:15 -0700)]
mds: rev mds internal protocol

We're changing the way cluster-internal messages are forward

15 years agomon: Fix resend_routed_requests.
Greg Farnum [Mon, 22 Mar 2010 18:04:33 +0000 (11:04 -0700)]
mon: Fix resend_routed_requests.
Stuff was left over from when forwards came in as a standard
PaxosServiceMessage, which is now removed.

15 years agomon: another forwarding fix for resend_routed_requests
Greg Farnum [Mon, 22 Mar 2010 17:23:45 +0000 (10:23 -0700)]
mon: another forwarding fix for resend_routed_requests

15 years agomon: Forwarding fixes.
Greg Farnum [Mon, 22 Mar 2010 17:15:21 +0000 (10:15 -0700)]
mon: Forwarding fixes.

forward_request_leader now uses messenger->send_message because it's created
a new message to forward.
resend_routed_requests properly decodes forwards to an MForward* rather than
a PaxosServiceMessage*.

15 years agomsg: Remove dead code MSG_OSD_IN/OUT
Greg Farnum [Fri, 19 Mar 2010 23:30:01 +0000 (16:30 -0700)]
msg: Remove dead code MSG_OSD_IN/OUT

15 years agomon: x has little meaning for a mon, let's not confuse things for pool ops
Greg Farnum [Thu, 18 Mar 2010 21:39:21 +0000 (14:39 -0700)]
mon: x has little meaning for a mon, let's not confuse things for pool ops

15 years agomon: use our standard indicator for locked/unlocked in ms_dispatch:
Greg Farnum [Thu, 18 Mar 2010 21:26:08 +0000 (14:26 -0700)]
mon: use our standard indicator for locked/unlocked in ms_dispatch:
ms_dispatch locks and calls _ms_dispatch.

15 years agoobjecter: don't lose reply codes when we wait_for_new_map
Greg Farnum [Thu, 18 Mar 2010 21:15:47 +0000 (14:15 -0700)]
objecter: don't lose reply codes when we wait_for_new_map

15 years agorados: add undocumented option to specify auid when making pools
Greg Farnum [Thu, 18 Mar 2010 18:47:00 +0000 (11:47 -0700)]
rados: add undocumented option to specify auid when making pools

15 years agomon: msg: Better output/debugging
Greg Farnum [Thu, 18 Mar 2010 18:46:37 +0000 (11:46 -0700)]
mon: msg: Better output/debugging

15 years agoobjecter: always fill in auid
Greg Farnum [Thu, 18 Mar 2010 17:50:59 +0000 (10:50 -0700)]
objecter: always fill in auid

15 years agomsg: MPoolOp now encodes its auid, prints more.
Greg Farnum [Thu, 18 Mar 2010 17:50:30 +0000 (10:50 -0700)]
msg: MPoolOp now encodes its auid, prints more.

15 years agomon: handle_subscribe now uses check_privileges instead of get_caps.
Greg Farnum [Thu, 18 Mar 2010 16:07:06 +0000 (09:07 -0700)]
mon: handle_subscribe now uses check_privileges instead of get_caps.

15 years agomon: Pretty sure MDS BEACON messages should only come from MDSes
Greg Farnum [Wed, 17 Mar 2010 22:42:13 +0000 (15:42 -0700)]
mon: Pretty sure MDS BEACON messages should only come from MDSes

15 years agoosdc: fix truncation of multiple extents of the same object
Yehuda Sadeh [Thu, 18 Mar 2010 21:35:24 +0000 (14:35 -0700)]
osdc: fix truncation of multiple extents of the same object

15 years agomds: fix resolve stage
Sage Weil [Thu, 18 Mar 2010 20:38:00 +0000 (13:38 -0700)]
mds: fix resolve stage

This was recently broken by b818f5bc.

15 years agomds: drop gather if it's empty
Sage Weil [Thu, 18 Mar 2010 04:47:00 +0000 (21:47 -0700)]
mds: drop gather if it's empty

This can happen from scatter_nudge, which may add a sub and then
complete it, emptying out the C_Gather.

