Activity
From 05/13/2017 to 06/11/2017
06/11/2017
- 08:48 PM rbd Feature #18984: RFE: let rbd export write directly to a block device
- Couldn't you just run "rbd export <image-spec> - | dd of=/dev/someblockdevice" and achieve the desired outcome?
- 01:58 PM rbd Feature #18984: RFE: let rbd export write directly to a block device
- Note, write serialization is not the only difference between writing to a file and to stdout. Another difference is t...
- 07:53 PM Backport #12959 (Closed): udev: add devicemapper to partuuid-workaround
- The referenced PR didn't get merged. There is ongoing work to support LVM stuff now.
- 07:52 PM RADOS Bug #13146 (Resolved): mon: creating a huge pool triggers a mon election
- We're throttling PG creates now.
- 07:47 PM Support #12443 (Closed): The ceph cluster will be stuck after delete a 65535 pgs pool
- This seems to just be about throttling PG deletes. I think we are more careful about that now?
- 07:46 PM Bug #12444: WorkQueue.cc: unintended behavior for ThreadPool::drain()?
- Kefu, ever look at this?
Without much context I think the condition is correct as originally written: we keep wait... - 07:28 PM RADOS Bug #11907: crushmap validation must not block the monitor
- Don't we internally time out crush map testing now? Does it behave sensibly if things take too long?
- 07:25 PM Bug #11034 (Closed): GenericObjectMap::clear_header misuses KeyValueDB::rmkeys_by_prefix
- This was part of KeyValueStore, which is dead.
- 07:23 PM Bug #10020: bloom filter unit tests fail (power8)
- This test was failing on power8.
- 06:57 PM Bug #10020 (Closed): bloom filter unit tests fail (power8)
- Our unit tests aren't failing at the moment, so this must have been fixed.
- 07:22 PM Bug #10974 (Duplicate): missing pool= in osd caps is validated but breaks access
- 07:21 PM RADOS Bug #9523 (Closed): Both op threads and dispatcher threads could be stuck at acquiring the budget...
- Based on the PR discussion it seems the diagnosed issue wasn't the cause of the slowness. Closing since it hasn't (kn...
- 06:58 PM Bug #10583 (Closed): keyvaluestore: properly handle db backend error
- KeyValueStore is gone
- 06:49 PM Bug #7822 (Resolved): examples/librados/hello_world.cc broken on master
- "Associated Revision" 26bcb362
- 12:15 PM Revision b9509335 (ceph): rgw: user const rgw_bucket in quota
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 11:47 AM CephFS Fix #20246 (Resolved): Make clog message on scrub errors friendlier.
- Currently it looks something like this:...
- 11:19 AM mgr Bug #20245 (Duplicate): PyFormatter aborts dumping PGMapDigest (missing dump_format_va)
- Looks like something changed in PGMap that now requires this type of dumping -- need to go implement it in PyFormatte...
- 07:13 AM Revision 6983eee5 (ceph): rgw: fix rgw bucket policy IfExists position
- Signed-off-by: yuliyang <yuliyang@cmss.chinamobile.com>
06/10/2017
- 10:12 PM Revision b8272f36 (ceph): rgw: only log metadata on metadata master zone
- Fixes: http://tracker.ceph.com/issues/20244
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 10:03 PM rgw Bug #20244: multisite: log_meta on secondary zone causes continuous loop of metadata sync
- The radosgw-admin commands for zone/zonegroup generally prevent this from happening, but it was observed after an upg...
- 09:59 PM rgw Bug #20244 (Resolved): multisite: log_meta on secondary zone causes continuous loop of metadata sync
- If log_meta is set on a secondary zone, it will add another mdlog entry for everything it syncs from the master zone....
- 06:31 PM rbd Backport #19611 (In Progress): kraken: Issues with C API image metadata retrieval functions
- 06:30 PM Revision 27cbff11 (ceph): librbd: fix rbd_metadata_list and rbd_metadata_get
- - properly check for val_len in rbd_metadata_list
- don't expect output buffers are zero pre-filled
Fixes: http://tr... - 05:50 PM Revision 9f259cb9 (ceph): Merge pull request #15610 from wjwithagen/wip-wjw-freebsd-py-pecan
- core: Install Pecan for FreeBSD
- 05:11 PM rbd Bug #19942 (Duplicate): "[ FAILED ] TestLibRBD.Metadata" in upgrade:client-upgrade-kraken-distr...
- 04:59 PM rbd Bug #19942: "[ FAILED ] TestLibRBD.Metadata" in upgrade:client-upgrade-kraken-distro-basic-smithi
- This tests shows a real bug that was fixed in master #19588 and the test was extended to catch it then. I believe it ...
- 03:24 PM rbd Bug #20223 (Resolved): rbd.ImageNotFound: __init__() takes exactly 3 positional arguments, 1 given
- 03:24 PM Revision c42c9f9a (ceph): Merge pull request #15574 from dillaman/wip-20223
- pybind/rbd: OSError should be picklable
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 01:39 PM Revision fe491909 (ceph): Merge pull request #15576 from dachary/wip-ceph-disk
- ceph-disk: sensible default for block.db
Reviewed-by: Sage Weil <sage@redhat.com> - 12:06 PM Bug #18580: WITH_SPDK=ON: /usr/local/lib/librte_eal.a: error adding symbols: Bad value
- Yes, it's resolved. Thanks.
- 10:12 AM Revision f7e18c29 (ceph): core: Install Pecan for FreeBSD
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 10:07 AM Revision 0c651cab (ceph): common: Remove redundant includes
- Fixed: error: field has incomplete type 'struct sockaddr_in'
Signed-off-by: Jos Collin <jcollin@redhat.com> - 08:22 AM Cleanup #20207 (In Progress): Remove the commented code in test submodule
- 08:21 AM Cleanup #3977 (Resolved): Do a great stream operator const cleanup!
- 04:27 AM Revision 3084fcfd (ceph): Merge pull request #15609 from stiwari/wip-19879
- Merge pull request from stiwari/wip-19879
- 02:00 AM Documentation #19879: ceph-osd cmdline options missing from man page
- https://github.com/ceph/ceph/pull/15609
06/09/2017
- 10:16 PM Revision 10a22815 (ceph): Merge pull request #12851 from zhangsw/fix-rgw-bucketcheck-bug
- rgw: bucket index check in radosgw-admin removes valid index.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:55 PM Bug #20057 (Resolved): ceph-osd: some flags are not documented in the help output
- 09:51 PM Bug #20057: ceph-osd: some flags are not documented in the help output
- https://github.com/ceph/ceph/pull/15606
- 01:48 AM Bug #20057: ceph-osd: some flags are not documented in the help output
- Just created a pull request, I hope I did it right.
https://github.com/stiwari/ceph/commit/a4754b8272c9c26a420909c... - 09:39 PM Documentation #19879: ceph-osd cmdline options missing from man page
- https://github.com/ceph/ceph/pull/15606
- 09:39 PM Documentation #19879 (Resolved): ceph-osd cmdline options missing from man page
- 01:49 AM Documentation #19879: ceph-osd cmdline options missing from man page
- Just created a pull request, I hope I did it right.
https://github.com/stiwari/ceph/commit/a4754b8272c9c26a420909c... - 12:22 AM Documentation #19879: ceph-osd cmdline options missing from man page
- Sameer Tiwari wrote:
> As first time contributor, I am working on this issue.
I am working on the master 12.02.
... - 09:39 PM Revision 2289e809 (ceph): Merge pull request #15606 from stiwari/fix_1
- Documentation Fixes for http://tracker.ceph.com/issues/19879
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:26 PM Bug #20216 (Resolved): mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- 09:26 PM Revision 4b8abef1 (ceph): Merge pull request #15588 from liewegas/wip-20216
- pybind/mgr/dashboard: monkeypatch os.exit to stop cherrypy from taking down mgr
Reviewed-by: John Spray <jspray@redh... - 09:23 PM Feature #7192: An easier-to-process health report
- Two questions:
1. Should the severity be a property of the error code? e.g., we define a table of possible error ... - 09:22 PM Revision 7376e813 (ceph): Merge pull request #15550 from jcsp/wip-doc-cephfs-objsize
- doc/cephfs: mention RADOS object size limit
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:05 PM rgw Backport #20088: valgrind reports leak in RGWRemoteMetadataCR
- h3. original description
similar leak report on RGWReadRemoteMDLogShardInfoCR as well... - 08:49 PM Bug #20104 (Fix Under Review): tell injectargs command error
- 08:53 AM Bug #20104: tell injectargs command error
- https://github.com/ceph/ceph/pull/15563
- 08:42 PM Bug #20240 (Fix Under Review): libradosstriper processes arbitrary printf placeholders in user input
- 04:48 PM Bug #20240: libradosstriper processes arbitrary printf placeholders in user input
- Red Hat has assigned CVE ID CVE-2017-7519 to this issue.
- 04:25 PM Bug #20240 (Resolved): libradosstriper processes arbitrary printf placeholders in user input
- I've discovered an issue with libradosstriper. It seems it's
processing the printf formatting placeholders in the o... - 08:40 PM rgw Bug #20231 (Fix Under Review): rgw: can't download large random file when compression enable
- 07:03 PM rgw Bug #20231: rgw: can't download large random file when compression enable
- previous pr was closed carelessly.
-https://github.com/ceph/ceph/pull/15605-
I think that one must use s3 multi... - 05:47 AM rgw Bug #20231: rgw: can't download large random file when compression enable
- -https://github.com/ceph/ceph/pull/15591-
- 05:43 AM rgw Bug #20231 (Resolved): rgw: can't download large random file when compression enable
- one can reproduce issue by steps(using tools s3cmd):
1. create a bucket with compression
2. use dd to create a big ... - 07:51 PM RADOS Bug #20243 (Resolved): Improve size scrub error handling and ignore system attrs in xattr checking
Something similar to this was seen on a production system. If all the object_info_t matched there would be no erro...- 06:50 PM Revision 2a5cd5dc (ceph): ceph-disk: sensible default for block.db
- If bluestore_block_db_size is unset or zero, fallback to a sensible
default which is block_size / 100. With a minimum... - 06:39 PM RADOS Bug #20242 (Resolved): Make osd-scrub-repair.sh unit test run faster
Most likely move some tests to the rados suite.- 06:38 PM Bug #20241: document renaming on cluster from non standard name to ceph
- Additional places where the name is used and may need changed...
- 06:36 PM Bug #20241 (Closed): document renaming on cluster from non standard name to ceph
- capturing the rename of cluster steps in tracker, once verified can use used for docs update....
- 06:04 PM rgw Bug #20210: rgw: fix input/output err when using radosgw-admin bi list
- Yehuda Sadeh wrote:
> Does that still happen, even after: https://github.com/ceph/ceph/pull/14981 ?
sorry, I thin... - 05:56 PM Revision 126cd325 (ceph): Merge pull request #13395 from dang/wip-quota-cache-doc
- Document RGW quota cache options
- 05:41 PM Revision 5e4f8f63 (ceph): Merge pull request #15568 from guihecheng/rgw_file-cleanup-names
- rgw: rgw_file cleanup names
- 05:39 PM rgw Bug #20211: rgw: bucket index not syncing when rados cluster abnormally
- Yehuda Sadeh wrote:
> I don't understand what step (4) is. What do you mean fail bucket index add op.
I consider ... - 05:13 PM rgw Bug #20211: rgw: bucket index not syncing when rados cluster abnormally
- Yehuda Sadeh wrote:
> I don't understand what step (4) is. What do you mean fail bucket index add op.
1. rados cl... - 05:39 PM Revision fd9256b7 (ceph): Merge pull request #14766 from smithfarm/wip-19757-jewel
- jewel: rgw: fix failed to create bucket if a non-master zonegroup has a single zone
Reviewed-by: Abhishek Lekshmanan... - 05:38 PM Revision 26ada59c (ceph): Merge pull request #14787 from linuxbox2/jewel-rgw-shard-limit-ck
- jewel: rgw: add bucket size limit check to radosgw-admin
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Revie... - 05:38 PM Revision fdd25c2b (ceph): Merge pull request #14789 from mdw-at-linuxbox/wip-jewel-rgw-rvk
- jewel: rgw: swift: disable revocation thread if sleep == 0 || cache_size == 0
Reviewed-by: Abhishek Lekshmanan <abh... - 05:36 PM Revision cfd67504 (ceph): Merge pull request #14815 from smithfarm/wip-19786-jewel
- jewel: rgw: failure to create s3 type subuser from admin rest api
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.co... - 04:48 PM Revision 05a390ba (ceph): Merge pull request #15541 from guihecheng/rgw_file-cleanup
- rgw_file: replace raw fs->fh_lru.unref with predefined fs->unref
- 04:36 PM Revision 8cf03733 (ceph): rados: fix typo in 'df' column name
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
- 04:27 PM Revision ab43b0dd (ceph): Merge pull request #15558 from Linbing/wip-osd-optimize-send-failues
- osd: when osd in not in failure_pending, we don't need to get osd inst from osdmap.
Reviewed-by: Kefu Chai <kchai@re... - 04:18 PM CephFS Backport #18283 (Closed): kraken: monitor cannot start because of "FAILED assert(info.state == MD...
- 04:07 PM rbd Bug #20175 (Fix Under Review): test_librbd_api.sh fails in upgrade test
- https://github.com/ceph/ceph/pull/15602
- 03:29 PM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- because the user applications do not link against libcommon, i think it'd be fine to backport the change of @prio_adj...
- 03:23 PM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- because the layout of @PerfCounters@ was changed in luminous: we added a new field of @ @prio_adjust@ to it. so the ...
- 12:59 PM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- ...
- 12:09 PM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- ...
- 11:34 AM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- ...
- 04:01 PM Revision 41a90b99 (ceph): Merge pull request #15223 from badone/wip-ceph_test_admin_socket_output
- tests: Add integration tests for admin socket output
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:00 PM mgr Bug #20208 (Fix Under Review): ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
- https://github.com/ceph/ceph/pull/15573 merged
- 04:00 PM Revision b38272a7 (ceph): Merge pull request #15573 from liewegas/wip-20208
- mon/PGMap: fix osd_epoch update when removing osd_stat
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Loic D... - 03:56 PM Bug #20239 (Resolved): doc: mgr setup docs are wrong
- also they don't document hwo to set up and configure our two modules, 'restful' and 'dashboard'.
also i'm not sure... - 03:43 PM Bug #20238 (Duplicate): "...broken packages" in upgrade:hammer-jewel-x-kraken-distro-basic-smithi
- Run: http://pulpito.ceph.com/teuthology-2017-06-09_02:25:02-upgrade:hammer-jewel-x-kraken-distro-basic-smithi/
Jobs:... - 03:41 PM Bug #20237 (Resolved): "HEALTH_WARN no legacy OSD present but 'sortbitwise' flag is not set" in u...
- Run: http://pulpito.ceph.com/teuthology-2017-06-09_02:25:02-upgrade:hammer-jewel-x-kraken-distro-basic-smithi/
Jobs:... - 03:36 PM bluestore Bug #20236 (New): bluestore: ObjectStore/StoreTestSpecificAUSize.Many4KWritesNoCSumTest/2 failure
- ...
- 03:26 PM rbd Bug #19889 (Need More Info): rbd/compatibility: rbd import fails with Jewel client, Kraken OSDs (...
- 02:50 PM Revision a4232706 (ceph): os/bluestore: set bluestore_cache_kv_ratio to configure rocksdb cache size
- Devote 40% to kv (rocksdb), 50% to metadata (onodes etc), 10% to data.
Note that if we don't consume the data portio... - 02:50 PM Revision 3990137b (ceph): kv/RocksDBStore: rocksdb_cache_row_ratio
- Specify portion of cache to devote to row cache (the rest goes to the
block cache).
Signed-off-by: Sage Weil <sage@r... - 02:50 PM Revision 3ae72a00 (ceph): Merge pull request #15594 from idryomov/wip-krbd-rados-ls
- qa: update krbd_data_pool.sh to match the new rados ls behavior
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:38 PM Revision 25c2a212 (ceph): selinux: Allow nvme devices
- This commit allows nvme devices which use a different label than
standard block devices.
Fixes: http://tracker.ceph.... - 02:13 PM Revision f3904aad (ceph): Merge pull request #15600 from ceph/luminous
- 12.0.3
- 02:05 PM rgw Bug #20037: rgw log includes zero byte sometimes
- https://github.com/ceph/ceph/pull/15599
- 01:17 PM rgw Bug #20037 (In Progress): rgw log includes zero byte sometimes
- seems like we're doing a str. assign where bufferlist::c_Str() itself would be sufficient
- 01:36 PM Revision b38bda73 (ceph): rgw: don't specify a length when convert bl -> string
- in rgw_admin we're assigning a string from a bufferlist by explicitly
specifying a size and using assign, in this cas... - 01:32 PM Revision b6a5b946 (ceph): Merge pull request #15180 from theanalyst/doc/rgw-dev-s3tests
- doc: dev improve the s3tests doc to reflect current scripts
- 01:30 PM Revision c7464183 (ceph): kv/RocksDBStore: make rocksdb_cache_type tunable (lru or clock)
- "[Clock is] Similar to NewLRUCache, but create a cache based on CLOCK
algorithm with better concurrent performance in... - 01:30 PM Revision d94fce02 (ceph): kv/RocksDBStore: allow cache_size to be specified explicitly
- (Not via a config option)
Signed-off-by: Sage Weil <sage@redhat.com> - 12:56 PM rgw Feature #20235 (Fix Under Review): vstart.sh fails to start more than one radosgw process
- When running something like...
- 12:53 PM rgw Bug #20234: rgw: shadow objects are sometimes not removed
- Verified that this also affects Jewel. But before committing a fix, better make sure that http://tracker.ceph.com/iss...
- 12:13 PM rgw Bug #20234 (Resolved): rgw: shadow objects are sometimes not removed
- Testing on master, after copying an object, then deleting the copy and finally deleting the original object, the asso...
- 12:40 PM Bug #19200 (In Progress): RHEL 7.3 Selinux denials at OSD start
- Upstream PR:
https://github.com/ceph/ceph/pull/15597 - 12:38 PM Revision eec4dfde (ceph): selinux: Allow nvme devices
- This commit allows nvme devices which use a different label than
standard block devices.
Fixes: http://tracker.ceph.... - 12:18 PM rgw Bug #20079 (Closed): rgw jewel: valgrind failure in receive_header
- 12:18 PM rgw Bug #20079: rgw jewel: valgrind failure in receive_header
- fixed with https://github.com/ceph/ceph/pull/15382
- 11:53 AM Revision 01c35281 (ceph): rgw: fix get bucket policy s3 compatible issue
- In AWS S3 get bucket policy should return 404 error code when bucket policy does not exist like following:
Response:... - 09:54 AM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- Later I found two more related problems that may need further discussion:
# Some tools(like fio) will set the size o... - 09:38 AM Revision 31d0d374 (ceph): os/bluestore/BlueFS:.slow should be compared with dirname
- Signed-off-by: zhanglei <243290414@qq.com>
- 08:44 AM Bug #20233 (New): Cannot remove striped object
- I have created a RADOS striped object using
$ dd someargs | rados --pool testpool --striper put testfile -
and ... - 08:14 AM Revision 31865246 (ceph): common/freebsd_errno.cc: ceph_to_host and host_toc_ceph errno translation
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 08:14 AM Revision f2404067 (ceph): common: add empty hostos_to_ceph_errno(), to allow linking to work
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 08:14 AM Revision 8392c255 (ceph): core: introduce (and fix) code to pass errno to other OSes
- - Some of the errno conversions were lost in the conversion
to Cmake config
- rename ceph_to_host_errno to _ceph_... - 07:50 AM Revision 4b713669 (ceph): test/unittest_bluefs: check whether rmdir success
- Signed-off-by: shiqi <1454927420@qq.com>
- 07:29 AM Fix #20224: ceph-disk deactivate fails with --verbose, and error message is confusing
- This error message (from another machine) is also confusing:...
- 07:00 AM Revision 9eda2bb9 (ceph): Merge pull request #15570 from joscollin/wip-cleanup-testmsgr-warning
- test/msgr: silence warnings from -Wsign-compare
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 06:27 AM rgw Bug #20232 (New): can not set more than one refer on bucket policy
- when i set ...
- 06:22 AM rgw Bug #20218: rgw: some problem set bucket policy in master branch
- sorry, this is my problem,i use git apply to cherry pick some code, and after i reclone the code ,this no NoSuchBucke...
- 02:14 AM Revision 13488adf (ceph): osd: the condition of last epoch <= superblock.newest_map epoch has been
- check before we puts diff osdmap to transaction, it's unnecessary to
check it again after that. last and superblock.n... - 01:39 AM Revision f7187559 (ceph): Merge pull request #15100 from kestrels/wip-crc32c-fastzero2
- crc32c: Add ppc64le fast zero optimized assembly.
Reviewed-By: Piotr Dałek <piotr.dalek@corp.ovh.com> - 01:39 AM Feature #20123 (Resolved): ceph df: add %used to the formatted output
- 01:39 AM Revision dc3b053f (ceph): Merge pull request #15387 from jecluis/wip-20123
- mon/PGMap: show %used in formatted output
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:39 AM Revision 642fe3bc (ceph): Merge pull request #15508 from tchaikov/wip-ceph.in-cleanup
- ceph.in: drop the compatiiblity to handle non json commands
- 01:38 AM Revision 6c776f5d (ceph): Merge pull request #15560 from dmick/master
- mgr/DaemonServer.cc: log daemon type string as well as id
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Joh... - 01:38 AM Revision c2e346cf (ceph): Merge pull request #15562 from tchaikov/wip-no-assert.h
- common,osdc: remove atomic_t completely
Reviewed-by: Sage Weil <sage@redhat.com> - 01:38 AM Revision 6f561c8c (ceph): Merge pull request #15567 from Fabian-Gruenbichler/pull/logrotatesync
- debian: sync logrotate packaging with downstream
Reviewed-by: Sage Weil <sage@redhat.com> - 01:37 AM Revision 860d5cee (ceph): Merge pull request #15578 from jcsp/wip-mgr-cleanup
- mgr: cleanup, stop clients sending in perf counters
Reviewed-by: Sage Weil <sage@redhat.com> - 01:37 AM Bug #20226 (Resolved): recovery sleep event wakes up with bogus PG*
- 01:37 AM Revision 840eb7fa (ceph): Merge pull request #15582 from liewegas/wip-20226
- osd: take PGRef for recovery sleep wakeup event
Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by: Josh D... - 01:33 AM Bug #20230 (Resolved): mon: fail to form large quorum; msg/async busy loop
- ...
- 01:26 AM RADOS Bug #20169: filestore+btrfs occasionally returns ENOSPC
- ugh just saw this on xenial too. hrm.
/a/sage-2017-06-08_20:27:41-rados-wip-sage-testing2-distro-basic-smithi/127... - 01:19 AM Bug #19948: LibRadosTwoPools[EC]PP.PromoteSnap
- /a/sage-2017-06-08_20:27:41-rados-wip-sage-testing2-distro-basic-smithi/1271605
rados/thrash/{0-size-min-size-overri...
06/08/2017
- 11:48 PM Bug #20057: ceph-osd: some flags are not documented in the help output
- Sameer Tiwari wrote:
> As first time contributor, I am working on this issue.
As of the master branch 12.02, the ... - 11:45 PM Bug #20057: ceph-osd: some flags are not documented in the help output
- As first time contributor, I am working on this issue.
- 11:45 PM Documentation #19879: ceph-osd cmdline options missing from man page
- As first time contributor, I am working on this issue.
- 10:14 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- 10:12 PM Bug #20216 (Fix Under Review): mgr: dashboard failure to bind to port 7000 (or whatever) makes mg...
- https://github.com/ceph/ceph/pull/15588
- 04:04 PM Bug #20216: mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- Seriously antisocial behaviour from cherrypy there. In this context monkey patching os._exit doesn't seem unreasonab...
- 12:25 PM Bug #20216: mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- Adding the following to src/pybind/mgr/dashboard/module.py "fixes" the problem....
- 06:44 AM Bug #20216: mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- I'll try to do something about this. Looks like cherrypy will call os_.exit() if exceptions are thrown during startu...
- 10:12 PM Revision c1c4a59d (ceph): pybind/mgr/dashboard: monkeypatch os.exit to stop cherrypy from taking ...
- Fixes: http://tracker.ceph.com/issues/20216
Suggested-by: Tim Serong <tserong@suse.com>
Signed-off-by: Sage Weil <sag... - 10:07 PM Revision 1101661a (ceph): Merge pull request #15405 from liewegas/wip-rest-test
- pybind/mgr/restful: improve cert handling; work with vstart
Reviewed-by: Boris Ranto <branto@redhat.com> - 09:45 PM Revision 0f23f352 (ceph): debian/control: Build-Depends on python-pecan
- This is needed for make check (so that restful mgr module can load).
Signed-off-by: Sage Weil <sage@redhat.com> - 08:46 PM mgr Fix #19549 (Resolved): ceph-mgr should respawn when it goes inactive
- 08:46 PM Bug #19595 (Resolved): mgr: segv in msgr thread, with no core
- 08:45 PM Revision f05a34af (ceph): Merge pull request #15557 from liewegas/wip-mgr-respawn
- mgr/MgrStandby: respawn when deactivated
Reviewed-by: John Spray <john.spray@redhat.com> - 08:35 PM Bug #20229 (Fix Under Review): ceph-disk systemd unit timesout too quickly
- https://github.com/ceph/ceph/pull/15585
- 08:28 PM Bug #20229 (Resolved): ceph-disk systemd unit timesout too quickly
- When there are more than a few disks, it is likely to take longer than five minutes.
http://tracker.ceph.com/issu... - 08:29 PM Revision a9eb52e0 (ceph): ceph-disk: set the default systemd unit timeout to 3h
- There needs to be a timeout to prevent ceph-disk from hanging
forever. But there is no good reason to set it to a val... - 08:28 PM rgw Bug #19870: rgw: bytes_send and bytes_recv in the msg of usage show returning is 0 in master branch
- cbodley has a fix for a similar problem with swift:
https://github.com/ceph/ceph/pull/14042
I believe it may be ... - 08:01 PM Revision babd25fa (ceph): Merge pull request #15301 from shashalu/rgw-ssl
- rgw: add "rgw_verify_ssl" config
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:00 PM Revision 734083b0 (ceph): Merge pull request #15257 from shashalu/fix-rgw-admin-retcode
- rgw: fix radosgw-admin retcode
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:59 PM Revision 43cad44c (ceph): Merge pull request #14950 from fangyuxiangGL/set-obj-accounted-size
- rgw: set object accounted size correctly
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:35 PM Fix #20224: ceph-disk deactivate fails with --verbose, and error message is confusing
- There's a more serious bug here, I think. When I run ...
- 01:14 PM Fix #20224: ceph-disk deactivate fails with --verbose, and error message is confusing
- When ceph osd dump cannot be run for some reason, the error message should at least include the stderr instead of a t...
- 12:56 PM Fix #20224 (New): ceph-disk deactivate fails with --verbose, and error message is confusing
- I can reproduce this most of the time in a 12.0.3 cluster running in OpenStack.
While the ceph-osd@ systemd servic... - 07:26 PM Bug #20219 (Fix Under Review): upgrade/jewel-x: ceph_test_rados_api_stat hangs on getpoolstats
- 07:26 PM Bug #20219: upgrade/jewel-x: ceph_test_rados_api_stat hangs on getpoolstats
- https://github.com/ceph/ceph/pull/15584
- 02:00 AM Bug #20219: upgrade/jewel-x: ceph_test_rados_api_stat hangs on getpoolstats
- a few ways to fix this:
1. make mgrstatmonitor ignore the version entirely
2. somehow make mgrstatmonitor advance... - 01:58 AM Bug #20219 (Resolved): upgrade/jewel-x: ceph_test_rados_api_stat hangs on getpoolstats
- ...
- 06:52 PM RADOS Bug #20227 (Need More Info): os/bluestore/BlueStore.cc: 2617: FAILED assert(0 == "can't mark unlo...
- Hmm, I see the fault_range call (it's in the new ec unclone code), but it's only dirtying the range including extents...
- 06:18 PM RADOS Bug #20227: os/bluestore/BlueStore.cc: 2617: FAILED assert(0 == "can't mark unloaded shard dirty")
- /a/sage-2017-06-08_02:04:29-rados-wip-sage-testing-distro-basic-smithi/1269367 too
- 06:14 PM RADOS Bug #20227 (Resolved): os/bluestore/BlueStore.cc: 2617: FAILED assert(0 == "can't mark unloaded s...
- ...
- 06:44 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- @Greg the original bug description was updated with a simpler reproducer which does not involve copying objects. I be...
- 06:34 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- Right, but what you've said here is that if you have pool size one, and kill the only OSD hosting it, then no other O...
- 02:58 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- FWIW it was reproduced by badone.
- 12:20 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- @Greg the first reproducer was not trying to rados put the same object. It was trying to rados put another object. I ...
- 12:18 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- The reproducer works as expected on 12.0.3. The behavior changed somewhere in master after 12.0.3 was released.
- 12:17 PM RADOS Bug #20221: kill osd + osd out leads to stale PGs
- I don't understand what behavior you're looking for. Hanging is the expected behavior when data is unavailable.
- 10:07 AM RADOS Bug #20221 (New): kill osd + osd out leads to stale PGs
- h3. description
When the OSD is killed before ceph osd out, the PGs stay in stale state.
h3. reproducer
From... - 06:39 PM rgw Bug #18355 (In Progress): when call the multiparts upload API TransferManager.upload() by s3 java...
- 06:38 PM rgw Bug #18437: error log's error code is not right in data sync
- The error code there should probably be changed to signed int. Should be trivial to fix.
- 06:34 PM rgw Bug #20107: rgw: Truncated objects
- Ah, no, no different pools involved.
And no, with the volume of requests we are dealing with, we are already at ab... - 06:30 PM rgw Bug #20107: rgw: Truncated objects
- Do you have a reference to that bug? I haven't been able to find anything that looked like it would match. Also, the ...
- 06:21 PM rgw Bug #20107: rgw: Truncated objects
- The bug I mentioned was dealing with copying objects that resided on different pools. Do you have a scenario where th...
- 06:15 PM rgw Bug #20107: rgw: Truncated objects
- A copy operation should increase the tail's refcount. The garbage collection will try to remove it by dropping the re...
- 06:34 PM rgw Bug #20128 (Resolved): rgw: teuthology failure in the rgw task (configured via rgw_snaps.yaml)
- 06:33 PM rgw Bug #20166: RGW: Bad error handling when tail object is missing
- Do you have any proposed change?
- 06:30 PM Revision 390ad903 (ceph): pybind/mgr/dashboard: get_localized_config for server_{addr,port}
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:30 PM Revision 30ae537a (ceph): mgr/Mgr: fix deadlock in load_config
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision a0600031 (ceph): vstart.sh: start up mgr restful API
- We try to stagger the ports that mgr modules bind to so that
concurrent vstart instances can run with consecutive por... - 06:29 PM Revision 66e2c3f7 (ceph): mon/ConfigKeyService: more useful status message
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision b5994f3e (ceph): mgr/PyModules: prefix by mgr/, not mgr/$id/
- If modules want per-instance state, they can include
the mgr id in their portion of the key name.
Signed-off-by: Sag... - 06:29 PM Revision c7cfbc2b (ceph): mgr/PyState: add get_mgr_id() to module interface
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision 2535c269 (ceph): pybind/mgr/restful: localize key/crt keys
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision 1ebc3f12 (ceph): mgr: add get_config_prefix
- Fetch a dict of all config options with a given prefix.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:29 PM Revision de6af1b2 (ceph): pybind/mgr/restful: prefix commands with 'restful'
- And use - instead of _, following the ceph convention.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:29 PM Revision 455318ef (ceph): pybind/mgr/restful: store each key+pass in a separate key
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision 1bf53c1f (ceph): qa/workunits/rest/test_mgr_rest_api.py: improvements
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision 84e13070 (ceph): vstart.sh: start mgr dashboard, echo URL(s)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision aec50b90 (ceph): test/vstart_wrapper.sh: fix MGR_PYTHON_PATH
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision d48a29a9 (ceph): vstart.sh: load 'restful' (not 'rest') mgr module
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:29 PM Revision 6bf68ce2 (ceph): ceph.spec.in: add python-pecan as BuildDepends too
- For install-deps.sh's benefit.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:29 PM Revision 38ef1b5a (ceph): pybind/mgr/restful: all crt/key or filename in config-key
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:27 PM rgw Bug #20190 (Pending Backport): "datalog trim" can't work as expected
- 06:26 PM Revision 2076175e (ceph): Merge pull request #15507 from zhangsw/fix-rgw-logtrim-bug
- rgw: datalog trim and mdlog trim handles the result returned by osd incorrectly.
Reviewed-by: Casey Bodley <cbodley@... - 06:23 PM rgw Bug #20205: rgw: s3 api, need to return error NoSuchVersion when object does not exist and versio...
- https://github.com/ceph/ceph/pull/15528
- 06:23 PM rgw Bug #20206: rgw: delete null versioned object doesn't return x-amz-version-id http header
- https://github.com/ceph/ceph/pull/15528
- 06:15 PM Revision b0e9f3ed (ceph): Merge pull request #15102 from majianpeng/blockdevice-pmem
- os/bluestore/BlockDevice: support pmem device as bluestore backend
Reviewed-by: Sage Weil <sage@redhat.com> - 06:09 PM Bug #20226 (Fix Under Review): recovery sleep event wakes up with bogus PG*
- https://github.com/ceph/ceph/pull/15582
- 06:07 PM Bug #20226 (Resolved): recovery sleep event wakes up with bogus PG*
- ...
- 06:08 PM Revision a40f9871 (ceph): osd: take PGRef for recovery sleep wakeup event
- The raw PG* may not remain valid when the event fires.
Fixes: http://tracker.ceph.com/issues/20226
Signed-off-by: Sa... - 06:06 PM rgw Bug #20210: rgw: fix input/output err when using radosgw-admin bi list
- Does that still happen, even after: https://github.com/ceph/ceph/pull/14981 ?
- 06:03 PM rgw Bug #20211: rgw: bucket index not syncing when rados cluster abnormally
- I don't understand what step (4) is. What do you mean fail bucket index add op.
- 06:01 PM Revision a3e23a7c (ceph): qa: update krbd_data_pool.sh to match the new rados ls behavior
- See commit e9973adf1fb7 ("PendingReleaseNotes: notes on whiteouts vs
pgnls").
Signed-off-by: Ilya Dryomov <idryomov@... - 05:56 PM rgw Bug #18596: rgw: object owner should not be able to download the obj without container permission...
- Not quite. There are a set of permissions that will do that, however, if these permissions are not set then users wil...
- 05:56 PM Revision 108b38ef (ceph): Merge pull request #15577 from jcsp/wip-dashboard-cleanup
- mgr: dashboard code cleanup
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 05:53 PM RADOS Bug #19960 (Pending Backport): overflow in client_io_rate in ceph osd pool stats
- 03:14 PM RADOS Bug #19960: overflow in client_io_rate in ceph osd pool stats
- > By which commit/PR?
554cf8394a9ac4f845c1fce03dd1a7f551a414a9
Merge pull request #15073 from liewegas/wip-mgr-stats - 05:26 PM Revision 651fcd44 (ceph): objclass-sdk: use namespace ceph for bufferlist
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 03:49 PM rgw Bug #17779 (Fix Under Review): rgw: s3 API does not honor rgw_keystone_implicit_tenants when keys...
- https://github.com/ceph/ceph/pull/15572
- 03:43 PM Revision f23c68f1 (ceph): mgr/dashboard: fix error handling in remote_view_cache
- Signed-off-by: John Spray <john.spray@redhat.com>
- 03:43 PM Revision f1750905 (ceph): mgr/dashboard: fix server view on funny version format
- Signed-off-by: John Spray <john.spray@redhat.com>
- 03:43 PM Revision b48011d6 (ceph): mgr/dashboard: remove confusing SyncObject stuff
- This was a hangover from when these wrapper classes
were borrowed from Calamari, which used these
versions/equality f... - 03:43 PM Revision 4296962e (ceph): mgr/dashboard: keep a global librados instance
- ...so that classes that need one aren't creating
their own all the time.
Signed-off-by: John Spray <john.spray@redha... - 03:11 PM Documentation #20199 (Resolved): [doc] Default values in docu does not reflect changes in the sou...
- https://github.com/ceph/ceph/pull/15566
- 03:10 PM Revision 630010fd (ceph): Merge pull request #15566 from baruza/wip-doc-20199
- doc: Change the default values of some OSD options
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:02 PM Revision 5bfd0b45 (ceph): Merge pull request #15485 from ceph/wip-hdd-throttle-cost
- common/config_opts.h: Lower HDD throttle cost.
Reviewed-by: Sage Weil <sage@redhat.com> - 02:59 PM Revision d010f6a1 (ceph): Merge pull request #15203 from Liuchang0812/wip-kill-broken-links
- doc: kill some broken links
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:53 PM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- it's not relevant. and jewel's "ceph_test_librbd_api" crashed in a different way when dynamically linked against libr...
- 02:25 PM Bug #19200: RHEL 7.3 Selinux denials at OSD start
- I originally opened this issue on Kraken and my configuration consists of HDD OSD and multiple journal partitions on ...
- 11:04 AM Bug #19200: RHEL 7.3 Selinux denials at OSD start
- Hi Boris,
Indeed, I use a single NVME device for both the OS filesystems, and the 12 journal partitions for my OSD... - 02:12 PM rgw Bug #20225 (Resolved): 'radosgw-admin usage show' listing 0 bytes_sent/received
- Fixed in master with: https://github.com/ceph/ceph/pull/14042
- 02:12 PM Revision 6ce28c40 (ceph): debian: sync logrotate packaging with downstream
- both Ubuntu and Debian put the logrotate script into
ceph-common, to ensure that radosgw logs are rotated as
well.
t... - 02:03 PM Revision 8f1146aa (ceph): mgr: don't let TYPE_CLIENT entities send stats
- Anyone instantiating librados instances ended up
appearing as a weird entry in DaemonStateIndex.
Come back to this a... - 02:03 PM Revision 040e8cf3 (ceph): mgr: drop PyModules::lock around module shutdown calls
- This deadlocked if the module's shutdown call was trying
to take a pythonland lock that was held by a thread
that was... - 01:57 PM Revision ec9801ec (ceph): mgr: don't log successful ceph_config_get as err
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:55 PM Revision cc7b8e46 (ceph): Merge pull request #15575 from liewegas/wip-pgnls-note
- PendingReleaseNotes: notes on whiteouts vs pgnls
- 01:52 PM Revision de6b679f (ceph): Merge pull request #15309 from ifed01/wip-bluestore-boost-statfs
- os/bluestore: keep statfs replica in RAM to avoid expensive KV retrieval
Reviewed-by: Sage Weil <sage@redhat.com> - 01:41 PM Revision e9973adf (ceph): PendingReleaseNotes: notes on whiteouts vs pgnls
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:32 PM rbd Bug #20223 (Fix Under Review): rbd.ImageNotFound: __init__() takes exactly 3 positional arguments...
- *PR*: https://github.com/ceph/ceph/pull/15574
- 01:29 PM rbd Bug #20223 (In Progress): rbd.ImageNotFound: __init__() takes exactly 3 positional arguments, 1 g...
- 01:29 PM rbd Bug #20223: rbd.ImageNotFound: __init__() takes exactly 3 positional arguments, 1 given
- OpenAttic serializes the exception via multiprocessing pipes. The new OSError exception cannot be properly serialized...
- 01:25 PM rbd Bug #20223: rbd.ImageNotFound: __init__() takes exactly 3 positional arguments, 1 given
- <jdillaman> sebastian-w: I wonder if the issue is that the new rbd.OSError is not picklable for the multiprocessing.P...
- 11:46 AM rbd Bug #20223 (Resolved): rbd.ImageNotFound: __init__() takes exactly 3 positional arguments, 1 given
- While investigating https://tracker.openattic.org/browse/OP-2311, I came across this lines:...
- 01:30 PM Revision c884cc01 (ceph): pybind/rbd: OSError should be picklable
- Fixes: http://tracker.ceph.com/issues/20223
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:24 PM mgr Bug #20222: v12.0.3 Luminous bluestore 'tp_osd_tp thread tp_osd_tp' had timed out after 60
- Note,, we are facing this issue, only with putting write load via librados with C API {http://docs.ceph.com/docs/mast...
- 11:05 AM mgr Bug #20222 (Duplicate): v12.0.3 Luminous bluestore 'tp_osd_tp thread tp_osd_tp' had timed out aft...
- Hello,
Env:-- 5 node, v12.0.3, EC 4+1 bluestore , RHEL 7.3 - 3.10.0-514.el7.x86_64
Problem desc...:-- bluestor... - 01:21 PM mgr Bug #20208: ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
- https://github.com/ceph/ceph/pull/15573 for the second instance that loic saw; haven't figured out the first instance...
- 07:47 AM mgr Bug #20208: ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
- I'm testing the proposed patch as well.
- 02:51 AM mgr Bug #20208 (In Progress): ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
- I think there are two crashes.. the second one,...
- 01:18 PM Revision a883bac0 (ceph): mon/PGMap: erase osd_epochs entry too when we erase osd_stat entry
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:17 PM Revision c2258991 (ceph): mgr/ClusterState: dump pgmap and inc at dout 30
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:43 PM Revision 82c77bcb (ceph): rgw: external auth engines of S3 honor rgw_keystone_implicit_tenants.
- Fixes: http://tracker.ceph.com/issues/17779
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 11:42 AM Revision 578468f3 (ceph): Merge pull request #15532 from dillaman/wip-rbd-mirror-stress
- rbd-mirror: lock loss during sync should wait for in-flight copies
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 11:41 AM Revision eac34cc5 (ceph): Merge pull request #15518 from dillaman/wip-rbd-missing-default-pool
- rbd: removed hardcoded default pool
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 11:38 AM Revision b14ced7b (ceph): os/bluestore: keep statfs replica in memory to avoid expensive KV access
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:38 AM Revision 07761f2a (ceph): os/bluestore: introduce debug parameter to bypass bdev verification
- E.g. this allows to backup WAL/DB volumes after preconditioning and quickly rollback to that state when needed.
Sign... - 11:38 AM Revision e081091a (ceph): os/bluestore: introduce a debug switch to bypass kv update.
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:37 AM Revision 2e47f36a (ceph): os/bluestore: move volatile_statfs struct out of TransContext
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:35 AM Revision 41305afe (ceph): test/fio: fix lack of setting for Sequencer::shard_hint
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:18 AM Revision e64b4c86 (ceph): test/msgr: silence warnings from -Wsign-compare
- The following warning appears during make in the latest code:
ceph/src/test/msgr/test_msgr.cc:1474:46: warning: comp... - 11:00 AM RADOS Bug #18746: monitors crashing ./include/interval_set.h: 355: FAILED assert(0) (jewel+kraken)
- Hi Greg,
Thank you for taking the time to look into this.
Following the incident of the present ticket the clus... - 10:52 AM Revision 40e84a13 (ceph): Merge pull request #15433 from wjwithagen/wip-wjw-prettytable
- ceph-disk: add setting for external py-modules for tox-testing
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:25 AM Revision 449b8b7f (ceph): rgw_file: use predefined format_child_name to replace raw string concat...
- Signed-off-by: Gui Hecheng <guihecheng@cmss.chinamobile.com>
- 09:49 AM Revision 706de54d (ceph): doc: Change the default values of some OSD options
- These values were changed to reflect this change a3f9cba
Fixes: http://tracker.ceph.com/issues/20199
Signed-off-by: ... - 09:33 AM Revision 91d36b64 (ceph): ceph-disk: use system modules if needed
- - prettytable usage was introduced in:
https://github.com/ceph/ceph/commit/3fa8bb1
It is in the install-deps.sh f... - 07:15 AM rgw Bug #20220 (Resolved): mismatch Signature in swift formpost
- When use the feature of swift FormPost correctly according to the doc, it will also return "FormPost: Invalid Signatu...
- 07:05 AM Revision 0e2223cf (ceph): rgw_file: pass bucketname instead of uri for bucket create/delete
- Signed-off-by: Gui Hecheng <guihecheng@cmss.chinamobile.com>
- 05:47 AM rgw Backport #19847 (In Progress): jewel: multisite: incremental metadata sync does not properly adva...
- 05:04 AM Revision cddef419 (ceph): mds: cleanup MDCache::eval_remote()
- MDCache::eval_remote() tries migrating stray to current mds even
remote dentry's auth mds is not current mds. This do... - 05:04 AM Revision d2ab40fe (ceph): mds: move MDCache::eval_remote into StrayManager
- Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
- 04:23 AM Revision 2b427198 (ceph): tools/rbd_mirror: do not include ununsed header
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:21 AM Revision a87fa37e (ceph): cmake,debian,rpm: remove atomic_t completely
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:21 AM Revision 5e06938b (ceph): client: s/atomic_t/std::atomic<>
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:20 AM Revision e7025645 (ceph): msg,client,os,journal: do not include unused header
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:51 AM Revision f6d67599 (ceph): msg/async: s/atomic_t/atomic<>/
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:46 AM Revision 161ea38f (ceph): osdc/Objecter: s/atomic_t/std::atomic<>/
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:46 AM Revision 28c83737 (ceph): msg,common: do not include assert.h everywhere to clobber <assert.h>
- * reverts c93daaf92b643a06a822558973d377733dbd9d85
* add "#include "include/assert.h" to where <cassert> or <assert.h... - 03:46 AM Revision a3a958fa (ceph): rgw: rgw_rados: s/atomic_t/atomic<>/
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:23 AM Revision fd48d550 (ceph): common/ceph_context: s/atomic_t/std::atomic<>/
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:00 AM Revision 0974691a (ceph): add default note info to size (create and resize)
- Signed-off-by: Zheng Yin <zhengyin@chinac.com>
- 02:52 AM Revision 0384acea (ceph): mgr/DaemonServer.cc: log daemon type string as well as id
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 01:57 AM Revision c7034595 (ceph): Merge pull request #14866 from chardan/jfw-wip-halflife_atomic_t-varan
- common,test: migrate atomic_t to std::atomic
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:19 AM rgw Bug #20218 (Closed): rgw: some problem set bucket policy in master branch
- i test set bucket policy in master branch ceph cluster, i test RGW Bucket Policies #14307 in my ceph cluster, but i s...
- 01:17 AM Bug #18580 (Closed): WITH_SPDK=ON: /usr/local/lib/librte_eal.a: error adding symbols: Bad value
- it looks resolved
- 12:46 AM Bug #20217 (Closed): cephfs can be mounted even when keyring is modified
- Modified the last letter of keyring, cephfs can be mounted with this wrong keyring and write/read operation is also a...
- 12:43 AM Revision 1eae74ec (ceph): osd: when osd is not in failure_pending, we don't need to get osd inst ...
- Signed-off-by: linbing <linbing@t2cloud.net>
06/07/2017
- 11:16 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- Yes, that's correct.
- 10:23 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- Just to check I understand -- the claim is that we are seeing the object in pgnls output because it has a snapshot th...
- 10:04 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- Agree with Greg. Also: making pgnls skip whiteout objects means we need to load the object_info_t, which is signific...
- 07:45 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- I don't think we want a plain "rados ls" with no flags (--all?) output something that can't be "rados stat"ed. Suppo...
- 05:12 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- Hmm, listing and snapshots have never gotten along well, but that makes me think we should list stuff even if it does...
- 10:24 PM Bug #20216: mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- This appears to be something with cherrypy.. when restful fails to bind the module doesn't start but mgr survives. n...
- 08:52 PM Bug #20216 (Resolved): mgr: dashboard failure to bind to port 7000 (or whatever) makes mgr exit/fail
- ...
- 10:08 PM Revision 8a0d6720 (ceph): Merge pull request #15520 from liewegas/wip-max-object-size
- osd: reduce rados_max_object_size from 100 GB -> 128 MB
Reviewed-by: Gregory Farnum <gfarnum@redhat.com>
Reviewed-by... - 10:07 PM Revision ca3d9e6a (ceph): osd: reduce rados_max_object_size from 100 GB -> 128 MB
- I'm not sure why we had this so huge! 128 MB is a pretty reasonable size.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:03 PM Bug #19200: RHEL 7.3 Selinux denials at OSD start
- Hi Ruben,
what do you use as a storage? It looks like ceph-osd is trying to read/write /dev/nvme0n1p10. Do you use... - 09:00 PM Revision 8ded50ed (ceph): Merge pull request #15230 from chardan/jfw-wip-halflife_atomic_t-xio
- xio: migrate atomic_t to std::atomic<>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:00 PM Revision c011314b (ceph): Merge pull request #15516 from javacruft/i386-cmake-fixes
- cmake: misc fixes for build on i386
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:59 PM Revision 91c5af15 (ceph): Merge pull request #15525 from wjwithagen/wip-wjw-clang-testosdmap
- test: osd/TestOSDMap.cc: fix Clang complain about promotion
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:59 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- Guessing this is related, since it's also an incorrect prior_version:...
- 08:57 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-07_16:25:35-rados-wip-sage-testing2-distro-basic-smithi/1268182
rados/thrash-erasure-code/{ceph.ya... - 02:03 AM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-06_21:54:14-rados-wip-sage-testing-distro-basic-smithi/1265627
rados/thrash/{0-size-min-size-overr... - 08:55 PM Bug #19595 (Fix Under Review): mgr: segv in msgr thread, with no core
- https://github.com/ceph/ceph/pull/15557
- 08:54 PM Revision 2fd49a1a (ceph): mgr/MgrStandby: respawn when deactivated
- - It is ugly to unwind all of the Mgr state so that we can reactivate
later.
- It is perhaps impossible to do shut ... - 08:40 PM Bug #20063 (Resolved): mgr: cluster log messages appear as 'client.x' instead of 'mgr.name'
- 08:26 PM Revision e1cfaedc (ceph): rbd: removed hardcoded default rbd pool name
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:26 PM Revision d9a9a07c (ceph): pybind/rbd: module should depend on librbd not rbd CLI
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:26 PM Revision c6cd5a94 (ceph): rbd-replay: removed default rbd pool name
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:26 PM Revision 708d7bb0 (ceph): rbd-nbd: removed default rbd pool name
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:26 PM Revision af615a59 (ceph): common: new 'rbd_default_pool' configuration option
- The 'rbd' pool will no longer be automatically created. Allow
the user to specify a custom default RBD pool name.
Si... - 08:11 PM RADOS Documentation #20215 (New): librados documentation improvement for the use cases
- librados documentation improvement for the use cases including the tradeoffs of object size, i/o rate, and omap vs re...
- 08:09 PM Revision 21d19325 (ceph): rbd-mirror: narrowed scope of exclusive lock op tracking
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 07:33 PM Revision 02f9ea4b (ceph): rbd-mirror: partial revert of 649b29d
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:47 PM Revision 4327d1bd (ceph): Document RGW quota cache options
- Quota cache options were undocumented.
Fixes: http://tracker.ceph.com/issues/18747
Signed-off-by: Daniel Gryniewicz ... - 06:13 PM Revision ce1fc349 (ceph): Merge pull request #15312 from theanalyst/wip-20078
- jewel: rgw: only append zonegroups to rest params if not empty
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:05 PM Revision 3ff89b32 (ceph): rgw: change metadata read_sync_status interface
- makes the same change to read_sync_status() in RGWMetaSyncStatusManager,
needed to support multiple concurrent reader... - 06:05 PM Revision c9c90e42 (ceph): rgw: use RGWShardCollectCR for RGWReadSyncStatusCoroutine
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit a4bf014b8642073f3eac226a93f6360cdd9cee25)... - 06:05 PM Revision e02ad5d7 (ceph): rgw: period commit uses sync status markers
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit bb49e2fbed3a87de837329cfa0c11f8d97633a94)... - 06:05 PM Revision f6f01436 (ceph): rgw: require --yes-i-really-mean-it to promote zone with stale metadata
- if a zone is promoted to master before it has a chance to sync from the
previous master zone, any metadata entries af... - 06:05 PM Revision e0d2d4f2 (ceph): rgw: remove rgw_realm_reconfigure_delay
- when the master zone is changed, this config variable was increasing the
window of time where the old master zone wou... - 05:46 PM rgw Backport #19847: jewel: multisite: incremental metadata sync does not properly advance to next pe...
- https://github.com/ceph/ceph/pull/15556
- 05:43 PM Revision 3d49aace (ceph): rgw: store realm epoch with sync status markers
- sync status markers can't be compared between periods, so we need to
record the current period's realm epoch with its... - 05:43 PM Revision 6de70257 (ceph): rgw: RGWBackoffControlCR only retries until success
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit a898fb76a4179add68ccb526f2917768736ac52b)... - 05:43 PM Revision f16a9a23 (ceph): rgw: clean up RGWInitDataSyncStatusCoroutine
- RGWInitDataSyncStatusCoroutine operates on a given rgw_data_sync_status
pointer, which saves us from having to read i... - 05:42 PM Revision 5e78f0eb (ceph): rgw: fix marker comparison to detect end of mdlog period
- Fixes: http://tracker.ceph.com/issues/18639
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 05:42 PM Revision aa336287 (ceph): rgw: add == and != operators for period history cursor
- RGWMetaSyncCR was using operator== but it always returned true!
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(ch... - 05:39 PM Revision 457c01c7 (ceph): rgw: fix for broken yields in RGWMetaSyncShardCR
- Fixes: http://tracker.ceph.com/issues/18076
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 05:39 PM Revision 99603cdf (ceph): rgw: use separate http_manager for read_sync_status
- concurrent users of read_sync_status() use different cr managers, when get_resource must
use http_manager related to ... - 05:35 PM rgw Bug #20112 (Resolved): Use boost::regex instead of std::regex for rgw_iam_policy.cc and rgw_role.cc
- 05:29 PM Revision 7059b9b2 (ceph): Merge pull request #15498 from adamemerson/wip-fixation
- test: Fix narrowing conversion
rgw: Support certain archaic and antiquated distributions
Reviewed-by: Kefu Chai <kch... - 05:24 PM Revision 97ffe49d (ceph): test/rgw: fixes for test_multi_period_incremental_sync()
- test was only creating objects in subsequent periods, which wasn't
adding any entries to the mdlog. this wasn't corre... - 05:24 PM Revision 7966b846 (ceph): test/rgw: wait for realm reload after set_master_zone
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit 5cc99db52423f9ee98a549b215559c677f178f48) - 05:24 PM Revision 7c19e375 (ceph): test/rgw: meta checkpoint compares realm epoch
- avoid marker comparisons between different periods
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked f... - 04:44 PM RADOS Bug #18696: OSD might assert when LTTNG tracing is enabled
- Wonder if this PR https://github.com/ceph/ceph/pull/14304 fixes this issue as well.
- 04:39 PM Feature #20087: OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- Greg Farnum wrote:
> https://trello.com/c/CYMJXbY8/32-osd-make-osd-ping-messages-large
>
> https://github.com/cep... - 04:36 PM Revision 17376dbf (ceph): Merge pull request #15436 from liewegas/wip-versions
- mon: {mon,osd,mds} {versions,count-metadata}
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:17 PM Revision 2cbcec18 (ceph): Merge pull request #15501 from liewegas/wip-blocked-is-err
- mon/PGMap: call blocked requests ERR not WARN
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Greg Farnum <gf... - 04:16 PM Revision 7cacb701 (ceph): mon/PGMap: call requests blocked for 128x as long ERR not WARN
- - rename the option (max -> warn)
- add an err_..._ratio multiplier
- switch to HEALTH_ERR once requests are blocked ... - 04:11 PM Revision af8d9bdf (ceph): rgw: Support certain archaic and antiquated distributions
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 04:01 PM RADOS Bug #18750: handle_pg_remove: pg_map_lock held for write when taking pg_lock
- I think I remember this one and it wasn't really feasible to fix (at the time). If doing code inspection you'll want ...
