]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Sage Weil [Thu, 7 Jan 2016 14:14:57 +0000 (09:14 -0500)]
os/kstore: implement minimal fiemap
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 22:59:58 +0000 (17:59 -0500)]
os/bluestore: remove #warning cruft
These are on my todo list elsewhere.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 19:19:54 +0000 (14:19 -0500)]
os/fs: make aio EAGAIN backoff exponential
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 19:19:43 +0000 (14:19 -0500)]
os/bluestore/BlockDevice: reduce aio queue size
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 18:56:04 +0000 (13:56 -0500)]
os/bluestore: clean up _do_read debug output
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 18:55:47 +0000 (13:55 -0500)]
os/bluestore/BlueFS: fix _compact_log seq jump
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 17:57:12 +0000 (12:57 -0500)]
os/bluestore/BlockDevice: make pread() safe
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 17:54:23 +0000 (12:54 -0500)]
os/bluestore: fix fiemap
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 16:12:27 +0000 (11:12 -0500)]
os/bluestore: drop unused TransContext mutex and cond
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 16:12:18 +0000 (11:12 -0500)]
os/bluestore/BlockDevice: quieter default log level
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 03:04:28 +0000 (22:04 -0500)]
os/bluestore/BlockDevice: make flush a no-op if there was no IO
fdatasync(2) does a cache flush on the device, which we want to avoid if
we didn't actually write anything.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 14:00:32 +0000 (09:00 -0500)]
os/bluestore: fix fiemap on object with no data
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 03:13:07 +0000 (22:13 -0500)]
os/bluestore/BlockDevice: initiate bufferd writes at aio_write time
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Tue, 5 Jan 2016 03:08:31 +0000 (22:08 -0500)]
os/bluestore/BlueFS: buffered writes
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 18:49:23 +0000 (13:49 -0500)]
os/bluestore/BlueFS: no lock on read
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 18:44:32 +0000 (13:44 -0500)]
os/bluestore/BlueFS: do not wait for IO on flush
Wait on fsync and _flush_log only.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 18:42:51 +0000 (13:42 -0500)]
os/bluestore/BlueFS: read_random
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 18:42:06 +0000 (13:42 -0500)]
os/bluestore/BlockDevice: read_buffered
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 17:54:06 +0000 (12:54 -0500)]
os/bluestore/BlueFS: keep bool random in FileReader
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 16:29:47 +0000 (11:29 -0500)]
os/bluestore: reserve first block for label when bluefs = false
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 16:28:13 +0000 (11:28 -0500)]
os/bluestore: fix bdev label error message
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 16:11:53 +0000 (11:11 -0500)]
os/bluestore: send all old bluefs IOContexts for reap by bdev
Doing it in the aio thread ensures that there isn't a use-after-free.
Note that this is only bluefs written files.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 15:30:31 +0000 (10:30 -0500)]
os/bluestore: fix valgrind warning on fsid read
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 14:07:22 +0000 (09:07 -0500)]
os/keyvaluestore: fix valgrind warning on fsid read
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Mon, 4 Jan 2016 14:05:34 +0000 (09:05 -0500)]
os/filestore: fix valgrind warning on fsid read
Signed-off-by: Sage Weil <sage@redhat.com>
Loic Dachary [Fri, 8 Jan 2016 18:12:06 +0000 (19:12 +0100)]
Merge pull request #7161 from liewegas/wip-port
test/mon/osd-erasure-code-profile: pick new mon port
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Sage Weil [Fri, 8 Jan 2016 18:04:57 +0000 (13:04 -0500)]
test/mon/osd-erasure-code-profile: pick new mon port
7108 is used by mark-down.sh
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 8 Jan 2016 17:45:39 +0000 (12:45 -0500)]
Merge pull request #6911 from stiopaa1/const_variable_length
tests: add const for ec test
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 8 Jan 2016 17:44:46 +0000 (12:44 -0500)]
Merge pull request #6989 from stiopaa1/message_inline
msg: remove unneeded inline
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Fri, 8 Jan 2016 16:50:36 +0000 (11:50 -0500)]
Merge pull request #7160 from yehudasa/wip-rgw-warn
rgw: fix compilation warning
Reviewed-by: Sage Weil <sage@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 16:44:10 +0000 (08:44 -0800)]
rgw: fix compilation warning
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
Josh Durgin [Fri, 8 Jan 2016 02:29:15 +0000 (18:29 -0800)]
Merge pull request #7149 from fullerdj/wip-14280
cls_rbd: enable object map checksums for object_map_save
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Josh Durgin [Fri, 8 Jan 2016 02:01:07 +0000 (18:01 -0800)]
Merge pull request #7154 from liewegas/wip-make-check
unittest_ipaddr: fix segv
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Sage Weil [Fri, 8 Jan 2016 01:53:19 +0000 (20:53 -0500)]
unittest_ipaddr: fix segv
Since
b6d0fc9e0e515e50894c08217d688a8c94db7570 we need ifa_name to
be defined.
