]>
git.apps.os.sepia.ceph.com Git - ceph.git/log
Tiago Melo [Tue, 5 Jun 2018 11:30:10 +0000 (12:30 +0100)]
mgr/dashboard: fix lint error
Error was introduced in
78dc50443cf64168098f1fb5bc43b7d6125621b8 .
Signed-off-by: Tiago Melo <tmelo@suse.com>
Lenz Grimmer [Tue, 5 Jun 2018 11:19:29 +0000 (13:19 +0200)]
Merge pull request #21826 from tspmelo/rxjs6
mgr/dashboard: Update RxJS to version 6
Reviewed-by: Stephan Müller <smueller@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
Lenz Grimmer [Tue, 5 Jun 2018 10:33:34 +0000 (12:33 +0200)]
Merge pull request #22122 from tspmelo/wip-osd-scrub
mgr/dashboard: Add scrub action to the OSDs table
Reviewed-by: Patrick Nawracay <pnawracay@suse.com>
Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Ricardo Marques <rimarques@suse.com>
Reviewed-by: Sebastian Wagner <swagner@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
Kefu Chai [Tue, 5 Jun 2018 08:57:32 +0000 (16:57 +0800)]
Merge pull request #22392 from tchaikov/wip-cmake-boost-1.67
cmake: bump up the required boost version to 1.67
Reviewed-by: Kefu Chai <kchai@redhat.com>
Josh Durgin [Tue, 5 Jun 2018 03:00:00 +0000 (20:00 -0700)]
Merge pull request #22405 from neha-ojha/wip-24365
qa/tasks/cbt.py: changes to run on bionic
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Neha Ojha [Tue, 5 Jun 2018 00:23:21 +0000 (17:23 -0700)]
qa/tasks/cbt.py: changes to run on bionic
Signed-off-by: Neha Ojha <nojha@redhat.com>
Alfredo Deza [Mon, 4 Jun 2018 19:25:29 +0000 (15:25 -0400)]
Merge pull request #22393 from wido/ceph-volume-bluestore-tool
ceph-volume lvm.activate Do not search for a MON configuration
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Alfredo Deza <adeza@redhat.com>
Sage Weil [Mon, 4 Jun 2018 15:50:13 +0000 (10:50 -0500)]
Merge PR #22359 into master
* refs/pull/22359/head:
osdc/objecter: remove unused method finish_op
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Mon, 4 Jun 2018 14:27:55 +0000 (22:27 +0800)]
cmake: bump up the required boost version to 1.67
Signed-off-by: Kefu Chai <kchai@redhat.com>
Tiago Melo [Wed, 30 May 2018 09:59:16 +0000 (10:59 +0100)]
mgr/dashboard: Add scrub action to the OSD table
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Wed, 30 May 2018 09:58:38 +0000 (10:58 +0100)]
mgr/dashboard: Add OSD scrub modal component
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Fri, 11 May 2018 15:20:53 +0000 (16:20 +0100)]
mgr/dashboard: Add scrub methods to OSD controller and service
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Mon, 4 Jun 2018 13:39:06 +0000 (14:39 +0100)]
mgr/dashboard: Extract 'srt_to_bool' method
Signed-off-by: Tiago Melo <tmelo@suse.com>
Jason Dillaman [Mon, 4 Jun 2018 13:38:01 +0000 (09:38 -0400)]
Merge pull request #21247 from MahatiC/wip-rbd-datapool
rbd: add data pool support to trash purge
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Mon, 4 Jun 2018 12:56:14 +0000 (08:56 -0400)]
Merge pull request #22389 from MahatiC/nit-cleanup
doc: cleanup rendering syntax
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Yan, Zheng [Mon, 4 Jun 2018 12:40:57 +0000 (20:40 +0800)]
Merge pull request #22384 from ukernel/wip-mds-session-ref
mds: add reference when setting Connection::priv to existing session
Kefu Chai [Mon, 4 Jun 2018 11:53:18 +0000 (19:53 +0800)]
Merge pull request #22346 from dzafman/wip-scrub-omap
osd: Handle omap and data digests independently
Reviewed-by: Kefu Chai <kchai@redhat.com>
Mahati Chamarthy [Mon, 4 Jun 2018 11:50:57 +0000 (17:20 +0530)]
doc: cleanup
cleanup format
Signed-off-by: Mahati Chamarthy <mahati.chamarthy@intel.com>
Wido den Hollander [Mon, 4 Jun 2018 11:21:12 +0000 (13:21 +0200)]
ceph-volume lvm.activate Do not search for a MON configuration
This system might not have one nor can we be sure that we have
a client.admin keyring on the system.