- 04:00 PM Bug #19221 (Can't reproduce): unittest_compression segfaults in CompressionPlugin.all
- 03:59 PM Bug #19202 (Can't reproduce): FAILED assert(p != spanning_blob_map.end()) in ceph_test_objectstore
- i haven't seen it
- 03:59 PM RADOS Bug #18746: monitors crashing ./include/interval_set.h: 355: FAILED assert(0) (jewel+kraken)
- Pretty weird, that assert appears to be an internal interval_set consistency thing: https://github.com/ceph/ceph/blob...
- 03:58 PM RADOS Bug #19198: Bluestore doubles mem usage when caching object content
- 03:57 PM Bug #19197 (Can't reproduce): live obc after interval change on EC pool
- 03:57 PM Bug #19193 (Resolved): Latest 0.94.10 RPMs for Hammer / el6 / x86_64 missing at http://download.c...
- 03:56 PM Bug #19187 (Closed): Delete/discard operations initiated by a qemu/kvm guest get stuck
- 03:55 PM Bug #19138 (Won't Fix): "Ceph -w" may have overlapped output when there are too many PG status
- ceph -s is totally redone in luminous
- 03:53 PM Revision 9e37d893 (ceph): Documentation: Fixed my mistake of describing the journal allowed vs de...
- Update to Bug http://tracker.ceph.com/issues/19879
Signed-off-by: Sameer Tiwari <stiwari@salesforce.com> - 03:52 PM Bug #18739 (Won't Fix): FAILED assert(0 == "out of order op") in jewel integration testing
- Apparently this was a result of not recording failed ops in the PGLog. We are unlikely to fix that for Jewel — it's h...
- 03:50 PM RADOS Bug #18667: [cache tiering] omap data time-traveled to stale version
- Jason says this "seems to pop up randomly every few weeks or so", so it's definitely a live, going concern. :(
- 03:40 PM Bug #19100 (Can't reproduce): "AssertionError: failed to complete snap trimming before timeout" i...
- 03:40 PM RADOS Bug #19086 (Rejected): BlockDevice::create should add check for readlink result instead of raise ...
- 03:37 PM Revision 42fb84b8 (ceph): test: Fix narrowing conversion
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 03:37 PM Bug #19077 (Resolved): Resize TextTable columns to the widest element of each column
- This was recently reweritten to use TextTable, appeasr to be fine now:...
- 03:36 PM RADOS Bug #18647: ceph df output with erasure coded pools
- Let's verify this prior to Luminous and write a test for it!
- 03:33 PM Messengers Bug #18664: ceph_test_msgr SIGABRT in decode_message, SimpleMessenger, can't decode unknown messa...
- Apparently this hasn't reproduced?
- 03:30 PM Bug #19024 (Can't reproduce): ec pool stuck incomplete, active+remapped -- crush mapping anomaly?
- no logs. will keep an eye out on future runs.
- 03:30 PM Support #18630 (Closed): ceph osd after reinstall always in down state
- At a skim this is just the result of trying to reuse OSD IDs without having completely removed its existence from the...
- 03:29 PM RADOS Bug #19023 (Fix Under Review): ceph_test_rados invalid read caused apparently by lost intervals d...
- https://github.com/ceph/ceph/pull/15555
- 03:29 PM Revision d24a8886 (ceph): PG: set CLEAN if we have enough replicas
- Previously, we'd only set CLEAN if we were not also remapped, but we'd
set last_epoch_clean anyway. Unfortunately, t... - 03:27 PM Revision 31d3ae8a (ceph): PG: only mark_clean if we are active and not just peered
- Fixes: http://tracker.ceph.com/issues/19023
Signed-off-by: Samuel Just <sjust@redhat.com> - 03:25 PM Bug #18580: WITH_SPDK=ON: /usr/local/lib/librte_eal.a: error adding symbols: Bad value
- Still an issue?
- 03:23 PM Bug #19020 (Resolved): "unlikely race on master" OSDMapMapping.h: 31: FAILED assert(shards == 0)
- 03:22 PM Revision e25accff (ceph): os/bluestore/BlockDevice:support pmem device as bluestore backend.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 03:21 PM mgr Feature #17459 (Closed): Install rest module dependencies in test environment
- 03:20 PM mgr Feature #17456 (Resolved): Migrate nonessential PGMap data away from ceph-mon
- 03:20 PM mgr Bug #19399 (Won't Fix): mgr: add django packaging for ceph-mgr rest module
- 03:18 PM mgr Bug #19648 (Resolved): ceph-mgr aborted after start
- 03:18 PM mgr Bug #19913 (Resolved): load plugin `rest` failed
- 02:57 PM Revision 1cdb14cf (ceph): rgw:fix memory leaks
- Signed-off-by: weiqiaomiao <wei.qiaomiao@zte.com.cn>
(cherry picked from commit 73e5be2b6133cf4caa0e5e5c8c9eae748b785... - 02:55 PM Revision 5f9ed406 (ceph): rgw: dont spawn error_repo until lease is acquired
- if RGWDataSyncShardCR fails to acquire its lease, it doesn't call
error_repo->finish() to stop the coroutine. wait un... - 02:48 PM Revision 99332b9a (ceph): Merge pull request #15531 from liewegas/wip-osd-pglog
- osd: rename osd -> osd_pglog; include pglog-related bufferlists
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-b... - 02:48 PM Revision b7f52618 (ceph): osd: map ObjectModDesc to osd_pglog pool
- This can consume significant space for EC pools.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:48 PM Revision b322be3b (ceph): osd: put pg_log_entry_t::snaps in osd_pglog mempool
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:48 PM Revision 85887a7a (ceph): osd/osd_types: put pg_log_entry_t::extra_reqids in osd_pglog mempool
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:48 PM Revision 5b3cfc08 (ceph): osd: move pglog to osd_pglog mempool
- This actually everything in the osd mempool, so it's basically a rename.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:34 PM Revision 8f5a5a9c (ceph): Merge pull request #15413 from tchaikov/wip-rgw-boost-cleanup
- rgw: drop asio/{yield,coroutine}.hpp replacements
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:07 PM Revision b34507fb (ceph): Merge pull request #15434 from yuyuyu101/wip-lz4
- compressor: add LZ4 support
Reviewed-by: Sage Weil <sage@redhat.com> - 02:05 PM Revision 136b1c1f (ceph): Merge pull request #15512 from jcsp/wip-mgrmap-epoch
- mon: don't prefix mgr summary with epoch number
Reviewed-by: Sage Weil <sage@redhat.com> - 02:02 PM Revision fca17212 (ceph): Merge pull request #15437 from dachary/wip-bluestore
- ceph-disk: add --filestore argument, default to --bluestore
Reviewed-by: Sage Weil <sage@redhat.com> - 01:48 PM rbd Feature #3499 (Resolved): qemu-rbd: support bdrv_has_zero_init
- Addressed in upstream commit 3ac21627
- 01:45 PM Fix #6977 (Resolved): objecter: ENOSPC returned by pool quota will cause IO errors for non-cached...
- Fixed by #12018
- 01:43 PM Revision 8ccd0c79 (ceph): Merge pull request #15547 from wjwithagen/wip-wjw-freebsd-get_device_by_fd
- common/blkdev.cc: propagate get_device_by_fd to different OSes
Reviewed-by: Sage Weil <sage@redhat.com> - 01:41 PM Support #9249 (Closed): unable map stripe rbd
- Duplicate of #3837
- 01:41 PM Revision f477191a (ceph): Merge pull request #15435 from liewegas/wip-bluestore-warning
- os/bluestore: fix warning
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Jos Collin <jcollin@redhat.com> - 01:40 PM Feature #9251 (Duplicate): check consistency of rbd export and import function
- Duplicate of #6934
- 01:40 PM Feature #9401 (Resolved): RBD: Provide a way to know how much space is used by a clone
- 'rbd du' command can calculate disk usage of an image.
- 01:39 PM Revision 59dc84df (ceph): tools/rgw: add script to inspect admin socket "cr dump"
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 01:38 PM Tasks #10019 (Closed): rbd
- Assuming this is no longer an issue
- 01:35 PM Bug #18824 (Duplicate): Unclear about using v2 RBD image
- Duplicating to #19035
- 01:34 PM rbd Feature #18917: rbd: show the latest snapshot in rbd info
- Note that the most recent snapshot might not be what the HEAD revision of the image is based upon if a rollback was u...
- 01:31 PM Revision 94d17fbe (ceph): Merge pull request #15371 from liewegas/wip-mon-client-features
- mon: track features from connect clients, and use it to gate set-require-min-compat-client
Reviewed-by: Josh Durgin ... - 01:31 PM Bug #19459 (Won't Fix): snap rollback failed after rbd client exited or osd rebooted abnornally
- This is the expected behavior when using the exclusive lock functionality.
- 01:30 PM Feature #20001 (Duplicate): RBD cache persistence
- Duplicate of #15687
- 01:23 PM RADOS Bug #19960: overflow in client_io_rate in ceph osd pool stats
- Aleksei Gutikov wrote:
> fixed in master
By which commit/PR? - 12:04 PM RADOS Bug #19960: overflow in client_io_rate in ceph osd pool stats
- fixed in master
- 01:21 PM Documentation #20199: [doc] Default values in docu does not reflect changes in the source code
- @Bara - could you change the commit message so it says "Fixes: http://tracker.ceph.com/issues/20199" instead of "Fixe...
- 11:14 AM Documentation #20199: [doc] Default values in docu does not reflect changes in the source code
- Created this patch: https://github.com/baruza/ceph/commit/e51f5af78cc0f5583d296a06b7169cc391f1328f
(not sure what... - 01:19 PM rgw Bug #20211 (Fix Under Review): rgw: bucket index not syncing when rados cluster abnormally
- 08:25 AM rgw Bug #20211: rgw: bucket index not syncing when rados cluster abnormally
- https://github.com/ceph/ceph/pull/15545
- 08:15 AM rgw Bug #20211 (Fix Under Review): rgw: bucket index not syncing when rados cluster abnormally
- Bucket index syncing Issue occur in our environment.
I think one can reproduce it by steps:
1. deploy multisit... - 01:19 PM rgw Bug #20210 (Fix Under Review): rgw: fix input/output err when using radosgw-admin bi list
- 07:53 AM rgw Bug #20210: rgw: fix input/output err when using radosgw-admin bi list
- https://github.com/ceph/ceph/pull/15543
- 07:45 AM rgw Bug #20210 (Fix Under Review): rgw: fix input/output err when using radosgw-admin bi list
- radosgw-admin bi list report input/output err;
one can reproduce it by steps:
1.deploy a multisite environment and ... - 12:56 PM rgw Bug #20107: rgw: Truncated objects
- I found an example that is recent enough so that there are still some relevant logs available. Here an object got cop...
- 09:22 AM rgw Bug #20107: rgw: Truncated objects
- It seems this is happening when an object is copied, the copy has the same prefix for shadow objects as the original ...
- 12:06 PM rgw Backport #20088: valgrind reports leak in RGWRemoteMetadataCR
- Note the master commit is already in kraken:...
- 12:02 PM rgw Backport #20088 (Resolved): valgrind reports leak in RGWRemoteMetadataCR
- 11:48 AM Revision 7ca02525 (ceph): Merge pull request #15382 from theanalyst/wip-mem-leak2
- jewel: rgw:fix memory leaks in data/md sync
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 11:34 AM rgw-testing Bug #20214 (New): Add a test for multisite with 5G object
- 11:34 AM rgw-testing Bug #20213 (New): Add test for POST Content-MD5 header
- 11:14 AM CephFS Bug #20212 (Resolved): test_fs_new failure on race between pool creation and appearance in `df`
- ...
- 10:55 AM Revision 7b528b10 (ceph): doc/cephfs: mention RADOS object size limit
- Reflect the recent change in this limit
for 12.x.
Signed-off-by: John Spray <john.spray@redhat.com> - 10:48 AM Revision f3317f69 (ceph): rgw: introduce string_to_sign_t abstraction to the AWS auth.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:48 AM Revision bd81c216 (ceph): rgw: introduce rgw::auth::Strategy::apply() to deduplicate code.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:48 AM Revision 2417b640 (ceph): rgw: handle the Boto2 compatibility of AWSv4 in an abstract way.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 64cfc43f (ceph): rgw; rework interface and implementation of url_decode.
- This commit alters the url_decode() to remove its dependency
on Variable Length Array and unnecessary memory allocati... - 10:46 AM Revision 51383c3a (ceph): rgw: rework the implementation of rgw::auth::s3::get_v4_canonical_heade...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision e8dd37aa (ceph): rgw: use preallocated std::strings when concatenating in AWSv4.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 7e8d1d7c (ceph): rgw: replace magic strings in the AWSv4 code.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 5363643d (ceph): common/sstring: switch to boost::string_view as string_ref is deprecated.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision a8a9a840 (ceph): common/backport14: add the constexpr-capable variant of std::max().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision c8922285 (ceph): rgw: switch to Ceph's sstring in AWS signature generation process.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 20603086 (ceph): rgw: optimize AWSv4 parsing with Boost's small_vector.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 73e78ae0 (ceph): rgw: only rename AWSv2AuthStrategy -> AWSAuthStrategy.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 1cb269e1 (ceph): rgw: remove the duplicative trim_whitespace from rgw_common.cc.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision 7de45576 (ceph): rgw: drop 'using ceph::crypto::SHA256' from rgw_common.h.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:46 AM Revision c557fe2e (ceph): rgw: rework and optimise crafting of AWSv4's canonical query string.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 503d6878 (ceph): rgw: use std::make_shared for AWSv4 completers creation.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 1f628eb2 (ceph): rgw: clean-up AWSv4's Canonical QS crafting.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 5184842a (ceph): rgw: optimize and clean-up the AWSv4 signature processing.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision a5a8b272 (ceph): rgw: introduce rgw::auth::s3::AWS4_HMAC_SHA256_STR to kill magics.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 0e4e0e4d (ceph): rgw: switch from boost::string_ref to string_view in AWSv4-related code.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 8dab93de (ceph): rgw: switch from boost::string_ref to string_view in AWSv4-related code...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 29095d27 (ceph): rgw: ONLY move AWSv4Completer from rgw_rest_s3.cc to rgw_auth_s3.cc.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 139de6a0 (ceph): rgw: extend RGWRestfulIO to cover dynamic filter injection.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 2778a8ac (ceph): rgw: turn AWSv4Completer into a filter over rgw::io::RestfulClient.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 48093dca (ceph): rgw: drop aws4_auth_needs_complete from req_state.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision def8f641 (ceph): rgw: AWSv4Completer dechunks data in the streaming mode.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 25b71064 (ceph): rgw: implement calc_hash_sha256_restart_stream().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision eeb85997 (ceph): rgw: the AWSv4 completer verifies chunks' signatures now.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 0845d9c8 (ceph): rgw: remove the old AWS v4 streaming mode's implementation.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 68bc0d0b (ceph): rgw: split the AWSv4Completer and clean-up the code.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision dc270a61 (ceph): rgw: add support for HTTP_X_AMZ_DECODED_CONTENT_LENGTH.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 043abfa8 (ceph): rgw: handle AWSv4 in Browser Upload using the new auth infra.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 0b1d8b00 (ceph): rgw: clean-up rgw::auth::s3::get_v4_signature().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 4200e126 (ceph): rgw: rgw::auth::s3::parse_credentials() extracts access_key_id now.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision a33eb152 (ceph): rgw: make the get_v4_canonical_request_hash identified shorter.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 6e1daa88 (ceph): rgw: dissect AWSv4's expected payload extraction into a dedicated funct...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 420f1c00 (ceph): rgw: AWSv4's completer_factory takes the secret_key optionally.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision e126cadb (ceph): rgw: integrate AWSv4 auth schema with the new auth infra.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision a30d97a2 (ceph): rgw: make AWS_AUTHv4_IO const-friendly and const-correct.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 61d4f73b (ceph): rgw: switch to the Completer interface for the AWSv4 payload check.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 2d4e0006 (ceph): rgw: extend rgw::auth::Completer to handle commiting modifications to r...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision affa201e (ceph): rgw: implement the rgw::auth::Completer for AWSv4.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 36e1c34e (ceph): rgw: drop the old AWSv4 code.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 47d014c1 (ceph): rgw: implement rgw::auth::s3::is_v4_payload_empty.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 33f013b8 (ceph): rgw: refactor buf_to_hex and improve its const-correctness.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 405d31dc (ceph): rgw: clean up rgw::auth::s3::get_v4_signing_key.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 71417ca9 (ceph): rgw: eradicate req_state::aws4_auth::signed_hdrs.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 15144086 (ceph): rgw: eradicate req_state::aws4_auth::credential.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 619c8ed6 (ceph): rgw: decouple AWSv4 signature verification and payload fingerprint check.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 92409e10 (ceph): rgw: further minimise the req_state::aws4_auth shared state.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 79b826e5 (ceph): rgw: clean up the AWSv4 completion calls across RGWOps.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 06944f2e (ceph): rgw: AWSv4 completion verifies the payload's fingerprint only.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision fe4ef87d (ceph): rgw: decompose rgw::auth::s3::parse_credentials regarding the query str...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision d0b42311 (ceph): rgw: extend Version2ndEngine::Extractor to handle AWSv4 as well.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 8b4e1427 (ceph): rgw: ONLY change names due to AWSv4 adoption in the auth infra.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision e9a17ded (ceph): rgw: all S3 auth engines are able to use AWSv4 now.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision c9afd249 (ceph): rgw: get_v4_canonical_request_hash doesn't depend on req_state anymore.
- In AWSv4 the hash of real, transfered payload IS NOT necessary to form
a Canonical Request, and thus verify a Signatu... - 10:43 AM Revision 26952b94 (ceph): rgw: dissect AWSv4's Canonical URI crafting into a separated function.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision b000b352 (ceph): rgw: dissect AWSv4's Canonical QS crafting into a separated function.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 985c2bc5 (ceph): rgw: dissect AWSv4's Canonical Headers crafting into a separated function.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision b18996c5 (ceph): rgw: eradicate req_state::http_auth.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 67db70df (ceph): rgw: dissect basic AWSv4's credentials parsing into separated function.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 0b6adc66 (ceph): rgw: rgw::auth::s3::get_v4_signature doesn't depend on req_state anymore.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 9f594c57 (ceph): rgw: drop req_state::aws4_auth::payload_hash as it doesn't need to be g...
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 4b78946f (ceph): rgw: minimise the number of parameters of rgw::auth::s3::get_v4_signature.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 4e55c1d6 (ceph): rgw: add std::array-aware variants of calc_hmac_sha256() and buf_to_hex().
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision 195bf5c5 (ceph): rgw: split generation AWSv4's SigningKey into a separate func.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:43 AM Revision ac1a3f4a (ceph): rgw: aws4: add AWS4 auth support for S3 Post Object API
- RGW S3 supports HTTP POST requests so users can upload content directly.
This patch adds AWS v4 to handle form data ... - 10:43 AM Revision 98e153fe (ceph): rgw: rework interfaces of AWSv4 helper primitives.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 10:27 AM CephFS Feature #20196: mds: early reintegration of strays on hardlink deletion
- RP for the incomplete solution https://github.com/ceph/ceph/pull/15548
- 10:22 AM Revision 81c36dd5 (ceph): mds: link inode to newly created remote dentry
- this helps stray reintegration in workload that first creates new
hardlink, then removes old hardlink
Signed-off-by:... - 09:28 AM RADOS Bug #19783 (New): upgrade tests failing with "AssertionError: failed to complete snap trimming be...
- 09:21 AM Revision 6d83ae7d (ceph): common/blkdev.cc: propagate get_device_by_fd to different OSes
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 08:44 AM Revision a88896ac (ceph): Merge pull request #15530 from tchaikov/wip-jq-without-first
- qa/workunits/ceph-helpers.sh: use syntax understood by jq 1.3
Reviewed-by: David Zafman <dzafman@redhat.com> - 08:42 AM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- pull requests: https://github.com/ceph/ceph/pull/15544
- 08:32 AM mgr Bug #20208: ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
- Upgrading to urgent because it breaks some suites on master.
http://pulpito.ceph.com/loic-2017-06-07_08:03:59-ceph... - 05:53 AM mgr Bug #20208 (Resolved): ceph-mgr: mon/PGMap.cc: 1367: FAILED assert(end >= 0)
My wip-19657 is rebased on master at bc8c432a69cfb3ef0cc726c5ecd404a372a29d2b
http://pulpito.ceph.com/dzafman-20...- 08:13 AM Revision 998ee1d1 (ceph): doc: kill some broken links
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 08:08 AM ceph-ansible Bug #15569: Two logrotate scripts
- @Nathan:
I found my problem.
One of our ansible playbooks installed rados before the node had any clue about the ... - 07:22 AM Revision dcefefb5 (ceph): Documentation Fixes for http://tracker.ceph.com/issues/19879
- and related bug http://tracker.ceph.com/issues/20057
Signed-off-by: Sameer Tiwari <stiwari@salesforce.com> - 07:15 AM rgw Bug #19870: rgw: bytes_send and bytes_recv in the msg of usage show returning is 0 in master branch
- I may have found the teuthology tests. in ceph, master branch, "qa/tasks/radosgw_admin.py" and "qa/tasks/radosgw_adm...
- 06:50 AM rgw Bug #19432: rgw: folders starting with "_" underscore are not in bucket index
- Sorry for the delay.
I have reproduced it on master with Daniel Biazus instructions.
I could not reproduce it wit... - 06:48 AM Revision c5536b19 (ceph): tests: Add integration tests for admin socket output
- Add a framework to test all admin socket commands as reported by "help"
as well as custom commands.
Signed-off-by: B... - 06:34 AM RADOS Bug #19605: OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue.front() == repop)
- Zengran Zhang wrote:
> 2017-05-19 22:48:23.854608 7f14f1c1e700 0 -- 10.10.133.1:6823/2019 >> 10.10.133.1:6819/19544... - 06:25 AM rbd Subtask #18789 (Resolved): rbd-mirror A/A: coordinate image syncs with leader
- 06:03 AM Revision fcd313e3 (ceph): rgw_file: replace raw fs->fh_lru.unref with predefined fs->unref
- Cleanup for conciseness, also removes a ref on root_fh which does nothing.
Signed-off-by: Gui Hecheng <guihecheng@cm... - 05:47 AM Cleanup #20207: Remove the commented code in test submodule
- https://github.com/ceph/ceph/pull/15366
https://github.com/ceph/ceph/pull/15540 - 05:47 AM Cleanup #20207 (Resolved): Remove the commented code in test submodule
- During reviews, I found that there are lot of commented code exist in the test/ submodule. Some of them are single li...
- 05:09 AM Revision 853ae30b (ceph): Merge pull request #15423 from liewegas/wip-fix-indent
- mon/FSCommand: fix indentation
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:30 AM Revision b55b464f (ceph): Merge pull request #15497 from liewegas/wip-log-last
- mon/LogMonitor: 'log last' command
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:22 AM Bug #19901 (Pending Backport): LibRadosMiscConnectFailure.ConnectFailure hang
- 04:21 AM Bug #19901 (Resolved): LibRadosMiscConnectFailure.ConnectFailure hang
- 04:20 AM Revision 8904af1e (ceph): Merge pull request #15522 from liewegas/wip-19901
- ceph_test_rados_api_misc: fix LibRadosMiscConnectFailure.ConnectFailure retry
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:11 AM Revision b1726050 (ceph): mon/OSDMonitor: validate set-require-min-compat-client against connecte...
- Prevent the user from setting a require_min_compat_client if a disallowed
client is currently connected to the mon cl... - 03:11 AM Revision c73eeb58 (ceph): mon: add 'features' command to show connected client features
- for whole mon cluster
Signed-off-by: Sage Weil <sage@redhat.com> - 03:11 AM Revision 4c00be34 (ceph): common: ceph_release_[from_]features
- Map releases to client features (and back again).
Signed-off-by: Sage Weil <sage@redhat.com> - 03:09 AM Revision 0e28e758 (ceph): Merge pull request #15422 from liewegas/wip-osd-rotational
- osd: hdd vs ssd defaults for osd op thread pool
Reviewed-by: Mark Nelson <mnelson@redhat.com>
Reviewed-by: xie xingg... - 03:07 AM Revision bdbf7dce (ceph): Merge pull request #15517 from liewegas/wip-20197
- qa/suites/rados/upgrade: restart mds
- 03:04 AM Bug #16674 (Resolved): SELinux is preventing /usr/bin/ceph-osd from read access on the file blkid...
- 03:04 AM Revision c582c945 (ceph): Merge pull request #15523 from ceph/wip-16674
- selinux: Allow read on var_run_t
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:04 AM RADOS Bug #20000: osd assert in shared_cache.hpp: 107: FAILED assert(weak_refs.empty())
- ...
- 02:02 AM RADOS Bug #20169: filestore+btrfs occasionally returns ENOSPC
- /a/sage-2017-06-06_21:54:14-rados-wip-sage-testing-distro-basic-smithi/1265467
rados/thrash/{0-size-min-size-overrid... - 02:02 AM RADOS Bug #20169: filestore+btrfs occasionally returns ENOSPC
- /a/sage-2017-06-06_21:54:14-rados-wip-sage-testing-distro-basic-smithi/1265435
rados/thrash/{0-size-min-size-overr... - 01:52 AM Revision 7fd6e031 (ceph): rgw: datalog trim and mdlog trim handles the result returned by osd
- incorrectly.
Fixes: http://tracker.ceph.com/issues/20190
Signed-off-by: Zhang Shaowen <zhangshaowen@cmss.chinamobil... - 01:39 AM Backport #20032 (In Progress): jewel: osd_scrub_sleep option blocks op thread in jewel + later
- https://github.com/ceph/ceph/pull/15529
- 01:32 AM Revision a52445e3 (ceph): qa/workunits/ceph-helpers.sh: use syntax understood by jq 1.3
- trusty still ships jq 1.3 which does not offer "first". see
https://stedolan.github.io/jq/manual/v1.3/ .
Signed-off-... - 12:58 AM Revision aa0cd461 (ceph): osd: Move scrub sleep timer to osdservice
- PR 14886 erroneously creates a scrub sleep timer for every pg resulting
in a proliferation of threads. Move the timer... - 12:56 AM Revision 7bda34ea (ceph): Merge pull request #14745 from trociny/wip-18789
- rbd-mirror: coordinate image syncs with leader
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:32 AM Revision c41ab152 (ceph): Merge pull request #15243 from yuyuyu101/wip-20049
- msg: don't set msgr addr when disabing client bind
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:18 AM Revision 7bd8773f (ceph): Merge pull request #14117 from zhangsw/fix-rgw-getobjectmetadata-bug
- rgw: return the version id in get object and object metadata request.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
06/06/2017
- 11:26 PM Revision 48d596df (ceph): rgw: require --yes-i-really-mean-it to promote zone with stale metadata
- if a zone is promoted to master before it has a chance to sync from the
previous master zone, any metadata entries af... - 11:26 PM Revision cb957226 (ceph): rgw: remove rgw_realm_reconfigure_delay
- when the master zone is changed, this config variable was increasing the
window of time where the old master zone wou... - 11:26 PM Revision 81ced03d (ceph): rgw: period commit uses sync status markers
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit bb49e2fbed3a87de837329cfa0c11f8d97633a94)... - 11:16 PM Revision a9830dbd (ceph): rgw: use RGWShardCollectCR for RGWReadSyncStatusCoroutine
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit a4bf014b8642073f3eac226a93f6360cdd9cee25)... - 10:57 PM Revision c47bd056 (ceph): osd: Implement asynchronous scrub sleep
- Rather than blocking the main op queue just do an async sleep.
Fixes: http://tracker.ceph.com/issues/19497
Signed-o... - 10:48 PM Revision bc8c432a (ceph): Merge pull request #15386 from ivancich/wip-add-readme-that-dmclock-is-...
- doc: add README to dmclock subdir to inform developers it's a git subtree
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:46 PM Backport #20033 (In Progress): kraken: osd_scrub_sleep option blocks op thread in jewel + later
- https://github.com/ceph/ceph/pull/15526
- 10:44 PM Revision 0ab8e0ab (ceph): rgw: change metadata read_sync_status interface
- makes the same change to read_sync_status() in RGWMetaSyncStatusManager,
needed to support multiple concurrent reader... - 10:44 PM Revision 1c344e25 (ceph): rgw: add empty_on_enoent flag to RGWSimpleRadosReadCR
- RGWSimpleRadosReadCR won't currently fail with ENOENT, but instead
passes an empty object to handle_data(). add an em... - 10:44 PM Revision c19c7205 (ceph): rgw: add == and != operators for period history cursor
- RGWMetaSyncCR was using operator== but it always returned true!
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(ch... - 10:44 PM Revision 67011e51 (ceph): rgw: fix marker comparison to detect end of mdlog period
- Fixes: http://tracker.ceph.com/issues/18639
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 10:44 PM Revision 23736875 (ceph): rgw: clean up RGWInitDataSyncStatusCoroutine
- RGWInitDataSyncStatusCoroutine operates on a given rgw_data_sync_status
pointer, which saves us from having to read i... - 10:44 PM Revision 013d349c (ceph): rgw: RGWBackoffControlCR only retries until success
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit a898fb76a4179add68ccb526f2917768736ac52b) - 10:44 PM Revision ac9045ab (ceph): rgw: store realm epoch with sync status markers
- sync status markers can't be compared between periods, so we need to
record the current period's realm epoch with its... - 10:29 PM rgw Bug #20206 (New): rgw: delete null versioned object doesn't return x-amz-version-id http header
- 10:18 PM Revision 69af8fa2 (ceph): Merge pull request #15392 from dillaman/wip-20049
- msg: do not enable client-side binding by default
Reviewed-by: Haomai Wang <haomai@xsky.com> - 09:35 PM Revision 96f85585 (ceph): test: osd/TestOSDMap.cc: fix Clang complain about promotion
- /home/jenkins/workspace/ceph-freebsd/src/test/osd/TestOSDMap.cc:444:15: error: non-constant-expression cannot be narr...
- 09:27 PM rgw Bug #20205 (New): rgw: s3 api, need to return error NoSuchVersion when object does not exist and ...
- 09:15 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- Ah, yes, this is the SnapSet refactor, not bluestore. This was a semi-intentional change.
Before, we pgnls would i... - 08:31 PM Revision ba32343e (ceph): Merge pull request #15513 from Fabian-Gruenbichler/fixmgrdesc
- debian: ceph-mgr: fix package description
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <john.sp... - 08:27 PM Revision 6b30d660 (ceph): rgw: verify md5 in post obj
- Fixes: http://tracker.ceph.com/issues/19739
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:27 PM Revision c6742770 (ceph): Merge pull request #15375 from ivancich/wip-fix-dmclock-testing
- osd/dmclock/testing: reorganize testing, building now optional
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewe... - 08:26 PM Revision e3276bc2 (ceph): Merge pull request #15378 from Liuchang0812/print_ret_code_of_json_command
- ceph.in: print return code when json_command failed
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:26 PM Revision 61442139 (ceph): Merge pull request #15496 from wjwithagen/wip-wjw-host-to-ceph-errno
- core: include/types.h, introduce host_to_ceph_errno
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:25 PM Bug #20135 (Resolved): test/rest.py: PUT auth/add?entity=client.xx&caps=mon&caps=allow&caps=osd&c...
- 08:25 PM Revision 4a883677 (ceph): Merge pull request #15500 from liewegas/wip-20135
- pybind/ceph_argparse: fix empty string check
- 08:25 PM Revision 4d2d608e (ceph): Merge pull request #15502 from xiexingguo/wip-fix-overload-extents
- os/bluestore: avoid overloading extents during reshard; atomic deferred_batch_ops
Reviewed-by: Igor Fedotov <ifedoto... - 08:23 PM Revision 5d517f97 (ceph): qa/suites/rados/upgrade: restart mds
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:11 PM Feature #20087: OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- https://trello.com/c/CYMJXbY8/32-osd-make-osd-ping-messages-large
https://github.com/ceph/ceph/pull/15422
- 07:30 PM Bug #16674 (In Progress): SELinux is preventing /usr/bin/ceph-osd from read access on the file bl...
- 07:30 PM Bug #16674: SELinux is preventing /usr/bin/ceph-osd from read access on the file blkid.tab
- The code is still there. We already allow write on other caps on var_run_t so adding read does not seem like too much...
- 07:27 PM Revision 899adbf5 (ceph): selinux: Allow read on var_run_t
- Fixes: http://tracker.ceph.com/issues/16674
Signed-off-by: Boris Ranto <branto@redhat.com> - 07:16 PM Backport #19842: jewel: clean up min/max span warning
- Done, thanks.
- 07:15 PM Backport #19842 (In Progress): jewel: clean up min/max span warning
- 10:23 AM Backport #19842: jewel: clean up min/max span warning
- this backport issue is contained with another backport#19265
should we change some information about it? - 07:14 PM Bug #19901 (Fix Under Review): LibRadosMiscConnectFailure.ConnectFailure hang
- https://github.com/ceph/ceph/pull/15522
- 07:07 PM Bug #19901: LibRadosMiscConnectFailure.ConnectFailure hang
- 07:07 PM Bug #19901: LibRadosMiscConnectFailure.ConnectFailure hang
- it's LibRadosMiscConnectFailure.ConnectFailure...
- 07:14 PM Revision 087dff80 (ceph): ceph_test_rados_api_misc: fix LibRadosMiscConnectFailure.ConnectFailure...
- Fixes: http://tracker.ceph.com/issues/19901
Signed-off-by: Sage Weil <sage@redhat.com> - 07:03 PM Bug #20067 (Resolved): assert in OSDMonitor::update_creating_pgs()
- 07:02 PM RADOS Bug #20068 (Resolved): osd valgrind error in CrushWrapper::has_incompat_choose_args
- 07:02 PM Revision b3e677ab (ceph): osd/dmclock/testing: reorganize testing, building now optional
- Modify cmake files to take advantage or re-organization of dmclock's
cmake set-up, specifically not having dmclock's ... - 07:01 PM Revision 963a803d (ceph): Merge commit '5c612d7e32a07a01b3b97f9cf58f2a3cef0e2e73'
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 07:01 PM Revision 5c612d7e (ceph): Squashed 'src/dmclock/' changes from d6586d7..64bcc6e
- 64bcc6e Remove FindGTest and FindBoost, which already exist in cmake required version 2.8.11 and later. Also clean up...
- 07:01 PM Bug #19878 (Can't reproduce): msg/simple: reports lossy con on osd->osd connection
- osd<->osd connections are non-lossy. i think this was a problem with the hb change i was testing, though, closing!
- 06:52 PM Revision 189b17b7 (ceph): qa/workunits/cephtool/test.sh: test 'log last [n]'
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:50 PM Revision cb1f57c5 (ceph): common/LogEntry: make LogEntryKey opaque and cache its hash value
- This avoids recalculating. We eliminate the default ctor at the same
time and make the type totally opaque (so that ... - 06:36 PM rgw Bug #17964: rgw: multipart parts on versioned bucket create versioned bucket index entries
- https://github.com/ceph/ceph/pull/14500
- 06:34 PM rgw Bug #16355 (In Progress): radosgw-admin command, adding the tenants can not view the user usage
- 06:29 PM rgw Bug #19194 (In Progress): after s3cmd put file to bucket, 'radosgw-admin usage show --categories=...
- 06:28 PM rgw Bug #19219 (Resolved): Data sync problem in multisite
- 06:28 PM rgw Bug #19587 (In Progress): rgw: put lifecycle configuration fails if Prefix is not set
- 06:24 PM rgw Bug #19285: rgw: user quota did not work well on multipart upload
- 06:19 PM Revision d0109717 (ceph): Merge pull request #15390 from liewegas/wip-osdmap-state
- osd/OSDMap: make osd_state 32 bits wide
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Josh Durgin <... - 06:02 PM Bug #19947 (Fix Under Review): osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- https://github.com/ceph/ceph/pull/15519
- 06:01 PM Revision 845fc3ec (ceph): Merge pull request #15515 from tchaikov/wip-crc32-aarch64
- crc32c: include acconfig.h to fix ceph_crc32c_aarch64()
Reviewed-by: Dan Mick <dmick@redhat.com> - 05:57 PM rgw Bug #19739 (Fix Under Review): Content-MD5 header is not validated with POST uploads
- 05:57 PM rgw Bug #19870: rgw: bytes_send and bytes_recv in the msg of usage show returning is 0 in master branch
- while we're at it, we need to make sure that there's sufficient teuthology coverage for this issue. I think we do tes...
- 05:53 PM rgw Bug #20177: RGW lifecycle not expiring objects due to permissions on lc pool
- Some notes (cribbed from email by Dan Gryniewicz):
The lifecycle config looks sane; Dan, do you see anything here?... - 05:45 PM Revision 5cfe4cfa (ceph): ceph-disk: add --filestore argument, default to --bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 03:52 PM rgw Backport #19847: jewel: multisite: incremental metadata sync does not properly advance to next pe...
- i'll take this one - i expect to have a pr ready today
- 03:34 PM Revision 5d92c79b (ceph): build: misc fixes for cmake build on i386
- Scope SIMD CPU flag detection base on target architecture,
resolving build failures in gf-complete on i386; this is
i... - 03:31 PM Revision 67d3049b (ceph): crc32c: include acconfig.h to fix ceph_crc32c_aarch64()
- HAVE_ARMV8_CRC is defined by "acconfig.h". so we need to include it for
the definition.
it's a regresssion introduce... - 03:21 PM rgw Bug #20201 (Resolved): radosgw refuses upload when Content-Type missing from POST policy
- When doing an S3 upload, if Content-Type is missing from the policy part of the upload, then radosgw refuses the uplo...
- 02:16 PM Documentation #20199 (Resolved): [doc] Default values in docu does not reflect changes in the sou...
- The docu does not reflect changes of default values in the source code
http://docs.ceph.com/docs/jewel/rados/config... - 02:00 PM Bug #19252: read/write inconsistent
- Oh, I see. Writes are ordered with respect to other writes, and reads to other reads, but reads and writes are allow...
- 01:57 PM Revision e38ca149 (ceph): Merge pull request #15511 from tchaikov/wip-doc-cartesian-product
- doc: update sample explaning "%" operator in test suites
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: ... - 01:54 PM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- https://github.com/ceph/ceph/pull/15514
- 01:53 PM rgw Bug #20190 (Fix Under Review): "datalog trim" can't work as expected
- 07:56 AM rgw Bug #20190: "datalog trim" can't work as expected
- https://github.com/ceph/ceph/pull/15507
- 07:43 AM rgw Bug #20190 (Resolved): "datalog trim" can't work as expected
- The radosgw-admin command datalog trim can't remove the log as expected.
It returns "ERROR: trim_entries(): (61) No ... - 01:29 PM ceph-ansible Bug #15569: Two logrotate scripts
- https://github.com/ceph/ceph/pull/15514
- 09:03 AM ceph-ansible Bug #15569: Two logrotate scripts
- Alex Hart wrote:
> I'm seeing this with ceph 12.0.2-pve1 (Proxmox VE 5.0 beta2) as well:
>
probably a leftover ... - 01:25 PM Revision daa5126e (ceph): Merge pull request #14074 from jecluis/wip-mon-osd-replacement
- mon: replace osds with `osd destroy` and `osd new`
Reviewed-by: Sage Weil <sage@redhat.com> - 01:24 PM Revision 5c2b3cd4 (ceph): Merge pull request #15487 from liewegas/wip-no-more-stat-spam
- mgr/DaemonServer: stop spamming log with pg stats
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Josh ... - 01:24 PM Bug #20187 (Resolved): grep 'osd.0 is full at.*%' fails for cephtool/test.sh
- 08:48 AM Bug #20187 (Fix Under Review): grep 'osd.0 is full at.*%' fails for cephtool/test.sh
- 04:51 AM Bug #20187: grep 'osd.0 is full at.*%' fails for cephtool/test.sh
- 01:24 PM Revision 162440c7 (ceph): Merge pull request #15494 from liewegas/wip-20187
- qa/workunits/cephtool/test.sh: fix osd full health detail grep
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewe... - 01:23 PM Revision f37ab313 (ceph): pybind/ceph_argparse: fix no arg check
- This fixes breakage from commit a1214a702cfd8465deb91847f4dc63c0e80fb586
that caused a [] to be appended to some json... - 01:21 PM Revision 90c1a82f (ceph): ceph-mgr: fix package description
- Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
- 01:19 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-05_22:19:51-rados-wip-sage-testing-distro-basic-smithi/1262663
rados/thrash/{0-size-min-size-overr... - 01:16 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-05_22:19:51-rados-wip-sage-testing-distro-basic-smithi/1262583
rados/thrash/{0-size-min-size-overr... - 01:18 PM Bug #20198 (Resolved): mgr: tcmalloc segv in DaemonServer ctor
- ...
- 01:13 PM RADOS Bug #20133: EnvLibradosMutipoolTest.DBBulkLoadKeysInRandomOrder hangs on rocksdb+librados
- /a/sage-2017-06-05_22:19:51-rados-wip-sage-testing-distro-basic-smithi/1262365
- 12:55 PM Revision 08cb697a (ceph): tool/ceph: print return code when json_command failed
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 12:49 PM Revision b85bf0e6 (ceph): doc: update sample explaning "%" operator in tes suites
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 12:40 PM RADOS Bug #19605: OSD crash: PrimaryLogPG.cc: 8396: FAILED assert(repop_queue.front() == repop)
- 2017-05-19 22:58:05.142834 7f14de2a2700 0 osd.0 pg_epoch: 78440 pg[9.10cs0( v 78440'6350 (78438'4241,78440'6350] loc...
- 12:19 PM Bug #19427 (Need More Info): common/LogClient.cc: 310: FAILED assert(num_unsent <= log_queue.size())
- the osd.5 log is huge, and i cannot use zless to find the log lines i am interested. would be great if we can have an...
- 12:17 PM Revision 7e5799b0 (ceph): mon: don't prefix mgr summary with epoch number
- Missed this one when culling the various epochs
from the human readable ceph status output.
Signed-off-by: John Spra... - 11:42 AM Revision b9beaf51 (ceph): ceph.in: drop the compatiiblity to handle non json commands
- we has been using json command since giant. no need to bring this cruft
into luminous.
Signed-off-by: Kefu Chai <kch... - 11:36 AM Revision b1d06a6b (ceph): Merge pull request #15499 from jcsp/wip-doc-whitespace
- doc: fix syntax on code snippets in cephfs/multimds
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 11:30 AM Revision 1c5174eb (ceph): librbd: filter expected error codes from is_exclusive_lock_owner
- Fixes: http://tracker.ceph.com/issues/20182
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from c... - 11:30 AM Revision 48a8d100 (ceph): rbd: properly decode features when using image name optional
- Fixes: http://tracker.ceph.com/issues/20185
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from c... - 10:49 AM rbd Bug #20185 (Pending Backport): [cli] ensure positional arguments exist before casting
- 10:49 AM Revision e5c46aa8 (ceph): Merge pull request #15492 from dillaman/wip-20185
- rbd: properly decode features when using image name optional
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 10:49 AM rbd Bug #20182 (Pending Backport): [api] is_exclusive_lock_owner shouldn't return -EBUSY
- 10:48 AM Revision d3fa8f39 (ceph): Merge pull request #15483 from dillaman/wip-20182
- librbd: filter expected error codes from is_exclusive_lock_owner
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 10:38 AM Backport #20191 (In Progress): kraken: SELinux denials (the files in /var/log/ceph get mislabeled)
- https://github.com/ceph/ceph/pull/15509
- 09:58 AM Backport #20191 (Resolved): kraken: SELinux denials (the files in /var/log/ceph get mislabeled)
- https://github.com/ceph/ceph/pull/15509
- 10:38 AM Backport #20193 (In Progress): kraken: Speed up upgrade from non-SELinux enabled ceph to an SELin...
- https://github.com/ceph/ceph/pull/15509
- 09:58 AM Backport #20193 (Resolved): kraken: Speed up upgrade from non-SELinux enabled ceph to an SELinux ...
- https://github.com/ceph/ceph/pull/15509
- 10:36 AM Backport #20192 (In Progress): jewel: SELinux denials (the files in /var/log/ceph get mislabeled)
- 09:58 AM Backport #20192 (Resolved): jewel: SELinux denials (the files in /var/log/ceph get mislabeled)
- https://github.com/ceph/ceph/pull/14346
- 10:35 AM Backport #20194 (In Progress): jewel: Speed up upgrade from non-SELinux enabled ceph to an SELinu...
- 09:58 AM Backport #20194 (Resolved): jewel: Speed up upgrade from non-SELinux enabled ceph to an SELinux e...
- https://github.com/ceph/ceph/pull/14346
- 10:30 AM CephFS Feature #20196 (New): mds: early reintegration of strays on hardlink deletion
The same symptom as http://tracker.ceph.com/issues/11950
If someone creates a large number of files (1M+), hardl...- 10:12 AM CephFS Feature #9466 (Resolved): kclient: Extend CephFSTestCase tests to cover kclient
- This got done a while back.
- 10:01 AM rgw Backport #19723 (In Progress): kraken: rgw_file: introduce rgw_lookup type hints
- 10:00 AM rgw Backport #20195 (In Progress): kraken: rgw_file: restore (corrected) fix for dir "partial match"...
- 09:59 AM rgw Backport #20195 (Resolved): kraken: rgw_file: restore (corrected) fix for dir "partial match" (r...
- https://github.com/ceph/ceph/pull/13871
- 09:39 AM Revision e80605f0 (ceph): selinux: Install ceph-base before ceph-selinux
- We need to have ceph-base installed before ceph-selinux to use ceph-disk
in %post script. The default ordering is ran... - 09:36 AM Revision bf973c84 (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 09:32 AM Revision 6ca61b1b (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 09:32 AM Revision 7d6eea04 (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 09:27 AM Revision 904fc7cb (ceph): selinux: Install ceph-base before ceph-selinux
- We need to have ceph-base installed before ceph-selinux to use ceph-disk
in %post script. The default ordering is ran... - 09:26 AM Revision 30e3ae27 (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 09:24 AM Revision fa100ed5 (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 09:23 AM Revision 4e0cfecd (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 09:23 AM Feature #20077 (Pending Backport): Speed up upgrade from non-SELinux enabled ceph to an SELinux e...
- 08:49 AM Revision 4db1ee39 (ceph): rbd-mirror A/A: coordinate image syncs with leader
- Fixes: http://tracker.ceph.com/issues/18789
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 08:48 AM Bug #20184 (Pending Backport): SELinux denials (the files in /var/log/ceph get mislabeled)
- 08:47 AM Revision c65b6871 (ceph): Merge pull request #15490 from ceph/wip-fix-selinux
- selinux: Install ceph-base before ceph-selinux
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:42 AM Revision b0742609 (ceph): test/rbd_mirror: TestMockImageReplayer cleanup
- Remove unnecessary ImageSyncThrottler dependency.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 08:42 AM Revision def50d04 (ceph): rbd-mirror: make sync throttler per pool
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 08:42 AM Revision 55f9c625 (ceph): rbd-mirror: resolve potential recursive lock
- Would have been possible when release_image had lead to cancel
sync (i.e. cancel_sync_request).
Signed-off-by: Mykol... - 07:47 AM rgw Backport #19144 (In Progress): kraken: rgw_file: FHCache residence check should be exhaustive
- 07:39 AM rbd Bug #18963 (Resolved): rbd-mirror: forced failover does not function when peer is unreachable
- 07:38 AM Revision 7ce058fb (ceph): Merge pull request #15415 from dillaman/wip-rbd-valgrind
- librbd: fix valgrind errors and ensure tests detect future leaks
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 07:37 AM Revision 9c0dbfa2 (ceph): Merge pull request #15140 from dillaman/wip-18963
- rbd-mirror: permit release of local image exclusive lock after force promotion
Reviewed-by: Mykola Golub <mgolub@mir... - 07:14 AM Linux kernel client Bug #19958: missing i_nlink check while converting a file handle to dentry
- https://github.com/ceph/ceph-client/commit/890971d2e9b2f71c57ccf69f8f20c09c551eefc6
- 06:47 AM mgr Bug #20113: couldn't get command descriptions for [u'mgr', '']:
- Kefu Chai wrote:
> Chang, you are not listed as a developer of this project. see http://tracker.ceph.com/projects/ce... - 05:53 AM Bug #20189: fs
- ceph-fuse can successfully mounted when the keyring is modified
- 12:09 AM Bug #20189 (Duplicate): fs
- when last letter of keyring is modified, ceph-fuse can still mount the fs with this wrong keyring and write/read oper...
- 05:36 AM Revision a00b6c30 (ceph): os/bluestore: reduce overhead when trying to unshard blobs
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:35 AM Backport #20151 (In Progress): jewel: ceph-disk fails if OSD udev rule triggers prior to mount of...
- 03:28 AM Backport #20011 (In Progress): jewel: ceph-disk: separate ceph-osd --check-needs-* logs
- 02:41 AM Revision 7005bbf7 (ceph): os/bluestore: atomic deferred_batch_ops
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:41 AM Revision 71561a78 (ceph): os/bluestore: avoid overloading of extents during reshard
- This is potentially big stuff...
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:21 AM rgw Bug #20112 (Fix Under Review): Use boost::regex instead of std::regex for rgw_iam_policy.cc and r...
- https://github.com/ceph/ceph/pull/15498
- 01:22 AM Revision 282f8d4c (ceph): Merge pull request #15484 from Adirl/wip
- msg/async/rdma: Add DSCP support
Reviewed-by: Haomai Wang <haomai@xsky.com> - 12:10 AM Revision ef65defe (ceph): Merge pull request #15493 from yehudasa/wip-rgw-dynamic-sharding
- rgw: dynamic resharding
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
06/05/2017
- 11:31 PM Revision cd7aeba9 (ceph): xio: migrate atomic_t to std::atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 10:32 PM Bug #19947 (In Progress): osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- 10:31 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- trim_object() returns an OpContextUPtr that we feed to simple_opc_submit(), but we aren't calling finish_ctx() like e...
- 09:35 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-06-05_18:36:01-rados-wip-sage-testing2-distro-basic-smithi/1261940
rados/thrash/{0-size-min-size-over... - 09:34 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-06-05_18:36:01-rados-wip-sage-testing2-distro-basic-smithi/1261877
rados/thrash/{0-size-min-size-overri... - 06:32 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-06-05_14:47:27-rados-wip-sage-testing-distro-basic-smithi/1260429
rados/thrash-erasure-code-overwrite... - 10:13 PM Revision 159dc9ae (ceph): mon/PGMap: show %used in formatted output
- Match what we currently have for the freeform text output. This prevents
the user from having to go through some anno... - 10:01 PM Revision 014a4d07 (ceph): cls/rgw: add missing members initialization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:39 PM Revision 080f3433 (ceph): Merge pull request #14239 from liewegas/wip-bluestore-ec-clone
- os/bluestore: try to unshare blobs for EC overwrite workload
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 09:39 PM Revision 7eb4959c (ceph): Merge pull request #15299 from joscollin/wip-cleanup-redundant-headers-6
- common: Remove redundant includes - 6
Reviewed-by: Sage Weil <sage@redhat.com> - 09:36 PM mgr Bug #20130 (Resolved): mgr generates traceback about missing django.core.servers.basehttp module ...
- https://github.com/ceph/ceph/pull/15429
- 09:36 PM Revision 3c52569f (ceph): Merge pull request #15429 from jcsp/wip-nuke-rest
- pybind/mgr: Delete `rest` module
Reviewed-by: Sage Weil <sage@redhat.com> - 09:32 PM RADOS Bug #19518: log entry does not include per-op rvals?
- /a/sage-2017-06-05_18:36:01-rados-wip-sage-testing2-distro-basic-smithi/1261843...
- 08:37 PM Bug #20135 (Fix Under Review): test/rest.py: PUT auth/add?entity=client.xx&caps=mon&caps=allow&ca...
- https://github.com/ceph/ceph/pull/15500
- 03:02 PM Bug #20135: test/rest.py: PUT auth/add?entity=client.xx&caps=mon&caps=allow&caps=osd&caps=allow+*...
- i cannot reproduce this locally =(
- 08:18 PM Revision 13f2f36e (ceph): test/cli/radosgw-admin: update reference help.t
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:18 PM Revision 93b8e834 (ceph): rgw: fix a race
- We referred to complete_op_data after aio call that could have released
it.
Signed-off-by: Yehuda Sadeh <yehuda@redh... - 08:18 PM Revision ba1138d7 (ceph): rgw: new num shards proportional to number of objects per shard
- and also limit number of shards to not exceed the max.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:18 PM Revision 93106dac (ceph): rgw: increase max shard prime, consolidate logic
- Handle larger num of shards (max ~64k now). Use the same hash logic for shard ids
everywhere.
Signed-off-by: Yehuda ... - 08:18 PM Revision b2a6f0e3 (ceph): rgw: fix index completion
- Was missing bucket complete op, only had the guard (bad merge?).
Pass zones_trace as pointer and treat it as optional... - 08:18 PM Revision 2417c2c0 (ceph): rgw: ignore -ENOENT on bi_list()
- just treat it as success with empty result
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:18 PM Revision ef48cc41 (ceph): rgw: remove debug helper code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:18 PM Revision 3b7fd0ff (ceph): rgw: handle zones_trace in bi async completion handler
- needed following a rebase
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:18 PM Revision 246c78eb (ceph): rgw: update entry in resharding log when resharding has started
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:18 PM Revision 6c061113 (ceph): rgw: add check to see if out is null
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:18 PM Revision dc04b20f (ceph): rgw: run resharding thread only on master zone
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:18 PM Revision 45ad93dd (ceph): rgw: add bucket to resharding queue if needs resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:18 PM Revision f2b0eb08 (ceph): rgw: replace reshard blocking sleep with interruptible condition wait
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:18 PM Revision 9b3c91cb (ceph): rgw: start resharding theard
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 40faa8d9 (ceph): radosgw-admin: reshard execute output adjustments
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 07b21866 (ceph): rgw: update bucket instance with resharding details
- can be useful info for later in a cross zone sync
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision c6dc81cf (ceph): rgw-admin: radosgw-admin reshard execute -> reshard process
- to be in line with other radosgw-admin commands.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 7054308e (ceph): cls/rgw: fix reshard_list truncation identification
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 1da369e1 (ceph): rgw: reshard: renew lease and handle marker when listing reshard repo
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision aa3f71d6 (ceph): cls/rgw: remove unused field in reshard entry
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 81693efd (ceph): rgw: remove unneeded and duplicate code
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 6cb30f9c (ceph): cls/rgw: expose api to generate reshard indexing key
- So that we could use it as a marker when doing reshard_list.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 485a11fe (ceph): rgw-admin: revive reshard execute command
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 6c540bd5 (ceph): rgw: initialize bucket structure
- after reading bucket info
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision ed72675b (ceph): rgw: bucket_id does not include bucket name
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 436f151e (ceph): cls/rgw: reshard add command doesn't read existing status
- No need to read existing status.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 999cca4e (ceph): rgw: internal api cleanup
- rename method, minor change
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision b516c92a (ceph): rgw: bi_list() initialize is_truncated if -ENOENT
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 8e1bf1b9 (ceph): rgw: multiple fixes and adjustments related to resharding scheduler
- still wip, but:
- get rid of some unneeded rados locking
- rename shards to logshards where relevant to avoid confu... - 08:17 PM Revision f677d0e9 (ceph): cls/rgw: modify logshard key
- The logshard key shouldn't include bucket id.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 2da8dc5d (ceph): cls/rgw: fix remove_reshard objclass op
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 71141246 (ceph): rgw: actually reshard an entry from the resharding queue
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision cac047a8 (ceph): rgw: replace reshard blocking sleep with interruptible condition wait
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision b757e7e1 (ceph): rgw: fix compilation following rebase
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision e03b85e9 (ceph): rgw: check for bucket resharding when adding an object
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 444b9c91 (ceph): rgw: add bucket to resharding queue if needs resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision c7fc87f9 (ceph): rgw: check if buckets needs resharding on all ops that add new objects
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 553bf4b9 (ceph): rgw: add a check_bucket_shards to the quota
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 9a084497 (ceph): rgw: add a function to add a bucket to the resharding queue
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision ad138a4d (ceph): rgw: add resharding thread
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision dfdc2b2c (ceph): rgw: remove cct from RGWReshard and BucketIndexLockGuard
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 1ed76a68 (ceph): rgw: moved reshard_bucket into RGWReshard
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 42b3ee12 (ceph): rgw: fix deletion of index completion object
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 806d4732 (ceph): rgw: store new num shards in bucket index reshard entry
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 60778b02 (ceph): rgw: update data log after index completion reshard handling
- Also rearrange code a bit.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision da1f5bc9 (ceph): rgw: clean up index completions on shutdown
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 94e3c380 (ceph): rgw: reshard complete handling, use multiple locks
- to reduce contention. Also, fix completions cleanup.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 9677f7d3 (ceph): cls/rgw: changes to support reshard guard on olh bi ops
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision e18e2714 (ceph): rgw: reshard guard for versioned operations
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 245cd0f9 (ceph): rgw: guard resharding in async completions
- Catch return value from async index completions, resend operations
synchronously on a separate worker thread if neede... - 08:17 PM Revision d250fab2 (ceph): rgw: fix update_bucket_id, reshard blocking logic
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 8fd589d1 (ceph): rgw: handle reshard wait logic in cancel() too
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision e4d4aa8b (ceph): rgw: a few fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 09ccfebf (ceph): rgw: more detailed resharding status kept in bucket header
- So that we can differentiate between in-progress and complete status.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 9766f5b9 (ceph): rgw_admin: add rgw-admin reshard status command and initial blocking logic
- A command that returns the reshard status field on the bucket index objects (all
shards).
