ceph/doc/changelog/v0.56.3.txt

563 lines
19 KiB
Plaintext

commit 6eb7e15a4783b122e9b0c85ea9ba064145958aa5
Author: Gary Lowell <gary.lowell@inktank.com>
Date: Wed Feb 13 10:10:20 2013 -0800
v0.56.3
commit f5eb845a0f7a2c28d3a88a37479bcb34f882f40c
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Feb 8 13:14:49 2013 -0800
rgw: change json formatting for swift list container
Fixes: #4048
There is some difference in the way swift formats the
xml output and the json output for list container. In
xml the entity is named 'name' and in json it is named
'subdir'.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 3e4d79fe42dfc3ca70dc4d5d2aff5223f62eb34b)
commit f21543f0d88f7bacb69cef3712b0ce087f386e93
Author: Josh Durgin <josh.durgin@inktank.com>
Date: Mon Feb 11 17:08:55 2013 -0800
librbd: unprotect any non-unprotected snapshot
Include snapshots in the UNPROTECTING state as well, which can occur
after an unprotect is interrupted.
Fixes: #4100
Backport: bobtail
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit fe283813b44a7c45def6768ea0788a3a0635957e)
commit 65969f8fbef02ee39f6c2365fffbcd3f633f4b37
Author: Sage Weil <sage@inktank.com>
Date: Fri Feb 8 21:36:13 2013 -0800
java: make CephMountTest use user.* xattr names
Changes to the xattr code in Ceph require
a few tweaks to existing test cases.
Specifically, there is now a ceph.file.layout
xattr by default and user defined xattrs
are prepended with "user."
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joe Buck <jbbuck@gmail.com>
Reviewed-by: Noah Watkins <noahwatkins@gmail.com>
commit 14fddc3ce85d3695aad9d3597f8f50dba5960a86
Author: Sage Weil <sage@inktank.com>
Date: Fri Feb 8 09:59:25 2013 -0800
mon: fix typo in C_Stats
Broken by previous commit.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3cf3710be0b4cccc8de152a97be50d983c35116d)
commit 0453140d187016a61950a8836da57f54d2c34602
Author: Sage Weil <sage@inktank.com>
Date: Thu Feb 7 23:13:11 2013 -0800
mon: retry PGStats message on EAGAIN
If we get EAGAIN from a paxos restart/election/whatever, we should
restart the message instead of just blindly acking it.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com>
(cherry picked from commit 4837063d447afb45554f55bb6fde1c97559acd4b)
commit e68fcec78286363935cf731015108b9ea36b50a6
Author: Sage Weil <sage@inktank.com>
Date: Thu Feb 7 22:06:14 2013 -0800
mon: handle -EAGAIN in completion contexts
We can get ECANCELED, EAGAIN, or success out of the completion contexts,
but in the EAGAIN case (meaning there was an election) we were sending
a success to the client. This resulted in client hangs and all-around
confusion when the monitor cluster was thrashing.
Backport: bobtail
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com>
(cherry picked from commit 17827769f1fe6d7c4838253fcec3b3a4ad288f41)
commit 20ec490555728251444833520a40b20dc8015216
Author: Sage Weil <sage@inktank.com>
Date: Tue Feb 12 14:11:09 2013 -0800
osd: only share maps on hb connection of OSD_HBMSGS feature is set
Back in 1bc419a7affb056540ba8f9b332b6ff9380b37af we started sharing maps
with dead osds via the heartbeat connection, but old code will crash on an
unexpected message. Only do this if the OSD_HBMSGS feature is present.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 302b26ff70ee5539da3dcb2e5614e2b7e83b9dcd)
commit cbf63b633e7a59456f503af487fd4ad2607bbd76
Author: Sage Weil <sage@inktank.com>
Date: Tue Feb 12 14:10:51 2013 -0800
osd: tolerate unexpected messages on the heartbeat interface
We should note but not crash on unexpected messages. Announce this awesome
new "capability" via a feature bit.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit afda30aeaae0a65f83c6886658354ad2b57c4c43)
Conflicts:
src/include/ceph_features.h