15 years agocontext: don't complete C_Gather until finisher is set
Sage Weil [Thu, 18 Mar 2010 04:46:00 +0000 (21:46 -0700)]
context: don't complete C_Gather until finisher is set

We often create a C_Gather, add a bunch of subs, and set a
finisher at the end.  Occasionally we create a sub and it gets
finished immediately, in which case we don't want the gather to
get finished and deleted already.  So don't 'complete' the gather
until it's by activated by setting the finisher.

15 years agoinit-ceph: do already running check early to avoid extra work
Sage Weil [Wed, 17 Mar 2010 16:46:02 +0000 (09:46 -0700)]
init-ceph: do already running check early to avoid extra work

15 years agotodo
Sage Weil [Thu, 18 Mar 2010 17:20:34 +0000 (10:20 -0700)]
todo

15 years agomds: session is always defined in handle_client_reconnect
Sage Weil [Thu, 18 Mar 2010 17:20:10 +0000 (10:20 -0700)]
mds: session is always defined in handle_client_reconnect

15 years agoqa: make pjd test behave when run twice in same dir
Sage Weil [Thu, 18 Mar 2010 00:01:19 +0000 (17:01 -0700)]
qa: make pjd test behave when run twice in same dir

15 years agomds: acknowledge reconnect success with a session open message
Sage Weil [Wed, 17 Mar 2010 23:17:59 +0000 (16:17 -0700)]
mds: acknowledge reconnect success with a session open message

15 years agoqa: add fsx workunit
Sage Weil [Wed, 17 Mar 2010 18:49:16 +0000 (11:49 -0700)]
qa: add fsx workunit

15 years agomon: msg: better output
Greg Farnum [Wed, 17 Mar 2010 21:52:50 +0000 (14:52 -0700)]
mon: msg: better output

15 years agomon: don't use get_priv() without put!
Greg Farnum [Wed, 17 Mar 2010 18:57:18 +0000 (11:57 -0700)]
mon: don't use get_priv() without put!

15 years agomon: forwarded messages should use the same connection as their carrier message
Greg Farnum [Wed, 17 Mar 2010 17:57:24 +0000 (10:57 -0700)]
mon: forwarded messages should use the same connection as their carrier message

15 years agomon: when possible, fill PaxosServiceMap::caps before exiting ms_dispatch
Greg Farnum [Wed, 17 Mar 2010 17:56:42 +0000 (10:56 -0700)]
mon: when possible, fill PaxosServiceMap::caps before exiting ms_dispatch

15 years agomon: let ms_dispatch be non-locking for forwards
Greg Farnum [Wed, 17 Mar 2010 16:08:21 +0000 (09:08 -0700)]
mon: let ms_dispatch be non-locking for forwards

15 years agomon: Encapsulate forwarded PaxosServiceMessages into MForward with their caps
Greg Farnum [Tue, 16 Mar 2010 21:48:31 +0000 (14:48 -0700)]
mon: Encapsulate forwarded PaxosServiceMessages into MForward with their caps

15 years agomon: Use PaxosServiceMessage::caps instead of Session::caps where applicable
Greg Farnum [Wed, 17 Mar 2010 16:03:45 +0000 (09:03 -0700)]
mon: Use PaxosServiceMessage::caps instead of Session::caps where applicable

15 years agomsg: Add a new MForward message for encapsulating client caps and messages
Greg Farnum [Tue, 16 Mar 2010 19:53:44 +0000 (12:53 -0700)]
msg: Add a new MForward message for encapsulating client caps and messages

15 years agoqa: add loopall.sh
Sage Weil [Wed, 17 Mar 2010 18:13:53 +0000 (11:13 -0700)]
qa: add loopall.sh

15 years agomds: fix up root/base inode special cases
Sage Weil [Wed, 17 Mar 2010 18:08:21 +0000 (11:08 -0700)]
mds: fix up root/base inode special cases