Just prime the directory and have the OSD then use it's own cephx
key to communicate with the MONs.
Signed-off-by: Wido den Hollander <wido@42on.com>
Lenz Grimmer [Mon, 4 Jun 2018 10:22:06 +0000 (12:22 +0200)]
Merge pull request #22328 from tspmelo/wip-tslint-unused
mgr/dashboard: Add 'no-unused-variable' rule to tslint
Reviewed-by: Volker Theile <vtheile@suse.com>
Kefu Chai [Mon, 4 Jun 2018 10:01:21 +0000 (18:01 +0800)]
Merge pull request #22350 from theanalyst/doc-mimic-index-fix
doc: mimic is stable!
Reviewed-by: Kefu Chai <kchai@redhat.com>
Yan, Zheng [Mon, 4 Jun 2018 05:56:44 +0000 (13:56 +0800)]
mds: fix MDSRank::send_message_client_counted()
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Yan, Zheng [Mon, 4 Jun 2018 05:40:00 +0000 (13:40 +0800)]
mds: add reference when setting Connection::priv to existing session
the bug was introduced by commit
72883956c26 "use intrusive_ptr for
holding Connection::priv"
Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
Tiago Melo [Wed, 30 May 2018 15:04:01 +0000 (16:04 +0100)]
mgr/dashboard: Add 'no-unused-variable' rule to tslint
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Fri, 4 May 2018 19:07:21 +0000 (20:07 +0100)]
mgr/dashboard: Update RxJS to version 6
I used rxjs-tslint tool to automatically update most of the necessary code.
I added a new package, rxjs-compat, to maintain the compatibility
of external plugins that are still using RxJS v5.X.
Signed-off-by: Tiago Melo <tmelo@suse.com>
Kefu Chai [Sat, 2 Jun 2018 17:55:37 +0000 (01:55 +0800)]
Merge pull request #21718 from majianpeng/admin-socket-cleanup
common/admin_socket: add new api unregister_commands(AdminSocketHook …
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Sat, 2 Jun 2018 17:53:40 +0000 (01:53 +0800)]
Merge pull request #21913 from tspmelo/wip-cephfs-table
mgr/dashboard: Add Filesystems list component
Reviewed-by: Ricardo Dias <rdias@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
Kefu Chai [Sat, 2 Jun 2018 17:52:24 +0000 (01:52 +0800)]
Merge pull request #22196 from thinkercui/bugfix
osd: read object attrs failed at EC recovery
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Kefu Chai [Sat, 2 Jun 2018 17:51:00 +0000 (01:51 +0800)]
Merge pull request #22336 from majianpeng/bluestore-handle-kvdb-error
os/bluestore: firstly delete db then delete bluefs if open db met error.
