]> git.apps.os.sepia.ceph.com Git - ceph.git/log
ceph.git
15 years agoosd: implement bench command
Sage Weil [Fri, 18 Jun 2010 04:32:57 +0000 (21:32 -0700)]
osd: implement bench command

'bench [bsize] [total bytes]'

Result is reported via logclient.

15 years agomsgr: avoid calculating data crc is peer didn't either
Sage Weil [Fri, 18 Jun 2010 16:19:20 +0000 (09:19 -0700)]
msgr: avoid calculating data crc is peer didn't either

Otherwise we're just wasting CPU cycles!

15 years agomsgr: Fix crash in policy.throttler->get(message_size) when message_size == 0
Simone Gotti [Fri, 18 Jun 2010 15:34:14 +0000 (08:34 -0700)]
msgr: Fix crash in policy.throttler->get(message_size) when message_size == 0

Signed-off-by: Simone Gotti <simone.gotti@gmail.com>
Signed-off-by: Sage Weil <sage@newdream.net>
15 years agoqa: another mds test fix... wait long enough for the previous death to trigger
Sage Weil [Thu, 17 Jun 2010 20:44:12 +0000 (13:44 -0700)]
qa: another mds test fix... wait long enough for the previous death to trigger

15 years agomsgr: ref count Pipe to avoid use after free
Sage Weil [Thu, 17 Jun 2010 20:37:34 +0000 (13:37 -0700)]
msgr: ref count Pipe to avoid use after free

The Connection has a Pipe pointer to facilitate
 send_message(Message, Connection)
but the reaper() clears that pointer when tearing down old pipes.  This
leads to a race in which submit_message dereferences the old Pipe pointer.

Instead, make Pipe ref counted, and only submit_message() if we get a
valid Pipe reference.  This fixes races between send_message() and
reaper() (as well as any use of the Connection after the pipe is closed).

Signed-off-by: Sage Weil <sage@newdream.net>
15 years agoqa: fix mdstable failure tests
Sage Weil [Thu, 17 Jun 2010 20:09:22 +0000 (13:09 -0700)]
qa: fix mdstable failure tests

15 years agoceph: fix straggler header ifdef guards
Sage Weil [Thu, 17 Jun 2010 17:51:40 +0000 (10:51 -0700)]
ceph: fix straggler header ifdef guards

15 years agoBug #98: Unique names for include guards
Markus Elfring [Sat, 12 Jun 2010 13:04:11 +0000 (15:04 +0200)]
Bug #98: Unique names for include guards

A couple of preprocessor symbols for include guards tampered with the reserved namespace.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
15 years agoceph: remove leading _ from macro
Sage Weil [Thu, 17 Jun 2010 17:36:39 +0000 (10:36 -0700)]
ceph: remove leading _ from macro

Reported-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
15 years agoBug #98: Movement of an underscore for a data structure identifier
Markus Elfring [Sat, 12 Jun 2010 13:37:17 +0000 (15:37 +0200)]
Bug #98: Movement of an underscore for a data structure identifier

A leading underscore was moved to the back of a data structure identifier.

Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Sage Weil <sage@newdream.net>
15 years agoMerge branch 'unstable' of ssh://ceph.newdream.net/home/sage/ceph.newdream.net/git...
Sage Weil [Thu, 17 Jun 2010 17:04:20 +0000 (10:04 -0700)]
Merge branch 'unstable' of ssh://ceph.newdream.net/home/sage/ceph.newdream.net/git/ceph into unstable

15 years agoRevert "mkcephfs: cosd mkfs as root, then chown"
Sage Weil [Wed, 16 Jun 2010 20:49:08 +0000 (13:49 -0700)]
Revert "mkcephfs: cosd mkfs as root, then chown"

This reverts commit 0383878c4f5133f43ec16067a8917d3080adc690.

15 years agomds: fix cdir head/snap items/null accounting
Sage Weil [Sat, 12 Jun 2010 05:06:38 +0000 (22:06 -0700)]
mds: fix cdir head/snap items/null accounting

We were mixing up primary vs remote, partly due to the weird placement of
the counter adjustments.  Make those sane and clean things up a bit.