15 years agotodo: more kclient bugs
Sage Weil [Wed, 17 Mar 2010 17:45:03 +0000 (10:45 -0700)]
todo: more kclient bugs

15 years agoqa: runallonce.sh each workunit in a clean directory
Sage Weil [Tue, 16 Mar 2010 22:48:35 +0000 (15:48 -0700)]
qa: runallonce.sh each workunit in a clean directory

15 years agofilestore: fix CLONE_RANGE detection
Sage Weil [Tue, 16 Mar 2010 17:53:45 +0000 (10:53 -0700)]
filestore: fix CLONE_RANGE detection

15 years agotodo kclient osd_client bug
Sage Weil [Tue, 16 Mar 2010 21:36:04 +0000 (14:36 -0700)]
todo kclient osd_client bug

15 years agomds: fix SimpleLock::try_clear_more()
Sage Weil [Tue, 16 Mar 2010 21:28:05 +0000 (14:28 -0700)]
mds: fix SimpleLock::try_clear_more()

We were dropping gather state on the floor, which resulted in
general confusion and errors like this

10.03.16 14:17:17.622280 mds0.locker handle_simple_lock lock(a=lockack dn 1000000019c/NEWS1_1B.PRN snap head) on (dn xlock x=1 by 0x307c050) [dentry #1/clients/client2/~dmtmp/WORDPRO/NEWS1_1B.PRN [2,head] auth{1=1} (dn xlock x=1 by 0x307c050) v=90 inode=0x7f2fe90a7980 | nref=5 0x7f2fe0349b80]
mds/Locker.cc: In function 'void Locker::handle_simple_lock(SimpleLock*, MLock*)':
mds/Locker.cc:2424: FAILED assert(lock->get_state() == 7 || lock->get_state() == 12)
 1: (Locker::handle_simple_lock(SimpleLock*, MLock*)+0x374) [0x8607bc]
 2: (Locker::handle_lock(MLock*)+0x18b) [0x861b91]
 3: (Locker::dispatch(Message*)+0x41) [0x86470b]
 4: (MDS::_dispatch(Message*)+0x1b42) [0x72ce68]
 5: (MDS::ms_dispatch(Message*)+0x2f) [0x72e1e9]
 6: (Messenger::ms_deliver_dispatch(Message*)+0x55) [0x72086b]
 7: (SimpleMessenger::dispatch_entry()+0x4f4) [0x70d50e]
 8: (SimpleMessenger::DispatchThread::entry()+0x29) [0x7095bd]
 9: (Thread::_entry_func(void*)+0x20) [0x71a9e1]
 10: /lib/libpthread.so.0 [0x7f2fe8d6573a]
 11: (clone()+0x6d) [0x7f2fe7f906dd]
 NOTE: a copy of the executable, or `objdump -rdS <executable>` is needed to interpret this.

15 years agomds: fix add_replica_dir to use is_base() helper for adjusting subtree auth
Sage Weil [Tue, 16 Mar 2010 20:58:03 +0000 (13:58 -0700)]
mds: fix add_replica_dir to use is_base() helper for adjusting subtree auth

15 years agomds: fix SimpleLock state encode/decode
Sage Weil [Tue, 16 Mar 2010 19:51:58 +0000 (12:51 -0700)]
mds: fix SimpleLock state encode/decode

This was broken when we changed the size of SimpleLock::state
to __u16.

15 years agoMerge branch 'unstable' into mds
Sage Weil [Tue, 16 Mar 2010 19:39:17 +0000 (12:39 -0700)]
Merge branch 'unstable' into mds

15 years agomds: remove unlinked metadata after replay
Sage Weil [Tue, 16 Mar 2010 19:35:28 +0000 (12:35 -0700)]
mds: remove unlinked metadata after replay

We can get unlink metadata after replay:

 create some auth metadata (possibly a whole tree)
 export to another mds
 other mds deletes it
 reimport tree, original link to root is broken by EImportStart
-> entire tree is unlinked

Find any unlinked metadata (that's not a base inode) and remove
it (recursively) after journal replay.

