Commit Graph

52938 Commits

Author SHA1 Message Date
Sage Weil
449f81eede Merge pull request #8763 from wjwithagen/patch-10
os/filestore: Make sure str-pointer is not 0x0 when referenced

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2016-05-04 09:14:11 -04:00
Sage Weil
b84f9067d9 Merge pull request #8808 from wjin/fast_heartbeat
osd: fast dispatch heartbeat message

Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 09:13:47 -04:00
Sage Weil
2c6b95eb70 Merge pull request #8811 from stiopaa1/log_includes
log: remove unnecessary includes from header file

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 09:12:47 -04:00
Sage Weil
62a4264207 Merge pull request #8831 from wjin/clean
osd: clean heartbeat dispatch message

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 09:12:34 -04:00
Sage Weil
748fc66ebe Merge pull request #8821 from aderumier/deb-fix-default-ceph-location
debian: fix /etc/default/ceph location

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 09:07:57 -04:00
Sage Weil
3e71d8b699 osd/PG: update info.stats.* mappings on splitReviewed-by: Samuel Just <sjust@redhat.com>
osd/PG: update info.stats.* mappings on split

Reviewed-by: Samuel Just <sjust@redhat.com>
2016-05-04 09:06:55 -04:00
Sage Weil
6d4ab4c791 Merge pull request #8733 from xiexingguo/xxg-wip-fix-reweightlessutil
mon/OSDMonitor: improve reweight_by_utilization() logic

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 09:06:08 -04:00
Sage Weil
034cf6875a Merge pull request #8837 from liewegas/wip-reweight
mon/OSDMonitor: max_osds must be > 0 for reweight-by-*

Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
2016-05-04 09:05:14 -04:00
Loic Dachary
ee9a957162 Merge pull request #8926 from ceph/wip-ec-test-check
test/ec: build the libs only when 'make check'

Reviewed-by: Loic Dachary <ldachary@redhat.com>
2016-05-04 14:03:37 +02:00
John Spray
7093e87762 Merge pull request #8546 from jcsp/wip-15465
mds: fix auth caps with hyphen in path (#15465)

Reviewed-by: Yan, Zheng <zyan@redhat.com>
2016-05-04 05:50:03 -05:00
John Spray
0741b0c163 Merge pull request #8484 from jcsp/wip-15399
mds: use epoch as incarnation counter (#15399)

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-04 05:49:04 -05:00
Boris Ranto
0bbfea5cf1 test/ec: build the libs only when 'make check'
Currently, we are always building the erasure code libraries while we
need them only when 'make check' is run. Moving the test libraries to
check_LTLIBRARIES should fix this for us.

We no longer need to remove the libec libs manually, remove the lines
that do that.

Signed-off-by: Boris Ranto <branto@redhat.com>
2016-05-04 12:16:20 +02:00
songbaisen
8aee6bba37 show the total pg on each osd.
ceph pg dump osds
dumped osds in format plain
osdstat kbused kbavail kb hb in hb out pg sum
0 143304204 79623420 234882056 [1,2] [] 330
1 143304204 79623420 234882056 [0,2] [] 295
2 143304148 79623476 234882056 [0,1] [] 303
sum 429912556 238870316 704646168

Fixes:#14183
Signed-off-by: songbaisen song.baisen@zte.com.cn
2016-05-04 13:54:52 +08:00
Josh Durgin
ef972c6def Merge pull request #8876 from kmroz/wip-fix-rgw-lttng-segfault
global: don't link lttng into libglobal

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2016-05-03 17:32:16 -07:00
Matt Benjamin
4df918ae8c cmake: <UPPERCASED_NAME>_FOUND in Findxio.cmake
For uniformity, upcase all these variables.

Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
2016-05-03 17:36:59 -04:00
Casey Bodley
75a9e437aa Merge pull request #8637 from roidayan/xio-remove_rdma_and_ibverbs_from_configure
confiugre.ac: remove rdma and ibverbs dependency from xio
2016-05-03 17:11:01 -04:00
Casey Bodley
251104faf8 Merge pull request #8704 from ceph/wip-cmake-xio-libs
cmake: removed rdmacm & ibverbs parallel to PR#8637
2016-05-03 17:10:26 -04:00
Gregory Farnum
747814f7c4 Merge pull request #8914 from adamemerson/wip-grr-warnings
I have a hatred for warnings

Reviewed-by: Greg Farnum <gfarnum@redhat.com>
2016-05-03 13:37:41 -07:00
Sage Weil
56edf3a428 Merge pull request #8917 from liewegas/wip-civetweb-fix
civetweb: combine various submodule changes

Reviewed-by: Adam Emerson <aemerson@redhat.com>
2016-05-03 16:01:41 -04:00
David Zafman
a551b6bd5c rados: Don't bother showing list-inconsistent-* errors that aren't set
Signed-off-by: David Zafman <dzafman@redhat.com>
2016-05-03 12:11:56 -07:00
David Zafman
fdca113fc2 osd, rados: Fixes for list-inconsistent-snapset
Signed-off-by: David Zafman <dzafman@redhat.com>
2016-05-03 12:11:56 -07:00
David Zafman
4fc4326b36 include, rados: Fixes for list-inconsistent-obj and librados
Signed-off-by: David Zafman <dzafman@redhat.com>
2016-05-03 12:11:56 -07:00
Sage Weil
b99681de6a civetweb: combine various submodule changes
There were some accidental reverts, fixes, re-reverts,
and follow-on changes that are hard to follow and in the
end did not include what we want.  Merge it all together.

Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 15:01:19 -04:00
Karol Mroz
85a727f0a8 global: don't link lttng into libglobal
Rely on dynamic initialization instead. Linking lttng in this way had
the unfortunate side effect of causing radosgw to segfault (when
daemonized) during sigterm processing (ie. during lttng_ust_exit()).

This was originally removed in 638738f, but accidentally re-added via
5f61d36.

Signed-off-by: Karol Mroz <kmroz@suse.com>
2016-05-03 20:22:27 +02:00
Jason Dillaman
2c88ef8682 Merge pull request #8809 from trociny/wip-rbd-mirror-asok-restart
rbd-mirror: admin socket commands to start/stop/restart mirroring

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2016-05-03 14:13:46 -04:00
Jason Dillaman
4175db609c Merge pull request #8775 from cy-lee/fix-15604-rbd-nbd-write-error
rbd-nbd: fix rbd-nbd aio callback error handling

Reviewed-by: Jason Dillaman <dillaman@redhat.com>
2016-05-03 13:47:31 -04:00
Adam C. Emerson
4252357d55 test: Fix warnings in chain_xattr tests
Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
2016-05-03 13:26:54 -04:00
Josh Durgin
473ce61bea Merge pull request #8910 from dillaman/wip-15709
librbd: unlock image if journal error encountered during lock

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2016-05-03 10:13:58 -07:00
Adam C. Emerson
e1fc9f895a tests: Fix warnings in C write operations test
Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
2016-05-03 13:10:27 -04:00
Josh Durgin
1027e13674 Merge pull request #8907 from dillaman/wip-15690
librbd: possible race condition leads to use-after-free

Reviewed-by: Josh Durgin <jdurgin@redhat.com>
2016-05-03 10:09:07 -07:00
Yehuda Sadeh
8c3646a319 Merge pull request #8793 from cbodley/wip-rgw-admin-modify
radosgw-admin: update usage for zone[group] modify

Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
2016-05-03 08:26:39 -07:00
Sage Weil
8c761ac07b test/mon/mkfs.sh: clean up kv_backend file
Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 10:41:08 -04:00
Sage Weil
905bfb1edf mon/MonitorDBStore: remember kv backend type
If it is specified, use it; otherwise, go by the config
option.

Record the type when creating the store.

Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 10:41:07 -04:00
Jason Dillaman
a11f5e8e55 librbd: unlock image if journal error encountered during lock
Explicitly unlock to prevent a client from accidentally blacklisting
itself when retrying the lock.