Reviewed-by: Igor Fedotov <ifedotov@suse.com>
Kefu Chai [Sat, 2 Jun 2018 17:49:58 +0000 (01:49 +0800)]
Merge pull request #22306 from liewegas/wip-msgr-addrvec
msg: addr -> addrvec (part 1)
Reviewed-by: Ricardo Dias <rdias@suse.com>
Mykola Golub [Sat, 2 Jun 2018 06:47:16 +0000 (09:47 +0300)]
Merge pull request #22342 from dillaman/wip-23516
librbd: commit IO as safe when complete if writeback cache is disabled
Reviewed-by: Mykola Golub <mgolub@suse.com>
Mykola Golub [Sat, 2 Jun 2018 06:43:35 +0000 (09:43 +0300)]
Merge pull request #22348 from dillaman/wip-24169
rbd-mirror: ensure daemon can cleanly exit if pool is deleted
Reviewed-by: Mykola Golub <mgolub@suse.com>
Alfredo Deza [Fri, 1 Jun 2018 15:50:29 +0000 (11:50 -0400)]
Merge pull request #21812 from thmour/thmour_ceph-volume
ceph-volume: sort and align `lvm list` output
Reviewed-by: Alfredo Deza <adeza@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 13:56:46 +0000 (21:56 +0800)]
Merge pull request #22367 from tchaikov/wip-cmake-rgw
cmake: rgw_common should depend on tracing headers
Reviewed-by: Lenz Grimmer <lgrimmer@suse.com>
Sage Weil [Fri, 1 Jun 2018 13:15:29 +0000 (08:15 -0500)]
Merge pull request #22364 from tchaikov/wip-doc
doc: fix the links in releases/schedule.rst
Reviewed-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 21:13:32 +0000 (16:13 -0500)]
osd/OSDMap: switch to addrvec for public_addr
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:16:44 +0000 (15:16 -0500)]
mon/Session: avoid OSDMap::get_addr()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:16:20 +0000 (15:16 -0500)]
osd/OSDMap: remove get_addr()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:16:14 +0000 (15:16 -0500)]
osd/OSDMap: avoid get_addr()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:15:54 +0000 (15:15 -0500)]
msg/msg_types: entity_addrvec_t contains() and is_same_host()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:12:47 +0000 (15:12 -0500)]
osd: avoid OSDMap::get_addr()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:12:28 +0000 (15:12 -0500)]
client: use get_addrs()
These are legacy interfaces that should return an IP only.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:12:12 +0000 (15:12 -0500)]
msg/msg_types: entity_addrvec_t::front()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:09:22 +0000 (15:09 -0500)]
mgr: avoid OSDMap::get_addr()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:09:13 +0000 (15:09 -0500)]
msg/msg_types: entity_addrvec_t::probably_equals()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 20:03:50 +0000 (15:03 -0500)]
msg/msg_types: add entity_addrvec_t::get_ports()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:58:35 +0000 (14:58 -0500)]
mon/OSDMonitor: change 'osd find' output to list all addrs
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:38:43 +0000 (14:38 -0500)]
osd/OSDMap: remove get_inst()
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:38:39 +0000 (14:38 -0500)]
osdc/Objecter: use get_addrs
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:36:08 +0000 (14:36 -0500)]
messages/MRoute: remove unused entity_inst_t dest
This is unused in luminous and mimic, too, although the code was
never removed.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:01:40 +0000 (14:01 -0500)]
mon: remove dead try_send_message()
No more users!
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:01:17 +0000 (14:01 -0500)]
mon: remove dead send_command()
No users.
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 19:00:34 +0000 (14:00 -0500)]
mon/OSDMonitor: remove dead 'osd scrub' implementation from mon
This is now handled by the mgr (as of luminous).
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 18:56:52 +0000 (13:56 -0500)]
messages/MOSDMarkMeDown: use addrvec
Signed-off-by: Sage Weil <sage@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 12:38:25 +0000 (20:38 +0800)]
cmake: rgw_common should depend on tracing headers
see also:
4c0d3531
Signed-off-by: Kefu Chai <kchai@redhat.com>
Matt Benjamin [Fri, 1 Jun 2018 12:25:31 +0000 (08:25 -0400)]
Merge pull request #22324 from cbodley/wip-rgw-cache-time-added
rgw: update ObjectCacheInfo::time_added on overwrite
Mykola Golub [Fri, 1 Jun 2018 11:00:15 +0000 (14:00 +0300)]
Merge pull request #22327 from dillaman/wip-23512
librbd: utilize the journal disabled policy when removing images
Reviewed-by: Mykola Golub <mgolub@suse.com>
cuixf [Thu, 24 May 2018 00:01:25 +0000 (20:01 -0400)]
osd: retry to read object attrs at EC recovery
In EC recovery read, if the object's attrs read failed or with errors, we erase the attrs we have read and
try to read it again from left shards. This will make the primary osd get the object's attrs correct and
avoid assert.