Also, initial implementatio... - 08:17 PM Revision 7a34a049 (ceph): rgw: split per-bucket resharding logic out from general resharding
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision bb0cb4d7 (ceph): rgw: move resharding code to BucketReshard class
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 660a5126 (ceph): rgw: mark source bucket shards when starting reshard
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 7d44601e (ceph): cls/rgw: create an objclass method to guard in-progress resharding
- This method will be called on the bucket index shard.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:17 PM Revision 0bc15671 (ceph): rgw: revert some reshard blocking logic
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 04cf0ca0 (ceph): cls/rgw: minor changes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision a07e8eb6 (ceph): cls/rgw: adjust types and ops
- - don't keep data bufferlist in struct cls_rgw_bucket_instance_entry
- remove rgw_get_bucket_instance
We need to ke... - 08:17 PM Revision 4ddb785b (ceph): rgw: RGWReshard update to new cls API
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 82823667 (ceph): rgw: cls_reshard_get remove unneeded check for bufferlist length
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision f446b80e (ceph): cls/rgw: return default header if not initialized
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 44e46b35 (ceph): cls/rgw: generate_reshard_key, change output param
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision f3847081 (ceph): rgw: add guard class for bucket index lock
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 1ee15336 (ceph): rgw: get_bucket_header will return -ENOENT when there is no header
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 0af96c17 (ceph): rgw: use pointer for is_truncated
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision be156d08 (ceph): rgw: check for exisiting entries in cls_rgw_reshard_add
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 830ea538 (ceph): rgw: add reshard_pool_ctx
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 59c0c30a (ceph): rgw: use .rgw.log:reshard pool for resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision ae6a5eac (ceph): rgw: limit op.max and add extra entry to handle tuncation in cls_rgw_re...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision ea334d3f (ceph): rgw: cls_rgw_reshard use helper function the generate key
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 822a5fbd (ceph): rgw: remove cls_reshard_get_head
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 5828d4a6 (ceph): rgw: replace dout with ldout
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision a7154a6a (ceph): rgw: remove RGWReshard::get_head
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 3b41ca02 (ceph): rgw: block on bucket index operation when resharding the index
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 9e43e7f0 (ceph): rgw: handle correctly when there is no bucket or it doesn't have reshar...
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 149bfc43 (ceph): rgw: store resharding information in bucket header
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 2d23898b (ceph): rgw: add cls_rgw_get_resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision c000a15f (ceph): rgw: Add lock/unlock bucket instance and block_while_resharding methods
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 18c16f97 (ceph): rgw: add RGWReshard object to RGWRados
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 11e7cb1e (ceph): radosgw-admin: implement reshard execute command
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 8e30c378 (ceph): rgw: use const string for oid in get_bucket_instance_from_oid
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 38581714 (ceph): radsogw-admin add create_new_bucket_instance
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 0f53c5dc (ceph): rgw: add RGWReshard::set_bucket_resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 8b497b06 (ceph): rgw: add RGWReshard::clear_bucket_resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:17 PM Revision 98d85722 (ceph): rgw: add missing handles for set_resharding, clear_resharding
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 08:08 PM Revision 0144fde1 (ceph): client: avoid returning negative space available
- ...when a quota is set and the used bytes exceed
the quota.
Fixes: http://tracker.ceph.com/issues/20178
Signed-off-b... - 07:46 PM Revision f76208cb (ceph): doc: fix syntax on code snippets in cephfs/multimds
- Signed-off-by: John Spray <john.spray@redhat.com>
- 07:37 PM Revision e320c242 (ceph): mon/LogMonitor: 'log last [num]' command
- Default to 20 lines of log if not specified.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:31 PM Revision 0ee4baff (ceph): common/LogEntry: make LogSummary::contains() efficient
- A linear search here is dumb. Use an unordered_set.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:17 PM Revision f1239e2e (ceph): common/LogEntry: make prune size tunable (and raise 50 -> 1024)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:05 PM Revision 591e8d13 (ceph): core: include/types.h, introduce host_to_ceph_errno
- - As preparation for interconnecting ceph_daemons on
different platfoms
Signed-off-by: Willem Jan Withagen <wjw@d... - 06:35 PM Revision 3134fbbe (ceph): Merge pull request #14657 from chardan/jfw-wip-halflife_atomic_t-mothra
- messenger,client,compressor: migrate atomic_t to std::atomic
Reviewed-by: Sage Weil <sage@redhat.com> - 06:35 PM Revision 92d4866b (ceph): Merge pull request #15380 from xiexingguo/wip-cache-trim
- os/bluestore: move cache_trim into MempoolThread
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 06:34 PM Revision 52a98308 (ceph): Merge pull request #15409 from Liuchang0812/wip-support-mon-target-in-p...
- pybind: support mon target in pybind
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:33 PM Revision 765b9d25 (ceph): Merge pull request #15469 from wjwithagen/wip-wjw-revert-wvla
- build: revert -Wvla from #15342
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 06:33 PM Revision 06f097c4 (ceph): Merge pull request #15470 from xiexingguo/wip-rm-false-assert
- os/bluestore: fix false asserts in Cache::trim_all()
Reviewed-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision ac7c2c11 (ceph): Merge pull request #15478 from xiexingguo/wip-perf-avg-time
- common/perf_counters: add average time for PERFCOUNTER_TIME
Reviewed-by: Sage Weil <sage@redhat.com> - 06:31 PM Bug #19427: common/LogClient.cc: 310: FAILED assert(num_unsent <= log_queue.size())
- ...
- 06:27 PM RADOS Bug #20188 (New): filestore: os/filestore/FileStore.h: 357: FAILED assert(q.empty()) from ceph_te...
- ...
- 06:25 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-05_14:47:27-rados-wip-sage-testing-distro-basic-smithi/1260424
teuthology:1260424 06:25 PM $ cat s... - 06:24 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-05_14:47:27-rados-wip-sage-testing-distro-basic-smithi/1260344
teuthology:1260344 06:24 PM $ cat su... - 06:23 PM Bug #20187: grep 'osd.0 is full at.*%' fails for cephtool/test.sh
- https://github.com/ceph/ceph/pull/15494
- 06:21 PM Bug #20187 (Resolved): grep 'osd.0 is full at.*%' fails for cephtool/test.sh
- The 'health detail' output has changed (no longer includes percentage)
/a/sage-2017-06-05_14:47:27-rados-wip-sage-... - 06:23 PM Revision 3f32f340 (ceph): qa/workunits/cephtool/test.sh: fix osd full health detail grep
- This changed with the switch to OSDMonitor doing the fullness
and pgmonitor getting disabled.
Fixes: http://tracker.... - 05:19 PM rbd Bug #20185 (Fix Under Review): [cli] ensure positional arguments exist before casting
- *PR*: https://github.com/ceph/ceph/pull/15492
- 05:01 PM rbd Bug #20185 (Resolved): [cli] ensure positional arguments exist before casting
- For example: "rbd feature enable --image xyz" will crash since the feature name positional was not specified.
- 05:17 PM Revision f1b05a2b (ceph): rbd: properly decode features when using image name optional
- Fixes: http://tracker.ceph.com/issues/20185
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 05:16 PM Bug #20186 (Resolved): snapset xattr corruption propagated from primary to other shards
Suggested way to fix this:
1. Change be_select_auth_object() to pick primary everything else being equal
2. In ...- 05:11 PM Bug #20184: SELinux denials (the files in /var/log/ceph get mislabeled)
- Upstream PR:
https://github.com/ceph/ceph/pull/15490 - 05:03 PM Bug #20184: SELinux denials (the files in /var/log/ceph get mislabeled)
- This happened because the ceph-base was only required for runtime (not %post) and we were using ceph-disk from ceph-b...
- 04:53 PM Bug #20184 (Fix Under Review): SELinux denials (the files in /var/log/ceph get mislabeled)
- 04:35 PM Bug #20184 (Resolved): SELinux denials (the files in /var/log/ceph get mislabeled)
- Run: http://pulpito.ceph.com/yuriw-2017-06-03_15:35:34-rados-wip-yuri-testing_2017_7_4---basic-smithi/
Logs: http://... - 04:49 PM Revision e6908664 (ceph): selinux: Install ceph-base before ceph-selinux
- We need to have ceph-base installed before ceph-selinux to use ceph-disk
in %post script. The default ordering is ran... - 04:45 PM Revision 50fe3c39 (ceph): selinux: Install ceph-base before ceph-selinux
- We need to have ceph-base installed before ceph-selinux to use ceph-disk
in %post script. The default ordering is ran... - 04:37 PM ceph-ansible Bug #15569: Two logrotate scripts
- I'm seeing this with ceph 12.0.2-pve1 (Proxmox VE 5.0 beta2) as well:...
- 04:15 PM Revision b9ce1aa6 (ceph): rbd-mirror: ensure missing images are re-synced when detected
- Fixes: http://tracker.ceph.com/issues/19811
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from c... - 04:11 PM Revision 6a4f6511 (ceph): mgr/DaemonServer: stop spamming log with pg stats
- This clutters up the log. We should instead log to health, or other
important events.
Note that we still have ceph ... - 03:16 PM rbd Backport #20023 (In Progress): jewel: rbd-mirror replay fails on attempting to reclaim data to lo...
- 12:32 PM rbd Backport #20023 (New): jewel: rbd-mirror replay fails on attempting to reclaim data to local site...
- Jason agreed to do this one.
- 02:49 PM Revision bb8ac49c (ceph): common/config_opts.h: Lower HDD throttle cost.
- Signed-off-by: Mark Nelson <mnelson@redhat.com>
- 02:31 PM Revision c9e6cac1 (ceph): mon: add `osd new`
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 02:31 PM Revision 0df321b5 (ceph): mon/OSDMonitor: have `create` behavior on `new`
- `osd new` will eventually replace `osd create`, and so we want to keep
as close of a behavior as possible. Some conce... - 02:31 PM Revision b3464b34 (ceph): mon/OSDMonitor: make `destroy` and `purge` idempotent
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 02:31 PM Revision 9e0d3de6 (ceph): qa/workunits: adjust expected return on cephtool
- We changed the behavior of `osd create` to return EEXIST instead of
EINVAL if an uuid exists with a different `id` th... - 02:31 PM Revision 8ab3a1db (ceph): qa/workunits: add cephtool test for new commands
- Tests `ceph osd new`, `ceph osd destroy` and `ceph osd purge`.
Signed-off-by: Joao Eduardo Luis <joao@suse.de> - 02:31 PM Revision e80faf19 (ceph): doc/man: document new mon commands
- Includes brief description for `ceph osd new`, `ceph osd destroy` and
`ceph osd purge`.
Signed-off-by: Joao Eduardo ... - 02:31 PM Revision e1b21094 (ceph): mon/OSDMonitor: make them includes beautiful
- These were annoying me.
Signed-off-by: Joao Eduardo Luis <joao@suse.de> - 02:31 PM Revision a8b397a2 (ceph): mon/OSDMonitor: spin-off osd and crush rm functions
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 02:31 PM Revision e5a86733 (ceph): mon: add 'osd purge'
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 02:31 PM Revision b1156737 (ceph): mon/AuthMon: spin-off some functions for later reuse
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
- 02:31 PM Revision 52c0bffb (ceph): mon/OSDMonitor: rework `osd create`
- We're splitting the chunk of code from `prepare_command_impl()` into two
functions: one will validate if we can perfo... - 02:27 PM Revision ba1ee453 (ceph): os/bluestore: fix warning
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:21 PM Revision 07c2350a (ceph): mon: add `osd destroy`
- This new command will remove a given osd's auth keys, along with any
daemon-private and dm-crypt info contained in th... - 02:20 PM Revision de3fe89e (ceph): mon/Paxos: add plug/unplug
- Simple mechanism to prevent and immediate commit (until the caller does
more stuff, presumably).
Signed-off-by: Sage... - 02:20 PM Revision 465caef4 (ceph): mon/PaxosService: clean up dispatch()
- No functional change, just un-nesting these ifs.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:20 PM Revision 79929142 (ceph): mon/PaxosService: add force_immediate_propose mechanism
- Add an easy mechanism for a prepare method to force an immediate proposal.
(Otherwise they have to ensure that a futu... - 02:02 PM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- John Spray wrote:
> dongdong tao -- could you please open a pull request with your code change once it is working fo... - 01:46 PM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- dongdong tao -- could you please open a pull request with your code change once it is working for you?
- 12:52 AM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- dongdong tao wrote:
> Zheng Yan wrote:
> > the last cap message has CHECK_CAPS_SYNCHRONOUS flag. mds flushes mdlog ... - 01:51 PM rbd Backport #20022 (In Progress): kraken: rbd-mirror replay fails on attempting to reclaim data to l...
- 01:01 PM CephFS Bug #20131 (Fix Under Review): mds/MDBalancer: update MDSRank export_targets according to current...
- 12:41 PM rbd Support #20183 (New): Ceph RBD image-feature
- How can I run an image with all the features?
I am running:
cephuser@ceph01u:~$ ceph -v
ceph version 11.2.0 (f... - 12:33 PM rbd Bug #19811: rbd-mirror replay fails on attempting to reclaim data to local site (LS) from distant...
- OK, #20023 reassigned to Jason.
- 11:41 AM rbd Bug #19811: rbd-mirror replay fails on attempting to reclaim data to local site (LS) from distant...
- @Nathan: feel free to re-assign this one to me and I'll make the necessary changes.
- 12:31 PM rbd Bug #19907 (Resolved): rbd-mirror: admin socket path names collision
- 11:40 AM rbd Bug #19907: rbd-mirror: admin socket path names collision
- @Nathan: since this is more of a nice-to-have, I am also fine just dropping the need for a backport to jewel (and kra...
- 12:31 PM rbd Backport #20009 (Rejected): jewel: rbd-mirror: admin socket path names collision
- Backport is complicated and not worth the effort for a mere "nice-to-have" backport.
- 12:31 PM rbd Backport #20008 (Rejected): kraken: rbd-mirror: admin socket path names collision
- Backport is complicated and not worth the effort for a mere "nice-to-have" backport.
- 12:18 PM rbd Bug #20182 (Fix Under Review): [api] is_exclusive_lock_owner shouldn't return -EBUSY
- *PR*: https://github.com/ceph/ceph/pull/15483
- 12:06 PM rbd Bug #20182 (Resolved): [api] is_exclusive_lock_owner shouldn't return -EBUSY
- This error code indicates that another client owns the exclusive lock. Instead, it should return 0 with the boolean s...
- 12:17 PM Revision d4daaf54 (ceph): librbd: filter expected error codes from is_exclusive_lock_owner
- Fixes: http://tracker.ceph.com/issues/20182
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 11:01 AM Revision f14f0342 (ceph): msg/async/rdma: Add DSCP support
- From Ali
issue: none
Change-Id: Ib84bc0ea50626224c7ecd72bd9233770dcb1d048
Signed-off-by: Sarit Zubakov <saritz@mell... - 10:35 AM CephFS Bug #20178 (Fix Under Review): df reports negative disk "used" value when quota exceed
- https://github.com/ceph/ceph/pull/15481
- 12:56 AM CephFS Bug #20178 (Resolved): df reports negative disk "used" value when quota exceed
- first, set the maxbytes quota for a directory in cephfs,for example the directory named test and the quota is 10G;
... - 10:25 AM Revision 767502e2 (ceph): common/perf_counters: add average time for PERFCOUNTER_TIME
- Otherwise we'll have to calculate this manually, which is annoying.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 10:08 AM Revision 34b1ff73 (ceph): os/bluestore: fix false asserts in Cache::trim_all()
- These asserts are true if we are going to shutdown the BlueStore instance.
But the caller can also be something like ... - 09:39 AM Bug #20052 (Resolved): build/ops: librbd1 %post script might run before coreutils package is inst...
- 09:38 AM Revision b4560572 (ceph): Merge pull request #15231 from smithfarm/wip-20052
- build/ops: rpm: make librbd1 %post scriptlet depend on coreutils
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 09:24 AM RADOS Backport #16239 (Fix Under Review): 'ceph tell osd.0 flush_pg_stats' fails in rados qa run
- https://github.com/ceph/ceph/pull/15475
- 09:19 AM Revision 648dfa1e (ceph): qa: add a sleep after restarting osd before "tell"ing it
- without the fast-fail feature, the monitor does not mark osd down after
a grace time. so we cannot truest the "health... - 09:02 AM rgw Backport #19767 (In Progress): jewel: rgw: Delete non-empty bucket in slave zonegroup
- 08:09 AM Backport #19559 (In Progress): jewel: objecter: full_try behavior not consistent with osd
- 07:38 AM Backport #20080 (In Progress): jewel: Set subman cron attributes in spec file
- 07:03 AM CephFS Backport #20148 (In Progress): jewel: Too many stat ops when MDS trying to probe a large file
- 06:07 AM Revision b7e93733 (ceph): radosstriper: use intrusive_ptr to manage lifecycle of MultiAioCompleti...
- this change also silence some cppcheck warnings: we fail to rlease
references to MultiAioCompletionImpl in some of th... - 06:07 AM Revision 02fba124 (ceph): radosstriper: assert(ref==1) in MultiAioCompletion's dtor
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:44 AM Revision f71e64be (ceph): pybind: support mon target, and clean up tool
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 05:44 AM Revision 583cbbbd (ceph): tool/ceph: pep8 clean up
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 03:25 AM rgw Feature #20179: rgw: subuser usage log statistics
- https://github.com/ceph/ceph/pull/15064
- 03:24 AM rgw Feature #20179 (Fix Under Review): rgw: subuser usage log statistics
- current usage log statistics only support user level,this feature will expand usage log statistics to subuser level.
- 03:03 AM Revision 75ce2a94 (ceph): mds: fix Locker::calc_new_client_ranges()
- update 'max_increased' when adding new client writable range
Signed-off-by: "Yan, Zheng" <zyan@redhat.com> - 03:01 AM Revision 044fabd6 (ceph): client: don't re-send interrupted flock request
- don't re-send interrupted flock request in cases of mds failover
and receiving request forward.
Signed-off-by: "Yan,... - 02:15 AM Revision 4722abe9 (ceph): Merge pull request #15165 from badone/wip-cls-optimize-header-file-depe...
- cls: optimize header file dependency
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:29 AM Bug #20174 (Resolved): test_health_warnings.sh: test_mark_all_osds_down fails some time
- https://github.com/ceph/ceph/pull/15073
06/04/2017
- 11:08 PM mgr Bug #20130 (In Progress): mgr generates traceback about missing django.core.servers.basehttp modu...
- https://github.com/ceph/ceph/pull/15429
- 07:28 PM rgw Bug #20177 (Resolved): RGW lifecycle not expiring objects due to permissions on lc pool
- see http://lists.ceph.com/pipermail/ceph-users-ceph.com/2017-June/018367.html
- 07:26 PM CephFS Backport #20140 (In Progress): jewel: Journaler may execute on_safe contexts prematurely
- 07:25 PM Revision bdf524e0 (ceph): build: revert -Wvla from #15342
- - VLAs are in GCC and Clang, and are there to stay forever,
if only to be compatible with all the software that is... - 07:13 PM Linux kernel client Bug #20164: libceph: got bad padding
- They all running over VMWare machines and a debian 8 instalation. I am using Jewel ceph instalation.
What could be... - 07:12 PM rgw Backport #19613 (Need More Info): jewel: multisite: rest api fails to decode large period on 'per...
- 07:12 PM rgw Backport #19613: jewel: multisite: rest api fails to decode large period on 'period commit'
- This backport depends on https://github.com/ceph/ceph/commit/35375b75160 - marked the PR DNM until we determine wheth...
- 07:01 PM Revision e6daee8a (ceph): Client.cc: adjust Client::_getattr calls
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 06:36 PM Revision 554cf839 (ceph): Merge pull request #15073 from liewegas/wip-mgr-stats
- mon,mgr: extricate PGmap from monitor
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:35 PM Revision 69bb53b0 (ceph): qa/workunits/rados/test_health_warning: misc fixes
- * do not let osd shutdown itself by enlarge osd_max_markdown_count and
shorten osd_max_markdown_period
* do not shu... - 06:35 PM Revision 8185bc05 (ceph): qa/suites/upgrade/hammer-jewel-x: don't initially start mgr daemons
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 01:14 PM rgw Bug #20176 (Fix Under Review): rgw bugfix:s3 aws v2 signature priority between header['X-Amz-Date...
- 01:01 PM rgw Bug #20176 (Resolved): rgw bugfix:s3 aws v2 signature priority between header['X-Amz-Date'] and h...
- as http://docs.aws.amazon.com/AmazonS3/latest/dev/RESTAuthentication.html Time Stamp Requirement section metioned
... - 10:28 AM mgr Bug #20113 (In Progress): couldn't get command descriptions for [u'mgr', '']:
- 10:28 AM mgr Bug #20113: couldn't get command descriptions for [u'mgr', '']:
- Chang, you are not listed as a developer of this project. see http://tracker.ceph.com/projects/ceph. probably you pin...
- 09:45 AM CephFS Backport #19762 (In Progress): jewel: non-local cephfs quota changes not visible until some IO is...
- 09:44 AM Revision a2c7a226 (ceph): qa/cephfs: use getfattr/setfattr helpers
- Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit dd43d3bc646aeab88486b0963fc83de0b18800c4... - 09:43 AM Revision 12aa35a6 (ceph): tasks/cephfs: fix race while mounting
- This could fail if the mount hadn't finished
coming up.
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry pi... - 09:38 AM Revision a7b69926 (ceph): qa: add test for reading quotas from different clients
- Fixes: http://tracker.ceph.com/issues/17939
Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from com... - 09:38 AM Revision 8b8ee392 (ceph): client: _getattr on quota_root before using in statfs
- ...so that after someone adjusts the quota settings
on an inode that another client is using as its mount root,
the c... - 09:38 AM Revision dd7d59a0 (ceph): client: getattr before read on ceph.* xattrs
- Previously we were returning values for quota, layout
xattrs without any kind of update -- the user just got
whatever... - 09:37 AM rgw Backport #19772 (In Progress): jewel: rgw: swift: disable revocation thread under certain circums...
- 09:35 AM rgw Backport #20155 (In Progress): jewel: fix: rgw crashed caused by shard id out of range when listi...
- 09:33 AM rbd Backport #20153 (In Progress): jewel: Potential IO hang if image is flattened while read request ...
- 09:12 AM rbd Backport #19808 (In Progress): jewel: [test] remove hard-coded image name from TestLibRBD.Mirror
- 08:23 AM rbd Backport #19808 (Need More Info): jewel: [test] remove hard-coded image name from TestLibRBD.Mirror
- 08:19 AM rbd Backport #19808 (In Progress): jewel: [test] remove hard-coded image name from TestLibRBD.Mirror
- 08:58 AM rbd Backport #20017 (In Progress): jewel: rbd-nbd: kernel reported invalid device size (0, expected 1...
- 08:40 AM rbd Bug #19907: rbd-mirror: admin socket path names collision
- @Jason There is no PoolReplayer::print_status in jewel, so the backport would have to be done manually in src/tools/r...
- 08:40 AM rbd Backport #20009 (Need More Info): jewel: rbd-mirror: admin socket path names collision
- There is no PoolReplayer::print_status in jewel, so the backport would have to be done manually in src/tools/rbd_mirr...
- 08:34 AM rbd Backport #20023 (Need More Info): jewel: rbd-mirror replay fails on attempting to reclaim data to...
- @Jason The test in the master commit does not backport cleanly to jewel. It appears to depend on 19dd5a82bb8 but the ...
- 08:33 AM rbd Bug #19811: rbd-mirror replay fails on attempting to reclaim data to local site (LS) from distant...
- @Jason The test in the master commit does not backport cleanly to jewel. It appears to depend on 19dd5a82bb8 but the ...
- 08:25 AM rbd Backport #19957 (Need More Info): jewel: rbd: Lock release requests not honored after watch is re...
- Non-trivial backport
- 08:13 AM rbd Backport #19795 (In Progress): jewel: [test] test_notify.py: assert(not image.is_exclusive_lock_o...
- 08:11 AM rbd Backport #17843 (In Progress): jewel: object-map: batch updates during trim operation
- 07:54 AM rgw Backport #19758: jewel: multisite: after CreateBucket is forwarded to master, local bucket may us...
- Casey Bodley wrote:
> https://github.com/ceph/ceph/pull/15010 merged, please include in backports
@Casey: That co... - 07:53 AM rgw Backport #20159 (In Progress): jewel: rgw_file: RGWLibFS::get_inst() not stable
- 07:50 AM rgw Backport #20157 (Resolved): jewel: rgw_file: handle chunked readdir
- 07:49 AM rgw Bug #19624: rgw_file: handle chunked readdir
- @Matt - https://github.com/ceph/ceph/pull/14458 was backported to jewel by https://github.com/ceph/ceph/pull/14653 . ...
- 07:46 AM rgw Backport #20142 (In Progress): jewel: rgw_file: unlink assert unsafe in multi-gateway environments
- 07:44 AM rgw Backport #20138 (In Progress): jewel: rgw_file: attempt to unlink non-empty bucket could lead to ...
- 07:43 AM rgw Backport #20144 (In Progress): jewel: rgw_file: cannot delete bucket w/uxattrs
- 07:28 AM rgw Bug #20064 (Pending Backport): allow empty data_extra_pool in zone placement
- 07:24 AM rgw Bug #20064 (Need More Info): allow empty data_extra_pool in zone placement
- The master commit changes a line in the function "rgw_get_obj_data_pool" which was added by 9c1b828e838. That commit ...
- 07:28 AM rgw Backport #20136 (Need More Info): jewel: allow empty data_extra_pool in zone placement
- The master commit changes a line in the function "rgw_get_obj_data_pool" which was added by 9c1b828e838. That commit ...
- 07:27 AM rgw Backport #20137 (Need More Info): kraken: allow empty data_extra_pool in zone placement
- The master commit changes a line in the function "rgw_get_obj_data_pool" which was added by 9c1b828e838. That commit ...
- 07:06 AM rgw Backport #20029 (In Progress): jewel: multisite: radosgw-admin period commands cant use --remote ...
- 05:58 AM rbd Bug #20175: test_librbd_api.sh fails in upgrade test
- TracepointProvider.cc was in libcommon.a which is in turn included by librbd.so in jewel, but in luminous, it is move...
- 05:51 AM rbd Bug #20175 (Resolved): test_librbd_api.sh fails in upgrade test
- ...
06/03/2017
- 11:59 PM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- @Nathan, Yes mate, please do and I'll see what I can do about it. b7e77996586daa46da6be0bfbb8c2b93e203a83a shouldn't ...
- 12:23 PM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- @Brad - yes, when you open the backport PR, just mention both backport tracker issues in the commit message ;-)
I ... - 06:49 PM Linux kernel client Bug #20164: libceph: got bad padding
- That's the kernel client. Probably means you have a mismatch between how your daemons and clients are set up for auth...
- 06:46 PM RADOS Bug #20169: filestore+btrfs occasionally returns ENOSPC
- It's less likely on Centos, but I think we've seen this before and it's usually been a btrfs kernel bug that got reso...
- 06:34 PM rgw Backport #20020 (In Progress): jewel: multisite: RGWPeriodPusher CRThread startup races with RGWH...
- 06:32 PM rbd Backport #18137 (Need More Info): jewel: rbd-mirror: image sync should send NOCACHE advise flag
- 06:26 PM rgw Backport #20018 (In Progress): jewel: multisite: memory leak on failed lease in RGWDataSyncShardCR
- 06:22 PM rgw Backport #20003 (In Progress): jewel: rgw_file: v3 write timer does not close open handles
- 06:21 PM rgw Backport #19847 (Need More Info): jewel: multisite: incremental metadata sync does not properly a...
- Non-trivial RGW multisite backport. Abhi, want to have a go at it?
- 06:16 PM rgw Backport #19844 (Need More Info): jewel: Add custom user data support in bucket index
- 06:16 PM rgw Backport #19844: jewel: Add custom user data support in bucket index
- Ordinarily we don't backport features to stable releases, but assigning to Pavan if he wants to have a go at it.
- 06:09 PM rgw Backport #19838 (In Progress): jewel: reduce log level of 'storing entry at' in cls_log
- 06:07 PM rgw Backport #19775 (In Progress): jewel: multisite: realm rename does not propagate to other clusters
- 06:05 PM rgw Backport #19768 (Need More Info): jewel: [multisite] operating bucket's acl&cors is not restricte...
- Needs https://github.com/ceph/ceph/pull/15260 once it's merged.
- 06:05 PM rgw Backport #19768 (In Progress): jewel: [multisite] operating bucket's acl&cors is not restricted o...
- 05:37 PM Revision c24a08d6 (ceph): mon/OSDMonitor: add a space after __func__ in log message
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:00 PM Bug #20174 (Resolved): test_health_warnings.sh: test_mark_all_osds_down fails some time
- some osds just stay "down" after ...
- 04:43 PM Stable releases Tasks #19538: jewel v10.2.8
- h3. rgw suite on wip-jewel-backports-rgw-fixes branch
*86 pass, 10 fail (96 total)* http://pulpito.ceph.com/abhi-2... - 04:37 PM rgw Bug #18208: rgw: when uploading the objects continuesly in the versioned bucket, some objects wil...
- Zhandong Guo wrote:
> Do we have plan to patch this in 10.2.8?
This is probably missing the cutoff, and will be i... - 04:36 PM rgw Backport #19765 (In Progress): jewel: rgw: when uploading the objects continuesly in the versione...
- 04:17 PM rgw Backport #19158 (Resolved): jewel: RGW health check errors out incorrectly
- 04:16 PM rgw Backport #18903 (Need More Info): jewel: rgw: first write also tries to read object
- caused tests to fail
- 04:15 PM rgw Backport #19764 (In Progress): jewel: set latest object's acl failed
- 04:13 PM rgw Backport #19758 (Need More Info): jewel: multisite: after CreateBucket is forwarded to master, lo...
- 04:12 PM rgw Backport #19758: jewel: multisite: after CreateBucket is forwarded to master, local bucket may us...
- Need More Info (see comment in master issue)
- 04:10 PM rgw Backport #19758 (In Progress): jewel: multisite: after CreateBucket is forwarded to master, local...
- 04:09 PM rgw Bug #19745: multisite: after CreateBucket is forwarded to master, local bucket may use different ...
- Casey Bodley wrote:
> https://github.com/ceph/ceph/pull/15010 merged, please include in backports
@Casey: That co... - 02:40 PM rgw Backport #19724 (Resolved): jewel: RGW S3 v4 authentication issue with X-Amz-Expires
- 02:36 PM rgw Backport #19722 (Resolved): jewel: rgw_file: introduce rgw_lookup type hints
- 02:30 PM rgw Backport #19720 (In Progress): jewel: rgw_file: fix size and (c|m)time unix attrs in write_finish
- 02:21 PM rgw Backport #19143 (Resolved): jewel: rgw_file: FHCache residence check should be exhaustive
- 02:19 PM rgw Backport #19169 (Resolved): jewel: rgw_file: allow setattr on placeholder (common_prefix) direct...
- 02:19 PM rgw Backport #19167 (Resolved): jewel: rgw_file: RGWReaddir (and cognate ListBuckets request) don't ...
- 02:19 PM rgw Backport #19165 (Resolved): jewel: rgw_file: "exact match" invalid for directories, in RGWLibFS:...
- 02:18 PM rgw Backport #19161 (Resolved): jewel: rgw_file: fix marker computation
- 02:16 PM rgw Backport #19615 (In Progress): jewel: multisite: bucket zonegroup redirect not working
- 02:14 PM rgw Backport #19613 (In Progress): jewel: multisite: rest api fails to decode large period on 'period...
- 01:43 PM Revision 4cb62c2f (ceph): Merge pull request #15443 from trociny/wip-rbd_image_options_t
- librbd: remove unused rbd_image_options_t ostream operator
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:01 PM Revision 28a50987 (ceph): build/ops: rpm: make librbd1 %post scriptlet depend on coreutils
- Fixes: http://tracker.ceph.com/issues/20052
Signed-off-by: Giacomo Comes <comes@naic.edu>
Signed-off-by: Nathan Cutle... - 12:44 PM Revision 97d6e150 (ceph): Merge pull request #15347 from tchaikov/wip-cmake
- cmake: rgw: do not link against boost in a wholesale
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Nat... - 12:41 PM rgw Backport #19532 (Need More Info): jewel: radosgw-admin: unable to set global quotas in RGWPeriodC...
- 12:34 PM rgw Backport #19532 (In Progress): jewel: radosgw-admin: unable to set global quotas in RGWPeriodConfig
- 12:17 PM Backport #20173 (Resolved): kraken: PR #14886 creates a SafeTimer thread per PG
- https://github.com/ceph/ceph/pull/15526
- 12:17 PM Backport #20172 (Resolved): jewel: PR #14886 creates a SafeTimer thread per PG
- https://github.com/ceph/ceph/pull/15529
- 11:54 AM Revision 2b56d24f (ceph): Merge pull request #15353 from wjwithagen/wip-wjw-compare-object_catcher
- test/osdc: fix comparison error and silence warning from -Wunused-value
Reviewed-by: Jos Collin <jcollin@redhat.com> - 10:20 AM Bug #20091 (Fix Under Review): build/ops: rpm: Invalid SPDX license: GPL-2.0-with-autoconf-exception
- https://github.com/ceph/ceph/pull/15399
- 10:12 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- Must be backported together with #19497 - i.e. total of two master PRs
- 09:25 AM Revision ba1ca1ce (ceph): cmake: rgw: do not link against boost in a wholesale
- With the new Beast frontend, RGW now has a small Boost dependency [1] which was
being addressed by statically (and un... - 08:43 AM Revision c8717ca8 (ceph): librbd: remove unused rbd_image_options_t ostream operator
- This fixes librbd crashes currently observed on master, when
debug is on, because `rbd_image_options_t` is typedef-ed... - 07:58 AM CephFS Backport #20025 (In Progress): jewel: MDS became unresponsive when truncating a very large file
- 07:57 AM Revision 239a5fc3 (ceph): test_compression: add lz4
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 07:56 AM Revision a97a6e82 (ceph): compressor: add LZ4 support
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:40 AM CephFS Bug #20170 (Fix Under Review): filelock_interrupt.py fails on multimds
- https://github.com/ceph/ceph/pull/15440
- 04:27 AM Revision 0d71c612 (ceph): mds/flock: properly remove item from global_waiting_locks
- ceph_lock_state_t::remove_waiting() uses wrong key to search
global_waiting_locks. It should use item in waiting_lock... - 04:26 AM Revision a6b01939 (ceph): mds/flock: properly update ceph_lock_state_t::client_waiting_lock_counts
- no item is added to waiting_locks when deadlock check fails
Signed-off-by: "Yan, Zheng" <zyan@redhat.com> - 03:58 AM Revision 8d777c48 (ceph): mds/flock: don't import ceph_lock_state_t::waiting_locks
- Item in waiting_locks is associated with flock mds request in
exporter mds. If client re-sends the flock mds request ... - 03:15 AM CephFS Backport #20027 (In Progress): jewel: Deadlock on two ceph-fuse clients accessing the same file
- 01:24 AM Revision cb7f43cf (ceph): os/bluestore: move cache_trim into MempoolThread
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
06/02/2017
- 11:40 PM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- https://github.com/ceph/ceph/pull/15217 has merged and I have set http://tracker.ceph.com/issues/19986 pending backpo...
- 11:39 PM Bug #19986 (Pending Backport): PR #14886 creates a SafeTimer thread per PG
- 11:39 PM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- Awaiting backport via http://tracker.ceph.com/issues/19497
- 03:32 PM Bug #19986 (Resolved): PR #14886 creates a SafeTimer thread per PG
- 09:46 PM Revision 7c5ec1d1 (ceph): rgw: add cls _bucket_resharding_set and cls_bucket_resharding_clear
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:46 PM Revision 424dd652 (ceph): rgw: Add resharding flag and the new bucket instance id to RGWBucketInfo
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:44 PM Revision 0806a005 (ceph): radosgw-admin: move resharding into a separate function
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:44 PM Revision 94490951 (ceph): radosgw-admin: Add reshard add, list, execute and cancel commands
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:44 PM Revision fd9db9e0 (ceph): rgw: add reshard_pool
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:44 PM Revision a34f6af7 (ceph): rgw: add RGWReshard class
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 09:44 PM Revision 450ea1c4 (ceph): rgw: add cls_rgw_reshard ops
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 07:48 PM Revision c628a9e5 (ceph): osd: Object level shard errors are tracked and used if no auth available
- Shards with object mismatch are tracked to mark them inconsistent
Fix test because storing omap_digest in object_info... - 07:12 PM Revision cef5c1e2 (ceph): mon: clean up PGMapDigest encoding
- Remove compat cruft due to intitial testing on bigbang.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:02 PM Revision c93daaf9 (ceph): compile fixups for dout
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 06:46 PM Revision c38221d2 (ceph): mon: implement '{mon,osd,mds} versions' and '{mon,osd,mds} count-metada...
- Summarize running versions of mon, osd, and mds daemons, or similarly
tabulate daemons by any other metadata property... - 06:19 PM Revision 1d19254b (ceph): rgw: drop asio/{yield,coroutine}.hpp replacements
- as we requires boost 1.61+ now, which offers them. see
http://www.boost.org/doc/libs/1_61_0/boost/asio/.
Signed-off-... - 06:10 PM Revision afcfc1d7 (ceph): common/version: remove accidental space
- Introduced in 32f10b36529924d982093ad3b8e199d6e89664ee
Signed-off-by: Sage Weil <sage@redhat.com> - 06:09 PM Revision bf72bd8d (ceph): Merge pull request #15119 from ceph/wip-rgw-config-docs
- doc: mention certain conf vars should be in global
Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
Reviewed-by: Kef... - 06:01 PM Revision 7c6db70b (ceph): os/bluestore: try to unshare blobs from gen objects
- OSD EC write pattern clones a to-be-written range to a
gen object and then deletes it shortly after. Try to
unshare ... - 06:00 PM Revision 4fb50f72 (ceph): os/bluestore: drop unused dirty_range arg
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:00 PM Revision fdcaed2d (ceph): os/bluestore/bluestore_types: fix bluestore_shared_blob_t printer
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:00 PM Revision eebfd47e (ceph): os/bluestore: remove MUTABLE flag
- This flag is confusingly redundant as it is equivalent to !compressed &&
!shared. Remove the flag and reimplement is... - 05:17 PM CephFS Bug #20170 (In Progress): filelock_interrupt.py fails on multimds
- 04:17 PM CephFS Bug #20170 (Resolved): filelock_interrupt.py fails on multimds
- 05:06 PM Revision befe07f1 (ceph): mon/OSDMonitor: filter the added creating_pgs added from pgmap
- the creating_pgs added from pgmap might contains pgs whose containing
pools have been deleted. this is fine with the ... - 05:06 PM Revision e8b23d68 (ceph): qa/tasks: add a blacklist for flush_pg_stats()
- so we don't wait for marked out osds.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:06 PM Revision 8f6a526f (ceph): selinux: clip the ceph context to ceph-mgr also
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:06 PM Revision 8b164903 (ceph): mon: mgr: pgstats: do available-space calculations on mgr instead of mon
- This means we don't need the osd_stat map on the monitor at all. We're
about to remove it entirely!
Signed-off-by: G... - 05:06 PM Revision ce38a6c1 (ceph): mon: pgstat: remove unused get_osd_sum from post-luminous state
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 PM Revision 27c5f6b6 (ceph): mon: mgr: remove osd_stats map from PGMapDigest
- We use this information only for dumps. Stop dumping per-OSD stats as they're
not needed. In order to maintain pool "... - 05:06 PM Revision 5281a0ca (ceph): mon/MonmapMonitor: initialize new cluster monmap with default persisten...
- This is similar to what we do for OSDMonitor::create_initial().
Avoid setting these initial features just for teh mo... - 05:06 PM Revision d1eca5f6 (ceph): mon/OSDMonitor: print pgid before looking it up in mapping
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:06 PM Revision fc070255 (ceph): osdmonitor: use a new get_full_osd_counts to generate health without os...
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 PM Revision 459ec619 (ceph): mon: pgstat: remove get_osd_stat() from post-luminous state
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 PM Revision 9fd76f57 (ceph): mon: pgstat: remove get_num_pg_by_osd() from post-luminous state
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 PM Revision ad630462 (ceph): mon: pgstat: remove unused get_pg_sum interface
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 PM Revision af2994dc (ceph): osd: do_shutdown takes precedence over fetching more maps
- This is making my osd-markdown.sh test fail reliably.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:06 PM Revision aad1afcb (ceph): mgr: reset pending_inc after applying it
- we cannot apply pending_inc twice and expect the result is the same. in
other words, pg_map.apply_incremental(pending... - 05:06 PM Revision 6a68877f (ceph): mon/PGMap: strip out PGMapDigest compat cruft
- This was needed for bigbang testing, but not for the final version.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:06 PM Revision 2de0e07c (ceph): mon: handle MStatfs using PGStatService
- otherwise ceph_test_rados_api_stat: LibRadosStat.ClusterStat will always
timeout once the cluster is switched to lumi... - 05:06 PM Revision f42182c5 (ceph): mon: handle MGetPoolStats using PGStatService
- otherwise ceph_test_rados_api_stat: LibRadosStat.PoolStat will always
timeout once the cluster is switched to luminou... - 05:06 PM Revision 2f881dbf (ceph): mon/PGMap: count 'unknown' pgs
- Also, count "not active" (inactive) pgs instead of active so that we
list "bad" things consistently, and so that 'ina... - 05:06 PM Revision 9332bb9b (ceph): mgr: mgr_tick_period = 2
- 5 seconds is driving me nuts. We cap the health message size so the
digest is now small and lightweight.
Signed-off... - 05:06 PM Revision 60a30ff9 (ceph): mon: print log for the creating_pgs changes
- print more log messages when updating creating_pgs.
see-also: http://tracker.ceph.com/issues/20067
Signed-off-by: Ke... - 05:06 PM Revision ebc496d7 (ceph): osd/OSDMap: more efficient PGMapTemp
- Use a flat_map with pointers into a buffer with the actual data. For a
decoded mapping, we have just two allocations... - 05:02 PM Revision dcc4c52e (ceph): mgr/DaemonServer: log pgmap usage to cluster log
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 6afca3be (ceph): mgr/ClusterState: make pg stat filtering less fragile
- We want to drop updates for pgs for pools that don't exist. Keep an
updated set of those pools instead of relying on... - 05:02 PM Revision 15f823b4 (ceph): mgr/MgrStandby: reset subscriptions when we become non-active
- This is a goofy workaround that we're also doing in Mgr::init(). Someday
we should come up with a more elegant solut... - 05:02 PM Revision 578cd59d (ceph): mgr: drop useless __func__ prints
- This is part of the default prefix.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 50c617a4 (ceph): mon/OSDMonitor: clean up no-beacon message
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 3b049712 (ceph): mon/OSDMonitor: use newest creation epoch for pgs that we can
- If we have a huge pool it may take a while for the PGs to get out of the
queue and be created. If we use the epoch t... - 05:02 PM Revision 2e1f8fdb (ceph): mon/PGMap: encode delta info in digest
- It was already in PGMapDigest, but not encoded.
One field we didn't need; move that back to PGMap.
Signed-off-by: S... - 05:02 PM Revision d6d1db62 (ceph): mgr: apply PGMap incremental at same interval as reports
- We were doing an incremental per osd stat report; this screws up the
delta stats updates when there are more than a h... - 05:02 PM Revision 4c5064e7 (ceph): debian,rpm: add jq dependency to ceph-test
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 62a478cb (ceph): tools/ceph-monstore-update-crush.sh: switch from xmlstarlet to jq
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 46bf019c (ceph): test: switch from xmlstartlet to jq
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 85cc2595 (ceph): osd: work around bluestore fragmetned buffers in get_map_bl
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 0612b716 (ceph): mgr: simplify handling of new pgs/pools
- Instantiate barebones pg records (creating+stale) in our PGMap when pgs
are created. These will switch to 'creating'... - 05:02 PM Revision 02fd2960 (ceph): osd/osd_types: make 0 pg state 'unknown' instead of 'inactive'
- The OSD never reports PGs this way; we'll only see it from a mgr
PGMap that hasn't filled in the state.
Signed-off-b... - 05:02 PM Revision 1c8c3d70 (ceph): mon,mgr: update inc.osd_epochs when resetting osd_stat_updates
- otherwise we could have follow bt in ceph-mgr:
ceph version Development (no_version)
1: (ceph::__ceph_assert_fail(... - 05:02 PM Revision f0eff922 (ceph): mon/PGMap: update osd_epoch in synchrony with osd_stat_updates
- I'm not sure why this didn't bite us earlier, but there is an assert
in apply_incremental (not used in preluminous mo... - 05:02 PM Revision b4e17fbf (ceph): mon: speed up pg creates a bit
- I don't see any noticeable load on bigbang cluster, so let's bump this up
a bit. Not being super aggressive here, th... - 05:02 PM Revision 87a993a9 (ceph): ceph-kvstore-tool: implement 'rm' and 'rm-prefix' commands
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 90d45c1d (ceph): mon/PGMap: new check_osd_map that takes a OSDMap& const
- The previous version takes an Incremental and requires that we see
every single consecutive map in the history. This... - 05:02 PM Revision 681d37c0 (ceph): mgr/ClusterState: apply latest osdmap to pgmap
- In particular, clear out deleted pools and clear osd stats for
deleted/down/out osds.
Signed-off-by: Sage Weil <sage... - 05:02 PM Revision 818018a6 (ceph): mon/PGMap: fix deleted_pool cleanup
- - make sure num_pg_by_pool is cleared
- update_pool_deltas can repopulate pg_pool_sum; clear after that
Signed-off-b... - 05:02 PM Revision 057e4aaa (ceph): vstart: debug mon on mgr
- PGMap dout is tied to mon still; we want to see it on the mgr.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 229e56c7 (ceph): mon/PGMap: cap health detail messages at 50 (configurable)
- There are two cases where we spew health detail warnings for potentially
every pg. Cap those detail messages at 50 a... - 05:02 PM Revision 73ddcc37 (ceph): mon/MgrStatMonitor: fix version across restarts
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision d019d137 (ceph): mon/PGMap: explicitly count pg per pool
- This will more reliably remove empty pools from pg_pool_sum.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 7394b96d (ceph): mon/PGMap: use int32_t, not int
- These are encoded! Be explicit.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 9fa1b382 (ceph): mgr/DaemonServer: keep registry of osd sessions
- Occasionally we send them messages.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision b01c0d36 (ceph): mgr/DaemonServer: use registered osd session to send scrub messages
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision acfebf27 (ceph): mgr,mon: move 'osd {scrub,deep-scrub,repair}' handling to mgr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 7559f1c0 (ceph): mon/MgrStatMonitor: wrap digest encoding in bufferlist
- This is just for bigbang's benefit.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision f0d41736 (ceph): mon/MgrStatMonitor: trim mgrstat states
- We don't actually need any of these older states at all so I hard-coded
a constant (oh no!). In reality it doesn't m... - 05:02 PM Revision 11d1a4d3 (ceph): mon/PGMonitor: do not create/encode pending if luminous
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 30f0ae04 (ceph): qa/workunites/ceph-helpers.sh: move flush_pg_stats() here
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision b883d7a9 (ceph): test/osd/osd-dup.sh: flush_pg_stats before "ceph -s"
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 39b7dcb0 (ceph): test/cephtool-test-mon: make ec test less sensitive to crush
- With only 3 we can get into a situation where one slot is CRUSH_ITEM_NONE.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision c62e5dac (ceph): mon: move parse_* helpers into cmdparse
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 74752505 (ceph): mgr: add a command "mgr report"
- * extract send_report() out of tick() so it can be reused.
* add a commmand "mgr report-mon" for mgr, so we are able ... - 05:02 PM Revision 44708d83 (ceph): qa/workunits/cephtool/test.sh: use flush_pg_stats to sync mon with osd
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 3c12465f (ceph): qa/workunits/cephtool/test.sh: use jq instead of awk to select the requ...
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 7af652eb (ceph): mon/PGMonitor: reset PGMonitor member vars when luminous
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 85b17ba1 (ceph): osd: report a seq from flush_pg_stats command
- Report a sequence number when we flush_pg_stats. Combine the up_from and
a per-boot seq number to get a monotonicall... - 05:02 PM Revision fa70d0e8 (ceph): mon/PGMap: coalesce last osd stat seq in the PGMapDigest
- This is, strictly speaking, redundant, since the osd_stat is also in the
digest, but we plan to remove that.
Signed-... - 05:02 PM Revision aac073dc (ceph): mon: add 'osd last-stat-seq <osd>' command
- Return the latest seq for the osd reflected in the mon's digest stats.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision ab1b78ae (ceph): qa/tasks: use new reliable flush_pg_stats helper
- The helper gets a sequence number from the osd (or osds), and then
polls the mon until that seq is reflected there.
... - 05:02 PM Revision cd00aae1 (ceph): qa/workunits/cephtool/test.sh: fix flush_pg_stats usage
- Use a helper.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 1e9c95ac (ceph): mon/OSDMonitor: limit number of concurrently creating pgs
- There is overhead for PGs we are creating because the mon has to track
which OSD each one current maps to. This can ... - 05:02 PM Revision 1e3f1fcc (ceph): kv/RocksDBStore: make rmkeys_by_prefix efficient
- This matches what rm_range_keys does.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:02 PM Revision 3c96f2f7 (ceph): mon/PGMonitor: clear PGMap data when require_luminous is set
- Once the OSDMap flag is set there is no going back. Zero out the on-disk
PGMap data, and clear the in-memory PGMap to... - 05:02 PM Revision 38ddb686 (ceph): osd: include up_from, seq in osd_stat_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 3109da26 (ceph): mon: move dump_info() to PGStatService
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 62d1960c (ceph): test: pass mon_pg_warn_min_per_osd=3 to mgr also
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 58bf4a88 (ceph): mon/PGMonitor: disable when REQUIRE_LUMINOUS is set
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 5a700a46 (ceph): mon/OSDMonitor: fix bad update_pending_pgs call
- We are not persisiting the updated creating_pgs here; this is bad! I'm
not sure why it was there to begin with?
Sig... - 05:02 PM Revision 960a8d6f (ceph): mon/MgrStatMonitor: fix digest vs pending digest
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision a2fdede8 (ceph): mon/PGMap: add to mempool
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision a20c5e3c (ceph): test/cephtool-test-*: enable mgr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 53c96f22 (ceph): mon/OSDMonitor: do not reference pgservice if quorum not formed
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 063ad5aa (ceph): mon: more constness to PGStatService
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision 66bf3558 (ceph): mon/PGMap: use auto
- I'm not rewriting this to use range iterator syntax because I'm in a
hurry. This just lets me change the types withou... - 05:02 PM Revision 6d7e1c10 (ceph): test/osd/osd-dup.sh: run mgr with test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 07ddeb24 (ceph): qa/workunites/ceph-helpers.sh: do not bail when num_pg==0
- Right after the cluster is created when the first mgr report hasn't come
in yet we will report 0 pgs.
Signed-off-by:... - 05:02 PM Revision ba5c5f3f (ceph): mon/PGStatService: define maybe_trim_creating_pgs() method
- replace get_pg_stat() with maybe_trim_creating_pgs(), so it is more
symmetric: maybe_add_creating_pgs() versus maybe_... - 05:02 PM Revision 1c7b4be2 (ceph): mon/PGMapStatService: various updates
- * add override specifier
* s/parent/pgmap/
* remove unnecessary forward declarations
* make `pg_map` and `pgservice` ... - 05:02 PM Revision 71cbc2b7 (ceph): mon: accept health summary and detail messages from mgr
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision daa0793c (ceph): mon/PGMonitor: move most of get_health into PGMap
- Leave the legacy full/nearfull stuff in PGMonitor (although we'll still
need to clean out the PGMap fields too).
Thi... - 05:02 PM Revision 27bd39cd (ceph): mgr/ClusterState: report health about pgs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 7df32d11 (ceph): mon/PGMonitor: link PGStatService to the actual PGMap
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 8c0c09cd (ceph): mon: move mgr report handling into separate MgrStatMonitor
- We don't want this is MgrMonitor or else the MgrMap epoch will roll over
every few seconds when we get a mgr report. ... - 05:02 PM Revision 06476103 (ceph): mon/PGMonitor: reindent maybe_add_creating_pgs()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision b306e9e0 (ceph): osd: stop sending pgstat if luminous
- we don't send pgstat to mon from osd once we set
CEPH_OSDMAP_REQUIRE_LUMINOUS. and cleanup the pgstat queue when we
d... - 05:02 PM Revision 8e16c68b (ceph): mon/MgrStatMonitor: add override specifier for virtual methods
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision fb3405d0 (ceph): mon/OSDMonitor: avoid pulling pgmap ratio on mkfs
- If this is the first osdmap epoch there is nothing to be learned from
the PGMap.
Signed-off-by: Sage Weil <sage@redh... - 05:02 PM Revision b73e4374 (ceph): mgr: send PGMapDigest instead of PGMap to mon
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision fe40e263 (ceph): mon: remove last trace of PGMap from MgrMonitor
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 05:02 PM Revision db1b9815 (ceph): mon: adjust pgservice based on OSDMap require_luminous flag
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:02 PM Revision 17b699d9 (ceph): mon/PGStatService: implement pre-luminous methods in parent
- Many of these are only needed to support PGMonitor. Implement those
in the parent and make them ceph_abort() so that... - 05:02 PM Revision 8f252161 (ceph): mon/PGMap: move summary information into parent PGMapDigest object
- Everything summary-ish that we need to send to the mon is moved into a
parent class. The child PGMap retains the det... - 05:01 PM Revision 0e598d96 (ceph): mon/OSDMonitor: condition PGMap->creating priming on !luminous
- Once we set the luminous flag we shouldn't need this anymore. In fact,
we should stop needing this immediately after... - 05:01 PM Revision 08bd81fa (ceph): mon/PGMap: use num_pg where available
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:00 PM Revision 39d524a4 (ceph): mon/PGMap: remove version from summary
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:59 PM Revision 9b03a163 (ceph): mon: pgstats: move some creating_pgs maintenance into the PGStatService
- And remove get_pg_map() now that there are no users!
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 04:59 PM Revision ed1af717 (ceph): mon: move the PGStatService lifecycle into the MgrMon/PGMon
- I remain lazy enough that we just use the MgrMon right now for easier
testing.