15 years agoosd: make clean_up_local remove hardlinks from collection dirs
Sage Weil [Fri, 11 Jun 2010 18:07:32 +0000 (11:07 -0700)]
osd: make clean_up_local remove hardlinks from collection dirs

15 years agoosd: don't requeue null OSDOp on apply_and_flush_repops
Sage Weil [Fri, 11 Jun 2010 17:36:07 +0000 (10:36 -0700)]
osd: don't requeue null OSDOp on apply_and_flush_repops

(this triggers during snap trimming)

15 years agoosd: fix snap_trimmer AccessMode interaction
Sage Weil [Fri, 11 Jun 2010 17:34:14 +0000 (10:34 -0700)]
osd: fix snap_trimmer AccessMode interaction

Recheck access mode every time we retake the pg lock (each object). Sleep
if necessary.

15 years agofilejournal: journal write cache is safe on >= 2.6.33
Sage Weil [Thu, 17 Jun 2010 16:29:12 +0000 (09:29 -0700)]
filejournal: journal write cache is safe on >= 2.6.33

15 years agomkcephfs: error out of journal dev is included in btrfs devs
Sage Weil [Thu, 17 Jun 2010 16:14:32 +0000 (09:14 -0700)]
mkcephfs: error out of journal dev is included in btrfs devs

15 years agoosd: optionally periodically check pglog for corruption
Sage Weil [Fri, 11 Jun 2010 05:13:22 +0000 (22:13 -0700)]
osd: optionally periodically check pglog for corruption

...at least until we find this bug, periodically check pglog for corruption
and log it to the monitor when it happens.

Off by default.

15 years agologclient: clean up interaction with monclient, monitor
Sage Weil [Fri, 11 Jun 2010 04:40:24 +0000 (21:40 -0700)]
logclient: clean up interaction with monclient, monitor

Use monclient where available.  Otherwise, we are a monitor, so send to
ourselves.

Conflicts:

src/mon/MonmapMonitor.cc

15 years agofilejournal: log if journal item is larger than journal
Sage Weil [Wed, 16 Jun 2010 21:15:10 +0000 (14:15 -0700)]
filejournal: log if journal item is larger than journal

15 years agoosd: warn when failing to mount journal on ENOTTY
Yehuda Sadeh [Wed, 16 Jun 2010 17:53:08 +0000 (10:53 -0700)]
osd: warn when failing to mount journal on ENOTTY

suggest that the problem was due to journal size not configured

15 years agoconf: can specify environment variables for substitution
Yehuda Sadeh [Tue, 15 Jun 2010 21:13:13 +0000 (14:13 -0700)]
conf: can specify environment variables for substitution

15 years agoconf: fix buffer initalization
Yehuda Sadeh [Tue, 15 Jun 2010 21:11:55 +0000 (14:11 -0700)]
conf: fix buffer initalization

This fixes a bug where we didn't initialize the variable
post processing buffer, which would sometimes lead to
garbage data.

15 years agoosd: error out when failing to read journal header
Yehuda Sadeh [Tue, 15 Jun 2010 19:41:34 +0000 (12:41 -0700)]
osd: error out when failing to read journal header

This fixes bug #201.

15 years agoosd: mkfs failures are colored red
Yehuda Sadeh [Mon, 14 Jun 2010 19:22:54 +0000 (12:22 -0700)]
osd: mkfs failures are colored red

15 years agomon: make send_reply always consume reply ref (even if not sent); fix caller hackery
Sage Weil [Fri, 11 Jun 2010 17:08:10 +0000 (10:08 -0700)]
mon: make send_reply always consume reply ref (even if not sent); fix caller hackery

15 years agomds: add force_wrlock to lock states; use for filemax changes
Sage Weil [Wed, 9 Jun 2010 22:27:33 +0000 (15:27 -0700)]
mds: add force_wrlock to lock states; use for filemax changes

This lets us write out a max_size change when we revoke caps from a client
(thus excl->sync) and the client releases dirty caps.

