]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
David Zafman [Tue, 5 Mar 2013 18:25:49 +0000 (10:25 -0800)]
Merge branch 'wip-4207'
Feature: #4207: osd/librados: add ops to list snaps for an object
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reported-by: Sam Just <sam.just@inktank.com>
Gary Lowell [Tue, 5 Mar 2013 17:06:24 +0000 (09:06 -0800)]
Merge branch 'master' of https://github.com/ceph/ceph
Gary Lowell [Tue, 5 Mar 2013 17:05:21 +0000 (09:05 -0800)]
Merge branch 'next'
David Zafman [Sat, 2 Mar 2013 02:27:03 +0000 (18:27 -0800)]
Add list_snaps() calls to snapshots test cases
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman [Sat, 23 Feb 2013 04:36:28 +0000 (20:36 -0800)]
Add rados listsnaps command
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman [Fri, 22 Feb 2013 23:15:06 +0000 (15:15 -0800)]
osd/librados: add op to list clones/snaps for an object
Returning snap_set_t with clone info
and snapshots in ascending order
Add clones with snapshots to obj_list_snap_response_t
New rados_types.hpp with snap_set_t/clone_info_t
Move snap_t to rados_types.hpp
Add generate_test_instances() and TYPE() to encoding/types.h
Feature: #4207
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman [Thu, 28 Feb 2013 01:49:17 +0000 (17:49 -0800)]
Remove unused SnapContext in librados.hpp
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman [Wed, 27 Feb 2013 04:54:48 +0000 (20:54 -0800)]
osd: Improve snapshot test
In SelfManagedSnapRollbackPP add some overlapping writes
New SelfManagedSnapOverlap creates overlapping writes
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman [Wed, 27 Feb 2013 01:09:14 +0000 (17:09 -0800)]
osd: correct comment
SnapSet snaps are in descending order
Signed-off-by: David Zafman <david.zafman@inktank.com>
Josh Durgin [Tue, 5 Mar 2013 00:47:49 +0000 (16:47 -0800)]
debian: require >= python2.6 for ceph as well
ceph-disk-prepare and ceph-disk-activate use the with statement,
str.format, and possibly other new features from python 2.6.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Gary Lowell [Mon, 4 Mar 2013 23:18:24 +0000 (15:18 -0800)]
v0.58
Filippos Giannakos [Wed, 27 Feb 2013 11:56:08 +0000 (13:56 +0200)]
Add X-Python-Version >=2.6 to debian control file.
python-ceph complains when installed to debian squeeze about the 'with'
statement. Apparently installation tries to install the python-ceph package for
python 2.5, which does not support the 'with' statement natively.
Signed-off-by: Filippos Giannakos <philipgian@grnet.gr>
Samuel Just [Mon, 25 Feb 2013 21:28:31 +0000 (13:28 -0800)]
PG,ReplicatedPG: use pg_has_reset_since to discard old async events
Local async events are obsolete if the pg is deleting or if the
epoch at which they were created is prior to last_peering_reset.
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit
62999ea2d362b32dfc86a15dcb03b06fb5cb0572 )
Samuel Just [Mon, 25 Feb 2013 20:40:06 +0000 (12:40 -0800)]
PG::build_scrub_map: detect race with peering via last_peering_reset
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit
67225339dc3d62d7fe5a32eec65d51e53e8d35bb )
Samuel Just [Mon, 25 Feb 2013 20:36:29 +0000 (12:36 -0800)]
ReplicatedPG::C_OSD_CommittedPushedObject: use intrusive_ptr for pg
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit
04ee8f478bbd587a711d0668c471cfc5c1cab06c )
Samuel Just [Mon, 25 Feb 2013 20:35:26 +0000 (12:35 -0800)]
ReplicatedPG::C_OSD_CommittedPushedObject take epoch submitted
What we really care about is that the epoch in which the Context
was submitted is at complete() time >= last_peering_reset.