Signed-off-by: xiaofei cui <cuixiaofei@sangfor.com>
Jianpeng Ma [Fri, 1 Jun 2018 09:44:56 +0000 (17:44 +0800)]
os/bluestore: firstly delete db then delete bluefs if open db met error.
When create Rocksdb but failed, met the followong error messages:
2018-05-31 22:30:15.017
7facd3f4f240 -1 rocksdb: do_open Failed to create rocksdb column family: L
2018-05-31 22:30:15.017
7facd3f4f240 -1 bluestore(/home/jianpeng/ceph/build/dev/osd0) _open_db erroring opening db:
*** Caught signal (Segmentation fault) **
in thread
7facd3f4f240 thread_name:ceph-osd
ceph version
14.0.0-109-g9d317e5d23 (
9d317e5d23eb78deec1a048aff5c2a31997c8345 ) nautilus (dev)
1: (()+0x910ee0) [0x555727d3aee0]
2: (()+0x12890) [0x7facc9a8d890]
3: (pthread_mutex_lock()+0) [0x7facc9a84fa0]
4: (BlockDevice::queue_reap_ioc(IOContext*)+0x28) [0x555727ce4fa8]
5: (BlueFS::_close_writer(BlueFS::FileWriter*)+0x62) [0x555727ce9d52]
6: (BlueRocksWritableFile::~BlueRocksWritableFile()+0x49) [0x555727d0e659]
7: (rocksdb::WritableFileWriter::Close()+0x1e7) [0x555727ef0c77]
8: (rocksdb::log::Writer::~Writer()+0x4d) [0x555727dfbb1d]
9: (rocksdb::DBImpl::CloseHelper()+0x342) [0x555727d6d632]
10: (rocksdb::DBImpl::~DBImpl()+0x4dd) [0x555727d7cb6d]
11: (rocksdb::DBImpl::~DBImpl()+0x11) [0x555727d7cc11]
12: (RocksDBStore::~RocksDBStore()+0xc1) [0x555727c8a6f1]
13: (RocksDBStore::~RocksDBStore()+0x9) [0x555727c8aa29]
14: (BlueStore::_open_db(bool, bool)+0x2416) [0x555727c204b6]
15: (BlueStore::mkfs()+0x805) [0x555727c50105]
16: (OSD::mkfs(CephContext*, ObjectStore*, std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, uuid_d, int)+0x1b0) [0x5557277ffa70]
17: (main()+0x4222) [0x5557276ebb92]
18: (__libc_start_main()+0xe7) [0x7facc8948b97]
19: (_start()+0x2a) [0x5557277b0a9a]
2018-05-31 22:30:15.789
7facd3f4f240 -1 *** Caught signal (Segmentation fault) **
in thread
7facd3f4f240 thread_name:ceph-osd
This because the error handle for this case firstly delete bluefs then
db. Like close path, it should firstly delete db than delete bluefs.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
Kefu Chai [Fri, 1 Jun 2018 08:05:16 +0000 (16:05 +0800)]
doc: fix some redirected links reported by "build-doc linkcheck"
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 07:53:32 +0000 (15:53 +0800)]
doc: fix the links in releases/schedule.rst
they were broken in
e37e49b2
Signed-off-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 08:12:19 +0000 (16:12 +0800)]
Merge pull request #21864 from LenzGr/documentation-fixes
doc: fixed restful mgr module SSL configuration commands
Reveiwed-by: John Spray <john.spray@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 07:22:54 +0000 (15:22 +0800)]
Merge pull request #22295 from jan--f/cmake-fix-ceph-test-build
cmake: fix cython target in test/CMakeFile.txt
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 07:22:23 +0000 (15:22 +0800)]
Merge pull request #22317 from MahatiC/wip-doc-zipkin
doc: update blkin changes
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 07:22:00 +0000 (15:22 +0800)]
Merge pull request #22332 from TommyLike/bug/fix_typo
test/encoding: Fix typo in encoding/types.h file
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 06:15:40 +0000 (14:15 +0800)]
Merge pull request #22337 from tchaikov/wip-24361
osd,mon: enable level_compaction_dynamic_level_bytes for rocksdb
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Mark Nelson <mnelson@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 06:05:51 +0000 (14:05 +0800)]
Merge pull request #22285 from ricardoasmarques/wip-error-handling
mgr/dashboard: Log frontend errors + @UiController
Reviewed-by: Ricardo Marques <rimarques@suse.com>
Reviewed-by: Volker Theile <vtheile@suse.com>
Kefu Chai [Fri, 1 Jun 2018 06:04:56 +0000 (14:04 +0800)]
Merge pull request #22335 from majianpeng/bluestore-cleanup
os/bluestore: remove useless condtion.