Signed-off-by: Greg Farnum <gfarnum@r... - 04:59 PM Revision 504c7b8e (ceph): mon: give PGMonitor and MgrMonitor their own PGStatService implementations
- Right now they pretty much just copy the PGMapStatService, but it'll
let us slim down the MgrMonitor's one more easil... - 04:59 PM Revision 2148386d (ceph): mon: give PGStatService a reweight_by_utilization indirection
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision f8af069a (ceph): mon: subclass PGStatService into PGMapStatService
- Here we begin moving chunks into more appropriate locations.
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 04:59 PM Revision 02f7a189 (ceph): mon: pgstat: expose the full osd_stat map to remove a get_pg_map() call
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision e7830b95 (ceph): mon: pgstat: expose the full pg_stat map to remove a get_pg_map() call
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 5e0cbdf3 (ceph): mon: pgstat: remove unneeded StatIter functions
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision a6e669c4 (ceph): mon: give PGStatService a process_pg_command indirection
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 1ca47d75 (ceph): mon: use a pointer to PGStatService instead of putting it in Monitor
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 44e0228a (ceph): mon: yet more OSDMonitor dep-pgmap-ification
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 16c39e5f (ceph): mon: stop dereferencing pg_map for object stats in OSDMonitor
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision d8cd3190 (ceph): mon: get the OSDMonitor's pg info dump functions away from using PGMap
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 8e9b1093 (ceph): mon: kill direct references to pgmon from OSDMonitor
- The only one left now is where the OSDMonitor triggers
PGMonitor::check_osd_map() and that's going to die post-Lumino... - 04:59 PM Revision 2c82b9c9 (ceph): mon: FSCommands gets pool stats via PGService
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision f0e74fcf (ceph): mon: FSCommands gets pool stats via PGService
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision ff1b132f (ceph): mon: OSDMonitor starting to abstract PGMap via PGService
- We added an unfortunate get_pg_map() function but it's still easy
to find and puts off some of the logic work. We'll ... - 04:59 PM Revision 74c1a84a (ceph): mon: more OSDMonitor de-pgmap-ification
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 PM Revision 29acfa93 (ceph): mon: outline a PGStatService to replace raw PGMap calls
- Right now, this is a quick hack that derives from PGMap. Soon, it will
be more interesting.
Signed-off-by: Greg Farn... - 04:58 PM Revision 759c7d0a (ceph): mon: mgr: send a pgmap in reports
- This definitely isn't appropriate for long term but is a quick route to testing
Signed-off-by: Greg Farnum <gfarnum@... - 04:58 PM Revision 35fd964e (ceph): mgr: switch from send_beacon() to tick()
- We are about to want similar time-based stuff in our other
classes and it's simplest to coalesce them into a single w... - 04:58 PM Revision efbe4667 (ceph): mgr: create a skeleton MMonMgrReport message type
- We'll use this for sending data to the monitor at tick intervals.
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 04:58 PM Revision ff1258e7 (ceph): mgr: introduce tick() calls through the system
- Still empty for the moment
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 04:58 PM Revision 39bd83d6 (ceph): mon: route manager reports down to the MgrMon
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:58 PM Revision 3bbcdb84 (ceph): mon/MgrMap: prefix summary with epoch; add comma
- This matches the others now:
cluster 0d553373-5de6-4d90-bc60-cfd6f6554631
health HEALTH_OK
monmap e2: ... - 04:58 PM Revision 8d803e04 (ceph): MonClient: support "passthrough" of MonMap messages so other Dispatcher...
- Use this in the Manager so it can notify of new monitor maps.
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 04:57 PM Bug #20089 (Resolved): Can't repair when only an attr object error
- 02:40 AM Bug #20089 (Pending Backport): Can't repair when only an attr object error
- 12:36 AM Bug #20089: Can't repair when only an attr object error
- https://github.com/ceph/ceph/pull/15397
- 04:56 PM Backport #20125 (Resolved): Kraken: Can't repair when only an attr object error
- 04:56 PM Backport #20126 (Resolved): Jewel: Can't repair when only an attr object error
- 04:54 PM Revision 358081d2 (ceph): Merge pull request #15421 from dzafman/wip-20125
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
- 04:54 PM Revision 62c500f5 (ceph): Merge pull request #15416 from dzafman/wip-20126
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
- 04:16 PM Revision ea911b7f (ceph): Merge pull request #14351 from yehudasa/wip-rgw-mdsearch
- rgw: metadata search part 2
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Abhishek Lekshmanan <abhishe... - 03:34 PM Revision ffced8cf (ceph): Merge pull request #15427 from tchaikov/wip-vstart-osd-id
- vstart: print "start osd.$id" instead of "start osd$id"
Reviewed-by: Sage Weil <sage@redhat.com> - 03:32 PM Revision b98ad7ca (ceph): Merge pull request #15217 from badone/wip-async-sleep-timer-fix
- osd: Move scrub sleep timer to osdservice
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:30 PM Revision 6e406bab (ceph): Merge pull request #15396 from jcsp/wip-ceph-status
- mon: revise "ceph status" output
Reviewed-by: Sage Weil <sage@redhat.com> - 03:29 PM RADOS Bug #20169 (New): filestore+btrfs occasionally returns ENOSPC
- ...
- 03:20 PM Revision b735c5a9 (ceph): Merge pull request #15011 from xiexingguo/wip-crush-tool
- tools/crushtool: replicated-rule API support
Reviewed-by: Sage Weil <sage@redhat.com> - 03:20 PM Revision cd4acd8d (ceph): Merge pull request #15176 from SUSE/wip-mgr-fix-help
- mgr,osd: ceph-mgr --help, unify usage text of other daemons
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:19 PM Revision 6bedb4c3 (ceph): Merge pull request #15395 from liewegas/wip-log-entity
- common/LogEntry: include EntityName in log entries
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:19 PM Revision ecef6fd8 (ceph): Merge pull request #15398 from liewegas/wip-bluestore-leak
- os/bluestore: fix buffers pinned by indefinitely deferred writes
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:19 PM Revision 773a0ac2 (ceph): Merge pull request #15402 from liewegas/wip-bluestore-mempools
- os/bluestore: improve mempool usage
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:18 PM Revision a35cd1cb (ceph): Merge pull request #15403 from liewegas/wip-mempool-dump
- mempool: improve dump; fix buffer accounting bugs
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:15 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-06-02_08:32:01-rados-wip-sage-testing-distro-basic-smithi/1255551
rados/thrash/{0-size-min-size-overr... - 03:14 PM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-06-02_08:32:01-rados-wip-sage-testing-distro-basic-smithi/1255514
teuthology:1255514 03:14 PM $ cat su... - 03:13 PM Bug #19948: LibRadosTwoPools[EC]PP.PromoteSnap
- /a/sage-2017-06-02_08:32:01-rados-wip-sage-testing-distro-basic-smithi/1255484
description: rados/thrash/{0-size-min... - 03:12 PM Bug #19595: mgr: segv in msgr thread, with no core
- /a/sage-2017-06-02_08:32:01-rados-wip-sage-testing-distro-basic-smithi/1255413
/a/sage-2017-06-02_08:32:01-rados-wip... - 03:11 PM Bug #19741: test_envlibrados_for_rocksdb.yaml fails on crypto restart
- /a/sage-2017-06-02_08:32:01-rados-wip-sage-testing-distro-basic-smithi/1255399
- 03:01 PM rbd Bug #20168 (Resolved): IO work queue does not process failed lock request
- If the attempt to request the exclusive lock fails, the IO work queue will not attempt to recover. For example, in Je...
- 02:57 PM Revision e24d2ecd (ceph): mon/FSCommand: fix indentation
- Makes this warning go away
/home/sage/src/ceph4/src/mon/FSCommands.cc: In member function ‘virtual int SetHandler::h... - 02:09 PM Bug #20135: test/rest.py: PUT auth/add?entity=client.xx&caps=mon&caps=allow&caps=osd&caps=allow+*...
- http://pulpito.ceph.com/kchai-2017-06-02_09:03:21-rados-master---basic-smithi/...
- 03:09 AM Bug #20135 (Resolved): test/rest.py: PUT auth/add?entity=client.xx&caps=mon&caps=allow&caps=osd&c...
- ...
- 02:05 PM Revision a8a99695 (ceph): Merge pull request #15431 from rzarzynski/wip-rgw-vim-modeline-for-orhp...
- rgw: add the Vim's modeline into rgw_orphan.cc.
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 01:56 PM Revision d5f178f0 (ceph): Merge pull request #15425 from yaozongyou/fix-build-error
- cmake: link against fcgi only if enabled
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by: Kefu Chai <kcha... - 01:28 PM Bug #20167 (Resolved): osd/PG.cc: 806: FAILED assert(past_intervals.empty())
- ...
- 01:16 PM Revision 72785bb5 (ceph): rbd-mirror: fix valgrind memcheck errors
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:55 PM Revision 90353490 (ceph): qa: rbd valgrind tests should use failure exit code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:55 PM Revision 965ee270 (ceph): librbd: fix valgrind memcheck errors
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:35 PM rgw Bug #20037: rgw log includes zero byte sometimes
- Similar things happen in the output of @radosgw-admin object stat@, some strings are shown with a trailing @\u0000@:
... - 12:05 PM Revision e342c39a (ceph): rgw: add the Vim's modeline into rgw_orphan.cc.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 12:05 PM rgw Bug #20166 (New): RGW: Bad error handling when tail object is missing
- When doing an S3 GET on an object, it may happen that one of the tail objects does not exist. When radosgw notices th...
- 11:25 AM CephFS Bug #20165 (Fix Under Review): Deadlock during shutdown in PurgeQueue::_consume
- https://github.com/ceph/ceph/pull/15430
- 11:01 AM CephFS Bug #20165 (Resolved): Deadlock during shutdown in PurgeQueue::_consume
- PurgeQUeue does this while holding its lock:...
- 11:21 AM Stable releases Tasks #19538: jewel v10.2.8
- Adding an integration branch scheduling only the RGW memleak fix PRs (and the above rados PR which was already merged...
- 10:13 AM ceph-ansible Bug #15569 (New): Two logrotate scripts
- Christian, this is odd. I downloaded the ceph-base and ceph-common deb files from http://download.ceph.com/debian-jew...
- 07:40 AM ceph-ansible Bug #15569: Two logrotate scripts
- -https://github.com/ceph/ceph/pull/9995/commits/457ddea9c8b0f000476798e99ee0aaeb003402c9-
-Also needs the jewel ba... - 07:35 AM ceph-ansible Bug #15569 (Pending Backport): Two logrotate scripts
- The problem might be caused by this line [1] and, more generally, by not sufficiently reflecting the split of the for...
- 05:39 AM ceph-ansible Bug #15569: Two logrotate scripts
- @
# ceph --version
ceph version 10.2.7 (50e863e0f4bc8f4b9e31156de690d765af245185)
@
The packages are installed ... - 09:50 AM Revision 90dc421c (ceph): rc/test/osdc/object_cacher_stress.cc: fix comparison
- Clang complains:
/home/jenkins/workspace/ceph-freebsd/src/test/osdc/object_cacher_stress.cc:50:26: error: ordered c... - 09:33 AM Linux kernel client Bug #20164 (Resolved): libceph: got bad padding
- I have just instaled a 3 node ceph instalation. Each node acts as monitor and 2 osd (1 sata 1 ssd).
I am getting a l... - 09:01 AM Revision 17970283 (ceph): pybind: remove 'rest' module
- The 'restful' module is in there now and we don't need two.
Signed-off-by: John Spray <john.spray@redhat.com> - 09:01 AM Revision 0b24c028 (ceph): doc: remove reference to Calamari API
- ...to avoid confusion wrt new `restful` module.
Signed-off-by: John Spray <john.spray@redhat.com> - 07:39 AM Backport #20161 (Rejected): jewel: "assert len(unclean) == num_unclean" in dump_stuck.py in rados...
- 07:37 AM Revision ff549780 (ceph): the return value is not boolean
- Signed-off-by: zhanglei <243290414@qq.com>
- 07:37 AM rgw Backport #20160 (Rejected): kraken: rgw_file: RGWLibFS::get_inst() not stable
- 07:37 AM rgw Backport #20159 (Resolved): jewel: rgw_file: RGWLibFS::get_inst() not stable
- https://github.com/ceph/ceph/pull/15459
- 07:37 AM rgw Backport #20158 (Resolved): kraken: rgw_file: handle chunked readdir
- https://github.com/ceph/ceph/pull/13871
- 07:37 AM rgw Backport #20157 (Resolved): jewel: rgw_file: handle chunked readdir
- https://github.com/ceph/ceph/pull/14653
- 07:36 AM rgw Backport #20156 (Resolved): kraken: fix: rgw crashed caused by shard id out of range when listing...
- https://github.com/ceph/ceph/pull/16173
- 07:36 AM rgw Backport #20155 (Resolved): jewel: fix: rgw crashed caused by shard id out of range when listing ...
- https://github.com/ceph/ceph/pull/15465
- 07:36 AM rbd Backport #20154 (Resolved): kraken: Potential IO hang if image is flattened while read request is...
- https://github.com/ceph/ceph/pull/16184
- 07:36 AM rbd Backport #20153 (Resolved): jewel: Potential IO hang if image is flattened while read request is ...
- https://github.com/ceph/ceph/pull/15464
- 07:36 AM rbd Backport #20152 (Rejected): hammer: Potential IO hang if image is flattened while read request is...
- https://github.com/ceph/ceph/pull/15980
- 07:36 AM Backport #20151 (Resolved): jewel: ceph-disk fails if OSD udev rule triggers prior to mount of /var
- https://github.com/ceph/ceph/pull/15504
- 07:36 AM Backport #20150 (Resolved): kraken: ceph-disk fails if OSD udev rule triggers prior to mount of /var
- https://github.com/ceph/ceph/pull/16092
- 07:36 AM CephFS Backport #20149 (Rejected): kraken: Too many stat ops when MDS trying to probe a large file
- 07:36 AM CephFS Backport #20148 (Resolved): jewel: Too many stat ops when MDS trying to probe a large file
- https://github.com/ceph/ceph/pull/15472
- 07:36 AM rgw Backport #20147 (Resolved): kraken: rgw: 'gc list --include-all' command infinite loop the first ...
- https://github.com/ceph/ceph/pull/16139
- 07:36 AM rgw Backport #20146 (Resolved): jewel: rgw: 'gc list --include-all' command infinite loop the first 1...
- https://github.com/ceph/ceph/pull/15719
- 07:36 AM rgw Backport #20145 (Rejected): kraken: rgw_file: cannot delete bucket w/uxattrs
- 07:36 AM rgw Backport #20144 (Resolved): jewel: rgw_file: cannot delete bucket w/uxattrs
- https://github.com/ceph/ceph/pull/15459
- 07:36 AM rgw Backport #20143 (Rejected): kraken: rgw_file: unlink assert unsafe in multi-gateway environments
- 07:36 AM rgw Backport #20142 (Resolved): jewel: rgw_file: unlink assert unsafe in multi-gateway environments
- https://github.com/ceph/ceph/pull/15459
- 07:36 AM CephFS Backport #20141 (Rejected): kraken: Journaler may execute on_safe contexts prematurely
- 07:36 AM CephFS Backport #20140 (Rejected): jewel: Journaler may execute on_safe contexts prematurely
- https://github.com/ceph/ceph/pull/15468
- 07:35 AM rgw Backport #20139 (Rejected): kraken: rgw_file: attempt to unlink non-empty bucket could lead to hang
- 07:35 AM rgw Backport #20138 (Resolved): jewel: rgw_file: attempt to unlink non-empty bucket could lead to hang
- https://github.com/ceph/ceph/pull/15459
- 07:35 AM rgw Backport #20137 (Rejected): kraken: allow empty data_extra_pool in zone placement
- 07:35 AM rgw Backport #20136 (Rejected): jewel: allow empty data_extra_pool in zone placement
- 07:10 AM Revision fda6e16c (ceph): vstart: print "start osd.$id" instead of "start osd$id"
- "osd.9" is more consistent with other places where an osd is referenced.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:57 AM Revision 8751a66a (ceph): rgw: lower some log's level in gc process.
- Signed-off-by: Zhang Shaowen <zhangshaowen@cmss.chinamobile.com>
- 05:54 AM Bug #20067 (Fix Under Review): assert in OSDMonitor::update_creating_pgs()
- https://github.com/liewegas/ceph/pull/48
- 05:41 AM Revision 371f227f (ceph): Merge pull request #15408 from yonghengdexin735/wip-zzz-add_const
- include/lru.h: add const to member functions
Reviewed-by: Jos Collin <jcollin@redhat.com> - 05:07 AM Revision 6e80b503 (ceph): mds/MDBalancer: remove useless check_targets and hit_targets logic from...
- Currently the logic that check and hit export targets has been moved to Migrator. So remove the check_targets and hit...
- 04:11 AM Revision 3b7ecf37 (ceph): Fix cmake build error.
- Signed-off-by: Yao Zongyou <yaozongyou@vip.qq.com>
- 03:52 AM Revision 5e08305e (ceph): osd: osd_tp -> peering_tp, osd_op_threads -> osd_peering_wq_threads
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:52 AM Revision d1f50d51 (ceph): osd: give op threads hdd/ssd specific defaults
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:52 AM Revision 3732d18b (ceph): osd: report overall 'rotational' status
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:52 AM Revision 45fceb27 (ceph): os/bluestore: implement is_rotational()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:52 AM Revision f697f09a (ceph): os/filestore: is_rotational()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:15 AM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- Zheng Yan wrote:
> the last cap message has CHECK_CAPS_SYNCHRONOUS flag. mds flushes mdlog when it sees the flag. Th... - 01:12 AM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- the last cap message has CHECK_CAPS_SYNCHRONOUS flag. mds flushes mdlog when it sees the flag. The patch isn't perfec...
- 03:08 AM Revision 17751bac (ceph): Merge pull request #15420 from yuriw/wip_remove_default_idle_timeout
- qa: Removed all 'default_idle_timeout' due to chnage in rwg task
- 02:40 AM Revision 1244c0a5 (ceph): Merge pull request #15397 from dzafman/wip-20089
- osd: Object level shard errors are tracked and used if no auth available
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 02:23 AM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-06-01_21:44:07-rados-wip-sage-testing---basic-smithi/1253654
teuthology:1253654 02:23 AM $ cat summary... - 02:22 AM Revision ea5b054e (ceph): qa/workunits/cephtool/test.sh: adjust watch test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:20 AM RADOS Bug #20134 (Rejected): test_rados.TestIoctx.test_aio_read AssertionError: 5 != 2
- <Pre>
2017-06-01T22:57:09.649 INFO:tasks.workunit.client.0.smithi084.stderr:========================================... - 02:15 AM Revision 66fe04bf (ceph): os/ObjectStore: is_rotational() interface
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:14 AM Revision 6912c4f9 (ceph): Merge pull request #15417 from smithfarm/wip-cond-epoch-2
- build/ops: rpm: move _epoch_prefix below Epoch definition
06/01/2017
- 11:55 PM Revision 75c5c2b7 (ceph): include/lru: add const to member function
- Signed-off-by: yonghengdexin735 <zhang.zezhu@zte.com.cn>
- 10:36 PM Revision 7a4ba158 (ceph): mgr: fixes compiler error because of atomic_t to <atomic>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 10:36 PM Revision 1fa473ae (ceph): common: migrate atomic_t to <atomic>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 10:35 PM Revision f22bd6e2 (ceph): test: migrate atomic_t to atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 09:40 PM Revision bf26c565 (ceph): osd: Object level shard errors are tracked and used if no auth available
- Shards with object mismatch are tracked to mark them inconsistent
Fix test because storing omap_digest in object_info... - 09:01 PM Revision 02242ea4 (ceph): Removed all 'default_idle_timeout' due to chnage in rwg task
- https://github.com/ceph/ceph/commit/8c74c8a639cd3dead52e1942b36f6eb3f1ceab2c#diff-995b04809fcabacc3e3ecfaea903a41aL53...
- 08:32 PM Revision 6594d972 (ceph): qa/tasks/rgw_multisite.py: adjust zone init
- zone is now a ZoneConn object. Also, change import to make it relative
so that qa task can locate it.
Signed-off-by:... - 07:37 PM Revision 3e302326 (ceph): build/ops: rpm: move _epoch_prefix below Epoch definition
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 07:22 PM Revision b5da257b (ceph): Merge pull request #15400 from yehudasa/wip-20128
- qa/rgw_snaps: move default_idle_timeout config under the client
- 05:58 PM Revision 000a9f62 (ceph): mon/mon_types: move C_MonOp to MonOpRequest.h
- Fixes a circular #include of
mon_types -> MonOpRequest -> Session -> mon_types
Signed-off-by: Sage Weil <sage@redha... - 05:58 PM Revision 1f68cef1 (ceph): mon: track connected mon client features
- Track counts of entities by their supported features.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:58 PM Revision 751514f8 (ceph): mon: share connected features with leader
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:51 PM Revision 8dd93cab (ceph): osd: Object level shard errors are tracked and used if no auth available
- Shards with object mismatch are tracked to mark them inconsistent
Fix test because storing omap_digest in object_info... - 05:46 PM Revision 1cacbea7 (ceph): osd: Object level shard errors are tracked and used if no auth available
- Shards with object mismatch are tracked to mark them inconsistent
Fix test because storing omap_digest in object_info... - 05:19 PM rbd Bug #18963 (Fix Under Review): rbd-mirror: forced failover does not function when peer is unreach...
- 05:09 PM Revision 955deac5 (ceph): osd-scrub-repair: Fix broken test and correctly handle ec overwrite tes...
- Caused by: 3ca750d41dfe33c6efea4abc96d2bd426a9742b9
Signed-off-by: David Zafman <dzafman@redhat.com> - 05:01 PM Revision 649b29d3 (ceph): rbd-mirror: ensure exclusive lock cannot be released with in-flight IO
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:01 PM Revision f51fb162 (ceph): librbd: track async exclusive-lock dependent operations
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:59 PM ceph-ansible Bug #15569 (New): Two logrotate scripts
- What does "ceph --version" say? Where did you get these packages, exactly?
I looked at the debian packaging for 10... - 10:00 AM ceph-ansible Bug #15569: Two logrotate scripts
- Please reopen the bug.
We still see the problem in a fresh install, just with other package names:
@
dpkg -l | g... - 04:54 PM Revision 8bcf3e57 (ceph): Merge pull request #15212 from neha-ojha/wip-fix-recovery-sleep-configu...
- osd: Implement asynchronous recovery sleep
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:54 PM Revision 703055b0 (ceph): Merge pull request #15262 from Adirl/revert_cm
- msg/async: Revert RDMA-CM
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:54 PM Revision 703125eb (ceph): Merge pull request #15307 from ovh/bp-64bit-mem-is-zero
- inline_memory: optimized mem_is_zero for non-x64
Reviewed-by: Sage Weil <sage@redhat.com> - 04:53 PM Revision 268d5cde (ceph): Merge pull request #15340 from wjwithagen/wip-wjw-libcommon
- cmake: do not link libcommon against some libs
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:53 PM Revision f6220d15 (ceph): Merge pull request #15342 from chardan/jfw-wip-add_VLA_warning
- build: Adds C++ warning flag for C Variable-Length Arrays.
Reviewed-by: Sage Weil <sage@redhat.com> - 04:52 PM Revision aee60f2d (ceph): Merge pull request #15364 from joscollin/wip-cleanup-putto-operator-const
- src: put-to operator function - const input cleanup
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 04:52 PM Revision d3887bfe (ceph): Merge pull request #15372 from ganeshmaharaj/reuse-isal
- erasure-code: Remove duplicate of isa-l files
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:51 PM Bug #19595: mgr: segv in msgr thread, with no core
- go ta stack trace and core this time!...
- 04:50 PM RADOS Bug #20133 (Can't reproduce): EnvLibradosMutipoolTest.DBBulkLoadKeysInRandomOrder hangs on rocksd...
- ...
- 04:49 PM Backport #20125 (New): Kraken: Can't repair when only an attr object error
- Oops, PR was closed.
- 04:48 PM Backport #20126 (New): Jewel: Can't repair when only an attr object error
- Oops, PR was closed.
- 04:48 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- ...
- 04:46 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-06-01_02:27:12-rados-wip-sage-testing2---basic-smithi/1249818
rados/thrash-erasure-code/{ceph.yaml cl... - 04:43 PM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-06-01_02:27:12-rados-wip-sage-testing2---basic-smithi/1249759
description: rados/singleton-bluestore/{a... - 04:28 PM Revision 4e160f20 (ceph): os/bluestore: release aios and pinned buffers on io complete
- Once we're done with our IO, clear the aio list so that the pinned buffers
are unpinned. This ensures we release mem... - 04:28 PM Revision d82af301 (ceph): os/bluestore: submit deferred if txc cleanup is blocked
- If we have a single deferred write, and then a uniform workload with *no*
deferred writes, we will never actually sub... - 04:28 PM Messengers Bug #16122 (Resolved): msg: upper 32-bits of message sequence get lost
- 04:26 PM Revision 8b618add (ceph): librbd: moved IO operation tracker to io namespace
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:26 PM Revision aff9e37e (ceph): Merge pull request #15209 from liewegas/wip-sortbitwise-notes
- doc/release-notes: update which jewel version does sortbitwise warning
- 04:26 PM Revision 5f1f5123 (ceph): librbd: guard journal replay from losing exclusive lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:25 PM Revision ff2d6257 (ceph): Merge pull request #15274 from liewegas/wip-auto-ccache
- do_cmake.sh: enable ccache if installed
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:25 PM Revision f251b07e (ceph): do_cmake.sh: enable ccache if installed
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:24 PM Revision 603f44a8 (ceph): librbd: new exclusive lock accept_replay helper method
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:23 PM Revision b348758b (ceph): librbd: accept_requests helper should accept optional return code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:22 PM Revision 8ca85fc0 (ceph): rbd-mirror: close local image before stopping remote journaler
- Fixes: http://tracker.ceph.com/issues/18963
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 04:22 PM Revision 62cce473 (ceph): rbd-mirror: permit release of exclusive lock if promoted
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:57 PM rgw Backport #20088 (In Progress): valgrind reports leak in RGWRemoteMetadataCR
- 03:55 PM Revision 405e31c8 (ceph): qa: remove metadata-light tasks from multimds
- These did not do enough metadata operations to
trigger any exports between MDS ranks, so it is
not useful to have the... - 03:32 PM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- Zheng Yan wrote:
> please try below patch. If it still doesn't work for you(there is no dirty caps), you need to imp... - 12:47 PM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- please try below patch. If it still doesn't work for you(there is no dirty caps), you need to implement mechanism tha...
- 10:22 AM CephFS Bug #20129: Client syncfs is slow (waits for next MDS tick)
- This is the same behaviour you would see if you were running "sync" on a filesystem.
We handle this for fsync (on ... - 03:42 AM CephFS Bug #20129 (Resolved): Client syncfs is slow (waits for next MDS tick)
- in function client::unmount there are codes below:
-------------
while (!mds_requests.empty()) {
ldout(cct, 10... - 03:16 PM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- Sage Weil wrote:
> or debug bluestore = 30 would be even better :)
The motherboard in my test box seems to have d... - 03:15 PM Revision cc5aed23 (ceph): Merge pull request #15391 from liewegas/wip-authors
- AUTHORS: update with release manager, backport team
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:05 PM CephFS Feature #18490: client: implement delegation support in userland cephfs
- Brief writeup of one way to implement this.
- 02:33 PM Bug #19941 (Pending Backport): ceph-disk fails if OSD udev rule triggers prior to mount of /var
- 09:41 AM Bug #19941: ceph-disk fails if OSD udev rule triggers prior to mount of /var
- Alternative fix proposed at -https://github.com/ceph/ceph/pull/15241- https://github.com/ceph/ceph/pull/15410
- 02:31 PM Revision 9c4aa772 (ceph): Merge pull request #15410 from dachary/wip-19941-ceph-disk
- ceph-disk: do not setup_statedir on trigger
Reviewed-by: David Disseldorp <ddiss@suse.de>
Reviewed-by: Kefu Chai <kc... - 12:57 PM Revision dd514aee (ceph): Merge pull request #15412 from dachary/wip-choose-args
- crush: add missing tunable in tests
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:56 AM Revision 82a703c9 (ceph): crush: add missing tunable in tests
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:41 AM Revision 92ebb703 (ceph): Merge pull request #15286 from smithfarm/wip-cond-epoch
- build/ops: rpm: apply epoch only if %epoch macro is defined
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:21 AM Revision d0798751 (ceph): qa: add counter check to multimds/basic
- ...so that we can't "pass" the test by accidentally
failing to ever export anything automatically
like in http://trac... - 11:18 AM Revision 6ef30d1e (ceph): qa: explicitly set up standby replay in test_journal_migration
- Previously this relied on being run in a special cluster configuration
that set up standby replay daemons. This chan... - 11:18 AM Revision b96e8648 (ceph): qa: merge fs/standbyreplay into fs/basic_functional
- This only had one test in it.
Signed-off-by: John Spray <john.spray@redhat.com> - 11:18 AM Revision 7e1be30b (ceph): qa: clean up test_exports.py
- Mainly just using the setfattr helper
instead of run_shell.
Signed-off-by: John Spray <john.spray@redhat.com> - 10:36 AM CephFS Feature #17980 (Resolved): MDS should reject connections from OSD-blacklisted clients
- 10:36 AM CephFS Feature #9754 (Resolved): A 'fence and evict' client eviction command
- 10:35 AM CephFS Bug #19239 (Resolved): mds: stray count remains static after workflows complete
- 10:35 AM CephFS Bug #19395 (Resolved): "Too many inodes in cache" warning can happen even when trimming is working
- 10:35 AM CephFS Bug #19630 (Resolved): StrayManager::num_stray is inaccurate
- 10:34 AM CephFS Bug #20055 (Pending Backport): Journaler may execute on_safe contexts prematurely
- 10:33 AM Revision b2678062 (ceph): Merge pull request #15240 from ukernel/wip-20055
- osdc/Journaler: avoid executing on_safe contexts prematurely
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:28 AM CephFS Bug #20076 (Resolved): Pass empty string to clear mantle balancer
- 10:28 AM Revision 284c96f0 (ceph): Merge pull request #15282 from david-z/wip-fix-mantle
- mds: Pass empty string to clear mantle balancer
Reviewed-by: John Spray <john.spray@redhat.com> - 10:25 AM Revision 607226bd (ceph): Merge pull request #15314 from renhwztetecs/renhw-wip-client-cleanup
- client: fix display ino in the ldout
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 10:24 AM CephFS Bug #20039 (Resolved): mds: replay of export pinned inode does not result in export
- 10:24 AM CephFS Bug #20083 (Resolved): TestExports.test_export_pin failing on master
- 10:24 AM Revision 1d83d775 (ceph): Merge pull request #15300 from ukernel/wip-20083
- mds: properly create aux subtrees for pinned directory
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 10:23 AM Revision 78a17fb1 (ceph): Merge pull request #15278 from viCEnTECheNg/wip-data-pools-type
- mds: change the type of data_pools
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: John Spray <john.spray@red... - 10:23 AM Revision 01c46bf8 (ceph): Merge pull request #15205 from batrick/i20039
- mds: check export pin during replay
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 09:37 AM Revision 16bfbdd3 (ceph): ceph-disk: do not setup_statedir on trigger
- trigger may run when statedir is unavailable and does not use it.
Fixes: http://tracker.ceph.com/issues/19941
Signe... - 07:53 AM Feature #19382: ceph_objectstore_tool pg reset last_complete
- https://github.com/ceph/ceph/pull/15047
- 07:33 AM CephFS Bug #20131: mds/MDBalancer: update MDSRank export_targets according to current balance state
- https://github.com/ceph/ceph/pull/15407
- 07:31 AM CephFS Bug #20131 (Resolved): mds/MDBalancer: update MDSRank export_targets according to current balance...
- I think this might be a regression issue introduced by https://github.com/ceph/ceph/commit/082e86c58f5abb93e2a912e603...
- 07:17 AM Revision f7edefb8 (ceph): Merge pull request #15406 from tchaikov/wip-setuptools-vendors-six-or-not
- install-deps.sh: workaround setuptools' dependency on six
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 06:52 AM Revision 30ce5e55 (ceph): install-deps.sh: workaround setuptools' dependency on six
- see also https://github.com/pypa/setuptools/issues/1042
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:39 AM mgr Bug #20130 (Resolved): mgr generates traceback about missing django.core.servers.basehttp module ...
- ...
- 05:37 AM mgr Bug #19919 (Duplicate): mgr: ImportError: No module named cherrypy
- Dup of http://tracker.ceph.com/issues/19913
- 02:50 AM Revision e84a9485 (ceph): os/bluestore: mempools for writing and writing_deferred
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:45 AM Revision e40f1973 (ceph): os/bluestore: bluestore_txc mempool
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:43 AM Revision bf790b6a (ceph): os/bluestore: rename cache mempools to bluestore_cache_*
- These map directly onto the bluestore_cache_size setting.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:32 AM Revision 0f3f3190 (ceph): os/bluestore: maybe_rebuild before adding to cache too
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:32 AM Revision 2419ec97 (ceph): AUTHORS: update with release manager, backport team
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:26 AM Revision 037d6a7d (ceph): Merge pull request #15370 from liewegas/wip-jewel-tunables
- crush, mon: make jewel the lower bound for client/crush compat for new clusters
Reviewed-by: Josh Durgin <jdurgin@re... - 02:25 AM Revision 8bcb4a66 (ceph): test/cli/osdmaptool/: fix tests
- CRUSH tunables now default to jewel; outputs vary and
upmap results are a bit different.
Signed-off-by: Sage Weil <s... - 02:20 AM Revision affc9ef6 (ceph): mempool: make dump more concise
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:20 AM Revision 52a857f5 (ceph): buffer: fix some append_buffer vs mempool assignment; add tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:01 AM Revision a69a8966 (ceph): crush: set default tunables to jewel
- For new clusters.
This is the last "disruptive" tunable change we've made (where adjusting/
fixing it requires lots ... - 02:01 AM Revision fdeb59d7 (ceph): mon: set mon_osd_initial_require_min_compat_client = jewel
- IMO a jewel lower bound is reasonable for new clusters.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:01 AM Revision 495f4c9d (ceph): test/cli/crushtool: adjust tests
- Specify chooseleaf_stable for --build tests to match prior output.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:39 AM Revision 569125c4 (ceph): Merge pull request #15267 from joscollin/wip-cleanup-redundant-headers-5
- common: Remove redundant includes - 5
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl> - 12:29 AM rbd Bug #18367: Zombie image snapshot problem
- Jason Dillaman wrote:
> @daolong: can you please provide the output from "rados -p volumes listomapvals rbd_header.2... - 12:14 AM Revision 1cb7f4aa (ceph): qa/rgw_snaps: move default_idle_timeout config under the client
- Fixes: http://tracker.ceph.com/issues/20128
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:12 AM rgw Bug #20128: rgw: teuthology failure in the rgw task (configured via rgw_snaps.yaml)
- this might solve it:
https://github.com/ceph/ceph/pull/15400
- 12:08 AM rgw Bug #20128 (Resolved): rgw: teuthology failure in the rgw task (configured via rgw_snaps.yaml)
- See the failure here: http://pulpito.ceph.com/sage-2017-05-31_18:45:30-rados-wip-sage-testing---basic-smithi/1248627
...
05/31/2017
- 11:40 PM Bug #20106 (Duplicate): Rename of assembler source code file from .S to .s breaks ppc64le build
- 05:48 AM Bug #20106: Rename of assembler source code file from .S to .s breaks ppc64le build
- 05:47 AM Bug #20106 (Resolved): Rename of assembler source code file from .S to .s breaks ppc64le build
- 11:18 PM rbd Bug #20111 (Rejected): Python RBD: diff_iterate_cb() does not acquire GIL before calling user-pro...
- Indeed -- the callback cdef functions have the "with gil" suffix to tell Cython to re-acquire the GIL.
- 09:03 AM rbd Bug #20111: Python RBD: diff_iterate_cb() does not acquire GIL before calling user-provided callb...
- Cython internally ensures (and acquires) GIL in such functions. Please close the bug. I verified, that GIL is locked ...
- 11:09 PM Revision bf82eb59 (ceph): Merge pull request #15311 from dachary/wip-crush-add-remove
- crush: update choose_args when items are added/removed
Reviewed-by: Sage Weil <sage@redhat.com> - 11:09 PM Revision e5242966 (ceph): Merge pull request #15318 from tchaikov/wip-20067
- mon: trim the creating_pgs after updating it with pgmap
Reviewed-by: Sage Weil <sage@redhat.com> - 11:08 PM Revision cbc5a34d (ceph): Merge pull request #15352 from liewegas/wip-buffer-mempools
- buffer: allow buffers to be accounted in arbitrary mempools
- 11:08 PM Revision 35e7bf19 (ceph): Merge pull request #15357 from ceph/typo_bluestore
- os/bluestore: fix a typo about bleustore
Reviewed-by: Varada Kari <varada.kari@gmail.com> - 11:06 PM Bug #20114 (Resolved): ERANGE and EOVERFLOW from set-redirect
- https://github.com/ceph/ceph/pull/15385
- 02:44 AM Bug #20114 (Resolved): ERANGE and EOVERFLOW from set-redirect
- ...
- 11:06 PM Revision 538dbb09 (ceph): Merge pull request #15385 from myoungwon/wip-20114
- test/osd/TestRados.cc: run set-redirect test after finishing setup
Reviewed-by: Sage Weil <sage@redhat.com> - 11:06 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-05-31_18:45:30-rados-wip-sage-testing---basic-smithi/1248735
- 11:05 PM Bug #19595: mgr: segv in msgr thread, with no core
- ...
- 11:05 PM Revision de97f8b6 (ceph): Revert "osd: When scrub finds an attr error mark shard inconsistent"
- This reverts commit 44736aac74493b5532c9e3574a37a3642766f212.
Signed-off-by: David Zafman <dzafman@redhat.com> - 10:57 PM Bug #20127 (Fix Under Review): make check fails if "which" not installed
- https://github.com/ceph/ceph/pull/15399
- 10:52 PM Bug #20127 (Resolved): make check fails if "which" not installed
- The following two tests are failing with "which: command not found"
run-tox-ceph-disk
osd-copy-from.sh - 10:48 PM Revision 2984e5a1 (ceph): Merge pull request #14457 from ceph/wip-rest-flask
- ceph-mgr: Implement new pecan-based rest api
- 10:01 PM Revision 4aea15fe (ceph): rgw: fix import
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:00 PM Revision 5a1009d3 (ceph): qa: whitelist MDS restarts when thrashing
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:00 PM Revision 0219fa71 (ceph): mon: emit cluster log messages on daemon failures
- Two reasons:
- usability
- make our tests fail on the WRN message if
a daemon unexpectedly bounces during a test... - 10:00 PM Revision 2a85dd82 (ceph): mon: don't kill MDSs unless some beacons are getting through
- ...to avoid killing MDSs when the MDS is fine, but the mon
is failing to process beacons due to a laggy peer.
Fixes:... - 10:00 PM Revision ce0b9e34 (ceph): qa: update log whitelist for new MDSMonitor messages
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:00 PM Revision 33263218 (ceph): qa: fix daemon restart between tests
- Previously, calling mds_stop without mds_fail meant
that if the filesystem creation was not quick, then
we would see ... - 10:00 PM Bug #20109: src/common/crc32c_ppc_asm.s ppc64le build break
- *master PR*: https://github.com/ceph/ceph/pull/15373
- 05:47 AM Bug #20109 (Resolved): src/common/crc32c_ppc_asm.s ppc64le build break
- 09:52 PM Revision 30da9b76 (ceph): mon: revise "ceph status" output
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:18 PM Bug #20089 (In Progress): Can't repair when only an attr object error
- Revising this fix
- 06:35 PM Bug #20089: Can't repair when only an attr object error
- fixed by https://github.com/ceph/ceph/pull/15368
- 05:05 PM Bug #20089 (Pending Backport): Can't repair when only an attr object error
- 08:57 PM Revision dc12370f (ceph): Merge pull request #15222 from guihecheng/rgw_file-fix-unlink
- rgw_file: fix flags set on unsuccessful unlink
- 08:35 PM Revision a94de3ae (ceph): Merge pull request #15329 from guihecheng/rgw_file-readdir
- rgw_file: add lock protection for readdir against gc
- 08:21 PM rbd Support #20120: libvirt creat volume io very slow
- Definitely not enough information to attempt to address.
- 09:22 AM rbd Support #20120 (Closed): libvirt creat volume io very slow
- use ceph client creat volume for test bw=260442KB/s, iops=65110
but cloudstack creat volume for test bw=9523.2KB/s... - 07:40 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- David Galloway wrote:
> Sage Weil wrote:
> > just saw this on smithi081, which had 2.4-0ubuntu5, but apt update + a... - 06:53 PM Revision f0864992 (ceph): Merge pull request #14871 from ceph/wip-selinux-optimize
- selinux: Do parallel relabel on package install
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Ken Dre... - 06:48 PM Revision e2b4a004 (ceph): buffer: allow buffers to map into arbitrary mempools
- - default is buffer_anon
- buffer_data includes *all* buffers across all mempools, and is the
*actual* allocation (in... - 06:48 PM Revision 390b4d15 (ceph): buffer: remove buffer_data mempool
- We are explicitly accounting for buffers via arbitrary pools, defaulting
to buffer_anon, so we don't need buffer_data... - 06:48 PM Revision 23a186c7 (ceph): os/bluestore: mark buffer caches buffers as bluestore_data
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:48 PM Revision 19658608 (ceph): osd: (loosely) mark cached map bl buffers as osd_mapbl
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:48 PM Revision 5f37da53 (ceph): mempool: dump total, too
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:47 PM Revision 429b65c6 (ceph): mempool: kill unittest_? mempools
- These were just annoying. Use some real ones that will be empty
for the unit tests.
Signed-off-by: Sage Weil <sage@... - 06:47 PM Revision 6cd6a513 (ceph): buffer: fix mempool accounting for claimed chars
- These are allocated by the caller, outside of the mempool; do not
deallocate via the mempool.
Signed-off-by: Sage We... - 06:47 PM Revision 1dc6393d (ceph): mempool: allow pool counts to be adjusted explicitly
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:47 PM Revision b19352ee (ceph): Merge pull request #15291 from liewegas/wip-osdmap-pgtemp
- osd/OSDMap: make pg_temp more efficient
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:46 PM Revision f78051cf (ceph): Merge pull request #15321 from liewegas/wip-failed-msg
- mon/OSDMonitor: change info in 'osd failed' messages
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:39 PM Revision 241683e0 (ceph): librados: add rados_monitor_log2 that includes EntityName
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:39 PM Revision 9628b0ed (ceph): pybind/rados: add monitor_log2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:39 PM Revision e19448c9 (ceph): common/entity_name: do not populate type_id string for type==0
- The EntityName ctor leaves type == 0. If we encode and
then decode that value, we end up calling set(), which
tries ... - 06:39 PM Revision 6c520ffb (ceph): common/LogEntry: include EntityName in log entries
- We want the auth name (mon.hostname), not the entity_name_t (mon.0) to
appear in the log messages. In particular thi... - 06:39 PM Revision 2a282677 (ceph): librados: use EntityName in monitor_log line
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:37 PM Backport #20125 (In Progress): Kraken: Can't repair when only an attr object error
- 06:34 PM Backport #20125 (Resolved): Kraken: Can't repair when only an attr object error
- https://github.com/ceph/ceph/pull/15421
- 06:37 PM Backport #20126 (In Progress): Jewel: Can't repair when only an attr object error
- 06:34 PM Backport #20126 (Resolved): Jewel: Can't repair when only an attr object error
- https://github.com/ceph/ceph/pull/15416
- 06:34 PM CephFS Feature #18490: client: implement delegation support in userland cephfs
- I have a couple of patches to start implementing this, but I've not had the time to really do a good job of it. The p...
- 06:24 PM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- Recent test run with issue: http://qa-proxy.ceph.com/teuthology/teuthology-2017-05-31_02:01:03-rbd-master-distro-basi...
- 06:22 PM Bug #20049 (Fix Under Review): msg: libraries are binding to incorrect client address
- 06:22 PM Bug #20049: msg: libraries are binding to incorrect client address
- Default client-side binding to false PR: https://github.com/ceph/ceph/pull/15392 -- merged
- 06:18 PM Revision e06b4fca (ceph): msg: do not enable client-side binding by default
- This breaks the usage of Ceph clients connecting to MONs and
OSDs behind a NAT since the client will incorrectly atte... - 06:12 PM rbd Bug #18367 (Need More Info): Zombie image snapshot problem
- @daolong: can you please provide the output from "rados -p volumes listomapvals rbd_header.2eb9e622cdd48" and "rados ...
- 05:57 PM Bug #18202 (Can't reproduce): rados list-inconsistent-obj can hang
Can't reproduce in master.- 03:39 PM Bug #18202: rados list-inconsistent-obj can hang
- David, did you learn anything more about this?
- 04:52 PM Revision 50d781af (ceph): crc32c: Add ppc64le fast zero optimized assembly.
- Allow faster calculation of crc32c when a NULL
buffer is passed.
Signed-off-by: Andrew Solomon <asolomon@us.ibm.com> - 04:38 PM Revision aa947702 (ceph): Merge pull request #15388 from idryomov/wip-krbd-fallocate-tests
- qa: krbd discard/zeroout tests
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:38 PM RADOS Bug #18043: ceph-mon prioritizes public_network over mon_host address
- and to elaborate on the fact that i have a branch and no pr, i do intend to finish this up soon, but likely only afte...
- 04:36 PM RADOS Bug #18043: ceph-mon prioritizes public_network over mon_host address
- fwiw, i've got a branch handling this from earlier this year: https://github.com/jecluis/ceph/commits/wip-mon-host
... - 04:04 PM RADOS Support #18508 (Closed): PGs of EC pool stuck in peering state
- There was clearly a lot going on here and none of it was clear. If switching to SimpleMessenger fixed it, I presume t...
- 04:03 PM Bug #17757 (Closed): test-erasure-eio.sh failing in jenkins tests on PRs
- Haven't seen this one recently.
- 04:03 PM Bug #17751 (Closed): "[ FAILED ] LibRadosMisc.WriteSame" in pgrade:jewel-x-master-distro-basic-vps
- 04:02 PM Revision 3c1e5821 (ceph): osd/OSDMap: make osd_state 32 bits wide in luminous
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:01 PM Support #18479 (Closed): Kraken split-brain, OSD auth connection drops
- Well, all those issues probably tie back to the first one where the monitors are disagreeing about the quorum state. ...
- 04:00 PM Bug #17727 (Can't reproduce): AssertionError: failed to recover before timeout expired
- 04:00 PM Bug #17726 (Can't reproduce): test_rados_tool.sh hangs or machine hangs
- 03:59 PM Revision a8fb39b5 (ceph): osd/OSDMap: make Incremental's new_state 32 bits wide (not 8)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:59 PM Bug #17724 (Can't reproduce): SubsystemMap.h: 62: FAILED assert(sub < m_subsys.size())
- 03:58 PM Feature #14041 (Closed): EC overwrites: deep scrub and checksumming
- We ended up relying on bluestore's checksums for this.
- 03:56 PM Bug #18381 (Closed): kraken: fails to build on Debian testing/unstable
- I think you did not initialize the ceph submodules. "git submodule update --init --recursive --force"
- 03:56 PM Bug #17704 (Resolved): osd: leaked pg refs on shutdown
- There have been fixes for some causes of this like https://github.com/ceph/ceph/pull/15214. Please reopen if you see ...
- 03:55 PM Bug #17109: ceph::crypto (NSS) memory leaks after global_init_daemonize()
- Hi Josh,
When running with @valgrind --tool=memcheck --leak-check=full --show-leak-kinds=all@, I am still seeing q... - 03:13 PM Bug #17109: ceph::crypto (NSS) memory leaks after global_init_daemonize()
- Casey, is this still an issue?
- 03:54 PM Bug #18380 (Closed): Test #131: unittest_lfnindex ................***Failed
- ENAMETOOLONG, which shouldn't happen with LFN but apparently can if you run the unit tests in a deep enough directory...
- 03:48 PM Bug #19187: Delete/discard operations initiated by a qemu/kvm guest get stuck
- Update: We have upgraded some of our clients to 10.2.6, and on these clients we can no longer reproduce the issue. I ...
- 03:47 PM Bug #17539 (Closed): erasure-code: jerasure kraken osdmap cleanup
- This is cleaned up in memory when the profile is read by OSDMonitor::check_legacy_ec_plugin()
- 03:46 PM Bug #18347 (Closed): osd crashed due to journal corrupt
- Yep, that's some kind of bad setting if power corruption results in a busted journal.
- 03:45 PM Bug #18332 (Closed): unrecognized command line option '-fdiagnostics-color=always'
- 03:44 PM Bug #17491 (Rejected): Hammer: PGBackend::objects_list_range includes end as well for ec pools
- hammer is about to be eol, and this doesn't affect upgrades.
- 03:43 PM Bug #17469 (Can't reproduce): Dead job rados, bench never finishes
- 03:42 PM Bug #18223 (Can't reproduce): osd: leaked MOSDMap::incremental_maps
- Believe we've been passing valgrind tests, so this presumably got cleaned up.
- 03:41 PM Bug #17442 (Resolved): EC Overwrites: for all scrubs, flush pending write-ahead updates on the ra...
- 03:41 PM Backport #18220 (Rejected): hammer: msg: upper 32-bits of message sequence get lost
- Hammer is EOL and I think this only ever really caused problems for the MDS anyway.
- 03:38 PM Revision 0a8beea8 (ceph): Merge pull request #15135 from cbodley/wip-denc-sstring
- denc: add encode/decode for basic_sstring
Reviewed-by: Sage Weil <sage@redhat.com> - 03:38 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- https://github.com/ceph/ceph/pull/15389
- 03:38 PM Revision 2c231f9b (ceph): Merge pull request #13802 from LiumxNL/wip-170306
- mon/OSDMonitor: use up set instead of acting set in reweight_by_utilization
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:37 PM Revision 59239614 (ceph): qa: do not restrict valgrind runs to centos
- This reverts 693bd238510e69569cc3461f84b04c8667bc11da, which was
added in response to http://tracker.ceph.com/issues/... - 03:36 PM Bug #18196 (Resolved): fail to build ceph-11.0.2 if yasm installed
- There were recent patches to fix stuff involving yasm and x86.
- 03:22 PM rgw Bug #18087 (Resolved): rgw: LCWorker's worktime is not the same as config rgw_lifecycle_work_time.
- 03:22 PM Bug #18073 (Can't reproduce): LibRadosIo.ReadTimeout segv
- 03:20 PM Bug #17417 (Can't reproduce): /var/log/ceph/valgrind/osd.1.log: <kind>Leak_DefinitelyLost</kind>
- 03:19 PM Bug #17396 (Resolved): "osd recovery max single start" is not documented
- 03:18 PM Bug #17228 (Can't reproduce): Hammer OSD memory use very high (EL6)
- If you do see this again, please re-open and we can debug further.
- 03:17 PM Bug #18046 (Closed): filestore: sync_entry timed out cause osd crash
- I don't think we can do anything at a micro level about running out of memory inside of mutexes.
- 03:16 PM Bug #18057 (Resolved): shoud output hb_peers, not hb_in
- http://github.com/ceph/ceph/pull/12178
- 03:14 PM RADOS Bug #17138: crush: inconsistent ruleset/ruled_id are difficult to figure out
- Some work in progress on this here: https://github.com/ceph/ceph/pull/13683
- 03:11 PM Bug #18005 (Closed): osd crushed in processing deep scrub
- Not enough info to do anything, and it's in FileStore so probably a bad disk.
- 02:56 PM Feature #20123 (Fix Under Review): ceph df: add %used to the formatted output
- https://github.com/ceph/ceph/pull/15387
- 01:22 PM Feature #20123 (In Progress): ceph df: add %used to the formatted output
- 01:16 PM Feature #20123: ceph df: add %used to the formatted output
- It would be great to have the %used value per pool, the global information might be sensible too.
- 10:35 AM Feature #20123 (Resolved): ceph df: add %used to the formatted output
- Unfortunately the used value in percent (%used) is missing in the formatted output of 'ceph df' or 'ceph df detail'. ...
- 02:44 PM Revision 371d45db (ceph): erasure-code: Remove duplicate of isa-l files
- There are two copies of isa-l. While one is a git submodule the other
was a static copy from an older version. This c... - 02:39 PM Revision e4f156f3 (ceph): Merge pull request #15295 from liewegas/wip-bluestore-fsck
- os/bluestore: fix fsck deferred_replay
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 02:31 PM Revision e1634464 (ceph): doc: add README to dmclock subdir to inform developers it's a git subtree
- Since dmclock was integrated into ceph a short time ago, twice now
contributors have submitted PRs to modify files be... - 02:26 PM rgw Backport #20015 (In Progress): kraken: multisite: bi_list() decode failures
- https://github.com/ceph/ceph/pull/15384
- 02:25 PM Revision a058ebbd (ceph): test/osd/TestRados.cc: run test after finishing redirect setup
- set-redirect test creates more objects than default due to redirect mapping
(let's assume that we create 500 objects,... - 02:21 PM Revision 72765362 (ceph): cls/rgw: list_plain_entries() stops before bi_log entries
- list_plain_entries() was using encode_obj_versioned_data_key() to set
its end_key, which gives a prefix of BI_BUCKET_... - 01:35 PM rgw Backport #20014 (In Progress): jewel: multisite: bi_list() decode failures
- https://github.com/ceph/ceph/pull/15383
- 01:32 PM rgw Backport #20088: valgrind reports leak in RGWRemoteMetadataCR
- wip jewel pr: https://github.com/ceph/ceph/pull/15382
- 01:14 PM Revision 59bd6711 (ceph): rgw:fix memory leaks
- Signed-off-by: weiqiaomiao <wei.qiaomiao@zte.com.cn>
(cherry picked from commit 73e5be2b6133cf4caa0e5e5c8c9eae748b785... - 01:05 PM rbd Bug #20110: RBD aio_ API does not provide awaiting of any completion from a list.
- @Марк: can you provide an example? Your ticket description clearly states "next I want to wait until any of them is c...
- 12:42 PM rbd Bug #20110: RBD aio_ API does not provide awaiting of any completion from a list.
- So, how should I wait for whole transfer completion?
What is the difference between rbd_read2() and rbd_aio_read2(... - 12:08 PM rbd Bug #20110 (Need More Info): RBD aio_ API does not provide awaiting of any completion from a list.
- @Марк: I am probably not understanding your goal, but since you can associate a callback with a completion, and said ...
- 12:39 PM Revision 156cf452 (ceph): qa: krbd discard/zeroout tests
- Signed-off-by: Ilya Dryomov <idryomov@gmail.com>
- 12:24 PM Revision b429fa18 (ceph): cls/rgw: list_plain_entries() stops before bi_log entries
- list_plain_entries() was using encode_obj_versioned_data_key() to set
its end_key, which gives a prefix of BI_BUCKET_... - 12:05 PM rgw Bug #20121 (Fix Under Review): rgw_file: missing lock protection for readdir against gc
- 09:27 AM rgw Bug #20121: rgw_file: missing lock protection for readdir against gc
- https://github.com/ceph/ceph/pull/15329
- 09:26 AM rgw Bug #20121: rgw_file: missing lock protection for readdir against gc
- The state.mtx protects state.events accessed both from readdir and gc.
- 09:26 AM rgw Bug #20121 (Resolved): rgw_file: missing lock protection for readdir against gc
- The state.mtx protects state.events accessed both from readdir and gc.
- 12:03 PM Revision 6991764f (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 09:45 AM rbd Documentation #20119: Documentation of Python RBD API does not say that aio_* functions call thei...
- Also it does not say, that `data` argument may be None, which signs error of read operation (I'm not sure, figured ou...
- 09:35 AM rbd Documentation #20119: Documentation of Python RBD API does not say that aio_* functions call thei...
- also, exceptions are silently ignored from these callbacks!
- 09:19 AM rbd Documentation #20119 (Closed): Documentation of Python RBD API does not say that aio_* functions ...