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit
a01dea6af9aacf0614570ebb5fa161d9dde9b6b6 )
Sage Weil [Mon, 4 Mar 2013 20:34:40 +0000 (12:34 -0800)]
init-ceph: fix --restart option
Reported-by: Bryan K. Wright <bkw1a@ayesha.phys.virginia.edu>
Signed-off-by: Sage Weil <sage@inktank.com>
John Wilkins [Mon, 4 Mar 2013 19:48:14 +0000 (11:48 -0800)]
doc: Updated year in footer.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Mon, 4 Mar 2013 18:59:50 +0000 (10:59 -0800)]
Merge branch 'master' of https://github.com/ceph/ceph
John Wilkins [Mon, 4 Mar 2013 18:59:18 +0000 (10:59 -0800)]
doc: Added instructions for ensuring ceph config file and keyring prior to mounting ceph fuse.
fixes: #3796
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Sage Weil [Mon, 4 Mar 2013 18:33:15 +0000 (10:33 -0800)]
Merge pull request #89 from Elbandi/master
remove unused variable from makefile
Sage Weil [Mon, 4 Mar 2013 18:08:49 +0000 (10:08 -0800)]
jounal: disable aio
There is a deadlock issue in the aio code, see #4079. Disable for the time
being.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Mon, 4 Mar 2013 17:18:28 +0000 (09:18 -0800)]
Merge remote-tracking branch 'gh/wip-3484'
Reviewed-by: Sage Weil <sage@inktank.com>
Andras Elso [Fri, 1 Mar 2013 15:34:01 +0000 (16:34 +0100)]
Build: no longer need to use LEVELDB_INCLUDE
Signed-off-by: Andras Elso <elso.andras@gmail.com>
Joao Eduardo Luis [Sat, 2 Mar 2013 18:36:37 +0000 (18:36 +0000)]
tools: ceph: add 'ceph df' usage
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis [Fri, 1 Mar 2013 16:32:24 +0000 (16:32 +0000)]
mon: Monitor: 'ceph df'
Fixes: #3484
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Gary Lowell [Sat, 2 Mar 2013 07:32:54 +0000 (23:32 -0800)]
README: Add libsnappy-dev to build requirements.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Dan Mick [Sat, 2 Mar 2013 03:53:33 +0000 (19:53 -0800)]
doc: missing blank line in radosgw/config-ref
Gary Lowell [Sat, 2 Mar 2013 03:09:04 +0000 (19:09 -0800)]
Merge pull request #85 from dalgaaf/wip-da-spec-1
Fix package requirements to get sgdisk and merge some changes back from SUSE spec file.
Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
Sage Weil [Sat, 2 Mar 2013 01:50:00 +0000 (17:50 -0800)]
Merge pull request #88 from nmtadam/master
librados.hpp typo
Adam Manzanares [Fri, 1 Mar 2013 23:49:26 +0000 (15:49 -0800)]
librados.hpp: replace paris with pairs
Signed-off-by: Adam Manzanares <nmtadam@gmail.com>
Working on a lua-rados library I noticed that paris was used
in the place of pairs in some comments.
John Wilkins [Fri, 1 Mar 2013 23:09:31 +0000 (15:09 -0800)]
doc: Instruction should have been noout, not nodown.
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins [Fri, 1 Mar 2013 19:35:47 +0000 (11:35 -0800)]
doc: Fixed OSD pool config settings. Should be in [global], not [osd].
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
Gary Lowell [Fri, 1 Mar 2013 18:38:49 +0000 (10:38 -0800)]
ceph.spec.in: Require gptfdisk for Suse, gdisk for otherwise
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Sage Weil [Fri, 1 Mar 2013 18:18:57 +0000 (10:18 -0800)]
Merge pull request #87 from dalgaaf/wip-da-sca-style-2
Fix more issues found via cppcheck
Reviewed-by: Sage Weil <sage@inktank.com>
Danny Al-Gaaf [Fri, 1 Mar 2013 17:52:27 +0000 (18:52 +0100)]
osd/Watch.cc: init NotifyTimeoutCB::canceled in constructor with false
Initialize NotifyTimeoutCB::canceled in the constructor with
false as already done in onter cases.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 17:44:59 +0000 (18:44 +0100)]
osd/ReplicatedPG.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 16:58:19 +0000 (17:58 +0100)]
ReplicatedPG.cc: remove unused variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 16:55:55 +0000 (17:55 +0100)]
ReplicatedPG.cc: remove consecutive return/break statement
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 16:14:53 +0000 (17:14 +0100)]
osd/PG.cc: reduce scope of listed_collection in read_log_old()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 16:11:31 +0000 (17:11 +0100)]
osd/PG.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 16:05:03 +0000 (17:05 +0100)]
osd/OSD.cc: remove unused variable 'map<int64_t, int> pool_resize'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:57:13 +0000 (16:57 +0100)]
osd/OSD.cc: reduce scope of "PG *pg" in OSD::handle_pg_query()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:54:26 +0000 (16:54 +0100)]
osd/OSD.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:37:36 +0000 (16:37 +0100)]
os/IndexManager.cc: reduce scope of 'int r' in IndexManager::build_index()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:33:40 +0000 (16:33 +0100)]