Signed-off-by: Sage Weil <sage@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 01:12:21 +0000 (17:12 -0800)]
Merge pull request #6002 from Sandy4999/wip-12890
rgw: add a method to purge all associate keys when removing a subuser
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 01:10:43 +0000 (17:10 -0800)]
Merge pull request #6080 from clever215/wkm-master-139
rgw: modify documents and help infos' descriptions to the usage of option date when executing command "log show"
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 01:01:15 +0000 (17:01 -0800)]
Merge pull request #4216 from rzarzynski/wip-10682
rgw: add support for "end_marker" parameter for GET on Swift account.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 00:53:22 +0000 (16:53 -0800)]
Merge pull request #6652 from ifed01/wip-13824
rgw_admin: orphans finish segfaults
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 00:48:19 +0000 (16:48 -0800)]
Merge pull request #7037 from mathslinux/rgw-add-missing-error-code
rgw: add missing error code for admin op API
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 00:46:35 +0000 (16:46 -0800)]
Merge pull request #7093 from dwj192/dwj-bucket-index-fix
rgw: radosgw-admin bucket check --fix not work
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Yehuda Sadeh [Fri, 8 Jan 2016 00:45:43 +0000 (16:45 -0800)]
Merge pull request #6817 from david-z/wip-fix-init-radosgw
rgw: fix a typo in init-radosgw
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
David Zafman [Thu, 7 Jan 2016 22:50:10 +0000 (14:50 -0800)]
Merge pull request #7102 from dzafman/wip-cot-fixes
Fix for make check.
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 7 Jan 2016 22:47:34 +0000 (17:47 -0500)]
Merge pull request #7153 from liewegas/wip-make-check
build: misc make check fixes
Sage Weil [Thu, 7 Jan 2016 22:36:18 +0000 (17:36 -0500)]
Merge pull request #7152 from liewegas/wip-hexdump
unittest_bufferlist: fix hexdump test
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Sage Weil [Thu, 7 Jan 2016 22:22:14 +0000 (17:22 -0500)]
unittest_bluefs: call close_for_write()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 7 Jan 2016 22:19:05 +0000 (17:19 -0500)]
test/test_objectstore_memstore.sh: clear store_test_temp_dir
ceph_test_objectstore now expects this to not exist.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Thu, 7 Jan 2016 19:31:09 +0000 (14:31 -0500)]
unittest_bufferlist: fix hexdump test
Signed-off-by: Sage Weil <sage@redhat.com>
Douglas Fuller [Thu, 7 Jan 2016 19:01:19 +0000 (11:01 -0800)]
cls_rbd: enable object map checksums for object_map_save
object_map_save disables CRCs when an object map footer isn't provided.
Unconditionally re-enable object map CRCs before re-encoding the new object
map.
Fixes: #14280
Signed-off-by: Douglas Fuller <dfuller@redhat.com>
Loic Dachary [Thu, 7 Jan 2016 13:22:30 +0000 (14:22 +0100)]
Merge pull request #6955 from dachary/wip-dev-guide-ceph-qa-suite
doc: dev: document ceph-qa-suite
Reviewed-by: Nathan Cutler <ncutler@suse.cz>
Loic Dachary [Wed, 16 Dec 2015 18:50:55 +0000 (19:50 +0100)]
doc: dev: document ceph-qa-suite
Signed-off-by: Loic Dachary <loic@dachary.org>
Kefu Chai [Thu, 7 Jan 2016 11:59:33 +0000 (19:59 +0800)]
Merge pull request #7131 from ceph/wip-cmake
cmake: made rocksdb an imported library
Reviewed-by: Kefu Chai <kchai@redhat.com>
Joao Eduardo Luis [Thu, 7 Jan 2016 11:49:53 +0000 (11:49 +0000)]
Merge pull request #7073 from dllgzcl/wip-zcl-show-version
tools: monstore: add 'show-versions' command.