Fixes: http://tracker.ceph.com/issues/15709
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
2016-05-03 10:15:08 -04:00
Sage Weil
fe20133543 Merge pull request #8893 from flyd1005/wip-fix-duplicated1
init-ceph.in: remove duplicated words
2016-05-03 09:08:22 -04:00
Sage Weil
ca14790ea3 Merge pull request #8894 from flyd1005/wip-fix-duplicated2
os: remove duplicated words
2016-05-03 09:08:14 -04:00
Sage Weil
55c7d5eb31 Merge pull request #8895 from flyd1005/wip-fix-duplicated3
pybind/rados: remove duplicated words
2016-05-03 09:08:05 -04:00
Sage Weil
839213a018 Merge pull request #8896 from flyd1005/wip-fix-duplicated4
mon: remove duplicated words
2016-05-03 09:07:52 -04:00
Sage Weil
4ec7cbf35b Merge pull request #8898 from flyd1005/wip-fix-duplicated6
libcephfs.h: remove duplicated words
2016-05-03 09:07:28 -04:00
Sage Weil
4bc87c77f0 Merge pull request #8899 from flyd1005/wip-fix-duplicated7
erasure-code: remove duplicated words
2016-05-03 09:07:00 -04:00
Sage Weil
76781ff6bb Merge pull request #8900 from flyd1005/wip-fix-duplicated8
common: remove duplicated words
2016-05-03 09:06:52 -04:00
Sage Weil
54f97aca95 Merge pull request #8901 from flyd1005/wip-fix-duplicated9
cls_user: remove duplicated words

Reviewed-by: Sage Weil <sage@redhat.com>
2016-05-03 09:06:42 -04:00
Sage Weil
88daf7b3f9 mon/MonitorDBStore: {read,write}_meta
These are lifted from ObjectStore.

Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 08:51:14 -04:00
Sage Weil
3f62c8463a mon/MonitorDBStore: move backend instantiation out of ctor
Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 08:51:12 -04:00
Sage Weil
3f3ef3faff mon/MonitorDBStore: fix bug in dump output file
Signed-off-by: Sage Weil <sage@redhat.com>
2016-05-03 08:50:43 -04:00
John Spray
d94115aa2a mds: fix upgrades with replay daemons in map
In the new world, a standby replay daemon which
is actively replaying has its rank set.  In the old
world it did not: map this during the upgrade/downgrade
paths in decode/encode.

Fixes: http://tracker.ceph.com/issues/15591
Signed-off-by: John Spray <john.spray@redhat.com>
2016-05-03 12:57:22 +01:00
John Spray
97dd6897ef doc: add cephfs daemon management docs
Principally to tell people how to configure
standby, but more generally as a place to define
our terms for GIDs etc.

Signed-off-by: John Spray <john.spray@redhat.com>
2016-05-03 12:57:22 +01:00
John Spray
ec8f3db3e5 mds: omit fscid in single-filesystem status output
Signed-off-by: John Spray <john.spray@redhat.com>
2016-05-03 12:57:22 +01:00
John Spray
2a2a56b2d0 mds: simplify standby/standby-replay logic
This used to use an arcane set of constants
in standby_for_rank, combined with daemons sometimes
sending requests to enter state STANDBY_REPLAY.

Simplify this so that there is only one place we
put daemons into standby replay, and that is
in tick->maybe_promote_staandby.

There is a behavioural change in here, which is
that we used to sometimes promote standbys to
be standby-replay, even if they didn't have
"standby replay = true", when they did have
a standby_for_rank or standby_for_name set.
I'm calling that a bug, and making it so that
daemons will only go into standby-replay if
"standby replay = true" is set.

Signed-off-by: John Spray <john.spray@redhat.com>
2016-05-03 12:57:22 +01:00
John Spray
cdf8a29f81 messages: add MMDSBeacon::standby_replay
So that daemons can explicitly say that they
want to be standby replay, instead of using
magic standby_for_rank values.

Because in some cases daemons would indicate this
with a beacon requesting STANDBY_REPLAY state, we
also munge these during decode to be normal STANDBY
requests with standby_replay=true.

Signed-off-by: John Spray <john.spray@redhat.com>
2016-05-03 12:57:22 +01:00