os/LevelDBStore.h: pass const string by reference to past_prefix()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:27:38 +0000 (16:27 +0100)]
os/FileStore.cc: fix warning about comparing int with bool
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:09:15 +0000 (16:09 +0100)]
os/FileStore.cc: remove identical else branch
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 15:04:24 +0000 (16:04 +0100)]
os/FileStore.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 14:54:21 +0000 (15:54 +0100)]
SimpleMessenger.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 14:40:51 +0000 (15:40 +0100)]
msg/Pipe.cc: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 14:09:37 +0000 (15:09 +0100)]
mon/Paxos.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:37:29 +0000 (14:37 +0100)]
mon/PGMonitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:33:39 +0000 (14:33 +0100)]
mon/PGMap.cc: remove useless assigment to 'first', it's never used
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:32:09 +0000 (14:32 +0100)]
mon/OSDMonitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:25:55 +0000 (14:25 +0100)]
mon/MonmapMonitor.cc: remove unused variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:22:20 +0000 (14:22 +0100)]
mon/MonmapMonitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:18:04 +0000 (14:18 +0100)]
mon/Monitor.cc: reduce scope of reuse_caps in Monitor::_ms_dispatch()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:15:08 +0000 (14:15 +0100)]
mon/Monitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 13:02:15 +0000 (14:02 +0100)]
mon/MonClient.cc: use static_cast instead of C-Style cast
Use static_cast<T*>(m) instead of C-Style cast, add missing
include needed for static_cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:57:39 +0000 (13:57 +0100)]
mon/MDSMonitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:53:54 +0000 (13:53 +0100)]
mon/LogMonitor.cc: move unused variable into related code block
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:51:57 +0000 (13:51 +0100)]
mon/LogMonitor.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:49:37 +0000 (13:49 +0100)]
mon/Elector.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:47:10 +0000 (13:47 +0100)]
mon/AuthMonitor.cc: remove unused 'std::stringstream ss'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:41:48 +0000 (13:41 +0100)]
mds/flock.cc: remove unused variable 'crossed_waiting_locks'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:38:11 +0000 (13:38 +0100)]
mds/Server.cc: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:33:12 +0000 (13:33 +0100)]
mds/Server.cc: : use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:27:03 +0000 (13:27 +0100)]
mds/Migrator.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:20:39 +0000 (13:20 +0100)]
mds/MDS.cc: remove unused variable 'oldresolve'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:20:03 +0000 (13:20 +0100)]
mds/MDS.cc: : use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:10:32 +0000 (13:10 +0100)]
mds/MDCache.cc: remove unused variables recover_q and check_q
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:05:32 +0000 (13:05 +0100)]
mds/MDCache.cc: reduce scope of 'in' in MDCache::open_root_inode()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 12:03:19 +0000 (13:03 +0100)]
mds/MDCache.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:49:37 +0000 (12:49 +0100)]
mds/MDBalancer.h: init some double variables in constructor
Initialize double variables my_load and target_load with 0.0 in
the constructor.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:40:01 +0000 (12:40 +0100)]
mds/MDBalancer.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:33:37 +0000 (12:33 +0100)]
ESession.h: initialze 'open' in the constructor with false
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:15:13 +0000 (12:15 +0100)]
mds/LogEvent.cc: use static_cast instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:11:01 +0000 (12:11 +0100)]
mds/Locker.cc: reduce scope of 'pool' in Locker::issue_client_lease()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 11:02:44 +0000 (12:02 +0100)]
ceph.spec.in: merge fdupes support from SUSE packages
Use fdupes to avoid duplicated files as done in the SUSE
packages. Since it doesn't work as expected on Fedora/RHEL
do this only on SUSE based distros.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 10:56:54 +0000 (11:56 +0100)]
ceph.spec.in: add on non-RHEL sharutils to 'BuildRequires:'
Add sharutils to 'BuildRequires:', needed for configure.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 10:51:26 +0000 (11:51 +0100)]
ceph.spec.in: fix 'Requires:' to get sgdisk into the system
Fix package Requirements to get sgdisk. On RHEL/CentOS/Fedora the
package is gdisk. On SUSE/openSUSE < 12.2 it's scsirastools on