15 years agorgw: put_obj uses write_full
Yehuda Sadeh [Thu, 10 Jun 2010 23:01:34 +0000 (16:01 -0700)]
rgw: put_obj uses write_full

15 years agotestradospp: add a test for librados trunc
Yehuda Sadeh [Thu, 10 Jun 2010 21:42:11 +0000 (14:42 -0700)]
testradospp: add a test for librados trunc

15 years agolibrados: add trunc operation
Yehuda Sadeh [Thu, 10 Jun 2010 21:41:53 +0000 (14:41 -0700)]
librados: add trunc operation

15 years agotestradospp: update test, use write_full
Yehuda Sadeh [Thu, 10 Jun 2010 21:12:20 +0000 (14:12 -0700)]
testradospp: update test, use write_full

15 years agolibrados: implement write_full
Yehuda Sadeh [Thu, 10 Jun 2010 21:04:07 +0000 (14:04 -0700)]
librados: implement write_full

15 years agoosd: fix null dereference in dout
Yehuda Sadeh [Thu, 10 Jun 2010 18:54:23 +0000 (11:54 -0700)]
osd: fix null dereference in dout

15 years agomds: be extra careful
Sage Weil [Thu, 10 Jun 2010 17:17:21 +0000 (10:17 -0700)]
mds: be extra careful

Probably implied by the refs == 0, but be explicit anyway.

15 years agomds: fix another instance of bad stray trimming code to use proper helper
Sage Weil [Thu, 10 Jun 2010 17:17:03 +0000 (10:17 -0700)]
mds: fix another instance of bad stray trimming code to use proper helper

15 years agomds: remove erroneous return statement
Greg Farnum [Thu, 10 Jun 2010 16:10:34 +0000 (09:10 -0700)]
mds: remove erroneous return statement

15 years agomds: a checker function like _is_dir_nonempty should only report results.
Greg Farnum [Thu, 10 Jun 2010 16:05:29 +0000 (09:05 -0700)]
mds: a checker function like _is_dir_nonempty should only report results.

Remove the call to reply_request and fix up the callers that need it.

15 years agomds: handle dup anchorclient ACKs gracefully
Sage Weil [Thu, 10 Jun 2010 05:17:22 +0000 (22:17 -0700)]
mds: handle dup anchorclient ACKs gracefully

One recovery scenario sees crisscrossing 'agree' and 'commit':

 C->S --> commit1
 S->C --> agree

 C<-S <== agree
  C->S --> commit2   .. client resends commit!

 S<-C <== commit1
  S->C --> ack      .. server resends ack!
 S<-C <== commit2
  S->C --> ack      .. server resends ack!

 C<-S <== commit1
  client journals ack
 C<-S <== commit2
  client should ignore dup ack  ***

*** but doesn't, because the 'remove from committing list' bit above was
never in the code, even as far back as v0.4 (just the comment).  Instead,
the map was getting fixed up in the _logged_ack() completion.  Move it
up here instead, where it belongs!

Signed-off-by: Sage Weil <sage@newdream.net>
15 years agomds: fix export caps
Sage Weil [Wed, 9 Jun 2010 21:43:32 +0000 (14:43 -0700)]
mds: fix export caps

Don't mangle sessionmap version by incrementing twice; pv is returned by
prepare_force_open_sessions().

15 years agomds: allow import caps pin from multiple replicas at once
Sage Weil [Wed, 9 Jun 2010 21:06:27 +0000 (14:06 -0700)]
mds: allow import caps pin from multiple replicas at once

e.g. on dentry unlink, replicas send their caps to the auth.  There may
be multiple replicas.