commit 102a519632f1b7a0fede9a3fbd4a5c1df0e732a5
Merge: 2c6afa0 2ebf4d0
Author: Sage Weil <sage@inktank.com>
Date: Tue Feb 12 13:39:52 2013 -0800
Merge remote-tracking branch 'gh/wip-bobtail-osd-msgr' into bobtail
commit 2c6afa058e8b1738c1400392320482945834de86
Author: Sage Weil <sage@inktank.com>
Date: Wed Jan 30 11:32:23 2013 -0800
test_libcephfs: fix xattr test
Ignore the ceph.*.layout xattrs.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit b0d4dd21c7be86eb47728a4702a3c67ca44424ac)
commit f11beb954976f66bfae75e847937f84958ebeaf3
Author: Sage Weil <sage@inktank.com>
Date: Thu Feb 7 22:51:29 2013 -0800
radosgw-admin: fix cli test
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1b05b0edbac09d1d7cf0da2e536829df05e48573)
commit ec1085e534eb39d999775bebdcdb997f893a04ae
Merge: 66d7758 62ed62f
Author: Sage Weil <sage@inktank.com>
Date: Thu Feb 7 23:25:30 2013 -0800
Merge remote-tracking branch 'gh/wip-bobtail-vxattrs' into bobtail
commit 66d775858004d1d4e8a138b8d33a3799e03ce26e
Author: Sage Weil <sage@inktank.com>
Date: Mon Feb 4 09:14:39 2013 -0800
mon: enforce reweight be between 0..1
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inktank.com>
(cherry picked from commit 4e29c95d6f61daa838888840cef0cceedc0fcfdd)
commit 8bab3a1c3d0d2f619ddf885bb9050ad9a1c43517
Author: Samuel Just <sam.just@inktank.com>
Date: Thu Feb 7 10:38:00 2013 -0800
PG: dirty_info on handle_activate_map
We need to make sure the pg epoch is persisted during
activate_map.
Backport: bobtail
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit dbce1d0dc919e221523bd44e1d0834711da1577d)
commit dffa386bc13370c0ef56acf740b5200b2054980f
Author: Sage Weil <sage@inktank.com>
Date: Thu Feb 7 10:21:49 2013 -0800
osd: flush peering queue (consume maps) prior to boot
If the osd itself is behind on many maps during boot, it will get more and
(as part of that) flush the peering wq to ensure the pgs consume them.
However, it is possible for OSD to have latest/recnet maps, but pgs to be
behind, and to jump directly to boot and join. The OSD is then laggy and
unresponsive because the peering wq is way behind.
To avoid this, call consume_map() (kick the peering wq) at the end of
init and flush it to ensure we are *internally* all caught up before we
consider joining the cluster.
I'm pretty sure this is the root cause of #3905 and possibly #3995.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit af95d934b039d65d3667fc022e2ecaebba107b01)
commit 47c9f46aac4afac37fb6ec72f0482e61f5e0d798
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Feb 6 17:10:00 2013 -0800
rgw: a tool to fix clobbered bucket info in user's bucket list
This fixes bad entries in user's bucket list that may have occured
due to issue #4039. Syntax:
$ radosgw-admin user check --uid=<uid> [--fix]
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit 9cb6c33f0e2281b66cc690a28e08459f2e62ca13)
Conflicts:
src/rgw/rgw_admin.cc
commit 6c8d63819fde1b6854f8fc03351465b420ff1bdc
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Wed Feb 6 16:43:48 2013 -0800
rgw: bucket recreation should not clobber bucket info
Fixes: #4039
User's list of buckets is getting modified even if bucket already
exists. This fix removes the newly created directory object, and
makes sure that user info's data points at the correct bucket.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit 9d006ec40ced9d97b590ee07ca9171f0c9bec6e9)
Conflicts:
src/rgw/rgw_op.cc
src/rgw/rgw_rados.cc
commit cc167914ac9603f87083c63f2cbc8dac9441329f
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Tue Feb 5 14:50:54 2013 -0800
rgw: a tool to fix buckets with leaked multipart references
Checks specified bucket for the #4011 symptoms, optionally fix
the issue.