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Ali Maredia [Wed, 6 Jan 2016 18:14:55 +0000 (13:14 -0500)]
cmake: made rocksdb an imported library
Systems with the minimum required version of CMake
such as Ubuntu Trusty Tahr don't support
INTERFACE_LINK_LIBRARIES, so rocksdb was made into
an IMPORTED library. Added ROCKSDB_INCLUDE_DIR to
simplify target_include_directories rocksdb.
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Josh Durgin [Thu, 7 Jan 2016 00:18:56 +0000 (16:18 -0800)]
Merge remote-tracking branch 'origin/jewel'
Josh Durgin [Thu, 7 Jan 2016 00:18:33 +0000 (16:18 -0800)]
Merge pull request #7129 from dillaman/wip-14167-jewel
librbd: disable copy-on-read when not exclusive lock owner
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin [Wed, 6 Jan 2016 23:49:56 +0000 (15:49 -0800)]
Merge pull request #6886 from ssssztes/renhw-wip-14047
rbd: rbd order will be place in 22, when set to 0 in the config_opt
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin [Wed, 6 Jan 2016 23:43:18 +0000 (15:43 -0800)]
Merge remote-tracking branch 'origin/jewel'
Josh Durgin [Wed, 6 Jan 2016 23:34:50 +0000 (15:34 -0800)]
Merge branch 'wip-14241-jewel' of git://github.com/dillaman/ceph into jewel
librbd: don't use write_full optimization with clones
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Josh Durgin [Wed, 6 Jan 2016 23:26:28 +0000 (15:26 -0800)]
Merge pull request #7127 from trociny/wip-rbd-nbd-misc
rbd-nbd: small improvements in logging and forking
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Gregory Farnum [Wed, 6 Jan 2016 21:55:18 +0000 (13:55 -0800)]
Merge pull request #6388 from ukernel/wip-13583
ceph-fuse: fix fsync()
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Greg Farnum [Wed, 6 Jan 2016 21:48:06 +0000 (13:48 -0800)]
Merge remote-tracking branch 'origin/jewel'
Greg Farnum [Wed, 6 Jan 2016 21:31:39 +0000 (13:31 -0800)]
Merge branch 'wip-client-readdir-fix' of git://github.com/ukernel/ceph into jewel
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Jason Dillaman [Wed, 6 Jan 2016 19:55:02 +0000 (14:55 -0500)]
librbd: disable write_full optimization if image has parent
Fixes: #14241
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Wed, 6 Jan 2016 19:12:43 +0000 (14:12 -0500)]
tests: new test case for write_full optimization
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Orit Wasserman [Wed, 6 Jan 2016 18:48:02 +0000 (19:48 +0100)]
Merge pull request #7032 from liupeiyang/wip_metadata_list
rgw:modify command stucking when operating radosgw-admin metadata list user
Jason Dillaman [Wed, 6 Jan 2016 17:39:46 +0000 (12:39 -0500)]
Merge pull request #7044 from HeyoQiang/master
rbd-fuse:image name can not include snap name
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Wed, 6 Jan 2016 17:14:52 +0000 (12:14 -0500)]
Merge pull request #7010 from majianpeng/skip-promote-for-writefull
osd: skip promote for writefull w/ FADVISE_DONTNEED/NOCACHE
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 17:14:24 +0000 (12:14 -0500)]
Merge pull request #7012 from chenji-kael/wip-fix-eth-bind
msg: filter out lo addr when bind osd addr
Reviewed-by: Sage Weil <sage@redhat.com>
Loic Dachary [Wed, 6 Jan 2016 16:06:59 +0000 (17:06 +0100)]
Merge pull request #6879 from dachary/wip-13970-ceph-disk-cciss
ceph-disk: ceph-disk list fails on /dev/cciss!c0d0
Reviewed-by: Sage Weil <sage@redhat.com>
Jason Dillaman [Wed, 6 Jan 2016 15:02:52 +0000 (10:02 -0500)]
librbd: directly execute copy-on-read copyup operations
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Wed, 6 Jan 2016 14:43:15 +0000 (09:43 -0500)]
Merge pull request #7052 from branch-predictor/bp-faster-kv-get
kv: implement value_as_ptr() and use it in .get()