15 years agoosd: return EINVAL when snapc is invalid and trying to write
Yehuda Sadeh [Wed, 9 Jun 2010 20:49:54 +0000 (13:49 -0700)]
osd: return EINVAL when snapc is invalid and trying to write

15 years agoosd: don't clobber racing pg_info on active pg
Sage Weil [Wed, 9 Jun 2010 20:30:30 +0000 (13:30 -0700)]
osd: don't clobber racing pg_info on active pg

Wido saw a pg go active, but an activate log+info update crossed paths with
a pg_notify info, and the primary overwrote it's updated shiny new info
with the stale old info from the replica.  Don't do that.  It causes
problems down the line.  In this case, we got

osd/OSD.cc: In function 'void OSD::generate_backlog(PG*)':
osd/OSD.cc:3863: FAILED assert(!pg->is_active())
 1: (ThreadPool::worker()+0x28f) [0x5b08ff]
 2: (ThreadPool::WorkThread::entry()+0xd) [0x4edb8d]
 3: (Thread::_entry_func(void*)+0xa) [0x46892a]
 4: (()+0x69ca) [0x7f889ff249ca]
 5: (clone()+0x6d) [0x7f889f1446cd]

on the replica because it was active but the primary was restarting peering
due to the bad info.

15 years agoosd: refine SnapContext::is_valid()
Sage Weil [Wed, 9 Jun 2010 19:29:03 +0000 (12:29 -0700)]
osd: refine SnapContext::is_valid()

15 years agoosd: implement SnapContext::is_valid()
Sage Weil [Wed, 9 Jun 2010 19:27:55 +0000 (12:27 -0700)]
osd: implement SnapContext::is_valid()

15 years agoinit-ceph: don't fail if we fail to umount
Sage Weil [Wed, 9 Jun 2010 17:56:17 +0000 (10:56 -0700)]
init-ceph: don't fail if we fail to umount

It may not be mounted to begin with.

15 years agoosd: add --dump-pg-log command
Sage Weil [Wed, 9 Jun 2010 05:34:57 +0000 (22:34 -0700)]
osd: add --dump-pg-log command

15 years agoosd: clear newly_removed_snaps on osdmap update if unchanged
Sage Weil [Wed, 9 Jun 2010 04:36:56 +0000 (21:36 -0700)]
osd: clear newly_removed_snaps on osdmap update if unchanged

We only want to apply _newly_ removed snaps once, or else we try to trim
the same snaps multiple times, and crash like so

./include/interval_set.h: In function 'void interval_set<T>::insert(T, T) [with T = snapid_t]':
./include/interval_set.h:202: FAILED assert(0)
 1: (interval_set<snapid_t>::insert(snapid_t, snapid_t)+0x12c) [0x6b1728]
 2: (interval_set<snapid_t>::insert(snapid_t)+0x2f) [0x6b195d]
 3: (ReplicatedPG::snap_trimmer()+0x1c02) [0x66d5d6]
 4: (OSD::SnapTrimWQ::_process(PG*)+0x24) [0x6dc2ac]
 5: (ThreadPool::WorkQueue<PG>::_void_process(void*)+0x28) [0x6fa28a]
 6: (ThreadPool::worker()+0x23a) [0x7f57a4]
 7: (ThreadPool::WorkThread::entry()+0x19) [0x73e9b1]
 8: (Thread::_entry_func(void*)+0x20) [0x6508a4]
 9: /lib/libpthread.so.0 [0x7fa2707dc73a]
 10: (clone()+0x6d) [0x7fa26fa0669d]

Signed-off-by: Sage Weil <sage@newdream.net>
15 years agomds: use helper to send message to client; fix send to null connection
Sage Weil [Tue, 8 Jun 2010 23:43:29 +0000 (16:43 -0700)]
mds: use helper to send message to client; fix send to null connection

Sometimes session->connection is NULL; use session->inst in that case.