openSUSE >= 12.2 it's in gptfdisk.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 10:41:06 +0000 (11:41 +0100)]
mds/Locker.cc: use static_cast instead of C-Style cast
Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Fri, 1 Mar 2013 10:22:23 +0000 (11:22 +0100)]
mds/CDir.h: use static_cast instead of C-Style cast
Use static_cast<T>() instead of C-Style cast.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Gary Lowell [Fri, 1 Mar 2013 06:30:43 +0000 (22:30 -0800)]
ceph.spec.in: gdisk for for rpm based systems instead of gptfdisk.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Sage Weil [Fri, 1 Mar 2013 00:58:02 +0000 (16:58 -0800)]
Merge branch 'next'
Sage Weil [Thu, 28 Feb 2013 20:46:00 +0000 (12:46 -0800)]
msgr: drop messages on cons with CLOSED Pipes
Back in commit
6339c5d43974f4b495f15d199e01a141e74235f5 , we tried to make
this deal with a race between a faulting pipe and new messages being
queued. The sequence is
- fault starts on pipe
- fault drops pipe_lock to unregister the pipe
- user (objecter) queues new message on the con
- submit_message reopens a Pipe (due to this bug)
- the message managed to make it out over the wire
- fault finishes faulting, calls ms_reset
- user (objecter) closes the con
- user (objecter) resends everything
It appears as though the previous patch *meant* to drop *m on the floor in
this case, which is what this patch does. And that fixes the crash I am
hitting; see #4271.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil [Thu, 28 Feb 2013 23:34:35 +0000 (15:34 -0800)]
osd: add 'osd debug op order' to track and assert order of client ops
Keep a big fat slow map in memory to ensure that client ops are applied to
objects in the order the clien sent them. This will make it easier to
catch ordering bugs due to requeuing as soon as they happen, when the logs
are easier to wade through, and not later when the client notices something
is awry.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Thu, 28 Feb 2013 23:32:24 +0000 (15:32 -0800)]
osd: include osdmap epoch in osd_op message operator<<
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Thu, 28 Feb 2013 23:32:47 +0000 (15:32 -0800)]
osd: useful debugging for when we drop requests
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just [Thu, 28 Feb 2013 23:46:08 +0000 (15:46 -0800)]
crush-map.rst: fix chooseleaf syntax in ssd example
Fixes: 4304
Backport: bobtail
Reviewed-by: Greg Farnum <greg@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com>
Sage Weil [Thu, 28 Feb 2013 22:59:19 +0000 (14:59 -0800)]
Merge pull request #84 from dalgaaf/wip-da-sca-style
Some more smaller fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 28 Feb 2013 21:45:04 +0000 (13:45 -0800)]
init-ceph: kick off ceph-create-keys when starting mons
We don't have a particularly tidy way to kick off ceph-create-keys from
sysvinit. So, do something simple, ugly, and functional: if we are
starting a mon, and it looks like a 'new' type that is in /var/lib/ceph,
then start ceph-create-keys too.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil [Thu, 28 Feb 2013 21:43:50 +0000 (13:43 -0800)]
init-ceph: fix default admin socket path used for status
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 28 Feb 2013 21:33:40 +0000 (13:33 -0800)]
osd: show retry attempt in MOSDOp operator<<
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil [Thu, 28 Feb 2013 21:01:27 +0000 (13:01 -0800)]
msg/Pipe: allow tuning of TCP receive buffer size
Performance tests on high-end machines have indicated the Linux autotuning
of the receive buffer sizes can cause throughput collapse. See bug
#2100, and this email discussion:
http://marc.info/?l=ceph-devel&m=
133009796706284 &w=2
Initially default to 0, which leaves us with the default. We may adjust
the default in the future.
Tested-by: Jim Schutt <jaschut@sandia.gov>
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil [Thu, 28 Feb 2013 21:00:19 +0000 (13:00 -0800)]
msg/Pipe: move setting of socket options into a common method
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just [Thu, 28 Feb 2013 00:58:45 +0000 (16:58 -0800)]
FileJournal::wrap_read_bl: adjust pos before returning
Otherwise, we may feed an offset past the end of the journal to
check_header in read_entry and incorrectly determine that the entry is
corrupt.
Fixes: 4296
Backport: bobtail
Backport: argonaut
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com>
Danny Al-Gaaf [Thu, 28 Feb 2013 18:45:29 +0000 (19:45 +0100)]
librbd/internal.cc: remove unused variable total_write
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf [Thu, 28 Feb 2013 18:41:37 +0000 (19:41 +0100)]
librbd/internal.cc: reduce scope of 'int r'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>