- Documentation of Python RBD API does not say that aio_* functions call their callbacks in DIFFERENT (dummy) thread
... - 09:44 AM CephFS Bug #20122 (Need More Info): Ceph MDS crash with assert failure
- The cluster is running Kraken on CentOS 7.3 and has 3 MDS servers, 01 was up:active and is the one that crashed as pe...
- 09:29 AM Revision 3b1d78bd (ceph): rgw_file: add lock protection for readdir against gc
- The state.mtx protects state.events accessed both from readdir and gc.
Fixes: http://tracker.ceph.com/issues/20121
S... - 07:50 AM Revision 37b7a1e8 (ceph): Merge pull request #15374 from yonghengdexin735/wip-zzz-mds
- mon: Removed unnecessary function declaration in MDSMonitor.h
Reviewed-by: Jos Collin <jcollin@redhat.com> - 07:30 AM Revision b02ad232 (ceph): crush: update choose_args when items are added/removed
- When items are added:
- the value in the weight set is set to the target weight. It is assumed
that weight set are... - 07:30 AM Revision 2e5fba07 (ceph): crush: update choose_args on adjust_item_weight
- The osd_crush_update_weight_set (true by default) can be used to disable
the update of the weights.
Signed-off-by: L... - 07:18 AM rgw Feature #19510: per-object storage class
- Chang Liu wrote:
> Hi, Is there anyone else doing this? let me know please.
Hi~ Liu Chang:
I'm investing to br... - 06:38 AM Revision 69522c61 (ceph): src: put-to operator function - const input cleanup
- Fixed the instances of the issue specified in Tracker#3977 inside src/ folder utmost, by adding
const input. This fix... - 06:03 AM Cleanup #3977 (In Progress): Do a great stream operator const cleanup!
- 05:46 AM Revision b41a8bb1 (ceph): Merge pull request #15373 from kestrels/wip-asm-capital-S
- build: Use .S suffix for ppc64le assembly files
Reviewed-by: Bassam Tabbara <bassam.tabbara@quantum.com>
Reviewed-By... - 05:01 AM CephFS Bug #20118 (Duplicate): Test failure: test_ops_throttle (tasks.cephfs.test_strays.TestStrays)
- http://qa-proxy.ceph.com/teuthology/teuthology-2017-05-30_05:10:01-fs-kraken---basic-smithi/1243987/teuthology.log
... - 04:05 AM mgr Bug #20113: couldn't get command descriptions for [u'mgr', '']:
- Sorry for this failed task. I'm working on it. Assignee it to me, please.
- 02:41 AM mgr Bug #20113 (Resolved): couldn't get command descriptions for [u'mgr', '']:
- ...
- 03:34 AM Revision 0c3c348a (ceph): mon:remove useless function for MDSMonitor::generate_mds_map()
- Signed-off-by: yonghengdexin735 <zhang.zezhu@zte.com.cn>
- 03:21 AM RADOS Bug #20117 (Rejected): BlueStore.cc: 8585: FAILED assert(0 == "unexpected error")
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 03:19 AM RADOS Bug #20116 (Can't reproduce): osds abort on shutdown with assert(ceph/src/osd/OSD.cc: 4324: FAILE...
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 03:04 AM Revision dfd4bb44 (ceph): test/unittest_bluefs: When fsync ret is less than 0, fsync can not be c...
- Signed-off-by: shiqi <1454927420@qq.com>
- 02:58 AM rgw Bug #20112: Use boost::regex instead of std::regex for rgw_iam_policy.cc and rgw_role.cc
- I only found it because it bit me too. Seems like it's a big club :)
- 02:24 AM rgw Bug #20112: Use boost::regex instead of std::regex for rgw_iam_policy.cc and rgw_role.cc
- i confirm this issue. i also found that that gcc 4.8's regex implementation was buggy and incomplete the hard way.
... - 02:48 AM Revision 49f64e7e (ceph): Merge pull request #15351 from liewegas/wip-osdmap-require-min-client
- osd/OSDMap: replace string-based min_compat_client with a CEPH_RELEASE_* uint8_t
Reviewed-by: Josh Durgin <jdurgin@r... - 02:47 AM Revision 633c20e1 (ceph): osdmaptool: fix cli tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:47 AM Revision 036a6880 (ceph): common: expand CEPH_RELEASE_ names; rename helper
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:47 AM Revision f22997e2 (ceph): osd/OSDMap: switch [require_]min_compat_client to CEPH_RELEASE_* values
- Instead of using a string, use the defined CEPH_RELEASE_* values. This
is simpler.
We allow decoding of post-kraken... - 02:47 AM Revision 32f10b36 (ceph): common/version: include release name and type in version string
- ceph version 12.0.2-1687-ge042051 (e0420518d712d87a4882b3a327eaf1d3fcea12df) luminous (dev)
Signed-off-by: Sage Weil... - 02:46 AM Bug #20115 (Resolved): rest.py: pool delete failure
- ...
- 02:45 AM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-30_17:22:40-rados-wip-sage-testing---basic-smithi/1244707
rados/thrash/{0-size-min-size-overrides/... - 01:57 AM Revision 13e73303 (ceph): Merge pull request #15331 from yonghengdexin735/wip-zzz-override
- mon: Add override for FsNewHandler::handle()
Reviewed-by: Jos Collin <jcollin@redhat.com> - 01:36 AM rgw Bug #20100: get wrong content when download object with specific range when compression was enabled
- the previous description is not proper.
In fact, this issue exists in s3 download with specific range for a multip... - 01:24 AM Bug #19864: src/rocksdb/db/write_thread.h:192:78: error: dereferencing type-punned pointer will b...
- Thanks Nathan.
- 01:14 AM Revision d7742d2c (ceph): build: Use .S suffix for ppc64le assembly files
- The assembly file name suffix was changed from .S to .s,
which caused a build break on ppc64le architecture.
To fix ... - 12:34 AM Revision 3011b11d (ceph): mon: Add override for FsNewHandler::handle()
- Signed-off-by: yonghengdexin735 <zhang.zezhu@zte.com.cn>
05/30/2017
- 11:35 PM Revision 0fc3b8d1 (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 11:35 PM rgw Bug #20112: Use boost::regex instead of std::regex for rgw_iam_policy.cc and rgw_role.cc
- please dont just do a search-and-replace. Put a regex in the ceph:: namespace so we can map it to the right thing dep...
- 11:08 PM rgw Bug #20112 (Resolved): Use boost::regex instead of std::regex for rgw_iam_policy.cc and rgw_role.cc
- src/rgw/rgw_iam_policy.cc and src/rgw/rgw_role.cc include code that uses the std::regex header.
Per https://bugzi... - 11:35 PM Revision 077038b4 (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 11:35 PM Revision 1cecddf0 (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 11:29 PM Revision f110a824 (ceph): osd: Move scrub sleep timer to osdservice
- PR 14886 erroneously creates a scrub sleep timer for every pg resulting
in a proliferation of threads. Move the timer... - 10:13 PM rbd Bug #20111 (Rejected): Python RBD: diff_iterate_cb() does not acquire GIL before calling user-pro...
- rbd_diff_iterate2() is called with GIL released. Callback it calls must acquire GIL.
Bug was not detected since Cy... - 09:37 PM rbd Bug #20110 (Closed): RBD aio_ API does not provide awaiting of any completion from a list.
- Suppose I want to copy RBD image in parallel 10 streams. Well, I can run 10 aio_read() functions and associate them w...
- 08:27 PM Revision 8519dc46 (ceph): test/rgw: drop use of urllib
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:27 PM Revision dd836161 (ceph): rgw: es: fix system user check
- check was inverted
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:27 PM Revision c3422bd2 (ceph): rgw: minor fixes following review
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:27 PM Revision 0a836bab (ceph): rgw: check init_sync return code
- fix following review
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:27 PM Revision 8f020cc5 (ceph): rgw: get_rest_filter() delete original rest manager
- When overriding rest manager, delete original.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:26 PM Revision 0b203537 (ceph): test/rgw/test_multi: cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 49f92f7d (ceph): test_multi: don't pass array as default param to constructor
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 16e07f04 (ceph): rgw: system users override elasticsearch permission filter
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision ea902d18 (ceph): rgw: package radosgw-es
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision c9e2aff8 (ceph): test_multi: realm checkpoint after init
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 7e4e7432 (ceph): rgw: use RGW_AMZ_META_PREFIX
- instead of defining X_AMZ_META_PREFIX
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:26 PM Revision 3a81d095 (ceph): rgw: adjust log levels
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision a42aad05 (ceph): rgw: minor cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 131f6a3c (ceph): rgw/test_multi: add tests for different key types
- add int and date tests
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:26 PM Revision c13ec1c4 (ceph): rgw: don't send raw date header to elasticsearch
- parse the header, and encode it in the json doc using
a format that ES can understand. Skip header if fails to
parse.... - 08:26 PM Revision d2309153 (ceph): rgw/test-multi: test more complicated queries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision cd3fb793 (ceph): rgw/test_multi: add test_es_bucket_conf test
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 366ffd58 (ceph): test/rgw/test_multi: differentiate between zone and zone connection
- Instead of having a Zone type used for the connection, create a new
ZoneConn type that represents the connection. Thi... - 08:26 PM Revision bbc5d486 (ceph): test/rgw/test_multi: initial es functional tests
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 7d3be066 (ceph): rgw/test_multi/es: extend test
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision f5037624 (ceph): rgw/test_multi: zone_conn can hold more than one bucket per zone
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 024d98cf (ceph): rgw: es: index and return versioned epoch
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision ba0626f2 (ceph): rgw/test_multi: add support for elasticsearch testing
- Add support for different zone types, and create an elasticsearch
zone type that deals with es testing.
Signed-off-b... - 08:26 PM Revision a680aa11 (ceph): rgw: es: use "null" as instance in case key.instance is empty
- when indexing objects. We can get either.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:26 PM Revision de9d2cb4 (ceph): rgw-admin: zone create handles --tier-config
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 1ca77abe (ceph): rgw: don't pass sync module to rest filter in creation
- sync module instance might change due to reconfiguration. Pass it into the
handler when executing op.
Signed-off-by:... - 08:26 PM Revision 6d3cc4b1 (ceph): rgw: move data sync instance_id initialization to caller
- so that caller can easily know the instance id.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:26 PM Revision 8bfe1379 (ceph): rgw: es: configurable number of replicas and shards
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 3f409381 (ceph): rgw: add missing custom meta map initialization
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 4a91a542 (ceph): rgw: fix time format that is sent to elasticsearch
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 2c9a7bc9 (ceph): rgw: es: generic keys are not case sensitive
- make map case insensitive, and explicitly define all generic keys
so that they can be forced to be lower case.
Signe... - 08:26 PM Revision 151a6eba (ceph): rgw: es: configurable list of buckets and owners to index
- and a tier configuration that allows to select both list of buckets
and list of bucket owners (if both configured the... - 08:26 PM Revision f5b158fc (ceph): rgw: es: elasticsearch index path unique per sync instance
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision fbae80ba (ceph): rgw: es: add a configurable to override index path
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:26 PM Revision 85310f0e (ceph): rgw: add "explicit_custom_meta" configurable to es sync module
- Modify all the map<string, string> that is used to pass in module config
to map<string, string, ltstr> so that it can... - 08:26 PM Revision b02d6162 (ceph): rgw: create helper for configurable item selection
- with optional prefix and suffix.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 874223b2 (ceph): rgw: es: handle get config api in es zone
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision f1e681bf (ceph): common/ceph_json: map type can handle 2 or 3 template arguments
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 6d5555ac (ceph): rgw: expose conf_get(), conf_get_int(), conf_get_bool()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision e4e6e1e5 (ceph): rgw: es: limit indexing to only configured user meta
- only metadata keys that are configured on user's bucket are allowed
to be indexed. Also, use the type of meta that wa... - 08:24 PM Revision 7b61c992 (ceph): rgw: es: also return custom int and date results
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision acba9161 (ceph): rgw: es: api to retrieve bucket mdsearch config
- GET /bucket?mdsearch
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 603863a4 (ceph): rgw: es: api to delete bucket mdsearch config
- DELETE /bucket?mdsearch
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 484fd2b8 (ceph): rgw: support field aliases in es compiler
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision de5bd34e (ceph): rgw: add dout defs
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 3f62f17f (ceph): rgw: guard restricted fields in es query
- don't allow users to use the 'permissions' field.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 8249f76b (ceph): rgw: new api to configure bucket's custom keys for mdsearch
- POST /bucket?mdsearch
x-rgw-meta-search: <x-amz-meta-key>[;<str|int|date>][,...]
note that x-amz-meta-search header ... - 08:24 PM Revision 1e886475 (ceph): rgw: metadata search pagination
- Leveraging elasticsearch "size" and "from" for doing pagination. This
is not optimal, but sadly it's currently the wa... - 08:24 PM Revision d026a23d (ceph): rgw: initial support for multiple types in es requests
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 42746ac9 (ceph): rgw: support for generic entities types in es
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 21ee7c11 (ceph): rgw: support more meaningful compilation error string
- in es module
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 698763fb (ceph): rgw: extend interfaces to allow sending data
- when retrieving REST resource
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 86fe1223 (ceph): rgw: send request to elasticsearch and parse response
- and send back response to user
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 0180650d (ceph): rgw: also dump custom meta entries
- when doing metadata search
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 99b49acc (ceph): rgw: add permissions and bucket to es query
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision c9d68822 (ceph): rgw: rename a few methods
- just rename calls
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 9f494ff4 (ceph): rgw: make key param in RGWRESTStreamRWRequest::send_request() optional
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 952e72d9 (ceph): rgw: can send data in RGWRESTStreamRWRequest::send_request()
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision b6fe05d9 (ceph): rgw: move code around
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision bb46f19e (ceph): rgw: work on REST handler for es module
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision e515bf3b (ceph): rgw: meta search rest handler can access es module
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 6de586ca (ceph): rgw: handle nested fields in es queries
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 86ea4243 (ceph): rgw: move code into class
- just cleaning up
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:24 PM Revision 0fdd24ff (ceph): rgw: simplify es compile interface
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 42130df3 (ceph): rgw: rename rgw_rest_es.cc to rgw_es_query.cc
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:24 PM Revision 67bfdb45 (ceph): rgw: implement init_sync() callback in es module
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:18 PM Revision 6d4733c5 (ceph): rgw: add init callback to sync modules
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:18 PM Revision 49b27f4f (ceph): rgw: define es index mapping
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 08:17 PM Revision 8fd55cc2 (ceph): rgw: initial implementation of mdsearch query compiler
- convert infix queries that look as follows:
[(]<name> <operator> <value> [)] [<and|or> ...]
into a prefix structure... - 08:09 PM Bug #16913 (Can't reproduce): multimds: OSD deep scrub failure
- Please reopen if it happens again.
- 07:39 PM Bug #16913: multimds: OSD deep scrub failure
- No, I haven't seen it anymore.
- 08:09 PM rgw Bug #17934 (Fix Under Review): rgw: /info lacks swift.max_meta_count
- https://github.com/ceph/ceph/pull/15369
- 08:09 PM Revision 760c5e4f (ceph): Merge pull request #15184 from cbodley/wip-qa-rgw-cleanup
- qa/rgw: remove apache/fastcgi and radosgw-agent tests
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:06 PM Bug #20109: src/common/crc32c_ppc_asm.s ppc64le build break
- Hi. I'm working on this issue, too - see #20106
So far I have determined that merely renaming crc32_ppc_asm.s to c... - 07:48 PM Bug #20109: src/common/crc32c_ppc_asm.s ppc64le build break
- I believe the original issue was specific to intel / yasm and had nothing to do with ppc64le. The ppc64le assembly f...
- 07:44 PM Bug #20109 (Resolved): src/common/crc32c_ppc_asm.s ppc64le build break
- It looks like there is a build break on ppc64le architecture associated with a recent change. The error message look...
- 06:16 PM Revision 6049d977 (ceph): Merge pull request #13851 from zhangsw/optimize-datasync
- rgw: optimize data sync. Add zones_trace in log to avoid needless sync.
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 05:46 PM Revision 1dbb15d3 (ceph): Merge pull request #15368 from dzafman/wip-20089
- osd: When scrub finds an attr error mark shard inconsistent
Reviewed-by: Sage Weil <sage@redhat.com> - 05:32 PM Revision e88cccf9 (ceph): Merge pull request #15350 from mrbojangles3/master
- libradosstriper: Add example code
- 05:29 PM Revision 3f99839b (ceph): Merge pull request #15356 from joscollin/wip-test-msgr-warning
- test/msgr: silence warnings from -Wsign-compare
- 05:28 PM Revision b38495c8 (ceph): Merge pull request #15362 from andihit/doc-rados-xattr-commands
- doc: add rados xattr commands to manpage
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:25 PM Revision 57bef92b (ceph): Merge pull request #15366 from joscollin/wip-cleanup-test-remove-commen...
- test/old: Removed commented code
Reviewed-by: Sage Weil <sage@redhat.com> - 04:32 PM Revision 44736aac (ceph): osd: When scrub finds an attr error mark shard inconsistent
- Fixes: http://tracker.ceph.com/issues/20089
Signed-off-by: David Zafman <dzafman@redhat.com> - 04:22 PM Bug #19813 (Resolved): mgr init deadlock
- hmm, actually, i think that was just a laggy mon.
- 03:31 PM Bug #19813: mgr init deadlock
- on bigbang,...
- 04:09 PM Revision acde67b3 (ceph): mds: check export pin during replay
- Fixes: http://tracker.ceph.com/issues/20039
Signed-off-by: Patrick Donnelly <pdonnell@redhat.com> - 04:08 PM Revision 76335b0e (ceph): qa: improve debug message for subtree wait
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
- 04:08 PM Revision 2cc1fb04 (ceph): mds: use generic name for export dir wait class
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
- 04:02 PM Revision 3d7a3d7a (ceph): Merge pull request #14971 from SUSE/wip-mgr-py-sub-interpreter
- mgr: load modules in separate python sub-interpreters
Reviewed-by: John Spray <john.spray@redhat.com> - 03:54 PM Revision 496d63a1 (ceph): os/bluestore: bluestore_debug_fsck_abort
- Abort fsck early to get a massif result.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:44 PM Revision 805acce7 (ceph): Merge pull request #15259 from zealoussnow/wip-0524
- build: remove ceph-disk-udev entirely
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Loic Dachary <loic@dach... - 03:42 PM Revision 7a2ca332 (ceph): Merge pull request #15285 from smithfarm/wip-kill-fcgi
- build/ops: drop libfcgi build dependency
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:31 PM Revision 1f32a9c5 (ceph): test/old: Removed commented code
- There were lot of commented code inside src/test/old/testcrush.cc. This was found while doing
the PR#15364. Removed t... - 03:29 PM Bug #19503 (Can't reproduce): mgr: segv in tcmalloc via ClusterState::set_fsmap, FSMap::operator=
- 03:29 PM rgw Bug #20098 (Fix Under Review): rgw: connection reset or radosgw crashed when download large zero ...
- https://github.com/ceph/ceph/pull/15335
- 03:19 PM Cleanup #3977 (Fix Under Review): Do a great stream operator const cleanup!
- Fixed the instances inside src/ folder utmost. This fix avoids the following directories inside src: rocksdb/ zstd/ b...
- 03:00 PM rgw Bug #20100 (Fix Under Review): get wrong content when download object with specific range when co...
- https://github.com/ceph/ceph/pull/15323
- 02:39 PM Revision 2badc241 (ceph): Merge pull request #15360 from liewegas/wip-jewel-master-mixed
- qa/workunits/rados/test-upgrade-*: whitelist tests for master
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:38 PM Revision aefd56b4 (ceph): Merge pull request #15359 from liewegas/wip-kraken-x
- qa/suites/upgrade/kraken-x: enable experimental for bluestore
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:02 PM Revision 5ededbef (ceph): doc: add rados xattr commands to manpage
- Signed-off-by: Andreas Gerstmayr <andreas.gerstmayr@catalysts.cc>
- 01:58 PM Revision 1f895c24 (ceph): qa/workunits/rados/test-upgrade-*: whitelist tests for master
- The jewel-x upgrade test now runs this script against a mixed cluster on
a machine with code from master installed. ... - 01:46 PM Revision 1a02bb4c (ceph): Merge pull request #15306 from mikulely/fix-test_multi
- rgw: fix test_multi.py default config file path
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 01:46 PM RADOS Support #20108 (Resolved): PGs are not remapped correctly when one host fails
- I have run into the following problem:
in a 6 node cluster we have 2 nodes/chassis, and the crush rule set to distri... - 01:45 PM RADOS Bug #20041: ceph-osd: PGs getting stuck in scrub state, stalling RBD
- Logs available on teuthology:/home/jdillaman/osd.23.log_try_rados_rm.gz
- 01:35 PM Linux kernel client Feature #17204 (Resolved): Implement new-style ENOSPC handling in kclient
- Ok, patches are now merged into mainline kernels and should make v4.12.
- 01:28 PM Revision 22ddc2e6 (ceph): qa/suites/upgrade/kraken-x: enable experimental for bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:22 PM Revision 99d96c3c (ceph): Merge pull request #15294 from liewegas/wip-osd-tree
- osd: 'osd tree in|out|up|down' to filter tree results
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:39 PM rgw Bug #20048 (Resolved): Ceph no longer builds for s390x after Beast submodule enabled
- 12:39 PM Revision a1842eb2 (ceph): mds: fix race between cross-authorty rename and mds failure
- If auth mds of rename srcdn fails, bystander mds may need to rollback
corresponding slave rename. If corresponding sl... - 12:39 PM Revision 9fd19500 (ceph): Merge pull request #15225 from smithfarm/wip-s390-rgw
- build/ops: conditionalize rgw Beast frontend so it isn't built on s390x architecture
Reviewed-by: Willem Jan Withage... - 12:21 PM Revision 0027a3b9 (ceph): mon: add up|down|in|out filters to 'osd tree'
- For example, 'ceph osd tree down' will show *just* down OSDs and their
ancestors. \o/
Signed-off-by: Sage Weil <sag... - 12:07 PM rgw Bug #20107 (Resolved): rgw: Truncated objects
- On a large cluster, we are seeing some objects being truncated at 512kb size. The behaviour when trying to access the...
- 11:40 AM Bug #20106 (Fix Under Review): Rename of assembler source code file from .S to .s breaks ppc64le ...
- https://github.com/ceph/ceph/pull/15358
- 10:42 AM Bug #20106 (Duplicate): Rename of assembler source code file from .S to .s breaks ppc64le build
- https://github.com/ceph/ceph/pull/15142 breaks the ppc64le build....
- 11:01 AM Revision 3dfffa59 (ceph): cmake: link radosgw with boost libraries
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 10:40 AM Revision b92cc082 (ceph): test/librados/aio.cc: silence coverity with scope_guard
- Fix for:
CID 1313405 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable my_completion2 going out of ... - 10:32 AM Revision 8f3ef393 (ceph): bluestore: fix a typo about bleustore
- Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
- 10:27 AM Revision 9a2bb9a2 (ceph): c_read_operations.cc: silence coverity with scope_guard
- CID 1219593 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable completion going out of scope leaks
t... - 10:01 AM Revision 11e4573e (ceph): LibradosTestStub.cc: memset struct sockaddr_in
- Fix for:
CID 1402624 (#1 of 1): Uninitialized scalar variable (UNINIT)
uninit_use: Using uninitialized value sin. F... - 09:29 AM Revision dae9c04f (ceph): common/Timer.h: ~SafeTimer needs to be virtual
- Fix for:
CID 1396232 (#1 of 1): Non-virtual destructor (VIRTUAL_DTOR)
nonvirtual_dtor: Class librbd::<unnamed>::Saf... - 09:00 AM Bug #19864: src/rocksdb/db/write_thread.h:192:78: error: dereferencing type-punned pointer will b...
- @Brad: I can also confirm that the latest GCC 7 fixes the issue for us.
- 04:54 AM Bug #19864: src/rocksdb/db/write_thread.h:192:78: error: dereferencing type-punned pointer will b...
- I created a test package here https://copr-be.cloud.fedoraproject.org/results/badone/misc/fedora-26-x86_64/00557857-g...
- 04:54 AM Bug #19864: src/rocksdb/db/write_thread.h:192:78: error: dereferencing type-punned pointer will b...
- https://bugzilla.suse.com/show_bug.cgi?id=1025891#c29
- 08:56 AM Revision ddb6037a (ceph): test_ipaddr.cc: memset with 0 and not '0'
- Fix for:
CID 1405070 (#1 of 1): Memset fill value of '0' (NO_EFFECT)
CID 1405071 (#1 of 1): Memset fill value of '0'... - 08:50 AM Linux kernel client Bug #18690 (Resolved): kclient: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=0a2ad541071f99eaf4589c3551176fca191c1ee...
- 08:42 AM Revision a3835991 (ceph): tools/rbd/Utils.cc: fixup RBD_IMAGE_OPTION_FEATURES_SET
- Fix for:
CID 1394854 (#1 of 1): 'Constant' variable guards dead code (DEADCODE)
dead_error_line: Execution cannot r... - 08:42 AM Revision ba95f395 (ceph): client/Client.cc: fix USE_AFTER_FREE
- Don't call put_request() twice, it's already called by
unregister_request()
Fix for:
CID 1405360 (#1 of 1): Use aft... - 08:42 AM Revision eee3387d (ceph): rbd/action/MergeDiff: fix error handling
- Fix for:
CID 1351525 (#1 of 1): Argument cannot be negative (NEGATIVE_RETURNS)
negative_returns: sd is passed to a ... - 08:42 AM Revision 6b603b05 (ceph): crush/CrushCompiler.cc: fix error handling
- calloc() does not take negative values, check return value from
get_max_buckets() and handle it correctly.
Fix for:
... - 08:42 AM Revision bab5e1f7 (ceph): osd/OSD.cc: fixup SWAPPED_ARGUMENTS
- Fix for:
CID 1400116 (#1 of 2): Arguments in wrong order (SWAPPED_ARGUMENTS)
swapped_arguments: The positions of ar... - 08:42 AM Revision 2568d522 (ceph): client/Client.cc: fix UNINIT_CTOR
- Fix for:
CID 1406088 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
uninit_member: Non-static class member ro... - 08:42 AM Revision 3ca4249b (ceph): client/MetaRequest.h: fix UNINIT_CTOR
- Fix for:
CID 717207 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
uninit_member: Non-static class member dir... - 05:19 AM Revision 80145b4c (ceph): test/msgr: silence warnings from -Wsign-compare
- The following warning appears during make:
ceph/src/test/msgr/test_msgr.cc: In member function ‘virtual void Messeng... - 05:02 AM Revision 4932a109 (ceph): osd: Reset() the snaptrimmer on shutdown
- We were failing to exit various wait states which held PGRefs. Error!
Fixes: http://tracker.ceph.com/issues/19931
S... - 05:02 AM Revision 2c7b8aeb (ceph): osd: do not default-abort on leaked pg refs
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 4caf2df0c380a1281db9509b3feb342705512b58)
... - 04:28 AM Revision 592d95e5 (ceph): Merge pull request #15355 from joscollin/wip-cleanup-testdenc-warning
- test: test_denc.cc: silence warning from -Wsign-compare
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:06 AM Revision e6a40e9e (ceph): test: test_denc.cc: silence warning from -Wsign-compare
- The following warning appears during make:
ceph/src/test/test_denc.cc:669:5: required from here
ceph/src/googletest... - 01:56 AM Revision f53f5635 (ceph): os/bluestore: deep decode onode value
- In particular, we want the attrs (map<string,bufferptr>) to be a deep
decode so that we do not pin this buffer, and s... - 01:56 AM Revision cf98e9d5 (ceph): buffer: make wasted() const
- Remove useless assert (we'll segv on the next line anyway).
Signed-off-by: Sage Weil <sage@redhat.com> - 01:56 AM Revision 87616245 (ceph): os/bluestore: rebuild Buffer buffers with too much waste
- Avoid pinning extra memory by rebuilding Buffer buffers when we waste too
much.
Signed-off-by: Sage Weil <sage@redha... - 01:56 AM Revision 0fae9bf4 (ceph): ceph-bluestore-tool: init deep = false
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:56 AM Revision 7a51a342 (ceph): include/cpp-btree/btree_set: add btree_set
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:56 AM Revision d334d2d3 (ceph): os/bluestore: fsck: use btree_set to replace set<uint64_t>
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:56 AM Revision 811c38ed (ceph): os/bluestore: fix fsck deferred_replay
- _deferred_replay needs the kv_sync_thread to complete IOs; start them
just for that, but then shut them down again. ... - 01:56 AM Revision ecb3167f (ceph): os/bluestore: wait for kv thread to start before stopping it
- Otherwise we can assert out when we try to join a thread that
hasn't started.
- move everything into _kv_start() and... - 01:47 AM Revision d79c7723 (ceph): Merge pull request #15058 from yuyuyu101/wip-rocksdb-opt
- kv/rocksdb: supports SliceParts interface
Reviewed-by: Sage Weil <sage@redhat.com> - 01:47 AM Revision 5988651e (ceph): Merge pull request #15068 from liewegas/wip-osdmap-require
- osd/OSDMap: replace require_*_osds flags with a single require_osd_release field
Reviewed-by: Kefu Chai <kchai@redha... - 01:42 AM Revision 43a58ec2 (ceph): Merge pull request #15313 from Linbing/wip-pg-scrub-code-optimize
- mon: it's no need to get pg action_primary osd twice in pg scrub
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:40 AM Bug #19595: mgr: segv in msgr thread, with no core
- and...
- 01:39 AM Bug #19595: mgr: segv in msgr thread, with no core
- /a/sage-2017-05-29_22:34:44-rados-wip-sage-testing---basic-smithi/1241864
2017-05-29T23:05:29.364 INFO:tasks.ceph.... - 01:34 AM Revision e570005e (ceph): osd: replace all require_*_osds flag checks with a require_osd_release ...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:34 AM Revision 3d6b6d72 (ceph): mon/OSDMonitor: fix osd metadata update ordering
- Do not do both.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:33 AM Revision 3d4c4d9d (ceph): osd/OSDMap: add require_osd_release numeric field, CEPH_RELEASE_*
- Instead of eating up a flag for each release, which is super-awkward and
annoying, just keep a numeric release versio... - 01:33 AM Revision 0b517992 (ceph): mon: new 'osd require-osd-release' command
- Note that we only allow setting this to 'luminous'. If the 'jewel' or 'kraken'
flags need to be set that can be done... - 01:33 AM Revision 3118d9a1 (ceph): osd: replace require_*_osds flags with require_osd_release field
- - OSDMap encode and decode translate between the flags and int
representations.
- OSDMap::Incremental only does decod...
05/29/2017
- 11:30 PM RADOS Bug #19790 (In Progress): rados ls on pool with no access returns no error
- 11:28 PM RADOS Bug #19790: rados ls on pool with no access returns no error
- https://github.com/ceph/ceph/pull/15354
Greg, will talk to you about the per-object cap semantics separately. - 08:47 PM Revision 9b1afe4a (ceph): cmake: delete excidentail reintroduced line.
- - This target got reintroduced by accident after the creation
of ceph-common in commit:
https://github.com/ceph... - 08:47 PM Revision 7d81a4b7 (ceph): build/ops: rpm: reverse s390 bcond conditional block
- I'm not a fan of "if NOT x - then - else" blocks.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 08:47 PM Revision 12625e1e (ceph): build/ops: rpm: no rgw Beast frontend on s390x
- Since the Beast frontend uses boost::context which is not supported on
s390x.
Signed-off-by: Nathan Cutler <ncutler@... - 08:47 PM Revision 25d794d9 (ceph): build/ops: deb: no rgw Beast frontend on s390x
- Signed-off-by: Kefu Chai <kchai@redhat.com>
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 08:47 PM Revision b22cde8e (ceph): cmake: build boost::context and coroutine only with rgw Beast frontend
- boost::context is currently (1.63) unsupported for s390x and anyway
it makes sense to conditionalize Boost components... - 07:50 PM Bug #20093 (Resolved): msg/async: dropped a message
- 07:49 PM Revision 676fc82c (ceph): Merge pull request #15324 from yuyuyu101/wip-20093
- msg/async: avoid requeue racing with handle_write
Reviewed-by: Sage Weil <sage@redhat.com> - 07:48 PM Revision 85541585 (ceph): Merge pull request #15325 from liewegas/wip-redirect
- osd,librados: add manifest, redirect
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redh... - 07:48 PM Revision 10b32aa5 (ceph): Merge pull request #15326 from xiexingguo/fix-kvtool-tip
- tools/ceph_kvstore_tool: add "bluestore-kv" to usage
Reviewed-by: Sage Weil <sage@redhat.com> - 07:47 PM Revision 0f803c5a (ceph): Merge pull request #15337 from wjwithagen/wip-wjw-freebsd-fix-includes
- common: include: Redo some includes for FreeBSD
- 07:45 PM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-05-28_05:00:18-rados-wip-sage-testing---basic-smithi/1238511
description: rados/singleton-bluestore/{... - 07:37 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-28_05:00:18-rados-wip-sage-testing---basic-smithi/1238213
rados/thrash/{0-size-min-size-overrides/... - 07:26 PM Revision 89e36def (ceph): Added libradosstriper example Signed-off-by: Logan Blyth <mrbojangles3@...
- 03:48 PM Revision 670997cc (ceph): rgw-admin: fix bucket limit check argparse, div(0)
- 1. normalize arg parsing for "bucket limit check"
1.1 s/buckets/bucket/
2. avoid dividing by num_shards when it is 0... - 02:51 PM RADOS Bug #17968: Ceph:OSD can't finish recovery+backfill process due to assertion failure
- https://github.com/ceph/ceph/pull/15349
- 12:55 PM Revision 7a5a0a89 (ceph): Merge pull request #15338 from trociny/wip-get_process_name
- common: get_process_name: use getprogname on bsd systems
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Will... - 10:58 AM Revision 83373c0e (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 10:55 AM Revision 5366fecc (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 08:26 AM Bug #19900 (Resolved): osd crash during shutdown
- 12:54 AM Bug #19900: osd crash during shutdown
- OMG.
How did we all (especially me) not realise there was a missing return statement in https://github.com/ceph/ce... - 08:25 AM Revision 24b0e2bb (ceph): Merge pull request #15345 from badone/wip-tracker-19900-wait_auth_rotat...
- osd: Return early on shutdown
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:49 AM rbd Feature #18430 (In Progress): Transparently support migrating images with minimal/zero downtime
- 04:14 AM Bug #18873: Need to use thread safe random number generation (unless c++11 already provides this)
- Jesse,
I didn't get time to focus on this. Assigning this to you, as you have a PR that implements random number g... - 01:29 AM Revision ae6e32dc (ceph): osd: Return early on shutdown
- eb5c02d was missing a return statement, rectify that.
Fixes: http://tracker.ceph.com/issues/19900
Signed-off-by: Br...
05/28/2017
- 10:53 PM Revision c5e8f586 (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 10:53 PM Revision e6756635 (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 10:53 PM Revision bbd0ea3a (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 09:17 PM RADOS Bug #19909: PastIntervals::check_new_interval: assert(lastmap->get_pools().count(pgid.pool()))
- I've no idea the repercussions (thinking I'll backup and recreate the cluster) but if you write an osdmap into all of...
- 05:43 PM Revision dd558967 (ceph): cmake: delete excidentail reintroduced line.
- - This target got reintroduced by accident after the creation
of ceph-common in commit:
https://github.com/ceph... - 04:44 PM Revision 0d3e6a9d (ceph): Merge pull request #15336 from wjwithagen/wjw-wip-iso_8601
- common/iso_8601.cc: Make return expression Clang compatible
Reviewed-By: Adam C. Emerson <aemerson@redhat.com>
Revie... - 03:48 PM Revision 7b874e11 (ceph): compressor: migrate atomic_t to <atomic>
- compare_exchange_strong() is used because on architectures without CaS instructions,
compare_exchange_weak() may fail... - 03:48 PM Revision 10b0a793 (ceph): messenger: migrate atomic_t to std::atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 03:48 PM Revision 42632790 (ceph): msg: migrate atomic_t to <atomic> (async)
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 03:47 PM Revision 9a208bf1 (ceph): client: migrate atomic_t to <atomic>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 03:47 PM Revision 99997237 (ceph): journal: migrate atomic_t to <atomic>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 12:57 PM Revision 2f1b0c18 (ceph): erasure-code/isa/ErasureCodePluginIsa.cc: fixup includes
- - Buffer.h is needed to prevent Clang seriously complaining
about missing and wrong forward declarations of
ceph:... - 12:56 PM Revision 973a4a01 (ceph): build/include: Redo som includes for FreeBSD
- - During include cleanup just a too bit much was removed for FreeBSD
to get things compiled.
This redoes some of ... - 12:51 PM Bug #19883: Remove redundant includes
- Willem Jan Withagen wrote:
> Willem Jan Withagen wrote:
> > Brad,
> >
> > How did you get these redundancies?
>... - 12:24 PM Revision de4d1113 (ceph): Adds C++ warning flag for C Variable-Length Arrays.
- C VLAs are not supported in C++. However, the GNU compiler allows
them as an extension, which it does not warn about ... - 06:45 AM Revision ef9d93b8 (ceph): Merge pull request #15055 from mogeb/wip-with-instrument-functions
- cmake: Add -finstrument-functions flag to OSD code
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:17 AM Revision 420dd7ff (ceph): Merge pull request #15319 from liewegas/wip-upmap
- mon,osd/OSDMap: a couple pg-upmap fixes
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:11 AM Revision d8f3ee16 (ceph): Merge pull request #15292 from liewegas/wip-map-cache
- osd: reduce map cache size
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:11 AM Revision a9a728fe (ceph): Merge pull request #15296 from liewegas/wip-fix-at-end
- qa/tasks/repair_test: unset flags we set
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:10 AM Bug #19595 (Resolved): mgr: segv in msgr thread, with no core
- hopefully! reopen if this pops up again!
- 03:10 AM Revision 040fd8ce (ceph): Merge pull request #15297 from liewegas/wip-19595
- mgr/MgrStandby: prevent use-after-free on just-shut-down Mgr
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:09 AM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-05-27_03:43:09-rados-wip-sage-testing2---basic-smithi/1235222
- 03:07 AM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-05-27_03:43:09-rados-wip-sage-testing2---basic-smithi/1235419
- 03:04 AM Bug #19900: osd crash during shutdown
- /a/sage-2017-05-27_03:43:09-rados-wip-sage-testing2---basic-smithi/1235367
the branch contained eb5c02d from https... - 02:38 AM Bug #19439 (Resolved): rebuild_mondb fails after the transition to ceph-mgr
- 02:38 AM Revision c6f1c06d (ceph): Merge pull request #14284 from tchaikov/wip-19439
- qa/tasks/rebuild_mondb: grant "mgr:allow *" to client.admin
Reviewed-by: Sage Weil <sage@redhat.com> - 02:33 AM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/kchai-2017-05-27_07:55:19-rados-wip-mgr-stats-kefu---basic-mira/1237260/remote/mira100/log/ceph-osd.2.log.gz
- 02:06 AM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-27_03:43:09-rados-wip-sage-testing2---basic-smithi/1235284
- 02:03 AM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-05-27_03:43:09-rados-wip-sage-testing2---basic-smithi/1235225
- 01:59 AM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-05-27_01:05:11-rados-wip-sage-testing---basic-smithi/1233483
- 02:02 AM Revision 0b0c7e56 (ceph): Merge pull request #15284 from majianpeng/bluestore-batch-throotle
- os/bluestore: batch throttle
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 02:01 AM Revision 5750523e (ceph): Merge pull request #15302 from xiexingguo/wip-fix-reg-leak
- common/ceph_context: fix leak of registered commands on exit
Reviewed-by: Sage Weil <sage@redhat.com> - 02:01 AM Bug #20067 (Resolved): assert in OSDMonitor::update_creating_pgs()
- 02:00 AM Revision c5628543 (ceph): Merge pull request #15320 from liewegas/wip-peon-mapping
- mon/OSDMonitor: cancel mapping job from update_from_paxos
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:59 AM Revision 8abc6e1b (ceph): qa/tasks/rebuild_mondb: update to address ceph-mgr changes
- - revive ceph-mgr after updating the keyring cap
- grant "mgr:allow *" to client.admin
- minor refactors
Signed-off-... - 01:57 AM RADOS Bug #20105 (Resolved): LibRadosWatchNotifyPPTests/LibRadosWatchNotifyPP.WatchNotify3/0 failure
- ...
05/27/2017
- 08:16 PM mgr Feature #19713 (Resolved): Enable `tell` (MCommand) from mgr python modules
- Forgot to close this one when the code merged.
- 12:17 PM mgr Feature #19713: Enable `tell` (MCommand) from mgr python modules
- see also: https://github.com/ceph/ceph/pull/14920
- 07:13 PM Revision 134e295c (ceph): common: get_process_name: use getprogname on bsd systems
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 05:02 PM Revision 0238bb55 (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 05:02 PM Revision b3dfa01b (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 04:36 PM Revision 50190741 (ceph): common/iso_8601.cc: Make return expression Clang compatible
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 12:15 PM mgr Feature #19885 (Resolved): `ceph tell mgr help` failed on Kraken
- https://github.com/ceph/ceph/pull/15111
- 12:11 PM Bug #20104 (Closed): tell injectargs command error
- ...
- 09:54 AM Support #20103 (Closed): ceph osd down
- *env*
system:centos7.1.1503 x64
kernel:3.10.0-229.el7.x86_64
ceph version:0.94.10
*error system log: /var/log/m... - 09:39 AM Revision 8b83b83d (ceph): rgw: add "rgw_verify_ssl" config
- http_client whether try to verify ssl when sent https request
Signed-off-by: Shasha Lu <lu.shasha@eisoo.com> - 08:36 AM Revision bc51f9af (ceph): rgw/rgw_op:Do some cleanup to prevent memory leaks when calling func sw...
- Signed-off-by: jimifm <hong.zhangoole@gmail.com>
- 08:32 AM rgw Bug #20101: swift slo/dlo download err when enable compression
- seems that compression is not supported for swift slo/dlo
- 03:47 AM rgw Bug #20101 (New): swift slo/dlo download err when enable compression
- swift slo/dlo object can't be downloaded.
issue can be reproduced with belown steps:
ceph version 10.2.3-62-g5f00... - 08:06 AM RADOS Bug #17968: Ceph:OSD can't finish recovery+backfill process due to assertion failure
- I have a document that provides the detail of our analysis of this problem, but it's written in chinese. If needed, I...
- 08:03 AM RADOS Bug #17968: Ceph:OSD can't finish recovery+backfill process due to assertion failure
- Hi, everyone.
Sorry, I forgot to watch my issues.
We found that the problem is due to "librados::OPERATION_BALA... - 08:00 AM Bug #19981: osds abort on shutdown with assert(/build/ceph-12.0.2/src/os/bluestore/BlueFS.cc: 898...
- I pulled out a disk, and then there was the problem
- 07:59 AM RADOS Bug #19983: osds abort on shutdown with assert(/build/ceph-12.0.2/src/os/bluestore/KernelDevice.c...
- I pulled out a disk, and then there was the problem.
- 07:27 AM Revision afe9d995 (ceph): rgw: get wrong content when download object with specific range when
- compression was enabled
look at the prototype:
RGWGetObj_Decompress::handle_data(bufferlist& bl, off_t bl_ofs, off_t... - 07:21 AM Revision 5d2a68eb (ceph): Merge pull request #15208 from liewegas/wip-sortbitwise-jewel
- mon: fix 'sortbitwise' warning on jewel
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:14 AM mgr Bug #20102 (Resolved): mgr crash in DaemonServer::ms_verify_authorizer()
- ...
- 03:06 AM Revision 5cace193 (ceph): tools/ceph_kvstore_tool: add "bluestore-kv" to usage
- We are soon going to use BlueStore as the default OS, and
hence "bluestore-kv" shall be the preferred option.
By app... - 03:06 AM RADOS Bug #20099: osd/filestore: osd/PGLog.cc: 911: FAILED assert(last_e.version.version < e.version.ve...
- fang yuxiang wrote:
> i think this is not functional issue of ceph, maybe your local fs data is corrupted.
>
> ar... - 03:01 AM RADOS Bug #20099: osd/filestore: osd/PGLog.cc: 911: FAILED assert(last_e.version.version < e.version.ve...
- `read_log 406'6529418` and `read_log 346'6529418` have the same seq
other, I use ceph-kvstore-tool can show as:
... - 02:46 AM RADOS Bug #20099: osd/filestore: osd/PGLog.cc: 911: FAILED assert(last_e.version.version < e.version.ve...
- i think this is not functional issue of ceph, maybe your local fs data is corrupted.
are you using any block cache... - 02:41 AM RADOS Bug #20099 (Need More Info): osd/filestore: osd/PGLog.cc: 911: FAILED assert(last_e.version.versi...
- My Ceph cluster is down when the server is powered off,
and when i restart my osd, it failed in read_log.
As fllow:... - 03:04 AM rgw Bug #20100 (Resolved): get wrong content when download object with specific range when compressio...
- create a bucket with compression enabled
Given a 32MB file, do steps:
1.divided the file into 4 parts
2.uplo... - 03:01 AM Revision 8491bc18 (ceph): ceph_test_rados_api_tier: skip redirect tests if not luminous
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 AM Revision af97f164 (ceph): Merge pull request #15111 from Liuchang0812/wip-19885-mgr-help
- ceph: introduce "tell x help" subcommand
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:52 AM Revision 9a22b1a6 (ceph): qa/suites/rados/thrash-luminous: redirects require luminous
- ...so skip the at-end variant of d-luminous.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:50 AM Revision a4247dd5 (ceph): Merge branch 'wip-extensible_tier-redirect' of git://github.com/myoungw...
- 02:45 AM Revision a0d88b09 (ceph): rgw: fix test_multi.py default config file path
- $ python test_multi.py --num-zonegroups=2 --num-zones 2 --gateways-per-zone 1
Traceback (most recent call last):
Fi... - 02:44 AM Revision cc45a8b9 (ceph): msg/async: keep _has_next_outgoing calling under write_lock
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:44 AM Revision 8fb779c5 (ceph): msg/async: avoid requeue racing with handle_write
- when the thread is calling AsyncConnection::handle_write, another thread may
replace it and requeue all messages. Bec... - 02:40 AM rgw Bug #20098: rgw: connection reset or radosgw crashed when download large zero object with compres...
- large zero object has a large compression rate, even 4M compressed data can decompress several GB data. Handle so muc...
- 02:36 AM rgw Bug #20098 (Resolved): rgw: connection reset or radosgw crashed when download large zero object w...
large zero object has a large compression rate, even 4M compressed data can decompress several GB data. Handle so m...- 02:02 AM Bug #20067 (Fix Under Review): assert in OSDMonitor::update_creating_pgs()
- https://github.com/ceph/ceph/pull/15320
- 12:47 AM rgw Backport #19806 (Resolved): jewel: APIs to support Ragweed suite
- 12:46 AM Revision 998d1ee4 (ceph): Merge pull request #14851 from yehudasa/wip-rgw-support-ragweed-jewel
- jewel: rgw: add apis to support ragweed suite
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 12:30 AM rgw Feature #20094: RFW: make civetweb max request size configurable to allow larger s3 object metadata
- PR was submitted to upstream civetweb and has been merged: https://github.com/civetweb/civetweb/pull/465
05/26/2017
- 11:12 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- https://github.com/ceph/dmclock/pull/25
- 10:59 PM Revision 97391bc0 (ceph): Run mvn verify integration tests for 2.8
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 10:48 PM Revision 5f003d6e (ceph): Merge pull request #15289 from ifed01/wip-bluestore-fix-bmap-assert
- os/bluestore: fix BitMapAllocator assert on out-of-bound hint value
Reviewed-by: Varada Kari <varada.kari@gmail.com> - 10:47 PM Bug #20062 (Resolved): msg/async/AsyncConnection.cc: 2525: FAILED assert(last_tick_id == id)
- 10:47 PM Revision c867a4d4 (ceph): Merge pull request #15288 from yuyuyu101/wip-20062
- msg/async: remove false alert "assert"
- 10:12 PM Feature #20087: OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- Greg Farnum wrote:
Thanks Greg for your inputs.
> I've seen stuff about this before but not been entirely clear... - 08:36 PM Feature #20087: OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- I've seen stuff about this before but not been entirely clear on what's happening. Is the issue that the local box is...
- 03:08 AM Feature #20087: OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- We have another feature request: http://tracker.ceph.com/issues/18438 for Configurable OSD Heartbeat packet size (MTU...
- 10:03 PM Bug #19931 (Resolved): osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has r...
- 09:39 PM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- Well, it's not exactly great but we didn't see the same issues on multisite:
http://pulpito.ceph.com/gregf-2017-05-2... - 10:02 PM Backport #20084: OSDs assert on shutdown when PGs are in snaptrim_wait() state
- https://github.com/ceph/ceph/pull/15322
- 08:38 PM Backport #20084: OSDs assert on shutdown when PGs are in snaptrim_wait() state
- (I think it just copied Need Review from the original tracker state, actually.)
- 08:38 PM Backport #20084 (In Progress): OSDs assert on shutdown when PGs are in snaptrim_wait() state
- Ah, sorry. I was going to but things got delayed due to slow builds yesterday and then I got asked to make some chang...
- 09:52 PM Revision 01abfed8 (ceph): osd: do not default-abort on leaked pg refs
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
(cherry picked from commit 4caf2df0c380a1281db9509b3feb342705512b58)
... - 09:52 PM Revision 967d6a54 (ceph): osd: Reset() the snaptrimmer on shutdown
- We were failing to exit various wait states which held PGRefs. Error!
Fixes: http://tracker.ceph.com/issues/19931
S... - 09:50 PM Revision 032466d7 (ceph): Merge pull request #15214 from gregsfortytwo/wip-19931-snaptrim-pgref
- osd: don't leak pgrefs or reservations in SnapTrimmer
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:44 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- http://pulpito.ceph.com/gregf-2017-05-26_06:45:56-rados-wip-19931-snaptrim-pgs---basic-smithi/1231020/
- 09:43 PM Revision 66ea9c1f (ceph): osd: shutdown our reserver_finisher earlier in the process
- This finisher thread has a lot of callbacks which can hold PGRefs. Make
sure we drain them out before checking that a... - 09:43 PM Revision 4caf2df0 (ceph): osd: do not default-abort on leaked pg refs
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 09:05 PM Revision 4c45d849 (ceph): Merge pull request #15316 from linuxbox2/wip-limitcheck-fixes
- rgw-admin: fix bucket limit check argparse, div(0)
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:07 PM Revision 4cb882e0 (ceph): mon/OSDMonitor: change info in 'osd failed' messages
- - put 'osd.NNN failed' at front
- drop the ip address
- include the crush location
- be consistent:
"osd.$id failed... - 07:49 PM Revision fb8e2fa6 (ceph): rgw-admin: fix bucket limit check argparse, div(0)
- 1. normalize arg parsing for "bucket limit check"
1.1 s/buckets/bucket/
2. avoid dividing by num_shards when it is 0... - 07:29 PM rgw Backport #20078 (In Progress): rgw jewel valgrind failure: make_params
- 02:00 PM rgw Backport #20078: rgw jewel valgrind failure: make_params
- https://github.com/ceph/ceph/pull/15312
- 01:59 PM rgw Backport #20078: rgw jewel valgrind failure: make_params
- Since this issue is already fixed in Kraken & master, it only appears in Jewel, need to copy the issue to backport tr...
- 06:09 PM Revision 2e6317a1 (ceph): mon/OSDMonitor: cancel mapping job from update_from_paxos
- On the leader we cancel the mapping job in encode_pending. On a peon,
we don't cancel it at all! It is surprising t... - 06:01 PM Revision a735244f (ceph): osd/OSDMap: some better pg-upmap debug output
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:00 PM Revision 90d32a1e (ceph): mon/OSDMonitor: allow upmap records for deleted pools to be removed
- Otherwise the offline osdmaptool --upmap-cleanup can't do its thing.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:32 PM Revision 50616b9e (ceph): mon/OSDMonitor: print more log when updating creating_pgs
- see-also: http://tracker.ceph.com/issues/20067
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:32 PM Revision 86031d02 (ceph): mon: trim the creating_pgs after updating it with pgmap
- see-also: http://tracker.ceph.com/issues/20067
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:26 PM Revision 36301656 (ceph): osd/OSDMap: encapsulate pg_temp
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:26 PM Revision e1bd8285 (ceph): osd/OSDMap: more efficient PGMapTemp
- Use a flat_map with pointers into a buffer with the actual data. For a
decoded mapping, we have just two allocations... - 04:26 PM Revision d64b481a (ceph): unittest_osdmap: parse env
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:11 PM Revision cc2780c4 (ceph): Merge pull request #15304 from Linbing/modify-note-word-error
- mon: Fixed typo in function comment blocks and in other comments
- 03:48 PM Revision cd86ef12 (ceph): crush: allow item addition/removal when choose_args exists
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:47 PM Revision ffc0d0f1 (ceph): crush: wrap crush_bucket_{remove,add}_item
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:42 PM Revision dba3d3e4 (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 03:41 PM Revision 6f8e5d2f (ceph): os/bluestore: fix BitMapAllocator assert on out-of-bound hint value
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:36 PM RADOS Bug #20068 (Need More Info): osd valgrind error in CrushWrapper::has_incompat_choose_args
- https://github.com/ceph/ceph/pull/15244 was merged recently and modified how things are handled. Let see if it happen...
- 03:34 PM rgw Bug #20096 (New): rgw: jewel valgrind failure RGWHTTPManager::add_request
- we're allocating a rgw_http_req_data and cleaning up on failures, not exactly for successful cases?...
- 02:48 PM Revision 4603e971 (ceph): Merge pull request #15256 from fangyuxiangGL/bucket-stats
- rgw: display more info when using radosgw-admin bucket stats
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:35 PM Revision e3bf1df9 (ceph): Merge pull request #15221 from fangyuxiangGL/set-placement-rule
- rgw: set placement rule properly
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:35 PM Revision ba545c12 (ceph): Merge pull request #15287 from ktdreyer/doc-ceph-fs-settings
- doc: describe CephFS max_file_size
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Alfredo Deza <adeza@... - 02:34 PM rgw Bug #20064 (Pending Backport): allow empty data_extra_pool in zone placement
- 02:34 PM Revision 30bc0f66 (ceph): Merge pull request #15219 from fangyuxiangGL/extra_pool
- rgw: use get_data_extra_pool() when get extra pool
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:33 PM Revision 456ac50a (ceph): Merge pull request #14341 from theanalyst/cleanup/rgw/str-find
- rgw_common: use string::npos for the results of str.find
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:30 PM Revision d6c49257 (ceph): Merge pull request #14746 from wjwithagen/wip-wjw-reduce-noise-2
- src/ceph.in: Use env(CEPH_DEV) to suppress noise from ceph
Reviewed-by: Sage Weil <sage@redhat.com> - 02:23 PM rgw Feature #20094: RFW: make civetweb max request size configurable to allow larger s3 object metadata
- Initial pull request at https://github.com/ceph/civetweb/pull/20, was requested to submit to upstream civetweb.
- 02:23 PM rgw Feature #20094 (New): RFW: make civetweb max request size configurable to allow larger s3 object ...
- Proposes to turn civetweb's macro for MAX_REQUEST_SIZE=16k into a configuration variable.
- 02:20 PM Revision 622c09cc (ceph): Merge pull request #15247 from liewegas/wip-upmap-save
- osdmaptool: require --upmap-save before modifying input osdmap
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:15 PM Bug #20093 (Resolved): msg/async: dropped a message
- osd.0 sees:...
- 02:12 PM rbd Bug #19832 (Pending Backport): Potential IO hang if image is flattened while read request is in-f...