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 14:42:44 +0000 (09:42 -0500)]
Merge pull request #5351 from Aran85/master
common/Formatter: avoid newline if there is no output
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Sage Weil [Wed, 6 Jan 2016 14:41:28 +0000 (09:41 -0500)]
Merge pull request #7065 from majianpeng/osd-recover-sleep-cause-thread-suicide
osd: prevent osd_recovery_sleep from causing recovery-thread suicide
Reviewed-by: Sage Weli <sage@redhat.com>
Sage Weil [Wed, 6 Jan 2016 14:40:45 +0000 (09:40 -0500)]
Merge pull request #7091 from liewegas/wip-14212
osd: clear pg_stat_queue after stopping pgs
Reviewed-by: Kefu Chai <kchai@redhat.com>
Sage Weil [Wed, 6 Jan 2016 14:40:24 +0000 (09:40 -0500)]
Merge pull request #7095 from xiexingguo/xxg-wip-14204
osd: kstore: small fixes to kstore
Reviewed-by: Sage Weil <sage@newdream.net>
Mykola Golub [Tue, 5 Jan 2016 15:02:06 +0000 (17:02 +0200)]
rbd-nbd: prefork only for map command
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Kefu Chai [Wed, 6 Jan 2016 11:54:04 +0000 (19:54 +0800)]
Merge pull request #7105 from vshankar/rdb-dist-cleanup
rocksdb: remove rdb sources from dist tarball
Reviewed-by: Kefu Chai <kchai@redhat.com>
Mykola Golub [Tue, 5 Jan 2016 14:15:08 +0000 (16:15 +0200)]
rbd-nbd: set reply error properly
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Mykola Golub [Tue, 5 Jan 2016 13:04:27 +0000 (15:04 +0200)]
rbd-nbd: improve logging
Signed-off-by: Mykola Golub <mgolub@mirantis.com>
Loic Dachary [Wed, 6 Jan 2016 10:15:19 +0000 (11:15 +0100)]
ceph-disk: retry cryptsetup remove
Retry a cryptsetup remove ten times. After the ceph-osd terminates, the
device is released asyncrhonously and an attempt to cryptsetup remove
will may fail because it is considered busy. Although a few attempts are
made before giving up, the number of attempts / the duration of the
attempts cannot be controlled with a cryptsetup option. The workaround
is to increase this by trying a few times.
If cryptsetup remove fails for a reason that is unrelated to timeout,
the error will be repeated a few times. There is no undesirable side
effect. It will not hide a problem.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Tue, 5 Jan 2016 16:42:11 +0000 (17:42 +0100)]
ceph-disk: fix regression in cciss devices names
The cciss driver has device paths such as /dev/cciss/c0d1 with a
matching /sys/block/cciss!c0d1. The general case is that whenever a
device name is found in /sys/block, the / is replaced by the !.
When refactoring the ceph-disk list subcommand, this conversion was
overlooked in a few places. All explicit concatenation of /dev with a
device name are replaced with a call to get_dev_name which does the same
but also converts all ! in /.
http://tracker.ceph.com/issues/13970 Fixes: #13970
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Tue, 5 Jan 2016 16:38:59 +0000 (17:38 +0100)]
ceph-disk: factorize duplicated dmcrypt mapping
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Tue, 5 Jan 2016 16:33:45 +0000 (17:33 +0100)]
ceph-disk: list accepts absolute dev names
The ceph-disk list subcommand now accepts /dev/sda as well as sda.
The filtering is done on the full list of devices instead of restricting
the number of devices explored. Always obtaining the full list of
devices makes things simpler when trying to match a dmcrypted device to
the corresponding raw device.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Tue, 5 Jan 2016 16:11:24 +0000 (17:11 +0100)]
ceph-disk: deactivate must unmap dmcrypted journal
If the journal is not unmapped, ceph-disk destroy will fail to zap the
corresponding devices because it is still held by devicemapper.