Reviewed-by: Igor Fedotov <ifedotov@suse.com>
wumingqiao [Fri, 1 Jun 2018 05:42:41 +0000 (13:42 +0800)]
osdc/objecter: remove unused method finish_op
Signed-off-by: wumingqiao <wumingqiao@inspur.com>
Kefu Chai [Fri, 1 Jun 2018 04:15:55 +0000 (12:15 +0800)]
Merge pull request #21689 from ovh/bp-reduce-bs-bl-rebuilds
os/bluestore/BlueFS: reduce bufferlist rebuilds during WAL writes
Reviewed-by: Adam C. Emerson <aemerson@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 04:14:59 +0000 (12:14 +0800)]
Merge pull request #21920 from cbodley/wip-async-librados
librados: use ceph::async::Completion for asio bindings
Reviewed-by: Adam C. Emerson <aemerson@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Kefu Chai [Fri, 1 Jun 2018 00:06:40 +0000 (08:06 +0800)]
Merge pull request #22056 from jiangxiyxy/Branch_master
mon: change monitor compact command to run asynchronously
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Jason Dillaman [Thu, 31 May 2018 18:09:30 +0000 (14:09 -0400)]
rbd-mirror: attempt to re-acquire leader lock if watcher recovered
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Thu, 31 May 2018 18:04:19 +0000 (14:04 -0400)]
librbd: ensure managed lock can shut down if stuck waiting for register
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Jason Dillaman [Thu, 31 May 2018 23:17:52 +0000 (19:17 -0400)]
qa/workunits/rbd: dump long image directory upon rbd-mirror test failure
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Abhishek Lekshmanan [Thu, 31 May 2018 22:43:34 +0000 (00:43 +0200)]
doc: mimic is stable!
Signed-off-by: Abhishek Lekshmanan <alekshmanan@suse.com>
Abhishek L [Thu, 31 May 2018 22:40:56 +0000 (00:40 +0200)]
Merge pull request #22319 from theanalyst/releases/mimic/13.2
doc: release/mimic: correct the changelog to the latest version
Tiago Melo [Thu, 10 May 2018 09:36:57 +0000 (10:36 +0100)]
mgr/dashboard: Remove unused data from summary controller
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Wed, 9 May 2018 17:13:06 +0000 (18:13 +0100)]
mgr/dashboard: Rename clients component to 'cephfs-clients'
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Wed, 9 May 2018 17:24:03 +0000 (18:24 +0100)]
mgr/dashboard: Rename cephfs component to 'cephfs-detail'
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Tue, 8 May 2018 15:17:10 +0000 (16:17 +0100)]
mgr/dashboard: Add Filesystems list component
Also adapted the existing cephfs components for them
to be used inside the new cephfs-list componment.
Fixes: https://tracker.ceph.com/issues/23825
Signed-off-by: Tiago Melo <tmelo@suse.com>
Tiago Melo [Tue, 8 May 2018 15:16:29 +0000 (16:16 +0100)]
mgr/dashboard: Refactor CephFS controller
Signed-off-by: Tiago Melo <tmelo@suse.com>
David Zafman [Wed, 30 May 2018 23:22:40 +0000 (16:22 -0700)]
Revert "qa/standalone/scrub/osd-scrub-repair.sh: drop omap_digest flag"
This reverts commit
886606bfd76b3f327b9376c4cc3875ae4991365a .