15 years agomds: remove erroneous bracket
Greg Farnum [Tue, 8 Jun 2010 23:33:59 +0000 (16:33 -0700)]
mds: remove erroneous bracket

15 years agoadd checks for being a snapshot root to dir_is_nonempty
Greg Farnum [Mon, 7 Jun 2010 17:04:33 +0000 (10:04 -0700)]
add checks for being a snapshot root to dir_is_nonempty

15 years agothrottle: allow take(0)
Sage Weil [Tue, 8 Jun 2010 22:36:55 +0000 (15:36 -0700)]
throttle: allow take(0)

15 years agomds: fix stale lease trimming xlist iterator abuse
Sage Weil [Tue, 8 Jun 2010 21:46:30 +0000 (14:46 -0700)]
mds: fix stale lease trimming xlist iterator abuse

15 years agomon: fix memory-leaked messages
Greg Farnum [Tue, 8 Jun 2010 19:10:47 +0000 (12:10 -0700)]
mon: fix memory-leaked messages

15 years agobuffer: fix padding distances
Greg Farnum [Mon, 7 Jun 2010 21:57:47 +0000 (14:57 -0700)]
buffer: fix padding distances

15 years agoosd: init auid to CEPH_AUTH_UID_DEFAULT in case authorizer doesn't set it.
Greg Farnum [Mon, 7 Jun 2010 19:01:34 +0000 (12:01 -0700)]
osd: init auid to CEPH_AUTH_UID_DEFAULT in case authorizer doesn't set it.

We should probably also require the authorizer to set it for us.

15 years agomds: scan stray dir, eval strays on mds startup
Sage Weil [Tue, 8 Jun 2010 20:38:15 +0000 (13:38 -0700)]
mds: scan stray dir, eval strays on mds startup

15 years agomon: make mon lease clock check protocol change backward compatible
Sage Weil [Tue, 8 Jun 2010 16:42:40 +0000 (09:42 -0700)]
mon: make mon lease clock check protocol change backward compatible

15 years agoqa: add untar_snap_rm.sh
Sage Weil [Tue, 8 Jun 2010 05:18:59 +0000 (22:18 -0700)]
qa: add untar_snap_rm.sh

15 years agoosd: print rollback osd_op nicely
Sage Weil [Tue, 8 Jun 2010 05:05:08 +0000 (22:05 -0700)]
osd: print rollback osd_op nicely

15 years agomds: wire Connection to Session when Session already exists on connect
Sage Weil [Mon, 7 Jun 2010 23:03:37 +0000 (16:03 -0700)]
mds: wire Connection to Session when Session already exists on connect

15 years agomds: funnel mds->client messages through single Session* helper
Sage Weil [Mon, 7 Jun 2010 23:03:14 +0000 (16:03 -0700)]
mds: funnel mds->client messages through single Session* helper

Simplify callers where possible.

15 years agomon: simplify clock drift checks
Sage Weil [Mon, 7 Jun 2010 22:42:19 +0000 (15:42 -0700)]
mon: simplify clock drift checks

Ignore lease sent vs lease_ack receive times bc multiple lease msgs may
be in flight and the ack may be from a previous one.  This was causing
spurious

 [WRN] : lease_ack from follower sent at time(10.06.07_15:07:11.441391), before lease extend was sent (10.06.07_15:07:11.826340)! Clocks not synchronized.

messages.

It is sufficient to just check for messages received from the future.  To
avoid cruftiness trying to do that when the only stamp is the lease
timeout, add a sent_timestamp to the message and use that instead.  This
simplifies things quite a bit, at the expense of not being backward
compatible.

15 years agomonc: behave in ms_handle_reset if cur_mon is < 0
Sage Weil [Mon, 7 Jun 2010 22:04:37 +0000 (15:04 -0700)]
monc: behave in ms_handle_reset if cur_mon is < 0

15 years agomsgr: don't throttle.get 0
Sage Weil [Mon, 7 Jun 2010 22:03:28 +0000 (15:03 -0700)]
msgr: don't throttle.get 0

15 years agothrottle: allow put(0)
Sage Weil [Mon, 7 Jun 2010 22:00:23 +0000 (15:00 -0700)]
throttle: allow put(0)

Still returns a consistent value for the count.