- 02:12 PM Revision 47ad4429 (ceph): Merge pull request #15234 from trociny/wip-19832
- librbd: potential read IO hang when image is flattened
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:12 PM rbd Bug #19962 (Resolved): Discard related IO should skip op if object map marks object as non-existent
- 02:12 PM Revision a38f0a5c (ceph): Merge pull request #15239 from trociny/wip-19962
- librbd: discard related IO should skip op if object non-existent
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:02 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-26_06:56:21-rados-wip-sage-testing---basic-smithi/1231195
core file in test dir along with a copy ... - 01:49 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- attached gdb dump
- 01:48 PM Revision 189ce0e5 (ceph): Merge pull request #15293 from linuxbox2/wip-rgwfile-buckattr
- rgw_file: store bucket uxattrs on the bucket
- 01:44 PM Revision aa995589 (ceph): rgw: rest conn functions cleanup, only append zonegroup if not empty
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 4e41af19846db75081cb0ddb7b33dc2bb9321ace) - 01:44 PM Revision 5d907984 (ceph): rgw: rest and http client code to use param vectors
- Replaces param/header lists with vectors. In these cases, we're only ever
adding to the back of the list, so a vector... - 01:36 PM Revision 730781af (ceph): mon: it's no need to get pg action_primary osd twice in pg scrub
- Signed-off-by: linbing <linbing@t2cloud.net>
- 01:27 PM Revision 32bd33eb (ceph): Merge pull request #15290 from idryomov/wip-krbd-unmap-straw
- qa/suites/krbd: unmap subsuite needs straw buckets
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:26 PM Bug #19741: test_envlibrados_for_rocksdb.yaml fails on crypto restart
- /a/sage-2017-05-26_06:56:21-rados-wip-sage-testing---basic-smithi/1231184 (centos)
- 12:40 PM RADOS Bug #20092 (Duplicate): ceph-osd: FileStore::_do_transaction: assert(0 == "unexpected error")
- http://pulpito.ceph.com/jdillaman-2017-05-25_16:48:38-rbd-wip-jd-testing-distro-basic-smithi/1229611...
- 12:38 PM Revision 4274c91c (ceph): doc: describe differences with "mds set" vs "fs set"
- Thanks to John Spray <jspray@redhat.com> on ceph-users for this
information.
Signed-off-by: Ken Dreyer <kdreyer@redh... - 12:38 PM Revision 02753cdb (ceph): doc: describe CephFS max_file_size
- Add a description of max_file_size to the CephFS admin docs.
Thanks to John Spray <jspray@redhat.com> on ceph-users ... - 11:17 AM Bug #19883: Remove redundant includes
- Hi Willem,
Which PRs/commits specifically are you having issues with?
I don't have access to FreeBSD to test wi... - 11:11 AM Bug #19883: Remove redundant includes
- Brad,
How did you get these redundancies?
Just running GCC on Linux?
Having a lot of fallout under FreeBSD/Cla... - 11:13 AM CephFS Bug #19706 (Fix Under Review): Laggy mon daemons causing MDS failover (symptom: failed to set cou...
- https://github.com/ceph/ceph/pull/15308
- 10:15 AM Revision 6435c4a2 (ceph): os/bluestore/BlueStore: batch handle Throttle.put.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 10:15 AM Revision 45113968 (ceph): os/bluestore/BlueStore: avoid iterating to get ios/cost in _kv_sync_thr...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 10:15 AM Revision 910e5801 (ceph): os/bluestore/BlueStore: Only call once notify_all.
- All txcs of deferred_running have the same osr, so only call once
notify_call.
Signed-off-by: Jianpeng Ma <jianpeng.... - 10:07 AM Revision f28f4cbc (ceph): ./qa/workunits/ceph-helpers.sh: Do not trace kill_daemon
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 10:07 AM Revision 0f8972dd (ceph): vstart:Suppress trivial logging info during devlopment
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 10:07 AM Revision f7e60bac (ceph): src/ceph.in: Use env(CEPH_DEV) to suppress noise from ceph
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 09:45 AM Revision 5b468b64 (ceph): Modify note error
- Signed-off-by: linbing linbing@t2cloud.net
- 09:39 AM Revision 9b5a1a4a (ceph): inline_memory: optimized mem_is_zero for non-X64
- mem_is_zero is fast for X64 where 128-bit registers are available,
but it's very easy to optimze it for 32-bit Intel ... - 09:39 AM Revision 5284778e (ceph): tool/ceph: support target mon in tell help subcommand
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 09:28 AM Revision 9939d5a8 (ceph): common/ceph_context: fix leak of registered commands on exit
- By unregister them properly.
Also rearrange commands order to keep pace with register process.
Signed-off-by: xie xi... - 09:04 AM Bug #20091 (Resolved): build/ops: rpm: Invalid SPDX license: GPL-2.0-with-autoconf-exception
- As of Version 2.0 of the SPDX Specification, "GPL-2.0-with-autoconf-exception" is not a valid license.
Quoting fro... - 08:53 AM CephFS Bug #19812: client: not swapping directory caps efficiently leads to very slow create chains
- The problem is that getattr requests for permission check should only get Ax, but they actually get pAsLsXsFs. gettin...
- 01:13 AM CephFS Bug #19812: client: not swapping directory caps efficiently leads to very slow create chains
- Zheng Yan wrote:
> The reason of slow creation/deletion is that ceph-fuse sends a getattr request (check permission ... - 08:48 AM Revision fc54b831 (ceph): client: fix display ino in the ldout
- Log need `ino`,not `address pointer`
Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn> - 07:54 AM Revision 88794eca (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 07:54 AM Revision d16262b9 (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 07:54 AM Revision ad2983db (ceph): rpm: Move ceph-disk to ceph-base
- The SELinux package now requires the ceph-disk binary but that one was
part of the ceph-osd package. The ceph-disk py... - 07:12 AM CephFS Bug #20083 (Fix Under Review): TestExports.test_export_pin failing on master
- https://github.com/ceph/ceph/pull/15300/commits
- 07:10 AM Revision 8bfa1681 (ceph): client: fix Dentry::dump
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 07:06 AM CephFS Bug #20076: Pass empty string to clear mantle balancer
- Changes have been made to use following command to clear mantle balancer...
- 07:00 AM Bug #18305: ceph-osd systemd unit files incomplete
- @Greg:...
- 06:58 AM Revision bd8c06de (ceph): mds/MDBalancer: put heartbeat msg ref after using mantle balancer
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 06:54 AM Revision a1214a70 (ceph): Pass empty string to clear mantle balancer
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 05:58 AM Revision 2a3382fa (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 05:33 AM Revision d60ddddf (ceph): rgw: multipart copy-part remove '/' for s3 java sdk request header.
- Fixes: http://tracker.ceph.com/issues/20075
Signed-off-by: donglinpeng@cmss.chinamobile.com - 04:57 AM rgw Bug #20048 (Fix Under Review): Ceph no longer builds for s390x after Beast submodule enabled
- https://github.com/ceph/ceph/pull/15225
- 04:52 AM Revision b0e9deee (ceph): osd: Reset() the snaptrimmer on shutdown
- We were failing to exit various wait states which held PGRefs. Error!
Fixes: http://tracker.ceph.com/issues/19931
S... - 03:46 AM Revision e901d7fe (ceph): mds: properly create aux subtrees for pinned directory
- Fixes: http://tracker.ceph.com/issues/20083
Signed-off-by: "Yan, Zheng" <zyan@redhat.com> - 03:29 AM Revision 6b6c14f8 (ceph): Merge pull request #14658 from chardan/jfw-wip-halflife_atomic_t-baragon
- librados,libradosstriper,test: migrate atomic_t to std::atomic (baragon)
Reviewed-by: Sage Weil <sage@redhat.com> - 03:28 AM Bug #20051 (Resolved): mgr: crash in MetadataUpdate::finish
- 03:28 AM Revision 0f01014b (ceph): Merge pull request #15227 from tchaikov/wip-20051
- mon/MonClient: cancel pending commands on shutdown
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:27 AM Revision 6650a18e (ceph): Merge pull request #15249 from Alessandro-Barbieri/patch-2
- yasm-wrapper: filter -pthread
Reviewed-by: Sage Weil <sage@redhat.com> - 03:27 AM Revision dcebdf4f (ceph): Merge pull request #15268 from ifed01/wip-bluestore-false-assert
- os/bluestore: fix false assert in IOContext::aio_wake
Reviewed-by: Sage Weil <sage@redhat.com> - 03:27 AM Revision 94c834ab (ceph): Merge pull request #15272 from tchaikov/wip-mon-cleanups
- mon: cleanups
Reviewed-by: Sage Weil <sage@redhat.com> - 03:13 AM Revision c1b92cdc (ceph): test/osd/osd-config.sh: fix test to isolate cases
- The third test (increasing osd_map_max_advance)
was triggering a warning from the 4th case (which
it didn't before).
... - 03:13 AM Revision 855955e5 (ceph): osd: reduce size of osdmap cache, messages
- On large clusters, these large caches can be problematic (as maps get big).
We've seen good results with extremely sm... - 02:52 AM Revision 73985a5b (ceph): osd: instrument osdmap bl cache hits and misses
- Add perfcounters so we can see whether we are missing osdmaps in the
cache. This will let us tell whether, given a w... - 02:52 AM Revision c489d451 (ceph): osd: fadvise hint WILL_NEED when reading encoded osdmaps
- This way will ensure we cache data for recent osdmaps if we need to for
the benefit of laggy clients... even if (in b... - 02:29 AM Revision c150cba8 (ceph): osd: remove osd_enxio_on_misdirected_op option
- There is no good reason anyone would want this turned on.
Introduced 923e7f5ce5ed437af15e178299a61029ff48e4a2 (post-... - 02:29 AM Revision 0ff3d429 (ceph): osd: do not bother with misdirected op diagnosis by default
- We enable osd_debug_misdirected_ops in QA, but this is wasted effort on
a production cluster. In particular, it mean... - 02:27 AM Revision 56809368 (ceph): tool/ceph: create "tell x help" command
- Fixes: http://tracker.ceph.com/issues/19885
Signed-off-by: liuchang0812 <liuchang0812@gmail.com> - 02:27 AM Revision a1cf9ae7 (ceph): doc/tool: introduce "ceph tell x help" command in man
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 02:27 AM Revision b0af3971 (ceph): test/cephtool: convert FS_NAME to local variable
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 02:27 AM Revision 9753a006 (ceph): tool/ceph: validate target in tell subcommand
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 02:27 AM Revision b2fcb62b (ceph): tool/ceph: remove old mon support and verbose support
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 01:29 AM Bug #20089 (In Progress): Can't repair when only an attr object error
- 12:21 AM Bug #20089 (Resolved): Can't repair when only an attr object error
A shard with only an attr error (attr_value_mismatch, attr_name_mismatch) isn't repaired because it ends up on the ...
05/25/2017
- 11:41 PM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- It depends on the interface above it. The block layer in linux, for example, has no way to indicate 'out of space' - ...
- 11:29 PM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- If I don't add more space, because I can't, then it will hang forever, hence the original reasoning behind this bug r...
- 08:50 PM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- How can you be sure the Ceph client will hang _forever_? If more space is added to the cluster, perhaps the operation...
- 01:05 AM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- They can't handle "out of space" error message, but can handle an infinite hang situation? So you're saying that if y...
- 12:53 AM Feature #16562 (New): rados put: use the FULL_TRY flag to report errors when cluster is full
- The behavior of blocking when full is intentionally the default for rados operations - too many consumers of the inte...
- 10:35 PM Revision 09624970 (ceph): Merge pull request #15192 from badone/wip-tracker-19900-wait_auth_rotat...
- mgr: Mark session connections down on shutdown
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:31 PM rgw Backport #20088 (Resolved): valgrind reports leak in RGWRemoteMetadataCR
- https://github.com/ceph/ceph/pull/15382
- 10:26 PM Bug #19595 (Fix Under Review): mgr: segv in msgr thread, with no core
- I think this is it... though only testing will tell. Luckily this comes up about once every other rados suite run.
... - 10:09 PM Bug #19595: mgr: segv in msgr thread, with no core
- /a/sage-2017-05-25_17:58:50-rados-wip-sage-testing2---basic-smithi/1229304
shortly after it's deactivated:... - 10:25 PM Revision 890f4825 (ceph): mgr/MgrStandby: prevent use-after-free on just-shut-down Mgr
- Fixes: http://tracker.ceph.com/issues/19595
Signed-off-by: Sage Weil <sage@redhat.com> - 10:18 PM Feature #20087 (Resolved): OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- - OSD: Add heartbeat message for Jumbo Frames(MTU 9000)
- When we have jumbo frames enabled in cluster network and... - 10:07 PM RADOS Bug #20086 (Can't reproduce): LibRadosLockECPP.LockSharedDurPP gets EEXIST
- ...
- 10:05 PM Revision d292b541 (ceph): qa/tasks/repair_test: unset flags we set
- In particular, noscrub and nodeepscrub leave a health
warning, which prevents shutdown with at-end.yaml.
Signed-off-... - 10:03 PM rgw Bug #20085 (New): valgrind failure on curl_multi_init
- could be a false +ve as well, we do a `curl_mutli_cleanup` in the destructor...
- 09:32 PM Backport #20084: OSDs assert on shutdown when PGs are in snaptrim_wait() state
- Greg, seeing that you set "Need Review" on this - did you already open the jewel PR?
- 08:55 PM Backport #20084 (Resolved): OSDs assert on shutdown when PGs are in snaptrim_wait() state
- https://github.com/ceph/ceph/pull/15322
- 09:29 PM Backport #20080: jewel: Set subman cron attributes in spec file
- We set target version only after backport PR is merged.
- 06:24 PM Backport #20080 (Resolved): jewel: Set subman cron attributes in spec file
- https://github.com/ceph/ceph/pull/15473
- 09:04 PM Revision ebe0fca1 (ceph): rgw_file: store bucket uxattrs on the bucket
- This turns out to be the corollary of the earlier bug in removing
buckets w/uxattrs. Rather than conditionally put th... - 08:53 PM Bug #19931 (Fix Under Review): osds abort on shutdown with assert(peering_queue.empty()) or 'pgid...
- Okay, my local testing was using init-ceph, and the way it repeatedly invokes kill signals means the OSD wasn't getti...
- 08:52 PM Revision 6dbcbb55 (ceph): osd: prevent upgrading unsupported cluster
- Signed-off-by: Myoungwon Oh omwmw@sk.com
Signed-off-by: Sage Weil sage@redhat.com - 08:45 PM CephFS Bug #20072: TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
- I've got a bunch of krbd test failures which I tracked down to a recent change in "rados ls" behavior.
Before:
... - 08:44 PM Fix #20074 (Pending Backport): Set subman cron attributes in spec file
- 08:43 PM Revision 25b8e0f6 (ceph): Merge pull request #15146 from tchaikov/wip-split-test-tiering
- qa: split test_tiering into smaller pieces
Reviewed-by: Sage Weil <sage@redhat.com> - 08:43 PM Revision 0f7e2698 (ceph): Merge pull request #15156 from tchaikov/wip-ceph.in-assert-connected
- ceph.in: assert(state==connected) before help_for_target()
Reviewed-by: Jos Collin <jcollin@redhat.com>
Reviewed-by:... - 08:40 PM rgw Backport #17546: jewel: rgw: bucket resharding
- See #17756 for the backport that was actually merged.
- 08:39 PM rgw Backport #17546 (Rejected): jewel: rgw: bucket resharding
- 08:40 PM Revision 516c3ec4 (ceph): Merge pull request #15224 from tchaikov/wip-denc-no-deep-copy-for-segme...
- denc: add need_contiguous to denc_traits
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@redh... - 08:31 PM Revision 9b81fa43 (ceph): crush/CrushTreeDumper: allow children to filter results
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:28 PM Revision 448edbfa (ceph): rgw_file: store bucket uxattrs on the bucket
- This turns out to be the corollary of the earlier bug in removing
buckets w/uxattrs. Rather than conditionally put th... - 07:35 PM CephFS Bug #20083 (Resolved): TestExports.test_export_pin failing on master
- Apparently we have already broken this!
See failures in this run:
http://pulpito.ceph.com/jspray-2017-05-25_12:58... - 07:16 PM Revision 27fe5320 (ceph): tracing: add cyg_profile tracepoint provider
- Signed-off-by: Mohamad Gebai <mgebai@suse.com>
- 07:16 PM Revision 73ab6c2d (ceph): tracing: add -finstrument-functions for OSD
- Signed-off-by: Mohamad Gebai <mgebai@suse.com>
- 07:16 PM Revision 021dcf7b (ceph): tracing: add documentation for function instrumentation
- Signed-off-by: Mohamad Gebai <mgebai@suse.com>
- 07:16 PM Revision 69d5ad52 (ceph): tracing: remove -pie if using function instrumentation
- Signed-off-by: Mohamad Gebai <mgebai@suse.com>
- 07:16 PM Revision 0baebc30 (ceph): cmake: configuration for OSD function instrumentation
- Signed-off-by: Mohamad Gebai <mgebai@suse.com>
- 07:01 PM rgw Bug #20082: rgw_file: bucket uxattrs not restored correctly (because set on "<bucket>/")
- Further explication: this reproduced as unix attrs set on buckets 'changing back' to their default values after a re...
- 06:59 PM rgw Bug #20082 (In Progress): rgw_file: bucket uxattrs not restored correctly (because set on "<bucke...
- This turns out to be the corollary of the earlier bug in removing buckets w/uxattrs. Rather than conditionally put t...
- 06:52 PM Documentation #20081 (Closed): Individual RGW Daemon ceph.conf configuration example should be [c...
- Here: http://docs.ceph.com/docs/jewel/rados/configuration/ceph-conf/ (perhaps elsewhere)
When describing per-insta... - 06:45 PM rgw Fix #19732: fix: rgw crashed caused by shard id out of range when listing data log
- *master PR*: https://github.com/ceph/ceph/pull/14389
- 06:42 PM Revision a3b028a6 (ceph): osd: print out pg debug ref counts on acquire/drop
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 06:42 PM Revision 0bce2c62 (ceph): osd: make sure we drop Backoff PGRefs on shutdown
- Fixes: http://tracker.ceph.com/issues/19931
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 06:42 PM Revision ec4185d1 (ceph): osd: repair the PG_DEBUG_REFS build
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 06:39 PM Revision 306ad85f (ceph): osd: use PGRef instead of boost::intrusive_ptr<PG> everywhere
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:55 PM rgw Backport #19736 (Resolved): radosgw/s3 chunked transfer encodings and fast_forward_request
- 05:51 PM Revision 5b5bae7f (ceph): ceph-disk: dmcrypt activate must use the same cluster as prepare
- When dmcrypt is used, the fsid cannot be retrieved from the data
partition because it is encrypted. Store the fsid in... - 05:46 PM rgw Bug #19870: rgw: bytes_send and bytes_recv in the msg of usage show returning is 0 in master branch
- duplicated of http://tracker.ceph.com/issues/19194
- 05:46 PM rgw Bug #19214 (Pending Backport): rgw_file: RGWLibFS::get_inst() not stable
- https://github.com/ceph/ceph/pull/13832
- 05:45 PM CephFS Bug #19912 (Resolved): kcephfs: Test failure: test_trim_caps
- 05:44 PM Revision f80e0973 (ceph): Merge pull request #15062 from ukernel/wip-19912
- qa/tasks/cephfs: use getattr to guarantee inode is in client cache
Reviewed-by: John Spray <john.spray@redhat.com> - 05:43 PM rgw Bug #19624 (Pending Backport): rgw_file: handle chunked readdir
- https://github.com/ceph/ceph/pull/14653
https://github.com/ceph/ceph/pull/14458 - 05:43 PM Revision 5b40557a (ceph): Merge pull request #15270 from ceph/wip-subman-cron-attr-tserlin
- Set subman cron attributes in spec file
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 05:36 PM rgw Bug #20045 (Pending Backport): rgw_file: cannot delete bucket w/uxattrs
- https://github.com/ceph/ceph/pull/15210
- 05:34 PM rgw Bug #20061 (Pending Backport): rgw_file: attempt to unlink non-empty bucket could lead to hang
- https://github.com/ceph/ceph/pull/15246
- 05:34 PM rgw Bug #20075 (Fix Under Review): rgw: multipart copy-part encounts 404 error by using S3 java sdk
- 08:34 AM rgw Bug #20075: rgw: multipart copy-part encounts 404 error by using S3 java sdk
- Fixed:https://github.com/ceph/ceph/pull/15283
- 03:55 AM rgw Bug #20075 (Resolved): rgw: multipart copy-part encounts 404 error by using S3 java sdk
- Testing multipart copy-part feature by using S3 java sdk(version:1.10.69) got 404 No Such Key. RGW log detail are as...
- 05:33 PM Bug #17266: virtualenv default paths not uniquely named
- This bites me every single time I build on a shared build machine; still think that at least /tmp/<username> is a bet...
- 05:22 PM rgw Bug #20079 (Closed): rgw jewel: valgrind failure in receive_header
- failure when adding the headers to the out_headers map ...
- 05:13 PM Bug #17821 (Resolved): ceph-disk and dmcrypt does not support cluster names different than 'ceph'
- 05:13 PM Backport #18972 (Resolved): jewel: ceph-disk does not support cluster names different than 'ceph'
- 05:09 PM Revision 19197d88 (ceph): Merge pull request #15253 from tchaikov/wip-ceph-daemon-termsize
- pybind/ceph_daemon.py: fix Termsize.update
Reviewed-by: Dan Mick <dmick@redhat.com> - 04:45 PM Revision 54bc1e13 (ceph): Merge pull request #14765 from smithfarm/wip-18972-jewel
- jewel: ceph-disk does not support cluster names different than 'ceph'
Reviewed-by: Alfredo Deza <adeza@redhat.com> - 04:23 PM CephFS Bug #19706: Laggy mon daemons causing MDS failover (symptom: failed to set counters on mds daemon...
- My assumption was just that this test was hammering the nodes hard, as it seems to be repeatedly failing on the same ...
- 04:19 PM CephFS Bug #19706: Laggy mon daemons causing MDS failover (symptom: failed to set counters on mds daemon...
- from /a/teuthology-2017-05-22_03:15:05-fs-master---basic-smithi/1205932/remote/smithi079/log/ceph-mon.c.log.gz...
- 03:54 PM CephFS Bug #19706: Laggy mon daemons causing MDS failover (symptom: failed to set counters on mds daemon...
- ...
- 04:10 PM CephFS Bug #2494: mds: Cannot remove directory despite it being empty.
- I'm observing this on our internal cluster. Attempting to remove empty dir ...
- 03:57 PM Revision 4ef5559f (ceph): Merge pull request #15279 from joscollin/wip-cleanup-rename-filejournal...
- test: Rename FileJournal object to distinguish
- 03:42 PM rgw Backport #20078 (Resolved): rgw jewel valgrind failure: make_params
- https://github.com/ceph/ceph/pull/15312
- 02:57 PM Revision 4926fbaf (ceph): test: add denc tests for sstring
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 02:31 PM Bug #20067: assert in OSDMonitor::update_creating_pgs()
- /a/yuriw-2017-05-25_00:40:22-rados-wip-yuri-testing_2017_5_24-distro-basic-smithi/1225508/remote/smithi188/log/ceph-m...
- 02:14 PM Bug #20067: assert in OSDMonitor::update_creating_pgs()
- /a/sage-2017-05-23_22:17:12-rados-wip-bigbang---basic-smithi/1222226/remote/smithi198/log/ceph-mon.c.log.gz
- 02:16 PM Revision a9eb6ece (ceph): Set subman cron attributes in spec file
- Fixes: http://tracker.ceph.com/issues/20074
Signed-off-by: Thomas Serlin <tserlin@redhat.com> - 02:11 PM Revision ffb9e09b (ceph): qa/suites/krbd: unmap subsuite needs straw buckets
- The default tunables for luminous allow straw2 buckets, which aren't
supported by pre-single-major.yaml kernel. The ... - 01:56 PM Revision 2f8c5695 (ceph): msg/async: remove false alert "assert"
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 01:38 PM Revision ce5d6818 (ceph): build/ops: rpm: apply epoch only if %epoch macro is defined
- This allows SUSE to drop a maintenance-intensive downstream patch.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 12:49 PM Feature #20077: Speed up upgrade from non-SELinux enabled ceph to an SELinux enabled one
- PR:
https://github.com/ceph/ceph/pull/14871 - 12:47 PM Feature #20077 (Resolved): Speed up upgrade from non-SELinux enabled ceph to an SELinux enabled one
- Currently, we do not do an SELinux relabel in parallel (per osd) on upgrade but thanks to ceph-disk fix command we can.
- 12:48 PM Revision d9b09490 (ceph): ceph-disk: Fix the file ownership, skip missing
- This commit fixes the file ownership for the /usr/bin/ and /etc/ceph
files and skips missing files as some of the fil... - 12:48 PM Revision 5fc1fed1 (ceph): selinux: Do parallel relabel on package install
- We can take advantage of ceph-disk fix subcommand when doing a package
install. We will keep using the differential f... - 11:53 AM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- blob id more than the maximum
BlueStore.cc :2256
dout(20) << __func__ << " adding spanning " << *b << dendl... - 11:52 AM Bug #19941: ceph-disk fails if OSD udev rule triggers prior to mount of /var
- 11:38 AM rgw Backport #19098 (Resolved): RGW/openssl fix for autoconf logic problem in Ubuntu Xenial
- 11:04 AM rgw Backport #19003 (Resolved): jewel: civetweb defaults to libssl.so and libcrypto.so when versions ...
- 10:46 AM CephFS Bug #19955 (Pending Backport): Too many stat ops when MDS trying to probe a large file
- 12:59 AM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- Yes, we should backport it
when writing large file, old client does not report file size in time. It may not repor... - 09:33 AM CephFS Bug #17606 (Resolved): multimds: assertion failure during directory migration
- 09:32 AM CephFS Bug #17113 (Can't reproduce): MDS EImport crashing with mds/journal.cc: 2929: FAILED assert(mds->...
- it's likely fixed by https://github.com/ceph/ceph/commit/a49726e10ef23be124d92872470fd258a1938d9e
- 09:30 AM Revision 69e8beed (ceph): build/ops: drop libfcgi build dependency
- Follow-up on https://github.com/ceph/ceph/pull/15070 and https://github.com/ceph/ceph/pull/15098
Signed-off-by: Nath... - 09:23 AM CephFS Bug #18680 (Resolved): multimds: cluster can assign active mds beyond max_mds during failures
- https://github.com/ceph/ceph/commit/2c08f58ee8353322a342ce043150aafc8dd9c381
- 09:22 AM CephFS Bug #18717 (Resolved): multimds: FAILED assert(0 == "got export_cancel in weird state")
- https://github.com/ceph/ceph/commit/2c08f58ee8353322a342ce043150aafc8dd9c381
- 09:18 AM Revision e9a81ba4 (ceph): Merge pull request #15200 from smithfarm/wip-rdma-devel
- build/ops: rpm: move RDMA and python-prettytables build dependencies to distro-conditional section
Reviewed-by: Kefu... - 09:11 AM Linux kernel client Bug #18671 (Resolved): kernel 4.8.15: BUG: soft lockup
- 09:05 AM Revision 9bdf1f43 (ceph): test/mon: fix segfault due to uninitialized member variable
- Signed-off-by: zhanglei <243290414@qq.com>
- 09:04 AM Revision 6d80995a (ceph): rgw_file: fix double lock on unlink bucket
- When stat_buckets with FLAG_LOCKED, we would not want to lock_guard
again to protect time attrs.
Signed-off-by: Gui ... - 09:04 AM Revision e1be6e7a (ceph): rgw_file: fix flags set on unsuccessful unlink
- Only set FLAG_DELETED when the object/bucket is successfully
deleted or ENOENT returned due to race with other s3 gat... - 08:29 AM CephFS Bug #20076: Pass empty string to clear mantle balancer
- https://github.com/ceph/ceph/pull/15282
- 08:27 AM CephFS Bug #20076 (Resolved): Pass empty string to clear mantle balancer
- Currently we can use "ceph fs set cephfs balancer <lua_conf_file>" to set mantle balancer. Then MDS balancer will try...
- 08:13 AM Revision 57f1b429 (ceph): Remove duplicate calls because the destructor has been processed
- Uniform class RGWObjectExpirer and class RGWGC's destructor
Signed-off-by: jimifm <hong.zhangoole@gmail.com> - 06:36 AM Revision 9c431c78 (ceph): test: Rename FileJournal object to distinguish
- Renamed FileJournal object for easier searching and identifying with in test_filejournal.cc
Signed-off-by: Jos Colli... - 06:11 AM RADOS Bug #19983: osds abort on shutdown with assert(/build/ceph-12.0.2/src/os/bluestore/KernelDevice.c...
- /a/bhubbard-2017-05-24_05:25:43-rados-wip-badone-testing---basic-smithi/1224591/teuthology.log...
- 05:56 AM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/bhubbard-2017-05-24_05:25:43-rados-wip-badone-testing---basic-smithi/1224546/teuthology.log
- 05:49 AM Bug #19741: test_envlibrados_for_rocksdb.yaml fails on crypto restart
- /a/bhubbard-2017-05-24_05:25:43-rados-wip-badone-testing---basic-smithi/1224665/teuthology.log
- 03:59 AM Revision 2f9ee0ba (ceph): Merge pull request #15258 from big-henry/wip-mds-misc-fix
- mds: fix client ID truncation
- 02:50 AM Revision 8f7c932f (ceph): cephfs: Add some check befor we want to add new data pool
- Signed-off-by: Vicente Cheng <vicente_cheng@bigtera.com>
- 02:50 AM Revision de0ce386 (ceph): mds: change the type of data_pools
- Change the type of data_pools from `set` to `vector`
In following scenario, we found something strange here.
Here... - 02:27 AM RADOS Bug #19964: occasional crushtool timeouts
- /a/sage-2017-05-24_22:20:09-rados-wip-sage-testing---basic-smithi/1225182
- 01:32 AM Revision 9e297686 (ceph): Merge pull request #15235 from smithfarm/wip-doc-empowers
- doc: fix factual inaccuracy in doc/architecture.rst
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil... - 01:21 AM Revision 539985a9 (ceph): rgw: set object accounted size correctly
- sometimes, object accounted size is set wrong,
because we don't konw the object size if don't resort to the compressi... - 01:07 AM Bug #17228: Hammer OSD memory use very high (EL6)
- Thanks Sage,
This is no longer an issue for this cluster. We have managed to work around the issue by "regeneratin... - 12:44 AM Revision 6b574394 (ceph): rgw: fix "radosgw-admin user rm" retcode
- when user.remove got negative retcode should return
Signed-off-by: Shasha Lu <lu.shasha@eisoo.com> - 12:16 AM RADOS Bug #19790: rados ls on pool with no access returns no error
- Looking into this
- 12:10 AM Bug #19990 (Resolved): EAGAIN: osd.4 is not up from rados/singleton-nomsgr/{all/health-warnings.y...
- 12:07 AM Revision 3f01eab5 (ceph): osd: re-queue recovery without pg lock
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 12:05 AM Revision 8b40a11e (ceph): osd: change default value of osd_recovery_sleep
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 12:05 AM Revision 814a6f3b (ceph): Merge pull request #15275 from ktdreyer/wip-17396
- docs: document "osd recovery max single start" setting
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:02 AM Revision a8cad419 (ceph): doc: add description about osd_recovery_sleep
- Signed-off-by: Neha Ojha <nojha@redhat.com>
05/24/2017
- 11:13 PM RADOS Bug #19939: OSD crash in MOSDRepOpReply::decode_payload
- Kefu, could you take a look at this one? Not sure if it's related to recent denc changes, or perhaps https://github.c...
- 10:26 AM RADOS Bug #19939: OSD crash in MOSDRepOpReply::decode_payload
- More instances from last night's master:
- http://pulpito.ceph.com/jspray-2017-05-23_22:31:39-fs-master-distro-basic... - 10:14 PM Bug #18088 (Can't reproduce): mon: segment fault when starts mon first
- maybe a corrupted package or broken install?
- 10:09 PM Revision 6d520e91 (ceph): Merge pull request #15276 from liewegas/wip-ext4-again
- qa/suites/rados/singleton-nomsgr: fix syntax
- 10:05 PM Revision 5d80c74e (ceph): Merge pull request #15252 from liewegas/wip-cleanup-tell
- qa/tasks/ceph_manager: 'ceph $service tell ...' is obsolete
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:05 PM Bug #19989 (Resolved): "OSDMonitor.cc: 3545: FAILED assert(num_down_in_osds <= num_in_osds)" in r...
- 10:05 PM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- Hi Nathan, Yes, https://github.com/ceph/ceph/pull/14886 causes problems (proliferation of threads) and should not be ...
- 08:29 PM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- Brad Hubbard wrote:
> Please see https://github.com/ceph/ceph/pull/15217 also
Brad, are you saying that https://g... - 10:04 PM Revision ee84a23e (ceph): Merge pull request #15250 from neha-ojha/wip-19989
- osd/OSDMap.cc: check if osd is out in subtree_type_is_down
Reviewed-by: Sage Weil <sage@redhat.com> - 10:03 PM Revision 035cad4f (ceph): Merge pull request #14944 from yuyuyu101/wip-msgr-throttle-ops
- ceph_osd: remove client message cap limit
Reviewed-by: Sage Weil <sage@redhat.com> - 10:03 PM Revision 499c1afc (ceph): Merge pull request #14655 from chardan/jfw-wip-halflife_atomic_t-gojira
- test: migrate atomic_t to std::atomic
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:02 PM Revision 8e72e0ee (ceph): Merge pull request #11966 from aclamk/wip-linear-zeros-crc
- common: Improved CRC calculation for zero buffers
- 10:01 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/sage-2017-05-24_18:40:38-rados-wip-sage-testing2---basic-smithi/1224933
- 09:58 PM Revision d2dac535 (ceph): qa/suites/rados/singleton-nomsgr/health...: whitelist wrongly marked me...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:46 PM Revision 85e2f3f3 (ceph): qa/suites/rados/singleton-nomsgr: fix syntax
- This parsed out as
tasks:
- install: null
- ceph:
conf:
osd: osd max object name len = 400 osd m... - 08:42 PM Bug #17396 (Fix Under Review): "osd recovery max single start" is not documented
- 08:42 PM Bug #17396: "osd recovery max single start" is not documented
- Thanks Sage, I've added the doc in https://github.com/ceph/ceph/pull/15275
- 03:37 PM Bug #17396: "osd recovery max single start" is not documented
- per osd.
- 08:41 PM Revision 87d47b0d (ceph): docs: document "osd recovery max single start" setting
- Fixes: http://tracker.ceph.com/issues/17396
Signed-off-by: Ken Dreyer <kdreyer@redhat.com> - 07:57 PM Revision cc52f051 (ceph): Merge pull request #15028 from pritha-srivastava/wip-rgw-bucket-policy-...
- rgw: Adding code to create tenanted user for s3 bucket policy tests.
- 07:53 PM Revision d06d1347 (ceph): Merge pull request #15070 from ceph/wip-turn-off-fcgi-tserlin
- rgw: Turn off fcgi as a frontend
- 06:32 PM rgw Bug #17632: byte ranges on slo/dlo objects broken in master
- is this still a problem?
- 06:20 PM rgw Bug #18977 (Fix Under Review): rgw: end_marker parameter doesn't work on Swift container's listing
- https://github.com/ceph/ceph/pull/15273
- 05:51 PM Revision 06018fa7 (ceph): build: remove ceph-disk-udev entirely
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 05:50 PM Fix #20074 (In Progress): Set subman cron attributes in spec file
- https://github.com/ceph/ceph/pull/15270
- 05:35 PM Fix #20074 (Resolved): Set subman cron attributes in spec file
- This will allow cron to run subman, which apparently doesn't have any execute bits set.
- 05:28 PM Revision 5b0abc54 (ceph): Add test for hadoop version 2.8.0
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 05:24 PM Revision c8177f0b (ceph): mon/PGMonitor: assert(format_version == 1)
- we have been PGMonitor's formart_version has been 1 since v0.67
(dumpling). so let's drop it.
Signed-off-by: Kefu Ch... - 05:16 PM Revision 983fe8ec (ceph): mon,mgr: std::move(osd_stat) when possible
- osd_stat_t could be a relatively large struct, so use std::move() when
possible
Signed-off-by: Kefu Chai <kchai@redh... - 05:07 PM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- But does this resolve the original issue of rados NOT giving error messages when space has been filled up? Or does ra...
- 03:17 PM Feature #16562 (Resolved): rados put: use the FULL_TRY flag to report errors when cluster is full
- 'rados rm' now has a --force-full option that lets deletes proceed.
- 05:01 PM Bug #17444 (Rejected): Data object missing xattr attrbutes on primary OSD will not be discovered ...
We've seen this before. If the OSD has the original unlinked file opened, it won't see the new one without the xat...- 04:08 PM Bug #17444: Data object missing xattr attrbutes on primary OSD will not be discovered by scrub/de...
- David, don't we checksum across all the metadata? Or is that a post-hammer bug?
- 04:38 PM Revision 773a3f3d (ceph): Merge pull request #15175 from cloudbau/update-rgw-docs
- doc: Update some RGW documentation
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 04:21 PM rgw Backport #17546 (Resolved): jewel: rgw: bucket resharding
- Fixed in https://github.com/ceph/ceph/pull/13341
- 04:17 PM Revision 959fc7cc (ceph): Set subman cron attributes in spec file
- Signed-off-by: Thomas Serlin <tserlin@redhat.com>
- 04:07 PM Revision 8c0b96c0 (ceph): Set subman cron attributes in spec file
- 04:06 PM Bug #16994 (Can't reproduce): "No package python-rados available" in upgrade:hammer-x-jewel-distr...
- 04:06 PM rgw Bug #16968 (Closed): synchonized bucket can't be used in other zonegroup
- 04:05 PM Bug #16965 (Can't reproduce): test time out in rados run
- 04:05 PM Bug #16953 (Resolved): hammer: ceph-disk prepare not working on el7 using dmcrypt
- This should be fixed in jewel. The changes were too large for backport to hammer.
- 04:03 PM Bug #16948 (Closed): filestore: fix skip omap clone in _collection_move_rename
- 04:03 PM Bug #16941 (Can't reproduce): "test_s3.test_list_buckets_invalid_auth ... FAIL" in smoke-master-d...
- 04:03 PM Bug #17552 (Can't reproduce): "ERROR: osd init failed" in upgrade:jewel-x-master-distro-basic-vps
- Permission error that we've only see once?
- 04:02 PM Bug #16913: multimds: OSD deep scrub failure
- Patrick, has this occurred again?
- 04:01 PM Bug #16910 (Closed): cluster takes 30 mins to detect node down and meanwhile rbd is unresponsive
- The 900 second timeout after a disk failure is from your 'mon osd report timeout' setting - perhaps the docs for that...
- 04:00 PM Bug #17565 (Resolved): mon/pgmap: DIRTY display "15E" when run command "ceph df detail"
- That PR was not involved but Sage did a bunch of fixes recently.
- 03:59 PM Bug #17578 (Closed): "[ FAILED ] LibRadosAio.TooBig " in upgrade:jewel-x-master-distro-basic-vps
- This looks like a one-off to me; it failed to connect to the cluster at all...
- 03:59 PM Bug #17587 (Resolved): Broken link on configuring ceph page for Cephx Authentication
- Resolved based on the linked commits.
- 03:58 PM Revision b758fa3c (ceph): mon/MonClient: drop unused param
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:58 PM Revision 83b9449c (ceph): mon/MonClient: cancel pending commands on shutdown
- Fixes: http://tracker.ceph.com/issues/20051
Signed-off-by: Sage Weil <sage@redhat.com>
Signed-off-by: Kefu Chai <kcha... - 03:51 PM CephFS Bug #20040 (Resolved): "terminate called after throwing an instance of 'std::out_of_range'" in po...
- 03:50 PM Revision 9dd2bc89 (ceph): Merge pull request #15213 from jcsp/wip-20040
- mon: fix accesing pending_fsmap from peon
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 03:50 PM Bug #17432 (Closed): CephFS - Bonnie++: Can't create file
- 03:49 PM CephFS Bug #19946 (Resolved): CInode.cc: 2481: FAILED assert(s == nested_auth_pins)
- 03:49 PM Revision 0f0fdeb1 (ceph): Merge pull request #15130 from ukernel/wip-19946
- mds: fix CDir::merge() for mds_debug_auth_pins
Reviewed-by: John Spray <john.spray@redhat.com> - 03:49 PM Bug #17431 (Resolved): RocksDBStore memory leak valgrind
- 03:48 PM Bug #17430 (Can't reproduce): rados -p rbd bench 15 write -b 4096 never completes
- no logs so it's hard to say what happened
- 03:48 PM Bug #18251 (Closed): There are some scrub errors after reset a node.
- 03:48 PM Bug #16897 (Can't reproduce): Multiple BlueFS crash during replay
- 03:48 PM Bug #18305: ceph-osd systemd unit files incomplete
- Loic, is this still a thing or did it get resolved in some of the other changes?
- 03:47 PM Bug #17428: systemd: Incorrect path to ceph-osd-prestart.sh in ceph-osd@.service on gentoo
- on gentoo everything is installed via 'make install', right?
- 03:45 PM Bug #17421 (Won't Fix): dmcrypt is broken when passing a data-dir
- dmcrypt requires a raw block device.
- 03:45 PM Bug #17419 (Can't reproduce): mon/crush_ops.sh fails with status 1
- 03:44 PM RADOS Bug #16890 (Fix Under Review): rbd diff outputs nothing when the image is layered and with a writ...
- 03:44 PM Bug #17418 (Duplicate): assert len(inactive) == num_inactive
- 03:43 PM RADOS Feature #16883: omap not supported by ec pools
- This is due to erasure coded pools not supporting omap operations. It's a limitation for the current cache pool code,...
- 03:42 PM Bug #17413 (Closed): objecter read request stuck for 2 days from OSD
- The helpful piece of info here would have been teh output from 'ceph daemon osd.nnn ops' (for the osd where the reque...
- 03:42 PM CephFS Bug #19892 (Resolved): Test failure: test_purge_queue_op_rate fails
- 03:41 PM Revision ef9d5559 (ceph): Merge pull request #15105 from ukernel/wip-19892
- qa/cephfs: disable mds_bal_frag for TestStrays.test_purge_queue_op_rate
Reviewed-by: John Spray <john.spray@redhat.com> - 03:41 PM Bug #16852 (Can't reproduce): "FAILED assert(m_total_bytes >= bl_old.length())" in rados run
- 03:41 PM Bug #16851 (Can't reproduce): "[ FAILED ] CReadOpsTest.Omap" in rados run
- 03:40 PM Revision ee753188 (ceph): Merge pull request #15122 from batrick/test-fragment-error
- qa: fix float parse error in test_fragment
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Kefu Chai <k... - 03:40 PM Bug #17739 (Closed): "Command failed on vpm031 with status 132: 'sudo MALLOC_CHECK_=3" in smoke
- Given the lack of repetition I think this must have been a hardware failure.
- 03:40 PM Bug #16849 (Can't reproduce): "MaxWhileTries: 'check health'" timed out in smoke-master-distro-ba...
- 03:40 PM Bug #17412 (Duplicate): Applying ruleset halts monitor
- 03:39 PM Bug #16846 (Resolved): Website ceph.com/get does not point to Jewel
- 03:39 PM rgw Bug #20073 (New): valgrind failures jewel: possible memory corruption in StreamRWReq::get_resource
- seen at http://pulpito.ceph.com/abhi-2017-05-23_12:16:16-rgw-wip-jewel-backports-mon-sortbitwise-distro-basic-smithi/...
- 03:39 PM Bug #16821 (Can't reproduce): s3tests' request time out (adjust the test ?)
- 03:38 PM Bug #17411 (Resolved): Wierd deadlock in OSD
- 03:38 PM Bug #17751: "[ FAILED ] LibRadosMisc.WriteSame" in pgrade:jewel-x-master-distro-basic-vps
- 95 is EOPNOTSUPP. I think this must have been an issue with invoking it against a pre-upgraded OSD.
- 03:37 PM Revision 6ca92c50 (ceph): Merge pull request #15106 from ukernel/wip-export-pin-cleanup
- ceph: simplify CInode::maybe_export_pin()
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 03:37 PM Revision db6890e2 (ceph): Merge pull request #15129 from ukernel/wip-mds-standby-for-rank
- mon/MDSMonitor: respect mds_standby_for_rank config
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 03:36 PM Bug #17389 (Can't reproduce): build failure
- are you on a non-x86 architecture? we haven't seen this (recently, at least!). please reopen if this is still a pro...
- 03:35 PM Tasks #17759: test radosgw with messenger failure injection and very short logs (osd min pg log e...
- Thanks Tamil.
- 03:35 PM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- Zheng -- should we backport this? What will happen to old clients trying to access MDSs using the new behaviour?
- 03:35 PM Bug #16802 (Can't reproduce): "AttributeError: managers" when running a rados qa suite
- This error is usually due to a bug in the suite - it's missing a 'ceph' task
- 03:34 PM Bug #17366 (Pending Backport): "assert len(unclean) == num_unclean" in dump_stuck.py in rados suite
- fixed by dd70a93181d15ffd56ce6a8330ae725a6ddd72aa
- 03:34 PM Revision 4f5d7aaf (ceph): Merge pull request #15131 from ukernel/wip-19955
- mds: limit client writable range increment
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: John Spray <john.sp... - 03:34 PM Bug #17772 (Closed): journal on ramdisk fails ceph-osd --mkfs
- I think this is a feature. People who want to test for speed purposes can hack around it. :)
- 03:33 PM Bug #17266 (Closed): virtualenv default paths not uniquely named
- 03:33 PM Bug #16781 (Can't reproduce): "Error: Failed to add partition" in ceph-disk-jewel-distro-basic-mira
- 03:32 PM Bug #17258 (Can't reproduce): lost-unfound-upgrade.yaml times out in rados qa run
- 03:32 PM Bug #16777 (Resolved): the recovering can lead some osds to reach 100% space usage.
- https://github.com/ceph/ceph/pull/13968
- 03:32 PM Bug #17778 (Closed): notional amount of data stored is greater than actual data in the cluster.
- I think this must be the result of using sparse objects and the way we count them.
- 03:31 PM Bug #17228 (Need More Info): Hammer OSD memory use very high (EL6)
- 03:31 PM Bug #17228: Hammer OSD memory use very high (EL6)
- Just saw this. Is this still a problem? Can you attach "ceph osd dump" output? Are you using and erasure coding pool?
- 03:31 PM Bug #17190 (Duplicate): ceph mon remove jam
- duplicated by http://tracker.ceph.com/issues/17725, and fixed by c9d46cfbf2512bc3495c6901de2b8f711bef9bae
- 03:30 PM Bug #16772 (Can't reproduce): seg fault in unittest_async_compressor during "make check" run
- 03:30 PM Bug #16763 (Resolved): rados --striper put failes when object size is 0 bytes
- this works in master
- 03:28 PM Bug #17226 (Rejected): Osd assert failed after large amount of write
- [392837.216467] INFO: task ceph-osd:11765 blocked for more than 120 seconds.
suggests it's a kernel issue. - 03:28 PM Bug #17807 (Closed): async messenger should rebind using the new nonce
- I think this was a thing from the FreeBSD port, but AFAIK that's going fine now so this must have been resolved. Poke...
- 03:28 PM Bug #16725 (Can't reproduce): "cephtool/test.sh) ... with status 22" failure in rados run
- 03:27 PM Bug #16749 (Won't Fix): Ceph filestore statfs assert and osd core dump
- This looks like a configuration issue where the statfs call or access to the disk wasn't allowed for your container.
- 03:26 PM Bug #17810 (Closed): "Command failed..: "sudo yum -y install '' libcephfs1-devel"" in upgrade:cli...
- Given this hasn't reproduced I assume it was a transient packaging failure.
- 03:26 PM Bug #17811 (Resolved): "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrade-jewel-...
- https://github.com/ceph/ceph-qa-suite/pull/1296
- 03:26 PM Bug #17174 (Rejected): Watcher not removed on host reboot
- 03:25 PM RADOS Bug #17170 (Can't reproduce): mon/monclient: update "unable to obtain rotating service keys when ...
- 03:25 PM Bug #17133 (Can't reproduce): rgw
- 03:24 PM Bug #17132 (Resolved): Clang: Naming conflic between math log() and namespace log
- 03:24 PM Bug #17117 (Can't reproduce): "FAILED assert(lock.is_locked())" in rados run
- 03:24 PM Bug #16692 (Duplicate): deep-scrub Error EAGAIN in cephmanager task in rados run
- 03:23 PM Bug #16723 (Can't reproduce): "TestIoctx.test_aio_read ... FAIL" in rados run
- 03:22 PM RADOS Bug #17929: rados tool should bail out if you combine listing and setting the snap ID
- There is discussion on that (closed) PR. We just don't want to do snap listing as it's even more expensive than norma...
- 03:22 PM Bug #16683 (Can't reproduce): dead job at "injecting socket failure" in rados run
- 03:22 PM Bug #16674 (Need More Info): SELinux is preventing /usr/bin/ceph-osd from read access on the file...
- Boris, is this still an issue?
- 03:21 PM Bug #16671 (Resolved): "ceph df"object num is negative
- There have been a few fixes to the stats that should fix this case too. Please reopen if you have a case with negativ...
- 03:20 PM Bug #17940 (Closed): Job(s) fail on vps and pass on smithi
- If there are specific tests not passing on VPS, we need to bugs for each test since the correct fix will be different...
- 03:17 PM Bug #17104 (Resolved): ceph kraken build failure for ppc64/ppc64le as PERF_LOCAL_FLAGS not defined
- 03:17 PM Bug #17039 (Can't reproduce): osd crash when generate past interval
- I think this has been fixed.
- 03:15 PM Bug #17002 (Won't Fix): pg marked as incomplete during cluster rebalance
- Thanks for your detailed account! This is a known bug on hammer (known in that it happens sometimes; the cause is no...
- 03:15 PM Bug #16508 (Won't Fix): osd thrasher pg export/import may skip over pg split epoch
- Doesn't seem worth trying to fix at the thrashosds layer - having facets that don't use ceph-objectstore-tool would g...
- 03:14 PM Bug #17955 (Resolved): rados/test_pool_quota.sh fails in hammer integration branch (0.94.10 prepa...
- I guess this is working now?
- 03:13 PM Revision 8535249b (ceph): Merge pull request #15198 from renhwztetecs/renhw-wip-client-inode
- client/inode: fix the dump type of Inode::dump()
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 03:13 PM RADOS Bug #17968 (Need More Info): Ceph:OSD can't finish recovery+backfill process due to assertion fai...
- 03:13 PM RADOS Bug #17968 (Can't reproduce): Ceph:OSD can't finish recovery+backfill process due to assertion fa...
- 02:51 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- Sage Weil wrote:
> just saw this on smithi081, which had 2.4-0ubuntu5, but apt update + apt install libgoogle-perfto... - 02:46 AM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- just saw this on smithi081, which had 2.4-0ubuntu5, but apt update + apt install libgoogle-perftools4 upgraded to 2.4...
- 02:26 PM CephFS Bug #20072 (Resolved): TestStrays.test_snapshot_remove doesn't handle head whiteout in pgls results
It's possible this was always the case but we only just happened to see it affect a test?
The CephFS test TestSt...- 02:01 PM Revision 5f53346d (ceph): os/bluestore: fix false assertion
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 01:56 PM Revision 3cd35b9f (ceph): os/bluestore: wrap IOContext::aio_wake with additional stuff to remove ...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 01:48 PM Revision 81e35b94 (ceph): qa/suites/rados/singleton-nomsgr/*: set sortbitwise after upgrade
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:43 PM Revision da7a99f5 (ceph): Merge pull request #15264 from xiexingguo/wip-kill-typo
- os/bluestore/KernelDevice: fix comments
Reviewed-by: Sage Weil <sage@redhat.com> - 01:41 PM CephFS Bug #20060 (Fix Under Review): segmentation fault in _do_cap_update
- Yes, seems to be.
- 08:50 AM CephFS Bug #20060: segmentation fault in _do_cap_update
- please use gdb to which code triggered segfault
probably fixed by https://github.com/ceph/ceph/pull/15125/commits/... - 12:57 PM rgw Bug #20071 (Resolved): wrong object size after copy of uncompressed multipart objects
- when compression is disabled, the object's accounted_size is set to the head object's size, rather than the size from...
- 12:05 PM RADOS Bug #20068 (In Progress): osd valgrind error in CrushWrapper::has_incompat_choose_args
- 10:34 AM RADOS Bug #20068: osd valgrind error in CrushWrapper::has_incompat_choose_args
- Oops, left off the actual link:
http://pulpito.ceph.com/jspray-2017-05-23_22:31:39-fs-master-distro-basic-smithi/122... - 10:33 AM RADOS Bug #20068 (Resolved): osd valgrind error in CrushWrapper::has_incompat_choose_args
- Loic: assigning to you because it looks like you were working in this function recently....
- 11:52 AM rbd Feature #20070 (Rejected): [qemu] implement bdrv_co_write_zeroes via discard
- 10:47 AM RADOS Bug #20069 (New): PGs failing to create at start of test, REQUIRE_LUMINOUS not set?
- http://pulpito.ceph.com/jspray-2017-05-23_22:31:39-fs-master-distro-basic-smithi/1222407...
- 10:41 AM Revision cc7dea59 (ceph): Merge pull request #15266 from ztczll/master
- test:Check make_writeable() return value
- 09:22 AM Revision 0bcb3d2f (ceph): test/:Check make_writeable return value
- Signed-off-by: zhanglei <243290414@qq.com>
- 09:15 AM Revision ba3d6b48 (ceph): os/bluestore/KernelDevice: fix comments
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:12 AM Revision ba3fd506 (ceph): mds: match EMetaBlob::add_dir_context with MDCache::create_subtree_map
- In EMetaBlob::add_dir_context(), the code that checks if a subtree
was journaled in the latest ESubtreeMap is differe... - 09:10 AM Revision cc6a9c8f (ceph): osd: Preserve OSDOp information for historic ops
- clear_buffers() actually clears all OSDOp informations, so that we can
only see empty ops with `dump_historic_ops`. T... - 08:52 AM RADOS Bug #19790: rados ls on pool with no access returns no error
- For what it's worth, this is a regression. In Hammer, the appropriate EPERM is raised:...
- 08:36 AM Revision 73a08e03 (ceph): mds: avoid sending duplicated cache rejoin ack
- Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
- 08:36 AM Revision 22369f44 (ceph): mds: properly update subtree map when merging dirfrags
- After introducing auxiliary subtree, the source dirfrags for merging
can be mixed with subtree dirfrags and non-subtr... - 08:36 AM Revision 2fa16d01 (ceph): mds: fix MDCache::trim_non_auth()
- After introducing the bottom_lru, "stop when we see a dentry the
second time" no longer works.
Signed-off-by: "Yan,... - 08:27 AM rgw Bug #16888: [multisite] operating bucket's acl&cors is not restricted on slave zone
- cors should be forward to master
https://github.com/ceph/ceph/pull/15260 - 06:58 AM Bug #20067 (Resolved): assert in OSDMonitor::update_creating_pgs()
- ...
- 06:57 AM Revision 1d74182a (ceph): Merge pull request #15206 from ifed01/wip-fix-rbd-bench
- rbd/bench: fix write gaps when doing sequential writes with io-threads > 1
Reviewed-by: Jason Dillaman <dillaman@red... - 06:46 AM Revision ebcd0dcd (ceph): rgw: fix radosgw-admin bucket_stats retcode
- should check RGWBucketAdminOp::info retcode
Signed-off-by: Shasha Lu <lu.shasha@eisoo.com> - 06:15 AM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- Actually there's a PrimaryLogPG::on_change and a PGBackend::on_change, they are distinct, and the PrimaryLogPG one is...
- 05:30 AM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- So, we identified today that it looks like the op Backoff code may have an issue with holding PGRefs past when we exp...
- 05:41 AM Revision 01865a10 (ceph): rgw: display more info when use bucket stats
- display the zonegroup uuid and placement rule of bucket, when using radosgw-admin bucket stats
Signed-off-by: fang y... - 05:24 AM Revision 36b993bb (ceph): pybind/mgr/fsstatus: use mds_mem.dn as dentry counter
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 04:25 AM Revision 7f7ae7ac (ceph): pybind/ceph_daemon.py: fix Termsize.update
- it's a regression introduced by 84f9c12
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:11 AM Revision eb5c02df (ceph): mgr: Mark session connections down on shutdown
- Also assert in OSD::ms_get_authorizer since it is dangerous to proceed
if we are shutting down.