Signed-off-by: David Zafman <dzafman@redhat.com>
Conflicts:
qa/standalone/scrub/osd-scrub-repair.sh (manually made equivalent changes)
Josh Durgin [Thu, 31 May 2018 18:07:50 +0000 (11:07 -0700)]
Merge pull request #22330 from neha-ojha/wip-async-up
osd/PG: do not choose stray osds as async_recovery_targets
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
David Zafman [Thu, 31 May 2018 00:18:03 +0000 (17:18 -0700)]
osd: Handle omap and data digests independently
Caused by:
be078c8b7b131764caa28bc44452b8c5c2339623
The original attempt above to fix the omap_digest handling when
data_digest isn't present had 2 errors. First, it checked
is_data_digest() and is_omap_digest() instead of digest_present and
omap_digest_present which indicate the source digest is available.
Second, MAYBE could only be set if both digests are available.
Fixes: http://tracker.ceph.com/issues/24366
Signed-off-by: David Zafman <dzafman@redhat.com>
Kefu Chai [Thu, 31 May 2018 16:20:41 +0000 (00:20 +0800)]
Merge pull request #22121 from mogeb/bluestore-mono-clock
os/bluestore: use the monotonic clock for perf counters latencies
Reviewed-by: Igor Fedotov <ifedotov@suse.com>
Kefu Chai [Thu, 31 May 2018 16:17:27 +0000 (00:17 +0800)]
Merge pull request #22318 from rjfd/wip-dashboard-rest-methods
mgr/dashboard: rest: add support for query params
Reviewed-by: Volker Theile <vtheile@suse.com>
Kefu Chai [Thu, 31 May 2018 16:15:53 +0000 (00:15 +0800)]
Merge pull request #18241 from hjwsm1989/wip-21756
osd: don't check overwrite flag when handling copy-get
Reviewed-by: Sage Weil <sage@redhat.com>
Kefu Chai [Thu, 31 May 2018 15:04:14 +0000 (23:04 +0800)]
mon: enable level_compaction_dynamic_level_bytes for rocksdb
Fixes: http://tracker.ceph.com/issues/24361
Signed-off-by: Kefu Chai <kchai@redhat.com>
Jason Dillaman [Thu, 24 May 2018 14:52:46 +0000 (10:52 -0400)]
qa/tasks: rbd_mirror_thrash should wait for daemon exit before restarting
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Kefu Chai [Thu, 31 May 2018 13:30:08 +0000 (21:30 +0800)]
Merge pull request #22174 from zhongyimao/cleanup
doc: fix typos
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com>
Jason Dillaman [Thu, 31 May 2018 13:29:00 +0000 (09:29 -0400)]
librbd: commit IO as safe when complete if writeback cache is disabled
We do not need to flush IO to ensure its safe if the writeback cache is
disabled when performing a journal replay. Instead, immediately mark the
IO as safe and let the journal's periodic commit throttle handle updating
the position.
Fixes: http://tracker.ceph.com/issues/23516
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
Sage Weil [Wed, 30 May 2018 18:48:14 +0000 (13:48 -0500)]
mon/OSDMonitor: avoid many/most OSDMap::get_inst() calls
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 18:34:08 +0000 (13:34 -0500)]
messages/MOSDFailure: use addrvec instead of addr
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 17:45:48 +0000 (12:45 -0500)]
osd: kill get_{cluster,hb_front,hb_back}_inst users
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 17:43:09 +0000 (12:43 -0500)]
mon/OSDMonitor: kill get_most_recent_inst usage
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 17:42:10 +0000 (12:42 -0500)]
osd/OSDMap: add addrvec accessors
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 15:43:57 +0000 (10:43 -0500)]
mds/MDSMap: remove inst and addr accessors
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 15:43:44 +0000 (10:43 -0500)]
client: switch to addrvec for MetaSession
Signed-off-by: Sage Weil <sage@redhat.com>
Sage Weil [Wed, 30 May 2018 15:52:05 +0000 (10:52 -0500)]
mds: use addrvec interface
Signed-off-by: Sage Weil <sage@redhat.com>