sytax:
radosgw-admin bucket check --bucket=<bucket> [--fix]
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 2d8faf8e5f15e833e6b556b0f3c4ac92e4a4151e)
Conflicts:
src/rgw/rgw_admin.cc
src/rgw/rgw_rados.h
commit 4d6964fc7ddd23806e225c95bcb90ef93e4d23a1
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Tue Feb 5 13:54:11 2013 -0800
rgw: radosgw-admin object unlink
Add a radosgw-admin option to remove object from bucket index
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 16235a7acb9543d60470170bb2a09956364626cd)
Conflicts:
src/rgw/rgw_admin.cc
src/rgw/rgw_rados.h
src/test/cli/radosgw-admin/help.t
commit 2ebf4d065af3dc2e581a25b921071af3efb57f8a
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 09:30:00 2013 -0800
osd: kill unused addr-based send_map()
Not used, old API, bad.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e359a862199c8a94cb238f7271ba1b0edcc0863c)
commit bac5b144b27f32da306161ae7018ccc337704121
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 09:29:37 2013 -0800
osd: share incoming maps via Connection*, not addrs
Kill a set of parallel methods that are using the old addr/inst-based
msgr APIs, and instead use Connection handles. This is much safer and gets
us closer to killing the old msgr API.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5e2fab54a4fdf2f59e2b635cbddef8a5909acb7c)
commit 9ca3a165ded62313ba153d7bab89dadf3f73999f
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 09:27:00 2013 -0800
osd: pass new maps to dead osds via existing Connection
Previously we were sending these maps to dead osds via their old addrs
using a new outgoing connection and setting the flags so that the msgr
would clean up. That mechanism is possibly buggy and fragile, and we can
avoid it entirely if we just reuse the existing heartbeat Connection.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 1bc419a7affb056540ba8f9b332b6ff9380b37af)
commit 4cb28b6ed5a702fdac99b8ec71233ef7f877a7a2
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 09:25:28 2013 -0800
osd: requeue osdmaps on heartbeat connections for cluster connection
If we receive an OSDMap on the cluster connection, requeue it for the
cluster messenger, and process it there where we normally do. This avoids
any concerns about locking and ordering rules.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 76705ace2e9767939aa9acf5d9257c800f838854)
commit e4f7ff8c288eac8a8b57382f11a4b6f93682315a
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 09:23:23 2013 -0800
msgr: add get_loopback_connection() method
Return the Connection* for ourselves, so we can queue messages for
ourselves.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a7059eb3f3922cf08c1e5bb5958acc2d45952482)
commit 62ed62f5e2fb068cee38612d7974526aa1b3c759
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 11:33:04 2013 -0800
qa: add layout_vxattrs.sh test script
Test virtual xattrs for file and directory layouts.
TODO: create a data pool, add it to the fs, and make sure we can use it.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 61fbe27a52d12ecd98ddeb5fc0965c4f8ee7841a)
commit d386622c3961a3b57eea42fdb82611cd2e904f4d
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 10:11:18 2013 -0800
mds: allow dir layout/policy to be removed via removexattr on ceph.dir.layout
This lets a user remove a policy that was previously set on a dir.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit db31a1f9f27416e4d531fda716e32d42a275e84f)
commit 6af5da7ae2c4ef95c16c6460770b6244d1aa1a6e
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 10:09:39 2013 -0800
mds: handle ceph.*.layout.* setxattr
Allow individual fields of file or dir layouts to be set via setxattr.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ebebf72f0993d028e795c78a986e1aee542ca5e0)
commit c0af056eb9bdb62cfd8a6f9054a3a3c78c8e7447
Author: Sage Weil <sage@inktank.com>
Date: Mon Feb 4 22:03:32 2013 -0800
mdsmap: backported is_data_pool()
This roughly corresponds to mainline commit 99d9e1d.
Signed-off-by: Sage Weil <sage@inktank.com>
commit 0407af4641ea19697f8feb0f48a92cde8dd4fbe4
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 10:04:05 2013 -0800
mds: fix client view of dir layout when layout is removed
We weren't handling the case where the projected node has NULL for the
layout properly. Fixes the client's view when we remove the dir layout.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 09f28541e374ffac198e4d48082b064aae93cb2c)
commit 8ce834d3f50b00fdd59cd237f3fb5fef1d57e1dd
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 10:04:39 2013 -0800
client: note presence of dir layout in inode operator<<
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 84751489ca208964e617516e04556722008ddf67)
commit 99824b93cec93daaa0d536f031eb3b6180f94e3b
Author: Sage Weil <sage@inktank.com>
Date: Sat Jan 19 09:05:59 2013 -0800
client: list only aggregate xattr, but allow setting subfield xattrs
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ba32ea9454d36072ec5ea3e6483dc3daf9199903)
commit 809cff488ea1ffa299edd678ba6260993771bde3
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 18 22:26:00 2013 -0800
client: implement ceph.file.* and ceph.dir.* vxattrs
Display ceph.file.* vxattrs on any regular file, and ceph.dir.* vxattrs
on any directory that has a policy set.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3f82912a891536dd7e930f98e28d9a8c18fab756)
commit 13babca354d9fbe255de8bae9608a0c158bf6c40
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 18 17:21:37 2013 -0800
client: move xattr namespace enforcement into internal method
This captures libcephfs users now too.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit febb96509559084357bfaabf7e4d28e494c274aa)
commit 65ab51740175254ba3ee050f0fd97332dffe2eb7
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 18 17:20:22 2013 -0800
client: allow ceph.* xattrs
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ad7ebad70bf810fde45067f78f316f130a243b9c)
commit 6f3c1cd2cc07d951dfc23e523b9c6400b7c77c72
Author: caleb miles <caselim@gmail.com>
Date: Mon Jan 14 12:16:12 2013 -0500
rgw_rest: Make fallback uri configurable.