Fixes: http://tracke... - 03:39 AM Revision 41618d8a (ceph): osdc/Journaler: use waitfor_safe map to find journal entry boundaries
- Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
- 03:36 AM Revision 6511e7a9 (ceph): osdc/Journaler: avoid executing on_safe contexts prematurely
- Journaler::_do_flush() can skip flushing some data when prezered
journal space isn't enough. Before updating Journale... - 03:29 AM Revision 77fbfc29 (ceph): denc: add need_contiguous to denc_traits
- so the decode() will not try to copy the bufferlist for a continous one
if the bufferlist is segmented *and* its leng... - 03:14 AM rgw Bug #20066 (New): rgw_admin:change the owner of a bucket, and the stats don't decline from the ol...
- when the bucket is unlinked, the stats don't decline from the old user.
- 03:08 AM Revision ba3e590f (ceph): Merge pull request #15238 from xiexingguo/wip-fix-blue-mkfs
- os/bluestore: write "mkfs_done" into disk only if we pass fsck() tests
Reviewed-by: Sage Weil <sage@redhat.com> - 03:08 AM Revision 2ebd3e8d (ceph): Merge pull request #15228 from chardan/jfw-wip-halflife_atomic_t-filestore
- filestore: migrate atomic_t to std::atomic<>
Reviewed-by: Sage Weil <sage@redhat.com> - 02:53 AM Revision 5ab996ab (ceph): qa/tasks/ceph_manager: 'ceph $service tell ...' is obsolete
- This died forever ago; no need for the fallback here.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:49 AM Revision 0aa04f52 (ceph): Merge pull request #9307 from cxwshawn/wip-tc7-fix
- crush: optimize header file dependency
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 02:49 AM Revision ff043152 (ceph): Merge pull request #14035 from liewegas/wip-bluestore-kv-finisher
- os/bluestore: separate kv_sync_thread into two parts
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Reviewed-by: ... - 02:48 AM Revision e8fd9867 (ceph): Merge pull request #14176 from LiumxNL/wip-170321
- mon: show io status quickly if no update in a long period
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:48 AM Revision f58ea041 (ceph): Merge pull request #15169 from joscollin/wip-cleanup-redundant-headers-2
- common: Remove redundant includes - 2
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 02:48 AM Revision 1f5c50aa (ceph): Merge pull request #15177 from liewegas/wip-bluestore-nonexperimental
- os: remove experimental status for BlueStore
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:47 AM Revision 9d51ab5b (ceph): Merge pull request #15244 from liewegas/wip-crush-features
- crush/CrushWrapper: fix has_incompat_choose_args()
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 02:47 AM Bug #20058 (Resolved): 'ceph pg dump sum -f json-pretty | grep num_legacy_snapsets | ...' fails
- 02:47 AM Revision 10a88f1c (ceph): Merge pull request #15245 from liewegas/wip-20058
- qa/suites/rados/*/at-end: wait for healthy before scrubbing
- 02:42 AM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-23_19:52:01-rados-wip-sage-testing2---basic-smithi/1221342
- 02:35 AM Messengers Bug #18351: msg/DispatchQueue.h: 228: FAILED assert(mqueue.empty())
- ...
- 01:23 AM Revision 95fc248c (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 01:17 AM Revision 5e9b4323 (ceph): osd: add the RWORDERED flag when the client need it
- Signed-off-by: Myoungwon Oh omwmw@sk.com
Signed-off-by: Sage Weil sage@redhat.com - 01:04 AM Revision 7868a18e (ceph): rgw: use get_data_extra_pool() when get data extra pool from RGWZonePla...
- use member data_extra_pool of RGWZonePlacementInfo isn't properly, because it maybe not configured.
Fixes: http://tr...
05/23/2017
- 11:38 PM Revision c59cfff6 (ceph): Merge pull request #15190 from tchaikov/wip-ceph-term-width
- ceph.in: adjust usage width according to user's tty
Reviewed-by: Dan Mick <dmick@redhat.com> - 11:23 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- OK Eric, sounds good. I will get a patch done and submit it ASAP.
- 10:35 PM Revision 69175515 (ceph): osd/OSDMap.cc: check if osd is out in subtree_type_is_down
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 10:30 PM Revision 761735a2 (ceph): filter -pthread
- Get confused for a yasm option
Signed-off-by: Alessandro Barbieri <ale.barbio@alice.it> - 10:18 PM rgw Bug #19956: radosgw Segmentation fault when service is restarted during lifecycle processing
- ...
- 09:18 PM rgw Bug #19956: radosgw Segmentation fault when service is restarted during lifecycle processing
- I got a coredump + symbols for this. let me know if you want the dump, here is the stack with full symbols:
#0 0x... - 10:05 PM rgw Bug #20047: rgw_file: unlink assert unsafe in multi-gateway environments
- PR to master: https://github.com/ceph/ceph/pull/15216
- 06:30 PM rgw Bug #20047 (Pending Backport): rgw_file: unlink assert unsafe in multi-gateway environments
- 09:56 PM Revision e03edc58 (ceph): osdmaptool: require --upmap-save before modifying input osdmap
- IMO it is dangerous to modify the provided osdmap in this case unless the
user explicitly asks for it. This was supe... - 08:52 PM Revision 415bef08 (ceph): rgw_file: release rgw_fh lock and ref on ENOTEMPTY
- An early return in new unlink bucket num_entries check was
missing a conditional unlock and unref.
Fixes: http://tra... - 08:51 PM Revision f9f09b0b (ceph): rgw_file: remove post-unlink lookup check
- This could induce asserts in multi-nfs-gateway scenarios.
Fixes: http://tracker.ceph.com/issues/20047
Resolves: rhbz... - 08:47 PM Revision 9f8f0d75 (ceph): Merge pull request #15246 from linuxbox2/wip-unlink-safe
- rgw_file: release rgw_fh lock and ref on ENOTEMPTY
- 08:45 PM rgw Bug #20064 (Resolved): allow empty data_extra_pool in zone placement
- RGWZoneParams::get_head_data_pool() and rgw_get_obj_data_pool() both use placement.data_extra_pool directly instead o...
- 08:37 PM Bug #20043 (Resolved): "** ERROR: osd init failed" in rados
- 08:37 PM Bug #19935 (Resolved): scrub test should not be run with d-luminous/at-end
- 08:37 PM Revision 88776b9c (ceph): Merge pull request #15202 from liewegas/wip-19935
- qa/suites/rados: temporarily remove scrub_test from basic/ until post-luminous
- 08:36 PM Revision 0e03c189 (ceph): Merge pull request #15207 from liewegas/wip-20043
- qa/suites/rados/singleton-nomsg/health-warnings: behave on ext4
- 08:36 PM Revision 27f71466 (ceph): Merge pull request #15092 from yuyuyu101/wip-msgr-writelock
- msg/async: reduce write_lock contention
Reviewed-by: Sage Weil <sage@redhat.com> - 08:35 PM Revision fea1f930 (ceph): Merge pull request #15172 from badone/wip-erasure-code-optimize-header-...
- erasure-code: optimize header file dependency
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil <sage... - 08:34 PM Revision aaaf48cb (ceph): Merge pull request #15187 from badone/wip-compressor-optimize-header-fi...
- compressor: optimize header file dependency
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:33 PM Bug #19990: EAGAIN: osd.4 is not up from rados/singleton-nomsgr/{all/health-warnings.yaml rados.y...
- merged
- 08:33 PM Revision 6b7d4db8 (ceph): Merge pull request #15201 from liewegas/wip-19990
- qa/workunits/rados/test_health_warning: misc fixes
Reviewed-by: Neha Ojha <nojha@redhat.com> - 08:25 PM Feature #19657 (In Progress): An EIO from a single device should not be a client-visible failure.
- 08:24 PM RADOS Bug #18165 (In Progress): OSD crash with osd/ReplicatedPG.cc: 8485: FAILED assert(is_backfill_tar...
- 08:22 PM Bug #20063 (Resolved): mgr: cluster log messages appear as 'client.x' instead of 'mgr.name'
- The problem is LogEntry has an entity_name_t instead of an EntityName. Mons also log as mon.nnn instead of mon.foo. ...
- 08:18 PM Revision 62c8dbcf (ceph): Merge pull request #15098 from cbodley/wip-rgw-default-frontend
- rgw: remove fastcgi from default rgw frontends
Reviewed-by: Sage Weil <sage@redhat.com> - 08:06 PM Bug #20062 (Resolved): msg/async/AsyncConnection.cc: 2525: FAILED assert(last_tick_id == id)
- on bigbang,...
- 07:51 PM Bug #20057: ceph-osd: some flags are not documented in the help output
- Similar issue with the man page, in #19879
- 05:23 PM Bug #20057 (New): ceph-osd: some flags are not documented in the help output
- I was trying to find about a few options on some flags I saw while deploying an OSD and they didn't come up when runn...
- 07:44 PM Revision 51c25593 (ceph): rgw_file: release rgw_fh lock and ref on ENOTEMPTY
- An early return in new unlink bucket num_entries check was
missing a conditional unlock and unref.
Fixes: http://tra... - 07:37 PM RADOS Bug #19790: rados ls on pool with no access returns no error
- Well, it's obvious enough, we go into PrimaryLogPG::do_pg_op() before we check op_has_sufficient_caps().
I think t... - 07:37 PM Bug #16259 (Duplicate): ceph osd processes crashes when doing a revert on unfound object
- 07:26 PM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- Oh, that's just what happens on peering until you commit something to the PG or make progress in backfill/logging. Ne...
- 07:22 PM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- I'm starting to think the leak is in peering now. All of them (except Casey's top one, which I didn't check and is ab...
- 01:41 AM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- I'm not sure these are actually the same bug. Sage's involves snaptrimming, but the others have no mention of it in t...
- 01:26 AM Bug #19931 (In Progress): osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X ha...
- Actually, this doesn't seem to be the issue. There's a race present but it's pretty narrow since we were already havi...
- 12:13 AM Bug #19931 (Fix Under Review): osds abort on shutdown with assert(peering_queue.empty()) or 'pgid...
- https://github.com/ceph/ceph/pull/15214
- 07:08 PM rgw Bug #20061 (Resolved): rgw_file: attempt to unlink non-empty bucket could lead to hang
- An early return in new unlink bucket num_entries check is
missing a conditional unlock and unref. - 07:05 PM CephFS Bug #20060: segmentation fault in _do_cap_update
- Full MDS log: https://www.dropbox.com/s/vfdqlqnyrjo4do6/mds.b.log.bz2
- 06:58 PM CephFS Bug #20060 (Resolved): segmentation fault in _do_cap_update
- ...
- 07:01 PM CephFS Bug #19969 (Resolved): CDir.cc: 909: FAILED assert(get_num_ref() == (state_test(STATE_STICKY) ? 1...
- 06:57 PM RADOS Bug #20059 (Resolved): miscounting degraded objects
- on bigbang,...
- 06:29 PM Revision 344135f2 (ceph): Merge pull request #15216 from linuxbox2/wip-rgw-file-unlink
- rgw_file: remove post-unlink lookup check
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:16 PM Revision e283924d (ceph): Merge pull request #15179 from liewegas/wip-fix-osd-health
- mon: fix a few bugs with the osd health reporting
Reviewed-by: Neha Ojha <nojha@redhat.com> - 06:15 PM Revision bac8e45f (ceph): Merge pull request #15188 from ShiqiCooperation/master
- mon: delete useless function definition
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:15 PM Revision 65b144d9 (ceph): Merge pull request #15204 from joscollin/wip-cleanup-redundant-headers-3
- common: Remove redundant includes - 3
- 06:14 PM Bug #19595: mgr: segv in msgr thread, with no core
- /a/sage-2017-05-23_06:26:57-rados-wip-sage-testing---basic-smithi/1220932
- 06:13 PM Bug #19948: LibRadosTwoPools[EC]PP.PromoteSnap
- /a/sage-2017-05-23_06:26:57-rados-wip-sage-testing---basic-smithi/1220717
- 06:12 PM Bug #20056 (Closed): ceph-osd: Permission Denied when reading a monmap
- Further digging this with Dan, we tried getting permissions up to the directory:...
- 05:04 PM Bug #20056 (Closed): ceph-osd: Permission Denied when reading a monmap
- I am trying to manually deploy an OSD, and regardless of the ownership or permissions for the 'activate.monmap' file ...
- 06:12 PM Bug #20058 (Fix Under Review): 'ceph pg dump sum -f json-pretty | grep num_legacy_snapsets | ...'...
- https://github.com/ceph/ceph/pull/15245
- 06:09 PM Bug #20058 (Resolved): 'ceph pg dump sum -f json-pretty | grep num_legacy_snapsets | ...' fails
- ...
- 06:12 PM Revision ce654c51 (ceph): qa/suites/rados/*/at-end: wait for healthy before scrubbing
- The scrub_pgs command also waits for healthy for a while, but fails
silently if it times out, which means the subsequ... - 05:55 PM rgw Fix #19732 (Pending Backport): fix: rgw crashed caused by shard id out of range when listing data...
- 05:54 PM Revision 2dc58597 (ceph): Merge pull request #14389 from mingshuaiwang/master
- rgw: segment fault when shard id out of range
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 05:54 PM rgw Bug #19978 (Pending Backport): rgw: 'gc list --include-all' command infinite loop the first 1000 ...
- 05:52 PM Revision 02477700 (ceph): Merge pull request #12774 from shashalu/gc-list
- rgw: fix 'gc list --include-all' command infinite loop the first items
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 05:50 PM Revision ddf0bb88 (ceph): crush/CrushWrapper: fix has_incompat_choose_args()
- Special case empty and return false. Otherwise the rest of the method
will dereference an invalid iterator on an emp... - 05:14 PM CephFS Bug #19706: Laggy mon daemons causing MDS failover (symptom: failed to set counters on mds daemon...
- The issue is that we're getting nice regular tick() calls even when we're not readable, so the code in ::tick to rese...
- 10:53 AM CephFS Bug #19706: Laggy mon daemons causing MDS failover (symptom: failed to set counters on mds daemon...
- Another one here, easily identifiable from teuthology log:...
- 04:44 PM Bug #20049: msg: libraries are binding to incorrect client address
- I guess https://github.com/ceph/ceph/pull/7256 could give a more precise description about the fix.
I propose a pu... - 04:28 PM Bug #20049: msg: libraries are binding to incorrect client address
- @Haomai: I don't really understand why we would want clients to implicitly bind to a learned address. I am using that...
- 04:16 PM Bug #20049: msg: libraries are binding to incorrect client address
- do you think set "ms_bind_before_connect = false" is the expected solution?
- 03:00 AM Bug #20049 (Closed): msg: libraries are binding to incorrect client address
- librados clients running within a VM with QEMU user networking (e.g. ip address 10.0.2.15) are incorrectly attempting...
- 04:41 PM Revision a2571dc4 (ceph): msg: don't set msgr addr when disabing client bind
- if disabling client bind, client side will send handshake message with blank
ip. so the server side will ignore this.... - 04:14 PM Revision eded0c11 (ceph): Merge pull request #15242 from liupan1111/wip-fix-msg
- msg/async: Lower down the AsyncMessenger's standby warning from debug
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:06 PM Revision ae19a960 (ceph): Merge pull request #15218 from liewegas/wip-crush-features
- crush/CrushWrapper: fix has_incompat_choose_args
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 03:58 PM Revision 5731e5fa (ceph): include/denc: templatize denc() for integer types
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:56 PM Bug #19941: ceph-disk fails if OSD udev rule triggers prior to mount of /var
- -Fix proposed via: https://github.com/ceph/ceph/pull/15241-
- 03:15 PM Revision c53d949e (ceph): msg/async: Lower down the AsyncMessenger's standby warning from debug
- level 0 to 10.
Signed-off-by: Pan Liu <wanjun.lp@alibaba-inc.com> - 02:56 PM Revision 9a10c5c7 (ceph): doc: doc/architecture.rst: unify initial caps in term Ceph Monitor
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 02:56 PM Revision d54d8095 (ceph): doc: fix factual inaccuracy in doc/architecture.rst
- Signed-off-by: Sage Weil <sage@redhat.com>
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 02:19 PM Revision 58291dd6 (ceph): os/bluestore: save "mkfs_done" only if we pass fsck() tests
- In our local test bed, we found mkfs() sometimes can fail
due to errors discovered by fsck(), and is therefore unreco... - 02:04 PM Revision ec2e6931 (ceph): msg/async/rdma: Use RDMA resources only after fork
- Thanks to previous patch [1], no need to access RDMA resources before
the fork. Initialize Infiniband class only befo... - 02:04 PM Revision e94ba0d2 (ceph): msg/async: Postpone bind if network stack is not ready
- RDMAStack shouldn't access hardware from the parent process.
The only reason to do so, is because bind is called befo... - 02:04 PM Revision fd14e71a (ceph): Revert "msg/async/rdma: Introduce Device.{cc,h}"
- This reverts commit d930a3db13d4a5f9ab408faae7cdc237d20466f2.
Change-Id: Ib55ff961af125be5800ea90b2cce6588e3122f4d
I... - 02:04 PM Revision 8a83ccd8 (ceph): Revert "msg/async/rdma: Move resource handling to Device"
- This reverts commit 9cba3b36ef90a1f3d5d474f0fefe48e9c7ec6bad.
Change-Id: I5953a9380ecd5a07e8ea107cf1fc35d0772e8f61
I... - 02:04 PM Revision c4d8c2c6 (ceph): Revert "msg/async/rdma: Move async event handling to Device"
- This reverts commit 4b10ba7578b5d378edf715711bbf222dfe41b91d.
Change-Id: I9a294890c1cf01461356d87491bfa5e954b42444
I... - 02:04 PM Revision 7072db45 (ceph): Revert "msg/async/rdma: Initialize device on first connect"
- This reverts commit 94eddb1ec53205e3e1b21033a9b841c4a72d7a77.
Change-Id: Ia16384eaed1295af6a4352e03308bc13bfb2f6d2
I... - 02:04 PM Revision a8e9ceda (ceph): Revert "msg/async/rdma: Extract sockets stuff from RDMAStack.h"
- This reverts commit 1890e924ca417c78c023f0a798ece8c3ea759413.
Change-Id: I66a33e55206b3f8f8c85d1f1ee1a2e85e3c2a3ad
I... - 02:04 PM Revision a0e06932 (ceph): Revert "msg/async/rdma: Introduce RDMAConnMgr"
- This reverts commit 91bb13dceddb433966e6f775716e53ec5f523f5e.
Change-Id: I91dbe3c02651402f0e97e89151ec6a5154afdca3
I... - 02:04 PM Revision 0df946d3 (ceph): Revert "msg/async/rdma: Debug prints for ibv_*"
- This reverts commit 7d1475f6274531988854cf62f6056f9cfd13ff29.
Change-Id: Ieae3ea07f4e40d4558332e15fe6fbfcd22e0553e
I... - 02:04 PM Revision 904d78af (ceph): Revert "Revert "msg/async/rdma: Debug prints for ibv_*""
- This reverts commit 7e0f0748ef59842e329aa845baf153e812349450.
Change-Id: Iaccdd1739647a82aeafeff3ab46ed9f4d3fe0782
I... - 02:04 PM Revision ff8a0b68 (ceph): Revert "msg/async/rdma: Debug prints for ibv_*"
- This reverts commit 42078045bc935122f939b71020bf3c66d7cef051.
Change-Id: If3a7b236636af0492bbe3576d25042b7a4dbf762
I... - 02:04 PM Revision fb0d8ccc (ceph): Revert "msg/async/rdma: Device::last_poll_dev must be positive"
- This reverts commit fb7787dd58988fcf0e36f0b4155d707fd77b6a71.
Change-Id: I42d47cd683bd69ac2ebac1a6379a1ee0f2c1d543
I... - 02:04 PM Revision 26af15f3 (ceph): Revert "msg/async/rdma: Fix small memory leaks detected by valgrind"
- This reverts commit 23fd3efaafd4b4034bded605c88b57932b06646f.
Change-Id: Id04d88f4d08174632271c6eb224212155e0a4a38
I... - 02:04 PM Revision 9a4ee00e (ceph): Revert "msg/async/rdma: Make port number an attribute of the Connection...
- This reverts commit af2f1ecd2700ef3fad7e7d16d61f8ee86794b3ae.
Change-Id: I40f1da9da613dfb90aa8f09073c70ebb30b59aa1
I... - 02:04 PM Revision 83205b30 (ceph): Revert "msg/async/rdma: Make poll_blocking() poll for async events in a...
- This reverts commit 2386cea1eb31bec9ec49eafa0135eff82bbe696c.
Change-Id: I93a23f216cd4ce55051b125e9dd7edb3e297aaad
I... - 02:04 PM Revision 9cd30c3c (ceph): Revert "msg/async/rdma: Pass specific ConnMgr info in constructor"
- This reverts commit ce4677612fdabab6e762cf0cd21914be438ce8e1.
Change-Id: I5098c109e7be17402ca512c25ba0c250ad610cea
I... - 02:04 PM Revision be76afe8 (ceph): Revert "msg/async/rdma: get_device() by ibv_context"
- This reverts commit f47025f83711d9af4a52470327fbd7411aafdafe.
Change-Id: Icc3667da1828868bc5001d1d8e8b2ec14e5f6c8e
I... - 02:04 PM Bug #20051 (Fix Under Review): mgr: crash in MetadataUpdate::finish
- https://github.com/ceph/ceph/pull/15227
- 07:01 AM Bug #20051: mgr: crash in MetadataUpdate::finish
- ...
- 03:52 AM Bug #20051 (Resolved): mgr: crash in MetadataUpdate::finish
- <pre
2017-05-23 04:10:15.731469 7f1579f6c700 10 mgr.server ms_handle_reset ms_handle_reset unregistering osd.5779 s... - 02:03 PM Revision 30b6fd99 (ceph): Revert "msg/async: Postpone bind if network stack is not ready"
- This reverts commit a5b87e2fb83adec2b0fe060d3b22acfb1b9db1ed.
Change-Id: Ia1bc0535636de27d599cfb2dc7be2a555e0a2cd7
I... - 02:03 PM Revision e5b9beaf (ceph): Revert "msg/async/rdma: Use RDMA resources only after fork"
- This reverts commit 972c7416deae2dd3a763643be6c9334d4edd1c17.
Change-Id: I4a5627ce02ef8e055c2088db41ac4897dd9a3425
I... - 02:00 PM CephFS Bug #20055 (Fix Under Review): Journaler may execute on_safe contexts prematurely
- https://github.com/ceph/ceph/pull/15240
- 01:45 PM CephFS Bug #20055 (Resolved): Journaler may execute on_safe contexts prematurely
- 01:57 PM Revision 8d85c52f (ceph): Merge pull request #14610 from jcsp/wip-17980
- #17980: MDS client blacklisting and blacklist on eviction
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 01:27 PM Revision 4f178b2a (ceph): rbd/bench: fixes write gaps when doing sequential writes with io-thread...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
Signed-off-by: Mykola Golub mgolub@mirantis.com - 01:22 PM rbd Bug #19962 (Fix Under Review): Discard related IO should skip op if object map marks object as no...
- PR: https://github.com/ceph/ceph/pull/15239
- 01:19 PM Revision 5da4ecb3 (ceph): librbd: discard related IO should skip op if object non-existent
- Fixes: http://tracker.ceph.com/issues/19962
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 12:37 PM Bug #20052 (Fix Under Review): build/ops: librbd1 %post script might run before coreutils package...
- https://github.com/ceph/ceph/pull/15231
- 09:35 AM Bug #20052 (Resolved): build/ops: librbd1 %post script might run before coreutils package is inst...
- Quoting from https://bugzilla.suse.com/show_bug.cgi?id=1040230
After I perform a standard installation that includ... - 12:14 PM Revision e875d7dd (ceph): Merge pull request #14550 from ukernel/wip-multimds-misc
- mds: miscellaneous multimds fixes
Reviewed-by: John Spray <john.spray@redhat.com> - 11:46 AM Backport #20035 (In Progress): kraken: mon: MAX AVAIL calcuation does not fact or in mon_osd_full...
- https://github.com/ceph/ceph/pull/15237
- 11:43 AM Revision 648c6adf (ceph): mon/PGMap: factor mon_osd_full_ratio into MAX AVAIL calc
- If we only fill OSDs to 95%, we should factor that into
the MAX AVAIL calculation for the pool.
Fixes: http://tracke... - 11:36 AM Backport #20036 (In Progress): jewel: mon: MAX AVAIL calcuation does not fact or in mon_osd_full_...
- https://github.com/ceph/ceph/pull/15236
- 10:48 AM Revision 328e2cc7 (ceph): mon/PGMap: factor mon_osd_full_ratio into MAX AVAIL calc
- If we only fill OSDs to 95%, we should factor that into
the MAX AVAIL calculation for the pool.
Fixes: http://tracke... - 10:47 AM rbd Bug #20054: librbd memory overhead when used with KVM
- Sorry, looks like I got some formatting issues there. Here again the overhead table:...
- 10:44 AM rbd Bug #20054 (Resolved): librbd memory overhead when used with KVM
- Hi,
we are running a jewel ceph cluster which serves RBD volumes for our KVM
virtual machines. Recently we noticed... - 10:17 AM rbd Bug #19832 (Fix Under Review): Potential IO hang if image is flattened while read request is in-f...
- PR: https://github.com/ceph/ceph/pull/15234
- 10:07 AM Revision 10d58618 (ceph): librbd: potential read IO hang when image is flattened
- Fixes: http://tracker.ceph.com/issues/19832
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 09:50 AM RADOS Bug #20053 (New): crush compile / decompile looses precision on weight
- The weight of an item is displayed with %.3f and looses precision that makes a difference in mapping.
Steps to rep... - 09:22 AM Revision ab8e328c (ceph): qa: clean up whitespace in test_misc.py
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision ee2683c8 (ceph): qa: update TestVolumeClient for new blacklisting
- Blacklisted clients will now proactively fail
outstanding operations, rather than blocking.
Signed-off-by: John Spra... - 09:22 AM Revision 3913ed0b (ceph): qa: refine assert_session_count (don't count killing)
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision dd08483b (ceph): mds: hook up autoclose to blacklisting eviction
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision 47a9c9ba (ceph): qa: add test_filelock_eviction
- To check that eviction is releasing flocks.
Signed-off-by: John Spray <john.spray@redhat.com> - 09:22 AM Revision 71229af5 (ceph): mds: tidy up 'kill_session' naming
- We had two kill_sessions. Leave Server::kill_session (the
one that actually operates on MDS sessions only), and rena... - 09:22 AM Revision 45caf261 (ceph): mds: improve eviction usability and update docs
- The "session ls" and "session evict" are now
"client ls" and "client evict" (the old ones
are still there for backwar... - 09:22 AM Revision 06935d40 (ceph): qa: log whitelist for eviction messages
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision c91ccac6 (ceph): qa: remove outdated TODO in TestVolumeClient
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision d6ce9d8b (ceph): mds: blacklist clients on eviction
- Fixes: http://tracker.ceph.com/issues/9754
Signed-off-by: John Spray <john.spray@redhat.com> - 09:22 AM Revision 05b171b5 (ceph): mds: update osdmap epoch barrier on eviction
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision 711ee5ee (ceph): mds: update osd epoch barrier when handling blacklist
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision 7d8281c8 (ceph): client: detect blacklisting of myself
- EIO all operations when this happens, and do a cut-down
unmount() so that once the user has noticed his mount
is brok... - 09:22 AM Revision 4a9386e4 (ceph): client: fix unmounting while blacklisted
- Previously, if you ever made it as far as ~Client
with any inodes in your cache, you'd hit the ObjectCacher
is_locked... - 09:22 AM Revision 048e8254 (ceph): mds: make blacklisting configurable in kill_session
- This makes the code a bit awkward because we now have
4x paths through this function (blocking, noblocking, blacklist... - 09:22 AM Revision d98ace13 (ceph): osdc: expose new blacklist entries from Objecter
- For the MDS which needs to know about new blacklist entries
in order to evict corresponding MDS sessions.
Fixes: htt... - 09:22 AM Revision fe56a74c (ceph): osd/OSDMap: std::set version of get_blacklist
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision 3fe5e734 (ceph): mds: apply OSDMap blacklist to CephFS clients
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:22 AM Revision dd173bd5 (ceph): mds: remove stale comment
- The code the comment is talking about went
away in 2490a0a1e.
Signed-off-by: John Spray <john.spray@redhat.com> - 09:22 AM Revision 3610729c (ceph): mon: permit MDS daemons to do blacklisting
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:09 AM Revision c3cd0ba5 (ceph): filestore: migrate atomic_t to std::atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 07:56 AM Revision 0d743343 (ceph): mds: use client_t instead of int for client ID
- 'int' causes value truncation since client ID is int64_t.
Signed-off-by: Henry Chang <henry_chang@bigtera.com> - 05:20 AM Revision 309442fa (ceph): Merge pull request #15220 from joscollin/wip-cleanup-rados-typo
- include/rados: Fix typo in rados_ioctx_cct() doc
- 04:19 AM Revision af42ac7a (ceph): rgw: set placement rule properly
- we should set placement rule in RGWObjManifest::obj_iterator::update_location()
when ofs < manifest->get_head_size().... - 04:03 AM Revision c969709b (ceph): include/rados: Fix typo in rados_ioctx_cct() doc
- This fixes PR#15077.
Signed-off-by: Jos Collin <jcollin@redhat.com> - 03:57 AM Backport #20033: kraken: osd_scrub_sleep option blocks op thread in jewel + later
- Please see https://github.com/ceph/ceph/pull/15217 also. Sorry about the timing.
- 03:56 AM Backport #20032: jewel: osd_scrub_sleep option blocks op thread in jewel + later
- Please see https://github.com/ceph/ceph/pull/15217 also. Sorry about the timing.
- 03:56 AM Bug #19497: osd_scrub_sleep option blocks op thread in jewel + later
- Please see https://github.com/ceph/ceph/pull/15217 also
- 03:55 AM Revision 84f9c125 (ceph): pybind/ceph_daemon.py: move _gettermsize() into Termsize
- as the latter is the only consumer of _gettermsize(). and a little bit
refactor to improve the readability and be mor... - 03:55 AM Revision 5f769f46 (ceph): ceph.in: adjust usage width according to user's tty
- fixed a pep8 warning also
Signed-off-by: Kefu Chai <kchai@redhat.com> - 03:39 AM RADOS Bug #20050: osd: very old pg creates take a long time to build past_intervals
- partially addressed by patch in wip-bigbang.
- 03:33 AM RADOS Bug #20050 (Resolved): osd: very old pg creates take a long time to build past_intervals
- (bigbang)
osds were down for a long time and pgs never got created. when the osds finally are up, they have to go... - 02:51 AM Revision b1e42955 (ceph): crush/CrushWrapper: fix has_incompat_choose_args
- If the map has *no* choose_args it does not have incompat choose args.
This makes the OSDMap::get_features() check
... - 02:23 AM Bug #19986 (In Progress): PR #14886 creates a SafeTimer thread per PG
- Have https://github.com/ceph/ceph/pull/15217 for now although this may need modification to account for the pg disapp...
- 02:08 AM Revision b3db617d (ceph): rgw_file: remove post-unlink lookup check
- This could induce asserts in multi-nfs-gateway scenarios.
Fixes: http://tracker.ceph.com/issues/20047
Signed-off-by... - 01:16 AM Support #19998 (Resolved): librados aio callbacks thread safety
- The librados API does not specify an order to the callbacks or guarantee you will only get one at a time. You should ...
- 01:06 AM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- 0> 2017-05-19 14:44:41.128625 7f8a6cc28700 -1 *** Caught signal (Aborted) **
in thread 7f8a6cc28700 thread_nam... - 12:42 AM Revision d6e6e7a5 (ceph): rgw_file: remove hidden uxattr objects from buckets on delete
- If a setattr (e.g., chown) has been performed on a bucket, then like
any directory it has a hidden object storing its... - 12:40 AM Revision 28390521 (ceph): Merge pull request #15210 from linuxbox2/wip-rgw-rmbuck
- rgw_file: remove hidden uxattr objects from buckets on delete
- 12:15 AM Revision 08bc5e65 (ceph): build/ops: rpm: move python-prettytable to distro-conditional section
- The correct package name in SUSE is python-PrettyTable
Signed-off-by: Nathan Cutler <ncutler@suse.com>
05/22/2017
- 11:23 PM rgw Bug #20048 (Resolved): Ceph no longer builds for s390x after Beast submodule enabled
- https://github.com/ceph/ceph/pull/14273 introduces a regression in that it breaks the s390x build.
The immediate c... - 11:05 PM RADOS Bug #19909: PastIntervals::check_new_interval: assert(lastmap->get_pools().count(pgid.pool()))
- Still happens in 12.0.3, with the patch [[https://github.com/ceph/ceph/pull/15046]] applied。
- 10:16 PM Revision 01e15c3e (ceph): rgw_file: remove hidden uxattr objects from buckets on delete
- If a setattr (e.g., chown) has been performed on a bucket, then like
any directory it has a hidden object storing its... - 09:53 PM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- (Note: definitely not sure the peering_queue assert is the same one. It could be related though.)
- 09:51 PM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- Yep, the snap trimming takes PGRefs and doesn't have a good way of dropping them for shutdown. Looking into it...`
- 09:51 PM devops Bug #17091: ceph-osd-prestart.sh fails confusingly when data directory does not exist
- -a would avoid the problem in https://bugzilla.redhat.com/show_bug.cgi?id=1454479
- 09:43 PM rgw Bug #20047 (Resolved): rgw_file: unlink assert unsafe in multi-gateway environments
- The assert that unlinked objects are really unlinked is not safe for production use, since the operation is only loca...
- 09:38 PM Bug #19993 (Need More Info): run-tox-ceph-disk fails related to prettytable
- I had asked in IRC if you had rerun install-deps.sh since the prettytable addition, and did not hear an answer. That...
- 09:14 PM CephFS Bug #20040 (Fix Under Review): "terminate called after throwing an instance of 'std::out_of_range...
- https://github.com/ceph/ceph/pull/15213
- 03:39 PM CephFS Bug #20040 (Resolved): "terminate called after throwing an instance of 'std::out_of_range'" in po...
- Run: http://pulpito.ceph.com/teuthology-2017-05-21_22:37:21-powercycle-master-testing-basic-mira/
Jobs: '1204386', '... - 09:13 PM Revision 24cabcfb (ceph): mon: fix accesing pending_fsmap from peon
- Fixes: http://tracker.ceph.com/issues/20040
Signed-off-by: John Spray <john.spray@redhat.com> - 08:35 PM RADOS Bug #20041: ceph-osd: PGs getting stuck in scrub state, stalling RBD
- ...
- 05:22 PM RADOS Bug #20041: ceph-osd: PGs getting stuck in scrub state, stalling RBD
- I've seen this on scrub as well.
- 03:55 PM RADOS Bug #20041 (Resolved): ceph-osd: PGs getting stuck in scrub state, stalling RBD
- See the attached logs for the remove op against rbd_data.21aafa6b8b4567.0000000000000aaa...
- 07:56 PM Support #20046 (Resolved): PGs stuck in active+rempped state
- ceph version 0.94.6 (e832001feaf8c176593e0325c8298e3f16dfb403)
I have attached a stuck PG dump to this ticket.
He... - 07:48 PM Revision 74be9d85 (ceph): restful: Add a qa workunit
- This commit adds a simple test that will send the requests to most of
the API endpoints and check the status code of ... - 07:46 PM Revision ba958c15 (ceph): osd: Implement asynchronous recovery sleep
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 07:08 PM Stable releases Tasks #19538: jewel v10.2.8
- Added https://github.com/ceph/ceph/pull/15208 on Sage's request,
build: https://shaman.ceph.com/builds/ceph/wip-j... - 06:51 PM rgw Bug #20045 (Resolved): rgw_file: cannot delete bucket w/uxattrs
- If a setattr (e.g., chown) has been performed on a bucket, then like any directory it has a hidden object storing its...
- 06:08 PM rgw Bug #20044 (New): Creating a zone does not add the realm ID to the zone's config
- When you create a zone, the output shows the realm id (which,
I have to assume, is supposed to be stored in the zone... - 05:46 PM Revision 7ebe7c1c (ceph): Merge pull request #15195 from theanalyst/doc/12.0.3-typo-fix
- doc: fixing an error in 12.0.3 release notes
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Loic Dachary... - 05:46 PM Revision 9f810486 (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 05:21 PM Revision 48ba07ac (ceph): restful: Use pecan hook instead of catch decorator
- This removes the catch decorator which was useful primarily for testing
purposes and instead switches to a pecan erro... - 05:21 PM Revision 10ebd6e3 (ceph): restful: List full requests in /request
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 05:21 PM Revision f45a282b (ceph): restful: Output sub-commands more clearly
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 05:21 PM Revision 884dfc2d (ceph): restful: Add pagination support
- This commit adds a pagination support via paginate decorator. The
decorator will paginate the output if it is told to... - 05:21 PM Revision 32dafc85 (ceph): restful: Use port 8003
- This allows us to run both calamari and the rest api at the same time.
Signed-off-by: Boris Ranto <branto@redhat.com> - 05:21 PM Revision 92fa210a (ceph): restful: Generate cert/key in post scripts
- This is the simplest way to generate the keys and probably the least
likely to cause trouble in the future.
Signed-o... - 05:20 PM Revision 4f452ade (ceph): restful: Do not store the config file in /etc/ceph
- This also contains a documentation fix for authentication in / endpoint.
Signed-off-by: Boris Ranto <branto@redhat.com> - 05:20 PM Revision aeed9a12 (ceph): restful: send_command changed type
- The send_command function now requires 6 arguments, switching back to
mon commands as that is what we used before.
S... - 05:20 PM Revision f59e9bf0 (ceph): restful: Use fixed cert/pkey files
- This allows users to create their own certificates that are signed by a
CA. If the keys are not present then a self-s... - 05:19 PM Revision cdd2079d (ceph): restful: Use keys instead of tokens+cephx
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 05:19 PM Revision e58ba75b (ceph): restful: Prepare for api file split
- The patch moves decorators into a separate file so they could be shared
amongst various files.
It also fixes key gen... - 05:19 PM Revision 21af9555 (ceph): restful: Split api.py file into a module
- The patch makes the REST api being served by a module, not a single
monolithic file.
Signed-off-by: Boris Ranto <bra... - 05:18 PM Revision 5ed2631b (ceph): ceph-mgr: Implement new pecan-based rest api
- The new rest API uses pecan for the restful functionality and simplifies
the code significantly. It should be mostly ... - 05:14 PM Revision bba7d0b7 (ceph): Merge pull request #15186 from adamemerson/wip-clangtastic-mr-clocks
- rgw: Remove pessimizing move
common: Forward-declare container I/O overloads
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:10 PM rgw Bug #19961: luminous: rgw: leaked _shadow_ zero size tail objects if whole object size is multipl...
- Fixed in v12.0.3
- 05:00 PM Revision 621a281a (ceph): doc/release-notes: update which jewel version does sortbitwise warning
- I'm am assuming this will make 10.2.8:
https://github.com/ceph/ceph/pull/15208
Signed-off-by: Sage Weil <sage@redha... - 04:54 PM Bug #20043 (Fix Under Review): "** ERROR: osd init failed" in rados
- https://github.com/ceph/ceph/pull/15207
- 04:32 PM Bug #20043 (Resolved): "** ERROR: osd init failed" in rados
- Run: http://pulpito.ceph.com/yuriw-2017-05-20_04:20:14-rados-master_2017_5_20---basic-smithi/
Job: 1199586
Logs: ht... - 04:53 PM Revision 657453d3 (ceph): qa/suites/rados/singleton-nomsg/health-warnings: behave on ext4
- We may land on an ext4 root partition.
Fixes: http://tracker.ceph.com/issues/20043
Signed-off-by: Sage Weil <sage@re... - 04:44 PM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- or debug bluestore = 30 would be even better :)
- 04:43 PM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- Nick, is this reproducible? Any chance you can reproduce with debug bluestore = 20?
- 03:14 PM Bug #19555: BlueStore.cc: 1941: FAILED assert(!force)
- I believe I may have just hit this. Was doing 4kb seq writes from fio to a EC pool with overwrites enabled, RBD image...
- 04:34 PM RADOS Bug #19964: occasional crushtool timeouts
- See this log as well:
http://qa-proxy.ceph.com/teuthology/yuriw-2017-05-20_04:20:14-rados-master_2017_5_20---basic... - 04:30 PM Revision 34a17d5f (ceph): Merge pull request #12861 from theanalyst/wip-absolute-urls
- rgw: pass authentication domain to civetweb
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:27 PM Bug #20042 (Rejected): "MaxWhileTries: 'wait_until_healthy' reached maximum" in rados-master_2017...
- jewel-x upgrade job seems timing out
Run: http://pulpito.ceph.com/yuriw-2017-05-20_04:20:14-rados-master_2017_5_20... - 03:59 PM Revision cea91e0c (ceph): Merge pull request #15150 from ovh/bp-doc-perf-histograms
- doc: document perf historgrams
Reviewed-by: Sage Weil <sage@redhat.com> - 03:53 PM Revision 756b3d59 (ceph): doc: document perf historgrams
- Documentation for perf histograms schema and dump.
Signed-off-by: Piotr Dałek <piotr.dalek@corp.ovh.com> - 03:49 PM Revision f2814e4d (ceph): mon/OSDMonitor: fixup sortbitwise flag warning
- "ceph -s" does not report warning when using
command "ceph osd unset sortbitwise" to drop
sortbitwise flag.
we should... - 03:48 PM Revision 02617188 (ceph): mon: remove config option to disable no sortbitwise warning
- We'll require this soon.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 04e3319e8aecde9ca58cc... - 03:41 PM CephFS Bug #20039 (Fix Under Review): mds: replay of export pinned inode does not result in export
- https://github.com/ceph/ceph/pull/15205
- 03:33 PM CephFS Bug #20039 (Resolved): mds: replay of export pinned inode does not result in export
- Found this while thrashing exports. Example log:...
- 03:28 PM Revision edbd6edb (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 03:25 PM Bug #20038 (Closed): Xenial librbd client unable to connect to Luminous OSDs
- http://qa-proxy.ceph.com/teuthology/teuthology-2017-05-22_02:01:01-rbd-master-distro-basic-smithi/1204512/remote/smit...
- 03:22 PM Revision 9fba0f1f (ceph): osdc: Use Finisher::enqueue from Objecter mostly
- Make DoWatchError and DoWatchNotify function objects instead of
Context*s. Since one is three pointers large and one ... - 03:22 PM Revision e38b2a58 (ceph): finisher: Work with functions
- We use a vector of unique functions instead of contexts, contexts are just
lambda captured. (Which doesn't take up an... - 03:22 PM Revision b691b7ed (ceph): finisher: Update to C++11 concurrency
- No changes visible to the caller.
Signed-off-by: Adam C. Emerson <aemerson@redhat.com> - 03:22 PM Revision 289d0192 (ceph): common: Add locking template functions and macros
- These infer the type of the unique/shared/shunique lock from the type of
the mutex.
Signed-off-by: Adam C. Emerson <... - 03:22 PM Revision 567f22e2 (ceph): common: Add make_named_thread
- To allow us to make a std::thread with a name.
Signed-off-by: Adam C. Emerson <aemerson@redhat.com> - 03:19 PM Revision 316c78d4 (ceph): submodule: David Krauss's cxx_function
- This function library is backwards-compatible with cxx_function and a
candidate for becoming (or at least strongly in... - 03:17 PM Revision ad2dbca0 (ceph): rgw: Remove pessimizing move
- Do not std::move values from returned functions.
Signed-off-by: Adam C. Emerson <aemerson@redhat.com> - 03:17 PM Revision a7fefb0e (ceph): common: Forward-declare container I/O overloads
- This will allow strict ADL to find the right overload in the case of a
container of containers and unbreak compilatio... - 02:55 PM rgw Feature #19917: radosgw access log is lacking useful information
- Pushed some initial code for the other information items at https://github.com/cloudbau/ceph/tree/wip-rgw-logging, he...
- 02:53 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- Based on the discussion here (https://github.com/ceph/ceph/pull/14997) I'm detaching dmclock's testing from ceph's te...
- 02:35 PM rgw Bug #20037 (Resolved): rgw log includes zero byte sometimes
- The log line looks like this:...
- 02:15 PM Bug #19935 (Fix Under Review): scrub test should not be run with d-luminous/at-end
- https://github.com/ceph/ceph/pull/15202
- 02:15 PM Revision 740f17eb (ceph): qa/suites/rados: temporarily remove scrub_test from basic/ until post-l...
- We don't want to do the at-end.yaml scrubbing business with this test.
Move it into a separate collection until after... - 02:10 PM Bug #19990 (Fix Under Review): EAGAIN: osd.4 is not up from rados/singleton-nomsgr/{all/health-wa...
- https://github.com/ceph/ceph/pull/15201
- 02:09 PM Revision aecaebe0 (ceph): qa/workunits/rados/test_health_warning: misc fixes
- - use 'noup' flag
- wait for healthy between each test
- check counts for each type
Fixes: http://tracker.ceph.com/i... - 12:52 PM Revision ba641b51 (ceph): build/ops: rpm: move RDMA build dependency to distro-conditional section
- SUSE ships this package under the name "rdma-core-devel". See
https://build.opensuse.org/package/view_file/openSUSE:F... - 12:51 PM rbd Bug #19970 (Resolved): Reduce the potential for erroneous blacklisting due to release lock race
- 12:50 PM Revision 1367ab2a (ceph): Merge pull request #15162 from dillaman/wip-19970
- librbd: reduce potential of erroneous blacklisting on image close
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 12:02 PM Revision c35629f1 (ceph): client/inode: fix the dump type of Inode::dump()
- Signed-off-by: huanwen ren ren.huanwen@zte.com.cn
- 11:40 AM CephFS Feature #17835: mds: enable killpoint tests for MDS-MDS subtree export
- (NB original PR was https://github.com/ceph/ceph/pull/13308)
- 11:38 AM rgw Bug #16293: Multipart objects are broken when using S3 and SWIFT API at the same time
- I tested it also on:
radosgw --version
ceph version 10.2.6 (656b5b63ed7c43bd014bcafd81b001959d5f089f)
and we hav... - 11:13 AM Revision 1d06152c (ceph): Update some RGW documentation
- - Update RGW quickstart doc to match current status
- Use --rgw_num option with vstart.sh
Signed-off-by: Jens Rosenb... - 10:37 AM rgw Backport #20007 (In Progress): jewel: rgw: remove unnecessary 'error in read_id for object name: ...
- 10:28 AM rgw Backport #20007 (Resolved): jewel: rgw: remove unnecessary 'error in read_id for object name: def...
- https://github.com/ceph/ceph/pull/15197
- 10:35 AM Backport #20006 (In Progress): jewel: build/ops: fix python-Sphinx package name for SUSE
- 10:28 AM Backport #20006 (Resolved): jewel: build/ops: fix python-Sphinx package name for SUSE
- https://github.com/ceph/ceph/pull/15196
- 10:31 AM Backport #20036 (Resolved): jewel: mon: MAX AVAIL calcuation does not fact or in mon_osd_full_ratio
- https://github.com/ceph/ceph/pull/15236
- 10:30 AM Backport #20035 (Resolved): kraken: mon: MAX AVAIL calcuation does not fact or in mon_osd_full_ratio
- https://github.com/ceph/ceph/pull/15237
- 10:29 AM Backport #20034 (Resolved): kraken: ceph-disk: Racing between partition creation & device node cr...
- https://github.com/ceph/ceph/pull/16138
- 10:29 AM Backport #20033 (Resolved): kraken: osd_scrub_sleep option blocks op thread in jewel + later
- https://github.com/ceph/ceph/pull/15526
- 10:29 AM Backport #20032 (Resolved): jewel: osd_scrub_sleep option blocks op thread in jewel + later
- https://github.com/ceph/ceph/pull/15529
- 10:29 AM rgw Backport #20031 (Resolved): kraken: rgw: Swift's at-root features (/crossdomain.xml, /info, /heal...
- https://github.com/ceph/ceph/pull/16168
- 10:29 AM rgw Backport #20030 (Rejected): kraken: multisite: radosgw-admin period commands cant use --remote in...
- 10:29 AM rgw Backport #20029 (Rejected): jewel: multisite: radosgw-admin period commands cant use --remote in ...
- https://github.com/ceph/ceph/pull/15458
- 10:29 AM Backport #20002 (In Progress): jewel: infinit loops in filestore::fiemap()
- 10:28 AM Backport #20002 (Resolved): jewel: infinit loops in filestore::fiemap()
- https://github.com/ceph/ceph/pull/15189
- 10:29 AM CephFS Backport #20028 (Resolved): kraken: Deadlock on two ceph-fuse clients accessing the same file
- https://github.com/ceph/ceph/pull/16191
- 10:29 AM CephFS Backport #20027 (Resolved): jewel: Deadlock on two ceph-fuse clients accessing the same file
- https://github.com/ceph/ceph/pull/15438
- 10:29 AM CephFS Backport #20026 (Resolved): kraken: cephfs: MDS became unresponsive when truncating a very large ...
- https://github.com/ceph/ceph/pull/16190
- 10:29 AM CephFS Backport #20025 (Resolved): jewel: MDS became unresponsive when truncating a very large file
- https://github.com/ceph/ceph/pull/15442
- 10:29 AM Backport #20024 (Resolved): kraken: HEALTH_WARN pool rbd pg_num 244 > pgp_num 224 during upgrade
- https://github.com/ceph/ceph/pull/16137
- 10:29 AM rbd Backport #20023 (Resolved): jewel: rbd-mirror replay fails on attempting to reclaim data to local...
- https://github.com/ceph/ceph/pull/15488
- 10:29 AM rbd Backport #20022 (Resolved): kraken: rbd-mirror replay fails on attempting to reclaim data to loca...
- https://github.com/ceph/ceph/pull/15486
- 10:28 AM rgw Backport #20021 (Rejected): kraken: multisite: RGWPeriodPusher CRThread startup races with RGWHTT...
- 10:28 AM rgw Backport #20020 (Resolved): jewel: multisite: RGWPeriodPusher CRThread startup races with RGWHTTP...
- https://github.com/ceph/ceph/pull/15457
- 10:28 AM rgw Backport #20019 (Rejected): kraken: multisite: memory leak on failed lease in RGWDataSyncShardCR
- 10:28 AM rgw Backport #20018 (Resolved): jewel: multisite: memory leak on failed lease in RGWDataSyncShardCR
- https://github.com/ceph/ceph/pull/15457
- 10:28 AM rbd Backport #20017 (Resolved): jewel: rbd-nbd: kernel reported invalid device size (0, expected 1073...
- https://github.com/ceph/ceph/pull/15463
- 10:28 AM rbd Backport #20016 (Rejected): kraken: rbd-nbd: kernel reported invalid device size (0, expected 107...
- 10:28 AM rgw Backport #20015 (Resolved): kraken: multisite: bi_list() decode failures
- https://github.com/ceph/ceph/pull/15384
- 10:28 AM rgw Backport #20014 (Resolved): jewel: multisite: bi_list() decode failures
- https://github.com/ceph/ceph/pull/15383
- 10:28 AM Backport #20013 (Rejected): kraken: support Debian stretch
- https://github.com/ceph/ceph/pull/16136
- 10:28 AM Backport #20012 (Rejected): jewel: support Debian stretch
- 10:28 AM Backport #20011 (Resolved): jewel: ceph-disk: separate ceph-osd --check-needs-* logs
- https://github.com/ceph/ceph/pull/15503
- 10:28 AM Backport #20010 (Resolved): kraken: ceph-disk: separate ceph-osd --check-needs-* logs
- https://github.com/ceph/ceph/pull/16135
- 10:28 AM rbd Backport #20009 (Rejected): jewel: rbd-mirror: admin socket path names collision
- 10:28 AM rbd Backport #20008 (Rejected): kraken: rbd-mirror: admin socket path names collision
- 10:28 AM rbd Backport #20005 (Rejected): kraken: Lock release requests not honored after watch is re-acquired
- 10:28 AM rgw Backport #20004 (Rejected): kraken: rgw_file: v3 write timer does not close open handles
- 10:28 AM rgw Backport #20003 (Resolved): jewel: rgw_file: v3 write timer does not close open handles
- https://github.com/ceph/ceph/pull/15456
- 10:27 AM Bug #19996 (Pending Backport): infinit loops in filestore::fiemap()
- 08:46 AM Revision 9316b044 (ceph): client: update the 'approaching max_size' code
- The old 'approaching max_size' code expects MDS set max_size to
'2 x reported_size'. This is no longer true. The new ... - 08:45 AM Revision 538f35be (ceph): mds: limit client writable range increment
- For very large file, setting the writable range to '2 * file_size'
causes file recovery to run a long time. To recove... - 08:42 AM Revision 3cfe612e (ceph): doc: fixing an error in 12.0.3 release notes
- Thanks @smithfarm for pointing this out
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 06:54 AM Feature #20001 (Duplicate): RBD cache persistence
- Move RBd cache from memory to Harddisk,such as SSD.
- 06:52 AM Revision 3e0d1491 (ceph): mgr: load modules in separate python sub-interpreters
- This provides a reasonable amount of isolation between mgr
modules. Notably, with this change, it's possible to have... - 06:52 AM Revision f36b0d9d (ceph): mgr: use new Gil class in place of PyGILState_*() API
- Prep work for loading modules in separate python sub-interpreters.
According to the Python C API docs, mixing the PyG... - 06:51 AM RADOS Bug #20000 (Can't reproduce): osd assert in shared_cache.hpp: 107: FAILED assert(weak_refs.empty())
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+ec+overw... - 06:00 AM Feature #19278 (Fix Under Review): Support for Array Codes: Coupled Layer code implementation
- 03:46 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- This was a stupid error and I have a pretty simple fix. Testing it now and sorry for the mess.
[update]There's cur... - 02:30 AM Bug #19900 (In Progress): osd crash during shutdown
- https://github.com/ceph/ceph/pull/15192
- 02:22 AM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- It's possible that client_range is not properly cleared in some corner cases. Need detail log to find out.
- 02:00 AM Revision c89bbd66 (ceph): Merge pull request #15191 from Linbing/modify-note-word-error
- mon: Fixed typo in @post of _active()
- 12:32 AM Revision e10061ee (ceph): Note word error of _active(), take iif with if
- Signed-off-by: Linbing <hawkerous@gmail.com>
05/21/2017
- 10:10 AM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/kchai-2017-05-21_04:27:34-rados-wip-bigbang---basic-mira/1203867/remote/mira104/log/ceph-osd.0.log.gz
- 09:11 AM Support #19998 (Resolved): librados aio callbacks thread safety
- As stated in documentation (http://docs.ceph.com/docs/master/rados/api/librados/#asychronous-io):
> The callbacks ar...
05/20/2017
- 10:25 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- Would you be happy for me to submit a patch specifically for dmclock/test/test_dmclock_server.cc Eric?
- 04:22 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- Thanks, Brad. dmClock is an external library (brought into ceph via git-subtree). So the choices are to either duplic...
- 10:17 PM Bug #19989: "OSDMonitor.cc: 3545: FAILED assert(num_down_in_osds <= num_in_osds)" in rados run
- appears to be related to this code, which assumes the osd is out but may not be true. fix might be something like th...
- 02:44 PM Revision b52bfe6b (ceph): os/filestore: fix infinit loops in fiemap()
- since fiemap can get extents based on offset --> len
but we should consider last extents is retrieved when len == 0
e... - 02:36 PM Bug #19996 (Resolved): infinit loops in filestore::fiemap()
- since fiemap can get extents based on offset --> len
but we should consider last extents is retrieved when len == 0
... - 09:40 AM Revision 35bf4915 (ceph): mon: delete useless function definition
- Signed-off-by: shiqi <1454927420@qq.com>
- 06:41 AM RADOS Bug #19964: occasional crushtool timeouts
- this is not new, i've been spotting this occasionally in our jenkins run.