15 years agomds: do not add null dentry to frozen dir
Sage Weil [Tue, 16 Mar 2010 19:14:22 +0000 (12:14 -0700)]
mds: do not add null dentry to frozen dir

Otherwise we get confused when we unfreeze:

mds/mdstypes.h:1193: FAILED assert(ref_set.count(by) > 0)
 1: (MDSCacheObject::bad_put(int)+0x3e) [0x79acfc]
 2: (MDSCacheObject::put(int)+0x5a) [0x79e332]
 3: (CDentry::finish_export()+0x52) [0x8874ba]
 4: (Migrator::finish_export_dir(CDir*, std::list<Context*, std::allocator<Context*> >&, utime_t)+0x1a4) [0x8751fc]
 5: (Migrator::finish_export_dir(CDir*, std::list<Context*, std::allocator<Context*> >&, utime_t)+0x243) [0x87529b]

15 years agomon: declare class MonCaps in PaxosServiceMessage
Sage Weil [Tue, 16 Mar 2010 18:41:50 +0000 (11:41 -0700)]
mon: declare class MonCaps in PaxosServiceMessage

15 years agoosd: do no index reqid for CLONE ops (or BACKLOG ops)
Sage Weil [Tue, 16 Mar 2010 17:11:21 +0000 (10:11 -0700)]
osd: do no index reqid for CLONE ops (or BACKLOG ops)

We don't want to index the Log::Entry reqid for CLONE ops because
each CLONE is followed by a real op with the same reqid.. that's
the one that should get indexed.  Introduce a helper to keep
the logic consistent.

15 years agoceph: drop (broken) poll mode (use -w instead)
Sage Weil [Tue, 16 Mar 2010 18:37:57 +0000 (11:37 -0700)]
ceph: drop (broken) poll mode (use -w instead)

It wasn't working anyway.

15 years agoceph: add -s|--status command
Sage Weil [Tue, 16 Mar 2010 18:37:40 +0000 (11:37 -0700)]
ceph: add -s|--status command

Print one-shot summary of each paxos service.

15 years agoRevert "mon: PaxosServiceMessages now routed through paxos_dispatch and get caps...
Greg Farnum [Tue, 16 Mar 2010 18:16:44 +0000 (11:16 -0700)]
Revert "mon: PaxosServiceMessages now routed through paxos_dispatch and get caps set"

This reverts commit 0c688f94bef805ce6c6a777885406e3e43b90b65.

Revert "mon: Use PaxosServiceMessage::caps instead of Session::caps where applicable"

This reverts commit e33e17ec2f8994527d23fbc6bd1d064e90c7fce8.

This needs to be reworked slightly to handle inter-mon communication better.

15 years agomon: handle_route uses lazy_send_message for unknown MRoutes
Greg Farnum [Tue, 16 Mar 2010 18:09:50 +0000 (11:09 -0700)]
mon: handle_route uses lazy_send_message for unknown MRoutes

15 years agomon: add encode/decode functions to MonCaps
Greg Farnum [Tue, 16 Mar 2010 16:34:19 +0000 (09:34 -0700)]
mon: add encode/decode functions to MonCaps

15 years agomds: adjust rdlock forwarding on replicas
Sage Weil [Tue, 16 Mar 2010 18:10:58 +0000 (11:10 -0700)]
mds: adjust rdlock forwarding on replicas

Include LOCK, MIX, and associated gather states.  An EXCL on the
auth (which is not temporary) is a LOCK on the replica, so fw.
(Otherwise we'd need another state.)  MIX should fw too, since
it is also stable and the replcia can't rdlock.

Include leading states because rdlock waits for WAIT_RD, not
stable.