15 years agomsgr: don't thottle.put 0
Sage Weil [Mon, 7 Jun 2010 21:59:16 +0000 (14:59 -0700)]
msgr: don't thottle.put 0

15 years agoMerge remote branch 'origin/msgr' into unstable
Sage Weil [Mon, 7 Jun 2010 21:47:56 +0000 (14:47 -0700)]
Merge remote branch 'origin/msgr' into unstable

15 years agomds: use cap on head if there is none on the snapped inode
Sage Weil [Mon, 7 Jun 2010 19:05:55 +0000 (12:05 -0700)]
mds: use cap on head if there is none on the snapped inode

This is needed, in particular, when we're flushing snap data on an inode
that already got COWed.

15 years agoosd: use low-level helper getting obc in sub_op_push
Sage Weil [Mon, 7 Jun 2010 18:40:32 +0000 (11:40 -0700)]
osd: use low-level helper getting obc in sub_op_push

find_object_context does all sorts of stuff we don't need here: we know
which object the context is for.  Just set it up.

15 years agothrotle: add asserts on max and change parameters where appropriate
Greg Farnum [Mon, 7 Jun 2010 12:55:05 +0000 (05:55 -0700)]
throtle: add asserts on max and change parameters where appropriate

15 years agothrottle: fix assert count to actually use count
Greg Farnum [Mon, 7 Jun 2010 12:54:47 +0000 (05:54 -0700)]
throttle: fix assert count to actually use count

15 years agocrypto: don't clean up EVP table on every decrypt()
Sage Weil [Mon, 7 Jun 2010 05:14:50 +0000 (22:14 -0700)]
crypto: don't clean up EVP table on every decrypt()

Don't think that's appropriate?  And certainly doesn't happen for the
encrypt() case.

15 years agocrypto: don't leak memory in CryptoAES::encrypt()
Sage Weil [Mon, 7 Jun 2010 05:14:21 +0000 (22:14 -0700)]
crypto: don't leak memory in CryptoAES::encrypt()

15 years agomon: don't leak MAuth
Sage Weil [Mon, 7 Jun 2010 05:04:29 +0000 (22:04 -0700)]
mon: don't leak MAuth

15 years agothrottle: use signed counters and assert that count never drops below 0
Greg Farnum [Sat, 5 Jun 2010 00:01:32 +0000 (17:01 -0700)]
throttle: use signed counters and assert that count never drops below 0

15 years agomsgr: Fix uses of get_[data, payload, middle] to use throttling-aware functions.
Greg Farnum [Fri, 4 Jun 2010 23:19:00 +0000 (16:19 -0700)]
msgr: Fix uses of get_[data, payload, middle] to use throttling-aware functions.

15 years agomsgr: put throttler usage on Message destruct
Greg Farnum [Fri, 4 Jun 2010 22:01:30 +0000 (15:01 -0700)]
msgr: put throttler usage on Message destruct

15 years agoosd: fix compile issues
Greg Farnum [Fri, 4 Jun 2010 21:02:56 +0000 (14:02 -0700)]
osd: fix compile issues

15 years agomsgr: switch to get/set functions for Message:throttler
Greg Farnum [Fri, 4 Jun 2010 21:02:40 +0000 (14:02 -0700)]
msgr: switch to get/set functions for Message:throttler

15 years agoosd: add osd_client_message_size_cap option to config; default 500MB
Greg Farnum [Fri, 4 Jun 2010 20:37:25 +0000 (13:37 -0700)]
osd: add osd_client_message_size_cap option to config; default 500MB

And change the name in cosd to be that

15 years agoobjectcacher: add verify_stats() debugging helper
Sage Weil [Fri, 4 Jun 2010 23:31:42 +0000 (16:31 -0700)]
objectcacher: add verify_stats() debugging helper

15 years agoobjectcacher: fix stat accounting when resizing bufferheads
Sage Weil [Fri, 4 Jun 2010 23:31:08 +0000 (16:31 -0700)]
objectcacher: fix stat accounting when resizing bufferheads

Must keep stats in mind when adjusting bufferheads!