Some HTTP servers, notabily lighttp, do not set SCRIPT_URI, make the fallback
string configurable.
Signed-off-by: caleb miles <caleb.miles@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit b3a2e7e955547a863d29566aab62bcc480e27a65)
Conflicts:
src/rgw/rgw_rest.cc
commit f57d1b4c8cc4d08c6147423d7881be55ed2e88d9
Author: Yehuda Sadeh <yehuda@inktank.com>
Date: Fri Feb 1 10:56:11 2013 -0800
rgw: fix setting of NULL to string
Fixes: #3777
s->env->get() returns char * and not string and can return NULL.
Also, remove some old unused code.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit 9019fbbe8f84f530b6a8700dfe99dfeb03e0ed3d)
commit 55687240b2de20185524de07e67f42c3b1ae6592
Author: Samuel Just <sam.just@inktank.com>
Date: Fri Jan 11 10:44:04 2013 -0800
OSD: check for empty command in do_command
Fixes: #3878
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
(cherry picked from commit 8cf79f252a1bcea5713065390180a36f31d66dfd)
commit c3468f76a5e68a6426f03e508d8ecf26950fca2a
Author: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Date: Wed Jan 30 18:52:24 2013 +0100
PGMap: fix -Wsign-compare warning
Fix -Wsign-compare compiler warning:
mon/PGMap.cc: In member function 'void PGMap::apply_incremental
(CephContext*, const PGMap::Incremental&)':
mon/PGMap.cc:247:30: warning: comparison between signed and
unsigned integer expressions [-Wsign-compare]
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit b571f8ee2d22a3894120204bc5f119ff37e1de53)
commit 5a6b9af90f00d08ef97b34ee0b5abc7b0b63e72b
Author: Sage Weil <sage@inktank.com>
Date: Mon Jan 28 19:46:33 2013 -0800
mon: smooth pg stat rates over last N pgmaps
This smooths the recovery and throughput stats over the last N pgmaps,
defaulting to 2.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a7d15afb529615db56bae038b18b66e60d827a96)
commit 7fd7a5eed19d5ab508d5fe11ff8734bc2bc8c565
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 19:51:40 2013 -0800
mon/PGMap: report IO rates
This does not appear to be very accurate; probably the stat values we're
displaying are not being calculated correctly.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3f6837e022176ec4b530219043cf12e009d1ed6e)
commit 7f149cf6730280f0e633d9f5ef3f0f95c5a5e430
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 19:51:14 2013 -0800
mon/PGMap: report recovery rates
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 208b02a748d97378f312beaa5110d8630c853ced)
commit 8d2d396c6d02bff72aca53920e9ac93fe91428d3
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 19:50:45 2013 -0800
mon/PGMap: include timestamp
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 76e9fe5f06411eb0e96753dcd708dd6e43ab2c02)
commit 8ab77bd4b510149f4df6b3134de0ef59272cec71
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 19:49:16 2013 -0800
osd: track recovery ops in stats
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a2495f658c6d17f56ea0a2ab1043299a59a7115b)
commit 8fd8534b4b808292a4b7c6b9f2f866c431cf9645
Author: Sage Weil <sage@inktank.com>
Date: Fri Jan 25 19:06:52 2013 -0800
osd_types: add recovery counts to object_sum_stats_t
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 4aea19ee60fbe1106bdd71de2d172aa2941e8aab)