15 years agomds: send resolve to resolve_set
Sage Weil [Tue, 16 Mar 2010 16:54:36 +0000 (09:54 -0700)]
mds: send resolve to resolve_set

Not RESOLVE|REJOIN|CLIENTREPLAY|ACTIVE|STOPPING, according to
the current MDSMap.

Fixes problem where the resolve_set is empty, but we send
resolves out, and got != needed because got is a superset.

15 years agomds: fix replica dentry linkage updates
Sage Weil [Fri, 12 Mar 2010 00:52:44 +0000 (16:52 -0800)]
mds: fix replica dentry linkage updates

Previously we have a broken hack that would drop a replicated
null dentry if it got new linkage.  We already get an explicit
message if it was unlinked, that unlinks it cleanly.  Do the
same for links, and replicate the newly linked inode as
needed.  This is much cleaner and more correct.

Specifically, this fixes a problem where a create (link) and
unlink are pipelined by the same client under the same xlock,
so that the previous hack (in the handle_lock handler) never
triggers because the lock state doesn't toggle between the link
and unlink.

send_dentry_link sends current, not projected, linkage

15 years agoosd: only insert non-zero intervals into interval_set
Sage Weil [Tue, 16 Mar 2010 05:13:05 +0000 (22:13 -0700)]
osd: only insert non-zero intervals into interval_set

15 years agoqa: fix snaptest1.sh
Sage Weil [Tue, 16 Mar 2010 05:00:58 +0000 (22:00 -0700)]
qa: fix snaptest1.sh

15 years agomds: add array bounds check for null dentry lease
Sage Weil [Tue, 16 Mar 2010 04:56:49 +0000 (21:56 -0700)]
mds: add array bounds check for null dentry lease

15 years agomon: Use PaxosServiceMessage::caps instead of Session::caps where applicable
Greg Farnum [Tue, 16 Mar 2010 00:02:09 +0000 (17:02 -0700)]
mon: Use PaxosServiceMessage::caps instead of Session::caps where applicable

15 years agomon: PaxosServiceMessages now routed through paxos_dispatch and get caps set
Greg Farnum [Mon, 15 Mar 2010 23:53:33 +0000 (16:53 -0700)]
mon: PaxosServiceMessages now routed through paxos_dispatch and get caps set

15 years agomsg: PaxosServiceMessage includes a MonCap*
Greg Farnum [Mon, 15 Mar 2010 22:58:52 +0000 (15:58 -0700)]
msg: PaxosServiceMessage includes a MonCap*

15 years agomon: Add a Session operator<<, use it in OSDMonitor
Greg Farnum [Mon, 15 Mar 2010 21:45:30 +0000 (14:45 -0700)]
mon: Add a Session operator<<, use it in OSDMonitor

15 years agomds: avoid null deref of SimpleLock::_unstable
Sage Weil [Mon, 15 Mar 2010 18:01:50 +0000 (11:01 -0700)]
mds: avoid null deref of SimpleLock::_unstable

15 years agomds: use CDir::item_new for LogSegment::new_dirfrags elist
Sage Weil [Mon, 15 Mar 2010 17:58:57 +0000 (10:58 -0700)]
mds: use CDir::item_new for LogSegment::new_dirfrags elist

15 years agoauth: update documentation on caps
Greg Farnum [Mon, 15 Mar 2010 17:37:22 +0000 (10:37 -0700)]
auth: update documentation on caps

15 years agomon: return error codes from prepare_new_pool
Greg Farnum [Mon, 15 Mar 2010 17:03:39 +0000 (10:03 -0700)]
mon: return error codes from prepare_new_pool

15 years agomon: add warning/debugging prints to prepare_new_pool
Greg Farnum [Fri, 12 Mar 2010 23:45:31 +0000 (15:45 -0800)]
mon: add warning/debugging prints to prepare_new_pool

15 years agoMerge branch 'mds_mem' into unstable
Sage Weil [Sat, 13 Mar 2010 00:48:32 +0000 (16:48 -0800)]
Merge branch 'mds_mem' into unstable