15 years agoobjectcacher: cleanup formatting
Sage Weil [Fri, 4 Jun 2010 23:10:44 +0000 (16:10 -0700)]
objectcacher: cleanup formatting

15 years agoobjectcacher: fix use of invalid iterator in map_write()
Sage Weil [Fri, 4 Jun 2010 23:05:55 +0000 (16:05 -0700)]
objectcacher: fix use of  invalid iterator in map_write()

The p points to bh, which is removed by merge_left.  Move it back to final,
so we can advance to the new next a few lines down.

15 years agoobjectcacher: match states before merging in map_write
Sage Weil [Fri, 4 Jun 2010 21:26:05 +0000 (14:26 -0700)]
objectcacher: match states before merging in map_write

The caller is going to set us to dirty, so we don't care what state we
have, so long as the left and right bits we're merging match all is ok.

15 years agoosd: fix rollback when head points at the rolled back snapshot
Yehuda Sadeh [Fri, 4 Jun 2010 23:20:35 +0000 (16:20 -0700)]
osd: fix rollback when head points at the rolled back snapshot

15 years agomsg: remove copy_payload and copy_data functions; change set to use throttler
Greg Farnum [Fri, 4 Jun 2010 20:23:57 +0000 (13:23 -0700)]
msg: remove copy_payload and copy_data functions; change set to use throttler

15 years agoMerge branch 'rbd' into unstable
Sage Weil [Fri, 4 Jun 2010 20:10:28 +0000 (13:10 -0700)]
Merge branch 'rbd' into unstable

15 years agoosd: clean up rollback debug output
Sage Weil [Fri, 4 Jun 2010 20:09:42 +0000 (13:09 -0700)]
osd: clean up rollback debug output

15 years agouclient: handle inode with no caps from mds
Sage Weil [Fri, 4 Jun 2010 19:54:25 +0000 (12:54 -0700)]
uclient: handle inode with no caps from mds

This happens when you readdir and some inodes are in a different snaprealm.

15 years agoosd: filter_xattrs on a rollback op
Greg Farnum [Fri, 4 Jun 2010 19:57:59 +0000 (12:57 -0700)]
osd: filter_xattrs on a rollback op

15 years agoosd: fix naughty iterator usage after invalidating it
Greg Farnum [Fri, 4 Jun 2010 19:55:27 +0000 (12:55 -0700)]
osd: fix naughty iterator usage after invalidating it

15 years agoosd: _make_clone now properly duplicates xattrs
Greg Farnum [Fri, 4 Jun 2010 19:19:06 +0000 (12:19 -0700)]
osd: _make_clone now properly duplicates xattrs

15 years agoosd: add filter_xattrs function to remove non-user xattrs from a map of them
Greg Farnum [Fri, 4 Jun 2010 19:49:20 +0000 (12:49 -0700)]
osd: add filter_xattrs function to remove non-user xattrs from a map of them

15 years agoprogress
Greg Farnum [Fri, 4 Jun 2010 19:04:08 +0000 (12:04 -0700)]
progress

15 years agomds: fix straydn->first part deux
Sage Weil [Fri, 4 Jun 2010 18:07:09 +0000 (11:07 -0700)]
mds: fix straydn->first part deux

9ed0c30ecf6611193db52e1facc1f46b37f04bc4 forgot to remove the old code.

15 years agodebugging output
Greg Farnum [Fri, 4 Jun 2010 01:22:24 +0000 (18:22 -0700)]
debugging output

15 years agorados: print out pool instead of object
Greg Farnum [Fri, 4 Jun 2010 01:22:18 +0000 (18:22 -0700)]
rados: print out pool instead of object

15 years agomds: only purge dentries with no extra refs (besides dirty)
Sage Weil [Fri, 4 Jun 2010 00:32:39 +0000 (17:32 -0700)]
mds: only purge dentries with no extra refs (besides dirty)

Signed-off-by: Sage Weil <sage@newdream.net>