A consequence of this modification is that
ceph-disk activate --dmcrypt --reactivate
no longer works from the command line, because it does not map the
dmcrypted journal. The --reactivate option is added to activate-journal
which will map both the journal and the data devices, if necessary.
http://tracker.ceph.com/issues/14233 Fixes: #14233
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Tue, 5 Jan 2016 13:25:51 +0000 (14:25 +0100)]
ceph-disk: display OSD details when listing dmcrypt devices
The details about a device that mapped via dmcrypt are directly
available. Do not try to fetch them from the device entry describing the
devicemapper entry.
http://tracker.ceph.com/issues/14230 Fixes: #14230
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Wed, 9 Dec 2015 15:52:10 +0000 (16:52 +0100)]
tests: limit ceph-disk unit tests to test dir
Signed-off-by: Loic Dachary <loic@dachary.org>
Loic Dachary [Sat, 5 Dec 2015 17:28:46 +0000 (18:28 +0100)]
tests: update ceph-disk workunit debug reminders
Signed-off-by: Loic Dachary <loic@dachary.org>
root [Wed, 6 Jan 2016 03:13:53 +0000 (11:13 +0800)]
rgw:modify command stucking when operating radosgw-admin metadata list user
When no user exists,the command stucks by operating radosgw-admin metadata list user. It seems all right now.
Signed-off-by: Peiyang Liu <liu.peiyang@h3c.com>
Cilang Zhao [Tue, 5 Jan 2016 06:34:05 +0000 (14:34 +0800)]
tools: monstore: add 'show-versions' command.
Using this tool, the first/last committed version of maps will be shown.
Signed-off-by: Cilang Zhao <zhao.cilang@h3c.com>
Josh Durgin [Wed, 6 Jan 2016 00:45:18 +0000 (16:45 -0800)]
Merge pull request #7119 from dmick/master
admin/build-doc: make paths absolute
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Dan Mick [Tue, 5 Jan 2016 23:49:18 +0000 (15:49 -0800)]
admin/build-doc: make paths absolute
Build failure on docs.dhc because pip apparently was changing directory
before building rbd with cython, causing the relative library path
references to fail. Bite the bullet and make everything absolute (since
we already have TOPDIR to use).
Signed-off-by: Dan Mick <dan.mick@redhat.com>
Jason Dillaman [Tue, 5 Jan 2016 21:32:41 +0000 (16:32 -0500)]
librbd: disable copy-on-read when not exclusive lock owner
Fixes: #14167
Backport: infernalis, hammer
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Tue, 5 Jan 2016 19:33:55 +0000 (14:33 -0500)]
tests: fsx should disable journaling feature for krbd
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Casey Bodley [Tue, 5 Jan 2016 21:06:20 +0000 (16:06 -0500)]
Merge pull request #7103 from ceph/wip-cmake-reorg
cmake: cleanups and more features from automake
Ali Maredia [Mon, 4 Jan 2016 21:37:32 +0000 (16:37 -0500)]
cmake: udev linking and Findudev module changes
Linked udev into librbd, restored UDEV_I to
UDEV_INCLUDE_DIR in Findudev.cmake
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Ali Maredia [Mon, 4 Jan 2016 20:03:48 +0000 (15:03 -0500)]
cmake: Findxio.cmake update Xio OFF by default
Option WITH_XIO now OFF but required by default,
Findxio.cmake now using
FIND_PACKAGE_HANDLE_STANDARD_ARGS.
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Ali Maredia [Fri, 1 Jan 2016 20:44:32 +0000 (15:44 -0500)]
cmake: Check for required Cython package
Added a FindCython.cmake, Cython is required.
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Ali Maredia [Fri, 1 Jan 2016 04:34:51 +0000 (23:34 -0500)]
cmake: Added cls_numops_client library
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Ali Maredia [Fri, 1 Jan 2016 03:48:02 +0000 (22:48 -0500)]
cmake: test/erasure-code CMake additions
Added missing executables and libraries.
Signed-off-by: Ali Maredia <amaredia@redhat.com>
Ali Maredia [Fri, 1 Jan 2016 03:31:56 +0000 (22:31 -0500)]
cmake: test CMake additions
Added missing tests, changed linking, among
other changes.
Signed-off-by: Ali Maredia <amaredia@redhat.com>