15 years agomds: be consistent about list<>::item naming (item_foo)
Sage Weil [Sat, 13 Mar 2010 00:08:36 +0000 (16:08 -0800)]
mds: be consistent about list<>::item naming (item_foo)

15 years agodlist: fix pop_front/back
Sage Weil [Fri, 12 Mar 2010 23:57:04 +0000 (15:57 -0800)]
dlist: fix pop_front/back

15 years agoxlist: clean up interface
Sage Weil [Fri, 12 Mar 2010 23:28:27 +0000 (15:28 -0800)]
xlist: clean up interface

15 years agodlist: clean up interface
Sage Weil [Fri, 12 Mar 2010 23:26:15 +0000 (15:26 -0800)]
dlist: clean up interface

15 years agomds: use elist instead of dlist
Sage Weil [Fri, 12 Mar 2010 23:26:02 +0000 (15:26 -0800)]
mds: use elist instead of dlist

15 years agoelist: simpler embedded list
Sage Weil [Fri, 12 Mar 2010 18:13:20 +0000 (10:13 -0800)]
elist: simpler embedded list

This is more or less equivalent to the linux kernel list_head:
each embedded item struct has only a next and prev pointer. As
long as the same member item is always used, at a fixed offset
from the containing class, we can go from an item to a contained
class.

The offset can either be passed to the list (head) constructor,
or to the begin(), front(), back() members explicitly.

Iterator has 3 modes.. current (list_for_each), cache_next
(list_for_each_safe), and magic (uses cached next iff current is
empty).  Magic will work most of the time... as long as we don't
re-add ourselves to a different list inside the iterator loop.
(Note that if we do, we will iterator up to the other list's
head, not detect it is a head, an get an invalid pointer and
crash.)

elist: add to makefile

elist: require offset for cosntructor

elist: fix pop_front/back

15 years agorgw: remove unused refcount data member from XMLObj. Also clears up ctor
Greg Farnum [Fri, 12 Mar 2010 22:24:17 +0000 (14:24 -0800)]
rgw: remove unused refcount data member from XMLObj. Also clears up ctor

15 years agorgw: Add documentation
Greg Farnum [Thu, 11 Mar 2010 22:49:27 +0000 (14:49 -0800)]
rgw: Add documentation

15 years agoMerge branch 'mds_mem' into unstable
Sage Weil [Fri, 12 Mar 2010 17:09:09 +0000 (09:09 -0800)]
Merge branch 'mds_mem' into unstable

15 years agocephx: initialize values
Sage Weil [Fri, 12 Mar 2010 16:40:04 +0000 (08:40 -0800)]
cephx: initialize values

15 years agosynclient: print mount error
Sage Weil [Thu, 11 Mar 2010 17:40:09 +0000 (09:40 -0800)]
synclient: print mount error

15 years agoxlist: clean up users
Sage Weil [Fri, 12 Mar 2010 05:43:56 +0000 (21:43 -0800)]
xlist: clean up users

15 years agomds: use dlist instead of xlist for main cache objects
Sage Weil [Fri, 12 Mar 2010 05:43:37 +0000 (21:43 -0800)]
mds: use dlist instead of xlist for main cache objects

15 years agodlist: simpler version of xlist without _list pointer
Sage Weil [Fri, 12 Mar 2010 05:43:23 +0000 (21:43 -0800)]
dlist: simpler version of xlist without _list pointer

15 years agomds: reduce MDSCacheObject footprint a bit
Sage Weil [Fri, 12 Mar 2010 05:11:08 +0000 (21:11 -0800)]
mds: reduce MDSCacheObject footprint a bit

Save 8 bytes.  Whoop.

15 years agomds: replica_nonce can wrap; fix asserts
Sage Weil [Fri, 12 Mar 2010 05:07:00 +0000 (21:07 -0800)]
mds: replica_nonce can wrap; fix asserts