- 06:37 AM Bug #19974: "HEALTH_WARN too few PGs per OSD" test_wait_for_health_ok
- Dan, i was wrong. this is only related to testing of ceph.
- 03:21 AM Revision 2a7bb175 (ceph): tools/crushtool: replicated-rule API support
- This patch adds two interfaces to operate replicated crush rules,
namely "--create-simple-rule" and "--remove-rule".
... - 02:10 AM Revision 2980b112 (ceph): compressor: optimize header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> - 01:53 AM Revision e3319da5 (ceph): Merge pull request #15181 from tchaikov/wip-cxx1z-size
- common: add ceph::size()
Reviewed-By: Adam C. Emerson <aemerson@redhat.com> - 01:03 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- Yep, seemed like the simplest implementation but I guess I should have seen this coming... I'll work out a better way...
- 12:59 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- I guess in particular, the issue is that there is a cost per thread (not a huge one, but it exists). Mark is seeing i...
- 12:56 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- We just don't need a Timer object/thread for every PG, Brad. The snap trim timer does the same thing with sleeps but ...
- 12:08 AM Bug #19986: PR #14886 creates a SafeTimer thread per PG
- Hi Mark, Thanks for the report. The intention was that this should increase performance as it frees up the work queue...
- 12:41 AM mgr Bug #19994 (Resolved): ceph-mgr upstart issue on trusy - HEALTH_ERR no active mgr
on trusty the ceph-deploy tests fails, there is nothing special we currently do to enable/start ceph-mgr
the same ...
05/19/2017
- 11:14 PM Bug #19979: dmclock-tests passes but generates a segfault and coredump
- Check out src/include/coredumpctl.h and its use.
- 01:53 PM Bug #19979 (In Progress): dmclock-tests passes but generates a segfault and coredump
- The segfault is to be expected. This test makes use of gtest's _EXPECT_DEATH_IF_SUPPORTED_ feature. For details, see ...
- 01:21 AM Bug #19979 (Closed): dmclock-tests passes but generates a segfault and coredump
- ...
- 10:51 PM Bug #19993 (Can't reproduce): run-tox-ceph-disk fails related to prettytable
On Ubuntu 14.04.4 LTS after using install_deps.sh and removing and using do_cmake.sh from scratch
Added in 3fa8b...- 10:11 PM Feature #19975 (In Progress): RFE: expose OP_OMAP_RMKEYRANGE in librados and cls
- https://github.com/ceph/ceph/pull/15183
- 09:59 PM Revision de6c0bd6 (ceph): Merge pull request #14946 from dmick/wip-mgr-dashboard
- mgr: dashboard GUI module
- 09:58 PM Revision e01fd684 (ceph): Merge pull request #14994 from theanalyst/f/tier-fix
- rgw_rados: create sync module instances only if run_sync_thread is set
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 09:47 PM Revision 10b1fa21 (ceph): test: add mgr/ and smoke test for mgr dashboard
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 08:49 PM Revision 8dcf8d6e (ceph): doc: dev: improve the s3tests with vstart document
- update with the current qa workunits example and drop old info, also
update vstart doc dropping the -r and --num opti... - 08:08 PM Revision e46fc502 (ceph): rgw_rados: create sync module instances only if run_sync_thread is set
- This allows for radosgw-admin to run even if there was a
misconfiguration in setting tier types which would otherwise... - 08:05 PM Revision 8c74c8a6 (ceph): qa/rgw: remove apache/fastcgi
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 9d82486d (ceph): qa/rgw: remove radosgw-agent tests from radosgw_admin task
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 762e15fb (ceph): qa/rgw: remove radosgw-agent config from s3tests task
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision a05b3bb4 (ceph): qa/rgw: remove radosgw_agent task
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision c8d8b9ca (ceph): qa/rgw: remove unused helpers in util/rgw.py
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 90e188ea (ceph): qa/rgw: remove radosgw-agent tasks from rgw suites
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 0fb3e76e (ceph): qa/rgw: more cleanup in rgw.py
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 994751d2 (ceph): qa/rgw: dont install debuginfo
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision f62f3bd9 (ceph): qa/rgw: disable wait-for-scrub on multifs and singleton
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:53 PM Revision 898ab4bb (ceph): qa/rgw: remove multisite configuration from rgw task
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:03 PM Revision e7e7e940 (ceph): Merge pull request #15153 from zhangsw/optimize-torrent
- rgw: optimize generating torrent file. Object data won't stay in memory now.
Reviewed-by: Daniel Gryniewicz <dang@r... - 07:02 PM Revision e546f469 (ceph): Merge pull request #15001 from chardan/jfw-wip-halflife_atomic_t-kamakuras
- rgw: migrate atomic_t to std::atomic<>
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 07:01 PM Revision aa162484 (ceph): Merge pull request #14827 from liuyuhong66/rgw-swift-auth-improve
- rgw/rgw_swift_auth.cc: using string::back() instead as the C++11 recommend
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:58 PM Revision 97486e6e (ceph): Merge pull request #15025 from mikulely/jiaying-fix-lc-list
- rgw: fix lc list failure when shards not be all created
Reviewed-by: Daniel Gryniewicz <dang@redhat.com>
Reviewed-by... - 06:57 PM Revision 9bc4d0fc (ceph): Merge pull request #12300 from idealguo/rename-s3_code
- rgw: rename s3_code to err_code for swift
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:56 PM Revision f0300415 (ceph): Merge pull request #15045 from shashalu/fix-slo
- rgw: fix X-Object-Meta-Static-Large-Object in SLO download
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:54 PM Revision 81aeb528 (ceph): Merge pull request #14800 from theanalyst/doc/release-notes/sse-c-corre...
- doc: release-notes clarify about rgw encryption
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 06:41 PM Revision bb82a9c5 (ceph): Merge pull request #14922 from ukernel/wip-kcephfs-whitelist
- qa: update log whitelists for kcephfs suite
Reviewed-by: John Spray <john.spray@redhat.com> - 06:40 PM Revision 2c0fe978 (ceph): Merge pull request #14941 from wjwithagen/wip-wjw-freebsd-doc-manual-in...
- doc: add FreeBSD manual install
- 06:33 PM Revision d6ddaf94 (ceph): Merge pull request #14988 from ShiqiCooperation/master
- test/unittest_bluefs: check whether mounted success
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:30 PM Revision cff53b24 (ceph): Merge pull request #14688 from cbodley/wip-rgw-multi-suite
- qa/rgw: add multisite suite to configure and run multisite tests
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 06:26 PM Revision b2df8243 (ceph): Remove ubuntu 14.04 tests
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 06:25 PM Revision 590fd536 (ceph): Merge pull request #15071 from cbodley/wip-qa-dnsmasq
- qa: add task for dnsmasq configuration
Reviewed-by: Vasu Kulkarni <vasu@redhat.com>
Reviewed-by: Abhishek Lekshmanan... - 06:21 PM Revision 39430e96 (ceph): Merge pull request #15090 from theanalyst/release/v12.0.3/notes
- doc: release notes for v12.0.3 (dev)
- 06:13 PM Revision 910405c1 (ceph): Merge pull request #15133 from cbodley/wip-doc-rgw-remove-fcgi
- doc/rgw: remove fastcgi page and sample configs
Reviewed-by: Sage Weil <sage@redhat.com> - 06:03 PM Revision 790ceff3 (ceph): Merge pull request #15144 from drunkard/master
- doc: typo fixes on hyperlink/words
Reviewed-by: Sage Weil <sage@redhat.com> - 06:00 PM Revision 8e0c4ee1 (ceph): Merge pull request #15161 from dzafman/wip-test-fix
- test: Test fix for SnapSet change
Reviewed-by: Sage Weil <sage@redhat.com> - 04:40 PM Revision bc529f87 (ceph): common: add ceph::size()
- backport from C++17
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:38 PM RADOS Bug #19991 (New): dmclock-tests fail on my build VM
On my build machine which is a VM. It passes on Jenkins.
[ RUN ] test_client.full_bore_timing
/home/dz...- 04:33 PM Revision 4d1d9ca8 (ceph): Merge pull request #15147 from bassam/pr-speedup-ccache
- cmake: improved build speed by 5x when using ccache
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:33 PM Revision e965dac0 (ceph): Merge pull request #15158 from liewegas/wip-mgr-dump
- mon/MgrMonitor: add 'mgr dump [epoch]' command
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:32 PM Revision 5c203e86 (ceph): Merge pull request #15159 from LiumxNL/fix-ping-monitor
- pybind/rados: avoid call free() on invalid pointer
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:27 PM Revision bedcbcd0 (ceph): os/bluestore: separate kv_sync_thread into two parts
- The kv_sync_thread is a bottleneck; making it do less work improves
performance on fast devices.
Signed-off-by: Jian... - 04:21 PM Bug #19990: EAGAIN: osd.4 is not up from rados/singleton-nomsgr/{all/health-warnings.yaml rados.y...
- /a/yuriw-2017-05-18_23:49:52-rados-wip-yuri-testing_2017_5_19-distro-basic-smithi/1194057
- 04:19 PM Bug #19990 (Resolved): EAGAIN: osd.4 is not up from rados/singleton-nomsgr/{all/health-warnings.y...
- ...
- 04:16 PM Bug #19989 (Resolved): "OSDMonitor.cc: 3545: FAILED assert(num_down_in_osds <= num_in_osds)" in r...
- Run: http://qa-proxy.ceph.com/teuthology/yuriw-2017-05-19_03:47:57-rados-wip-yuri-testing_2017_5_19---basic-smithi
J... - 04:05 PM Revision 6a21da59 (ceph): mon/OSDMonitor: handle sparse type names
- It's possible a type id isn't defined/used by crush. Use the max id
instead and skip types without names.
Signed-of... - 04:04 PM Revision 9183375b (ceph): mon/OSDMonitor: separate health warnings into distinct messages
- Each warning is a distinct message; the caller formats it as it deems
appropriate.
Signed-off-by: Sage Weil <sage@re... - 03:58 PM Revision 500f6dac (ceph): mon/OSDMonitor: adjust stray osd message a bit
- 'kept' seems wrong in this context.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:58 PM Revision 0f2a1773 (ceph): mon/OSDMonitor: clean up whitespace a bit
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:57 PM Revision d1bf2f60 (ceph): Merge pull request #15164 from tchaikov/wip-check-gperf-before-using-it
- cmake: check the existence of gperf before using it
Reviewed-By: Adam C. Emerson <aemerson@redhat.com> - 03:39 PM Revision a4727f3f (ceph): qa: run-s3tests: use python2 for s3tests & set PATH correctly
- in case we're in a vstart deployment, update PATH so that rgw-admin is
found, also set path correctly if we're in a v... - 03:28 PM Revision dddea8cb (ceph): vstart.sh: add --filestore_path to direct osd.0 filestore data to speci...
- This hack only works for 1 osd, but it lets you put it on a specific
directory/device.
Signed-off-by: Sage Weil <sag... - 03:25 PM Revision d07cfd40 (ceph): test: migrate atomic_t to std::atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 03:24 PM Revision 13adcac4 (ceph): librbd: block RPC requests before unregistering watch during close
- The watch should be released after exclusive lock is released to
avoid a potential race condition which would result ... - 03:18 PM RADOS Bug #19909: PastIntervals::check_new_interval: assert(lastmap->get_pools().count(pgid.pool()))
i have the same error with 12.0.3...- 02:52 PM RADOS Bug #19803: osd_op_reply for stat does not contain data (ceph-mds crashes with unhandled buffer::...
- After switching to writeback cache mode, this error didn't occur again. So I'm confident the proxy mode of the cache ...
- 02:49 PM rgw Bug #19988 (Resolved): RGW: can't stack compression and encryption filters
- New compression and encryption filters do not stack, but logically could do so. Users must choose between at rest da...
- 02:32 PM Revision b2c2f759 (ceph): Merge pull request #15089 from zhsj/add-mirror
- doc: add new cn ceph mirror to doc and mirroring
Reviewed-by: Wido den Hollander <wido@42on.com>
Reviewed-by: Kefu C... - 02:32 PM rgw Feature #19917: radosgw access log is lacking useful information
- This https://github.com/civetweb/civetweb/commit/02992037dde3433285790f03ab632d4a8625d3b9
- 02:31 PM rgw Feature #19917: radosgw access log is lacking useful information
- This patch in civetweb upstream seems to be fixing issue #1.
- 02:21 PM Revision 6fcaf779 (ceph): Revert "test/crush: silence warnings from -Walloc-size-larger-than= and...
- 02:18 PM Revision 8348a13f (ceph): Merge pull request #15173 from joscollin/wip-test-crush-warning
- test/crush: silence warnings from -Walloc-size-larger-than= and -Wstringop-overflow=
- 02:10 PM Revision fccae0f1 (ceph): Merge pull request #15171 from ztczll/master
- test/objectstore: Check apply_transaction() return values
- 01:58 PM Revision 3b2df97b (ceph): restful: Add pagination support
- This commit adds a pagination support via paginate decorator. The
decorator will paginate the output if it is told to... - 01:49 PM Bug #19987: -DWITH_TESTS=OFF build fails on master
- -https://github.com/ceph/ceph/pull/15174-
- 01:49 PM Bug #19987 (Resolved): -DWITH_TESTS=OFF build fails on master
- h3. tl;dr
src/dmclock/CMakeLists.txt introduced by https://github.com/ceph/ceph/pull/14330 does not contain WITH_T... - 01:44 PM CephFS Bug #19854 (Duplicate): ceph-fuse write a big file,The file is only written in part
- It's a known issue. If you use ceph-fuse, and multiple client read/modify a file at the same time, you should disable...
- 01:41 PM Bug #19986 (Resolved): PR #14886 creates a SafeTimer thread per PG
- This appears to be causing huge numbers of idle safe_timer threads to be created on the OSD. While this is likely no...
- 01:34 PM Revision 036470a2 (ceph): os: remove experimental status for BlueStore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:21 PM Revision 069ca1a1 (ceph): Merge pull request #15034 from liewegas/wip-bluestore-sync-write
- os/bluestore/KernelDevice: fix sync write vs flush
Reviewed-by: Varada Kari <varada.kari@gmail.com> - 01:20 PM Revision 9cae712d (ceph): os/bluestore/KernelDevice: fix flush() vs sync write()
- We need to set the atomic flag so that a flush will actually flush.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:44 PM Revision 4da9b486 (ceph): osd/mon/mds: unify usage text, always use stdout
- This unifies the first line of usage text: angle brackets
to indicate a mandatory option, and uppercase ID to match
t... - 12:43 PM Revision 6fa25c2b (ceph): librbd: recheck current lock owner before blacklist
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:43 PM Revision 95937bcd (ceph): librbd: introduced support for blocking watch notifications
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:19 PM Revision 6135c97d (ceph): mgr: add generic --help output
- Creating an MgrStandby in order to call its usage() method has
two problems:
1) MgrStandby wants to connect to a run... - 11:15 AM Revision 49fd3365 (ceph): test/crush: silence warnings from -Walloc-size-larger-than= and -Wstrin...
- The following warnings appear during make:
/home/jcollin/workspace/ceph/src/test/crush/CrushWrapper.cc: In member fu... - 10:23 AM CephFS Bug #17468 (Closed): CephFs: IO Pauses for more than a 40 seconds, while running write intensive IOs
- Unable to consistently reproduce the bug.
- 09:45 AM Revision 1cf018d1 (ceph): Check apply_transaction return values
- Signed-off-by: zhanglei <243290414@qq.com>
- 09:02 AM Revision c586df56 (ceph): erasure-code: optimize header file dependency
- Tidy up for merging with current master.
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> - 08:58 AM Revision f498aa59 (ceph): doc: PendingReleaseNotes move the 12.0.2 section of release notes
- So that we can track whatever diff goes in after
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 08:58 AM Revision 6a407bdf (ceph): doc: v12.0.3 release notes
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 08:39 AM bluestore Bug #19984 (Can't reproduce): /build/ceph-12.0.2/src/os/bluestore/KernelDevice.cc: 364: FAILED as...
- version:11.2.0
bluestore+ec+iscsi
client writing files...
0> 2017-04-17 15:35:11.177901 7f1b346da700 -1 /home... - 08:30 AM RADOS Bug #19983 (Closed): osds abort on shutdown with assert(/build/ceph-12.0.2/src/os/bluestore/Kerne...
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 08:22 AM Bug #19982 (Closed): osds abort on shutdown with assert(/build/ceph-12.0.2/src/common/Mutex.cc: 1...
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 08:08 AM Bug #19981 (Rejected): osds abort on shutdown with assert(/build/ceph-12.0.2/src/os/bluestore/Blu...
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 07:58 AM Bug #19980: stop two osd-services,which caused "Caught signal ",in thread 7f6bc8225700 thread_nam...
- 0> 2017-03-28 20:41:17.910308 7f6bc8225700 -1 *** Caught signal (Aborted) **
in thread 7f6bc8225700 thread_name:s... - 07:43 AM Bug #19980 (Closed): stop two osd-services,which caused "Caught signal ",in thread 7f6bc8225700 t...
- version:
root@node0:~# ceph -v
ceph version 12.0.2 (5a1b6b3269da99a18984c138c23935e5eb96f73e)
bluestore+rbd+ec+o... - 07:45 AM rgw Bug #19894: Write fails on larger files on nfs-ganesha-rgw
- Matt Benjamin wrote:
> Hi Stein,
>
> I did a by-hand verify of current v10.2.7 stable and upstream nfs-ganesha v2... - 07:14 AM Revision 99f27c39 (ceph): erasure-code: optimize header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 07:08 AM Revision ff4c40fc (ceph): rgw: segment fault when shard id out of range
- Fixes: http://tracker.ceph.com/issues/19732
Signed-off-by: redickwang <redickwang@tencent.com> - 06:45 AM Revision 7979a98f (ceph): osd: haven't take acting into account here, remove unnecessary variable
- Signed-off-by: Mingxin Liu <mingxin@xsky.com>
- 05:09 AM Revision 987211a6 (ceph): mgr/PyModules: move constructor definition to .cc
- Otherwise, the incomplete ServeThread type causes problems
for others who include PyModules.h
Signed-off-by: Dan Mic... - 05:09 AM Revision dc15cd60 (ceph): mgr: change config_prefix to be 'mgr/<id>/' and separate handle/key by '/'
- dm_crypt config-key usage has established '/' as the separator; keep
that as a convention for now
Signed-off-by: Dan... - 05:09 AM Revision bd6f2d92 (ceph): ceph.spec.in, debian/control: build/runtime dependency for cherrypy
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:09 AM Revision 80dc6a1e (ceph): osd: wire up "histogram dump" to `tell`
- ...so that mgr modules can get at it.
Signed-off-by: John Spray <john.spray@redhat.com> - 05:09 AM Revision b83fe0e3 (ceph): vstart: enable gui plugin
- Signed-off-by: John Spray <john.spray@redhat.com>
- 05:09 AM Revision c2493667 (ceph): pybind/mgr: web dashboard
- A read only display of some of the cluster's state, plus
some cephfs/rbd/osd pages that demonstrate how to go
read st... - 05:09 AM Revision f4bc4f64 (ceph): ServeThread: add 'running' flag, don't notify non-running threads
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:09 AM Revision e146b857 (ceph): ceph_syn.cc, client/SyntheticClient.cc: Client -> StandaloneClient
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:09 AM Revision 8abd69df (ceph): client/SyntheticClient.cc: filer is now a std::unique_ptr
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:09 AM Revision f2d29d2c (ceph): mgr/PyModules.cc,PyState.cc: improve config access debug logging
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:09 AM Revision f69ce190 (ceph): pybind/mgr/dashboard/module.py: allow custom server addr, port
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 05:07 AM Revision 59f7b235 (ceph): cls: Formatting changes and merge fixup
- Fix white space inconsistencies and resolve compile error.
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> - 04:53 AM Revision f6b388a3 (ceph): Merge pull request #15148 from zealoussnow/wip-spec
- build: move bash_completion.d/ceph to ceph-common
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Ken Dre... - 04:47 AM Revision 6761a838 (ceph): cmake: check the existence of gperf before using it
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:46 AM Revision f2213331 (ceph): more trivial doc tests
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 03:34 AM Revision f1632a0a (ceph): another ignorable commi
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 03:32 AM Revision 2033ab4e (ceph): DNM test updating a doc file to test doc build
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 02:56 AM Revision 08c0b2ae (ceph): Merge pull request #15160 from bassam/pr-system-boost
- cmake: fix boost components for WITH_SYSTEM_BOOST
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:35 AM Revision f24f4c8a (ceph): Merge pull request #15107 from guihecheng/rgw_file-cleanup
- rgw: use pre-defined calls to replace raw flag operation
- 02:05 AM Revision 70ba67b2 (ceph): cls: optimize user header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 02:05 AM Revision 2a852662 (ceph): cls: optimize version header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 02:05 AM Revision 0094eec1 (ceph): cls: optimize timeindex header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 02:03 AM Revision 9168aa39 (ceph): cls: optimize rgw header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 02:03 AM Revision e1e65e35 (ceph): cls: optimize statelog header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision df907819 (ceph): cls: optimize cephfs header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision e2bc9c0f (ceph): cls: optimize journal header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision 2b1cd152 (ceph): cls: optimize lock header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision bb43d6db (ceph): cls: optimize log header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision 90853bb5 (ceph): cls: optimize numops header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision 3cae46fe (ceph): cls: optimize rbd header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision 285aec13 (ceph): cls: optimize refcount header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:54 AM Revision 8fb75ad8 (ceph): cls: optimize replica_log header file dependency
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:41 AM Revision 58ba14e2 (ceph): doc: hyperlink fixes
- Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
- 01:34 AM Revision 5e3ae6d9 (ceph): doc: typo fixes
- Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
- 01:17 AM Revision cf08d006 (ceph): rgw_file: use pre-defined calls to replace raw flag operation
- Signed-off-by: Gui Hecheng <guihecheng@cmss.chinamobile.com>
- 01:16 AM Revision 9eeec442 (ceph): doc: remove duplicated section in doc/radosgw/adminops
- Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
- 12:56 AM CephFS Feature #17835: mds: enable killpoint tests for MDS-MDS subtree export
- Taking this one. I'm working on a test now.
- 12:43 AM Revision fc29f52e (ceph): rgw: fix 'gc list --include-all' command infinite loop the first 1000 i...
- When the items to gc over 1000, 'gc list --include-all' command will infinite loop the first 1000 items.
Add next_mar... - 12:41 AM rgw Bug #19978 (Resolved): rgw: 'gc list --include-all' command infinite loop the first 1000 items
- https://github.com/ceph/ceph/pull/12774
- 12:32 AM rbd Bug #19970 (Fix Under Review): Reduce the potential for erroneous blacklisting due to release loc...
- *PR*: https://github.com/ceph/ceph/pull/15162
- 12:28 AM Revision 1eef4650 (ceph): Merge pull request #15053 from dillaman/wip-librbd-blkin
- blkin: librbd trace hooks
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
05/18/2017
- 10:46 PM CephFS Bug #17259 (Won't Fix): multimds: ranks >= max_mds may be assigned after reducing max_mds
- This affected kcephfs which was fixed in https://github.com/ceph/ceph-client/commit/76201b6354bb3aa31c7ba2bd42b9cbb8d...
- 10:43 PM CephFS Bug #19240: multimds on linode: troubling op throughput scaling from 8 to 16 MDS in kernel bulid ...
- To close this we should confirm hypothesis with new op tracking from http://tracker.ceph.com/issues/19362
I'll do ... - 10:13 PM Revision 8f65f61a (ceph): blkin: initial trace hooks for IO path
- To collect blkin traced for RBD, set the "rbd blkin trace all"
configuration parameter to true.
Signed-off-by: Jason... - 10:13 PM Revision d9395599 (ceph): blkin: rbd object map update traces
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision 600bfa2d (ceph): common/zipkin_trace: added missing include for encoding
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision e0fc3694 (ceph): blkin: pass trace information to object cacher
- Signed-off-by: Victor Araujo <ve.ar91@gmail.com>
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 10:13 PM Revision b33eb645 (ceph): blkin: improve trace visibility into object cacher
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision 6ce2656e (ceph): blkin: librados should start new child trace
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision fd235926 (ceph): blkin: improved objecter trace events
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision bdff47ea (ceph): blkin: add config variable rbd_blkin_trace_all
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 10:13 PM Revision 6dfcb119 (ceph): test/librados_test_stub: add new aio_operate overloads for tracing
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:47 PM Revision 5c788a1d (ceph): test: Test fix for SnapSet change
- Caused by: a7b59221691954aedfac88695df8c89e36e10739
Signed-off-by: David Zafman <dzafman@redhat.com> - 08:15 PM Revision a56871e6 (ceph): Merge pull request #10736 from oliveiradan/SebastienHan_config_diff_get_fr
- common/ceph_context: 'config diff get' option added
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Brad Hubb... - 08:12 PM Revision ef1c0240 (ceph): Merge pull request #14914 from neha-ojha/wip-mon-crushtype-health-warn
- mon: add crush type down health warnings
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@... - 06:51 PM Revision afdff8fc (ceph): restful: Output sub-commands more clearly
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 06:46 PM Revision fe4d750e (ceph): denc: add reserve() to boost::flat_set/map decode
- by reserving space up front, we avoid rellocating storage as elements
are inserted
Signed-off-by: Casey Bodley <cbod... - 06:46 PM Revision 3903c3b9 (ceph): sstring: add denc() support
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:45 PM Revision ba249854 (ceph): doc/rgw: update pool names, document namespaces
- Fixes: http://tracker.ceph.com/issues/19504
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:42 PM Revision 20231727 (ceph): restful: List full requests in /request
- Signed-off-by: Boris Ranto <branto@redhat.com>
- 06:29 PM Revision a28c3ad2 (ceph): Merge pull request #15086 from joscollin/wip-cleanup-redundant-headers-1
- common: Remove redundant includes
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 06:29 PM Revision 5d83781f (ceph): Merge pull request #15109 from tchaikov/wip-mgrmon-send-digests-using-t...
- mon/MgrMonitor: send digests only if is_active()
Reviewed-by: Sage Weil <sage@redhat.com> - 06:28 PM Revision e5815112 (ceph): Merge pull request #15116 from liewegas/wip-bluestore-aio-warning
- os/bluestore/KernelDevice: helpful warning when aio limit exhausted
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 06:28 PM Revision 739cbc98 (ceph): Merge pull request #15117 from liewegas/wip-luminous-legacy-check
- qa/suites/rados/thrash: make sure osds have map before legacy scrub
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:28 PM Revision 5a03220d (ceph): Merge pull request #15120 from liewegas/wip-ec-buffer
- osd: reduce buffer pinning from EC entries
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:27 PM Revision 4b0aa088 (ceph): Merge pull request #15121 from ivancich/wip-remove-an-unnecessary-loop
- osd/pglog: remove loop through empty collection
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Josh Durgin <... - 06:27 PM Revision 1a8ab080 (ceph): Merge pull request #15124 from cbodley/wip-osd-swap
- osd: fix argument-dependent lookup of swap()
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:27 PM Bug #19963 (Resolved): LibRadosListNP.ListObjectsError
- 06:26 PM Revision e35d635e (ceph): Merge pull request #15138 from liewegas/wip-list-objects-more
- ceph_test_rados_api_list: more fix LibRadosListNP.ListObjectsError
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:18 PM rgw Bug #17465 (Resolved): multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED errors
- both backports are resolved
- 06:09 PM Feature #19975 (Pending Backport): RFE: expose OP_OMAP_RMKEYRANGE in librados and cls
- Motivation:
cls_log and cls_rgw are currently implementing trim by listing 1000 entries with cls_cxx_map_get_vals(),... - 05:55 PM Tasks #19973 (Fix Under Review): detect broken links in documentation automatically
- 12:41 PM Tasks #19973: detect broken links in documentation automatically
- https://github.com/ceph/ceph/pull/15143
- 12:39 PM Tasks #19973 (Fix Under Review): detect broken links in documentation automatically
- we should create a test case since we support sphinx link-check already.
- 05:38 PM Revision e90bba65 (ceph): test/rgw: add timing config options to test_multi.py
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:38 PM Revision de836ee6 (ceph): qa/rgw: add test config to rgw_multisite_tests task
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:38 PM Revision f9fae9bf (ceph): test/rgw: add timing configuration
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:37 PM Revision 16ab3a08 (ceph): qa/rgw: add multisite suite
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:37 PM Revision ea245ca6 (ceph): test/rgw: add 5min timeouts to sync checkpoints
- if multisite tests are going to run in teuthology, they can't loop forever
Signed-off-by: Casey Bodley <cbodley@redh... - 05:37 PM Revision 98305932 (ceph): test/rgw: dont assume zone1 and zone2 are on different clusters
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:37 PM Revision efb3b181 (ceph): qa/rgw: add log_level argument to rgwadmin()
- changes default level from info to debug
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 05:29 PM Revision 6c270d56 (ceph): restful: Use pecan hook instead of catch decorator
- This removes the catch decorator which was useful primarily for testing
purposes and instead switches to a pecan erro... - 05:18 PM Revision 23b07323 (ceph): cmake: fix boost components for WITH_SYSTEM_BOOST
- when using WITH_SYSTEM_BOOST dont set header-only packages
for BOOST_COMPONENTS. On some distros these packages dont
... - 04:23 PM Revision 6dc842d2 (ceph): pybind/rados: avoid call free() on invalid pointer
- Signed-off-by: Mingxin Liu <mingxin@xsky.com>
- 04:07 PM CephFS Bug #19934 (Resolved): ceph fs set cephfs standby_count_wanted 0 fails on jewel upgrade
- https://github.com/ceph/ceph/pull/15126
- 04:06 PM Revision 450d6cb5 (ceph): Merge pull request #15126 from batrick/i19934
- qa: silence upgrade test failure
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:05 PM Revision b24fa931 (ceph): mon/MgrMonitor: add 'mgr dump [epoch]' command
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:00 PM Revision cf022fd9 (ceph): mon: quick start if no update in a long period
- Signed-off-by: Mingxin Liu <mingxin@xsky.com>
- 03:51 PM rbd Bug #19875 (Resolved): rbd osd ops repeat alloc hint
- 03:51 PM Revision 9b72f74e (ceph): Merge pull request #15037 from trociny/wip-19875
- librbd: optimize copy-up to add hints only once to object op
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:50 PM Revision 726515e6 (ceph): Merge pull request #15085 from runsisi/wip-fix-trashlist
- librbd: do not raise an error if trash list returns -ENOENT
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:50 PM Revision f6e513e2 (ceph): Merge pull request #15134 from runsisi/wip-fix-trashpy
- pybind/rbd: fix crash if more than 1024 images in trash bin
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:46 PM Bug #19974 (Fix Under Review): "HEALTH_WARN too few PGs per OSD" test_wait_for_health_ok
- https://github.com/liewegas/ceph/pull/38
- 01:42 PM Bug #19974: "HEALTH_WARN too few PGs per OSD" test_wait_for_health_ok
- ...
- 01:11 PM Bug #19974: "HEALTH_WARN too few PGs per OSD" test_wait_for_health_ok
- can be reproduced occasionally locally by running "ceph-helpers.sh test_wait_for_health_ok"
- 01:10 PM Bug #19974 (Resolved): "HEALTH_WARN too few PGs per OSD" test_wait_for_health_ok
- ...
- 02:29 PM Revision 319aac5d (ceph): restful: Use port 8003
- This allows us to run both calamari and the rest api at the same time.
Signed-off-by: Boris Ranto <branto@redhat.com> - 02:25 PM Revision 7cb9b101 (ceph): restful: Generate cert/key in post scripts
- This is the simplest way to generate the keys and probably the least
likely to cause trouble in the future.
Signed-o... - 02:20 PM Revision a8fc220a (ceph): Merge branch pull request #13551 from pritha-srivastava/wip-rgw-role-te...
- rgw: Replaced rgw userid with tenant in ARN for Roles.
rgw: Adding roles under the scope of tenants.
rgw: Added code ... - 01:48 PM Revision 53a9ccf9 (ceph): Merge pull request #15152 from guihecheng/rgw_file-extra-rele
- rgw_file: removed extra rele() on fs in rgw_umount()
- 12:47 PM Bug #15602 (Resolved): should fix the set_headless() in _scrub()
- Greg, nevermind. David has fixed this issue.
- 12:03 PM Revision a6e1fef3 (ceph): ceph.in: assert(state==connected) before help_for_target()
- we always call "cluster_handle.connect()", and error out if connect()
fails.
Signed-off-by: Kefu Chai <kchai@redhat.... - 10:42 AM Revision 8cd63deb (ceph): rgw: optimize generating torrent file. Object data won't stay in memory
- now.
Signed-off-by: Zhang Shaowen <zhangshaowen@cmss.chinamobile.com> - 10:38 AM Revision e40a3810 (ceph): Merge pull request #15142 from bassam/pr-ccache-s-files
- cmake: workaound ccache issue with .S assembly files
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:27 AM Revision 7720bca2 (ceph): rgw_file: fix extra rele on fs in close
- We got exactly a refcnt=0 after rele in close,
no need to rele twice.
Signed-off-by: Gui Hecheng <guihecheng@cmss.ch... - 10:18 AM Revision b4648bf6 (ceph): Merge pull request #15137 from theanalyst/rgw/cleanup/header-drop
- rgw: drop using std ns in header files and other cleanups
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Reviewed-by... - 10:06 AM Revision b7e65938 (ceph): Merge pull request #15145 from zealoussnow/wip-0518
- mailmap: Leo Zhang infomation and affiliation
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Abhishek ... - 09:22 AM Revision 9f90087a (ceph): build: move bash_completion.d/ceph from debian/ceph-base.install to deb...
- when only ceph-common is installed, can also use ceph completion
Signed-off-by: Leo Zhang <nguzcf@gmail.com> - 08:37 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- And I am confused, too.
# dpkg -s ceph-common
Package: ceph-common
Status: install ok installed
Priority: optio... - 07:59 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- ...
- 06:08 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- The files are reported as belonging to the ceph-base and ceph-common packages:
root@ceph-storage-02:/var/lib/dpkg/... - 12:10 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- ...
- 07:40 AM Revision 6f7b339d (ceph): Merge pull request #15143 from minshenglin/fix_broken_link
- doc: fix broken link in erasure-code.rst
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:31 AM Bug #15692: build failed caused by -momit-leaf-frame-pointer on ppc
- It was fixed in Ceph by https://github.com/ceph/ceph/pull/12908
- 07:30 AM rgw Bug #16098: client.radosgw.* vs. client.rgw.*; incompabilities and confusion in code and document...
- I was using the Ubuntu LTS version pre-systemd at that time. So if the init scripts are not maintained, I guess the p...
- 07:26 AM rgw Bug #16098: client.radosgw.* vs. client.rgw.*; incompabilities and confusion in code and document...
- With the advent of systemd, the sysvinit scripts are no longer maintained. Which operating system+version are you using?
- 06:22 AM Revision 58c4c925 (ceph): cmake: remove "-Wp" compile option to speedup ccache
- "-Wp" in not needed and when building with ccache the "cache hits"
only happen afer preproccessing which is slower th... - 06:20 AM devops Bug #19937 (Duplicate): ceph-common needs dependency to psmisc package (Ubuntu 16.04)
- 06:18 AM Revision 5356f2a8 (ceph): build: move bash_completion.d/ceph to ceph-common
- When only ceph-common is installed, can also use ceph completion
Signed-off-by: Leo Zhang <nguzcf@gmail.com> - 06:04 AM Bug #12100: OSD crash, uexpected aio error in FileJournal.cc
- Pontus Lindgren wrote:
> Lowering the queue depth from 32 to 1 solved this issue for us.
>
> @@echo 1 > /sys/bloc... - 05:58 AM Revision a4a72a9f (ceph): qa: split test_tiering into smaller pieces
- so we can debug them individually if anything goes wrong
Signed-off-by: Kefu Chai <kchai@redhat.com> - 04:19 AM Revision 518f516d (ceph): mailmap: Leo Zhang infomation and affiliation
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 03:53 AM CephFS Bug #19854: ceph-fuse write a big file,The file is only written in part
- hi zheng yan:
the problem occurs when multiple clients read/write a file at the same time in our environment; - 02:58 AM Messengers Bug #19705: Ubuntu amd64 client can not discover the ubuntu arm64 ceph cluster
- + ceph-mon.cc1.log
The client IP address is 172.12.55.166
Thanks - 02:49 AM Revision 014c55df (ceph): rgw: optimize data sync. Add zones_trace in bi log to avoid needless sync.
- Fixes: http://tracker.ceph.com/issues/19219
Signed-off-by: Zhang Shaowen <zhangshaowen@cmss.chinamobile.com> - 02:49 AM Documentation #19972 (In Progress): unknown target name in erasure-code.rst
- 01:57 AM Documentation #19972: unknown target name in erasure-code.rst
- https://github.com/ceph/ceph/pull/15143
- 01:47 AM Documentation #19972 (Closed): unknown target name in erasure-code.rst
- an error happened when build doc:
> /home/vincent/Downloads/ceph/doc/rados/operations/erasure-code.rst:141: ERROR:... - 01:48 AM Revision e86cef31 (ceph): doc: fix broken link in erasure-code.rst
- Fixes: http://tracker.ceph.com/issues/19972
Signed-off-by: MinSheng Lin <minsheng.l@inwinstack.com> - 01:14 AM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- John Spray wrote:
> File size recovery should only happen when a client has failed to reconnect properly during the ... - 12:51 AM Revision e1c39851 (ceph): cmake: workaound ccache issue with .S assembly files
- when building with -DWITH_CCACHE=ON recent versions of ccache
(for example 3.3.3) seem to mangle object files from th... - 12:14 AM CephFS Bug #19969 (Fix Under Review): CDir.cc: 909: FAILED assert(get_num_ref() == (state_test(STATE_STI...
- 12:14 AM CephFS Bug #19969: CDir.cc: 909: FAILED assert(get_num_ref() == (state_test(STATE_STICKY) ? 1:0))
- Fix is already in my wip-multimds-misc branch https://github.com/ceph/ceph/pull/14550/commits/b4e0d12c4d00e4994eff3d8...
05/17/2017
- 11:09 PM RADOS Bug #19971 (In Progress): osd: deletes are performed inline during pg log processing
- 11:09 PM RADOS Bug #19971 (Resolved): osd: deletes are performed inline during pg log processing
- With a large number of deletes in a client workload, this can easily saturate a disk and cause very high latency, sin...
- 10:19 PM ceph-ansible Bug #19949: ceph-ansible suite fails on jewel
- @Andrew from IRC chat:
@(04:34:26 PM) vasu: yuriw: neither 2.2.2 or 2.2.3 worked, same error message, you need to ... - 08:29 PM ceph-ansible Bug #19949: ceph-ansible suite fails on jewel
- I see this is using ansible==2.2.1, can we try with 2.2.3. I saw this issue with my ceph-installer tests and updating...
- 10:13 PM Bug #19948: LibRadosTwoPools[EC]PP.PromoteSnap
- ...
- 02:25 PM Bug #19948: LibRadosTwoPools[EC]PP.PromoteSnap
- /a/sage-2017-05-16_22:22:40-rados-wip-sage-testing2---basic-smithi/1186016
- 09:42 PM RADOS Bug #19700: OSD remained up despite cluster network being inactive?
- Was the cluster performing IO while this happened? Do your public and private networks perhaps route to each other?
... - 09:35 PM Bug #19878: msg/simple: reports lossy con on osd->osd connection
- Aren't OSD<->OSD connections supposed to be lossy? Not sure what you think the issue is here, although (without havin...
- 08:50 PM rbd Bug #19970 (Resolved): Reduce the potential for erroneous blacklisting due to release lock race
- There is a potential race when a client attempts to acquire the exclusive lock. If the current lock owner closes the ...
- 08:45 PM rbd Bug #18963: rbd-mirror: forced failover does not function when peer is unreachable
- *PR*: https://github.com/ceph/ceph/pull/15140
- 08:28 PM CephFS Bug #19969: CDir.cc: 909: FAILED assert(get_num_ref() == (state_test(STATE_STICKY) ? 1:0))
- MDS log: https://www.dropbox.com/s/hd7bk0lwznwxlcy/mds.a.log.bz2
- 08:20 PM CephFS Bug #19969 (Resolved): CDir.cc: 909: FAILED assert(get_num_ref() == (state_test(STATE_STICKY) ? 1...
- ...
- 08:06 PM Revision dcd1bfb3 (ceph): Merge branch 'wip-sts-authorization'
- Merge pull request #14307 from adamemerson/wip-sts-authorization
common: Add make_unique
submodule: Tencent's RapidJ... - 07:34 PM RADOS Bug #19790: rados ls on pool with no access returns no error
- Same issue even with just @rw@:...
- 06:38 PM RADOS Bug #19790: rados ls on pool with no access returns no error
- I'm not at a computer to check, but I'm pretty sure the "allow *" is short-circuiting other security checks here and ...
- 04:10 PM RADOS Bug #19790: rados ls on pool with no access returns no error
- 09:12 AM RADOS Bug #19790: rados ls on pool with no access returns no error
- Just checking: is anyone looking at this? It's arguably a security issue, after all.
- 07:00 PM Messengers Bug #19705: Ubuntu amd64 client can not discover the ubuntu arm64 ceph cluster
- We'd also need the logs from the server output. From the client-side one you provided it sure looks like it's connect...
- 10:57 AM Messengers Bug #19705: Ubuntu amd64 client can not discover the ubuntu arm64 ceph cluster
- Thanks for your response, The following logs can help you check this issue?
- 06:50 PM devops Bug #15872 (Fix Under Review): Removing ceph packages should remove 'ceph' user and 'ceph' group ...
- 06:48 PM Revision d67018cb (ceph): test/rgw: add import for StringIO
- also removes unnecessary tuple parens
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:48 PM Revision 4c59d343 (ceph): qa/rgw: move compression type out of ceph.conf
- this makes the 'compression type' setting global to all gateways, and
makes the setting visible to other tasks in ctx... - 06:48 PM Revision 76e14761 (ceph): qa/rgw: fixes for cluster name on cleanup
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:48 PM Revision 746c6309 (ceph): qa/rgw: move startup polling logic to util/rgw.py
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:48 PM Revision a86ce771 (ceph): qa/rgw: add symlink to qa/tasks/rgw_multi
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:48 PM Revision b6d86be2 (ceph): qa/rgw: add rgw_multisite task based on rgw_multi
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:48 PM Revision 4722d1d9 (ceph): qa/rgw: add rgw_multisite_tests task to run tests
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:22 PM Revision 56167d19 (ceph): rgw: Add is_identity to AuthApplier class
- Eventually this will allow us to match all authentication information
against all specified principals in a policy.
... - 06:22 PM Revision 9e8172b8 (ceph): rgw: Move globbing flags to header
- So they can be used when calling the function
Signed-off-by: Adam C. Emerson <aemerson@redhat.com> - 06:22 PM Revision 8416f1c5 (ceph): buffer: Make the use of static areas more convenient
- Make three wrapper functions to tidy up the process of making a
bufferlist holding a single static buffer.
The lack ... - 06:22 PM Revision 69a5eebd (ceph): rgw: Add basic support for IAM policies
- This support is currently incomplete but should provide a starting
point.
Signed-off-by: Adam C. Emerson <aemerson@r... - 06:22 PM Revision 908d9e46 (ceph): rgw: Build bucket permission and environment in req_state
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 06:22 PM Revision 266103fa (ceph): rgw: Verify policies as WELL as ACLs
- Only hook into object/bucket checks for now. Once we have STS (giving
us Roles) or User/Group policies it will make s... - 06:22 PM Revision b7d0b740 (ceph): rgw: RESTful bucket policy ops
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 06:22 PM Revision 80b285d3 (ceph): rgw: Write documentation for bucket policies
- Signed-off-by: Adam C. Emerson <aemerson@redhat.com>
- 06:22 PM Revision 7cd1ccf4 (ceph): common: Add ISO-8601 Date Support
- For parsing and unparsing from ceph::real_time.
Signed-off-by: Adam C. Emerson <aemerson@redhat.com> - 06:13 PM Revision b1658065 (ceph): doc/rgw: clean up multisite config options
- remove region stuff, radosgw-agent stuff, and zone/pool stuff that is
duplicated in the multisite page
moved sync lo... - 06:13 PM Revision f1c2f9a6 (ceph): doc/rgw: remove Federated Configuration page
- Fixes: http://tracker.ceph.com/issues/18082
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:13 PM Revision a9c71e12 (ceph): doc/rgw: remove Upgrade to Older Versions of Jewel page
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 06:13 PM Revision 0f9935cc (ceph): doc/rgw: update pool names, document namespaces
- Fixes: http://tracker.ceph.com/issues/19504
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:07 PM Revision 1711c1a3 (ceph): doc/rgw: update pool names, document namespaces
- Fixes: http://tracker.ceph.com/issues/19504
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 05:58 PM Revision a5bc87b4 (ceph): doc/rgw: clean up multisite config options
- remove region stuff, radosgw-agent stuff, and zone/pool stuff that is
duplicated in the multisite page
moved sync lo... - 05:58 PM Revision fa3b2e8f (ceph): doc/rgw: remove Federated Configuration page
- Fixes: http://tracker.ceph.com/issues/18082
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 05:58 PM Revision 5a7dff5f (ceph): doc/rgw: remove Upgrade to Older Versions of Jewel page
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:01 PM Revision ec4f4c8a (ceph): rgw: migrate atomic_t to std::atomic<>
- Signed-off-by: Jesse Williamson <jwilliamson@suse.de>
- 04:26 PM Revision 64acb163 (ceph): common: Add make_unique
- There are parts of C++14 that are both useful and easy to
implement. This is one of them.
Signed-off-by: Adam C. Eme... - 04:26 PM Revision c3f2447c (ceph): submodule: Tencent's RapidJSON library
- This is a high performance, MIT licensed JSON parsing library. It
provides a SAX interface so that I can compile an S... - 04:05 PM Bug #16685 (Closed): "saw valgrind issues" in rados run
- We have passed many valgrind runs with the AsyncMessenger in the past 9 months.
- 04:01 PM Bug #16497 (Can't reproduce): "Mutex.h:89: void Mutex::_post_lock(): Assertion `nlock == 0'" in u...
- 04:00 PM rgw Bug #16650 (Resolved): qa: rgw_roundtrip fail
- The PR merged so I assume this is done?
- 04:00 PM Bug #16457 (Can't reproduce): osd|messenger: valgrind leak of MOSDMap payload
- 04:00 PM Bug #16453 (Can't reproduce): "mon/Paxos.cc: 197: FAILED assert(mon->is_peon())" in rados-hammer-...
- 04:00 PM Bug #16629: [centos] hammer ceph-release-*.noarch.rpm packages have wrong baseurls in their ceph....
- Ken, do you know if this works now? I'm not even sure where it's configured. *blush*
- 03:57 PM Bug #16402 (Rejected): "bad_alloc" in rados-infernalis-distro-basic-openstack
- too little memory on the machines
- 03:57 PM Bug #16403 (Rejected): 'ceph::buffer::bad_alloc' in rados-hammer-distro-basic-vps
- too little memory on the machines
- 03:55 PM Revision 3bb9dd47 (ceph): ceph_test_rados_api_list: more fix LibRadosListNP.ListObjectsError
- Follow-on to d7e6e8d60309e4800389b36f786b633d0ca2ec07; we need to
make sure the client gets the updated osdmap.
Fixe... - 03:54 PM CephFS Bug #16588 (Resolved): ceph mds dump show incorrect number of metadata pools.
- 03:54 PM Bug #16359 (Duplicate): radosgw stats user's incomplete data upload
- 03:53 PM RADOS Bug #16567: Ceph raises scrub errors on pgs with objects being overwritten
- Hmm, similar reports have popped up (although with on-disk size 0) on the mailing list. Those involved cache tiers th...
- 03:53 PM Bug #16307 (Closed): make check failure while can not find gmock/lib/libgmock_main.la
- cmake used in master should fix this
- 03:51 PM RADOS Bug #16279: assert(objiter->second->version > last_divergent_update) failed
- xfs corruption means your setup was not safe for power failure, or your disk is dying. Neither is something that ceph...
- 03:50 PM Feature #16562: rados put: use the FULL_TRY flag to report errors when cluster is full
- David, can you confirm this is fixed after your work on full states?
- 03:49 PM Bug #16559 (Resolved): Incorrect parameter in call of bloom_filter leads to bad implicit conversion
- This was just wrong and got fixed.
- 03:45 PM Bug #16510 (Closed): the order“ceph osd df”show the repeated results
- According to the PR this is the result of linking OSDs into the tree in multiple places, and is desired behavior (bec...
- 03:44 PM Bug #16234 (Rejected): Ceph osd daemon keeps running even after disk has been pulled
- No cluster should be entirely idle. At the very least scrubbing should be running, and will get an error from the dis...
- 03:43 PM Revision 752b8389 (ceph): Merge pull request #13731 from liewegas/wip-19119
- PendingReleaseNotes: warning about 'osd rm ...' and #19119
- 03:43 PM rbd Bug #16502 (Need More Info): fio ended up with soft lockup - CPU#1 stuck for 22s!
- AFAIK this could happen for a bunch of reasons, including an unresponsive cluster.
- 03:42 PM Revision 3c6755e0 (ceph): PendingReleaseNotes: warning about 'osd rm ...' and #19119
- See http://tracker.ceph.com/issues/19119
Signed-off-by: Sage Weil <sage@redhat.com> - 03:42 PM Bug #16211 (Won't Fix): Some rbd images inaccessible after upgrade to jewel (error reading immuta...
- It sounds like this was caused by a firefly or older cluster, is not widespread, and has a simple workaround. It does...
- 03:41 PM Bug #19884: support Debian stretch
- Thanks Dan! i did also check the latest patch submitted Gaudenz before posting my pull request.
- 03:25 PM Bug #19884 (Pending Backport): support Debian stretch
- 03:38 PM RADOS Bug #15936: Osd-s on cache pool crash after upgrade from Hammer to Jewel
- Ping Joao? This looks to have been a crash in persisting/trimming HitSets, which I know underwent a bunch of changes/...
- 03:35 PM Bug #13522 (Resolved): Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocat...
- ...
- 03:34 PM Bug #15861 (Closed): yum update warnings in master: ldconfig: relative path `1' used to build cache
- Is this still a thing? We can reopen if so.
- 03:33 PM Bug #15813 (Can't reproduce): Assertion 0.94.5 - ceph-osd
- The crash here is about ephemeral state so there's no risk to the data being stored. I think we've fixed a few races ...
- 03:30 PM Bug #15782 (Can't reproduce): "kv/LevelDBStore.cc: 270: FAILED assert(value && (value->length() =...
- Don't see any other reports in my email and it's been a year.
- 03:30 PM Bug #15777 (Won't Fix): OSD: partially missing on disk osdmaps between superblock.oldest_map and ...
- If somebody can tell us how to reproduce we might take a look, but Hammer isn't being worked on much any more and the...
- 03:29 PM Revision c9464556 (ceph): Merge pull request #14873 from liewegas/wip-bluefs-position
- os/bluestore: put bluefs in the middle of the shared device
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 03:29 PM Revision 55c47ef6 (ceph): Merge pull request #14902 from liewegas/wip-upmap
- osd/OSDMap: improve upmap calculation
Reviewed-by: Loic Dachary <loic@dachary.org> - 03:29 PM Revision 35834a30 (ceph): Merge pull request #14933 from liewegas/wip-asok-schema
- common/perf_counters: make schema more friendly and update docs
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 03:28 PM Revision 16cce5a5 (ceph): Merge pull request #14967 from tchaikov/wip-faster-cull
- mgr: optimize DaemonStateIndex::cull() a little bit
Reviewed-by: John Spray <john.spray@redhat.com> - 03:28 PM Bug #15774 (Resolved): osd_op_queue_cut_off osd_op_queue debug_random generate assert failure.
- 03:27 PM Bug #16158 (Can't reproduce): "map e18 wrongly marked me down" in cluster log"
- 03:26 PM Bug #16139 (Closed): ceph health detail reports acting osd number of (MAX_INT+1) when insufficien...
- -1 represents lack of an osd there - iirc it's printed more nicely in master
- 03:26 PM Revision 81bd3025 (ceph): Merge pull request #15002 from dachary/wip-19836-crush-pre-luminous
- crush: encode can override weights with weight set
Reviewed-by: Sage Weil <sage@redhat.com> - 03:25 PM Bug #19836 (Resolved): crush: encode weight_set in a pre-weight-set crushmap
- 03:25 PM Revision 9a06fdbf (ceph): Merge pull request #15031 from tchaikov/wip-drop-unused-opts
- config_opts: drop unused opts
Reviewed-by: Sage Weil <sage@redhat.com> - 03:24 PM Revision 570f5764 (ceph): Merge pull request #15043 from tchaikov/wip-19884
- ceph-detect-init: detect init system by poking the system
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:24 PM Revision 0260a526 (ceph): Merge pull request #15059 from liewegas/wip-mon-kvtype
- mon: fix mon_keyvaluedb application
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:23 PM Bug #15763 (Closed): Slow recovery times, slowing further toward the end of the recovery
- There's been a bunch of work already to improve recovery handling and prioritization; there's planned work coming up....
- 03:22 PM Bug #15759 (Duplicate): hammer: ceph-disk: wrong log level of command
- #15775
- 03:21 PM Backport #15775 (Rejected): hammer: ceph-disk: wrong log level of command
- Following the PR chain, sounds like original reporter doesn't care and neither do we?
- 03:19 PM RADOS Bug #15741: librados get_last_version() doesn't return correct result after aio completion
- Any update on this, David? :)
- 03:19 PM Bug #15692 (Closed): build failed caused by -momit-leaf-frame-pointer on ppc
- 03:19 PM Bug #15663 (Closed): build failed on ppc ubuntu
- Not sure if this is working right now, but I know we've had PPC fix patches come in so it's building *somewhere* in t...
- 03:17 PM Bug #15640 (Resolved): mon: %USED shows (size of pool)/(raw space available on OSDs); should show...
- This got reworked recently by Sage. (February, Josh thinks?)
- 03:16 PM Bug #15629 (Can't reproduce): osd crashed after pg repair
- Log file is gone now.
- 03:15 PM Bug #16124 (Can't reproduce): kstore segv in _do_read_stripe
- 03:15 PM Bug #15624 (Closed): not able to set "Parent task set"
- 03:14 PM Bug #15620 (Closed): Error while doing service ceph start
- 03:14 PM Revision 6d991c5c (ceph): rbd: remove unnecessary -ENOENT check for rbd cli
- Signed-off-by: runsisi <runsisi@zte.com.cn>
- 03:14 PM Revision 3e3bb7b0 (ceph): librbd: translate error -ENOENT to 0 for list APIs
- Signed-off-by: runsisi <runsisi@zte.com.cn>
- 03:14 PM Bug #15616 (Resolved): ceph-osd crashes in FileStore::omap_get_values
- PR merged
- 03:14 PM Bug #16116 (Can't reproduce): "AssertionError: failed to recover before timeout expired" in rados...
- 03:14 PM rgw Bug #19965 (New): RGW handling of combined If-None-Match and If-Modified-Since request is not RFC...
- If you look at the rfc2616 (section 14.26), my interpretation is that is that the result should be as follow :
<pr... - 03:13 PM Bug #15602: should fix the set_headless() in _scrub()
- I have no idea what this ticket means?
- 03:12 PM Bug #15601 (Closed): ceph-deploy fails on RHEL 7.0 complaining about ceph-osd , ceph-md , ceph-mon
- I don't think anybody ships community Ceph for RHEL.
- 03:12 PM Bug #15596 (Can't reproduce): OSDs not mounted at boot, ceph-disk says "Error: unrecognized parti...
- Haven't heard anything about this and it's been a year...
- 03:11 PM Bug #16064 (Can't reproduce): AssertionError: Didn't find 'omap_digest_mismatch' in errors
- 03:11 PM Bug #16050 (Can't reproduce): abort in tcmalloc::Log() in firefly osd
- 03:10 PM Bug #16032 (Resolved): drop python-flask dependency from radosgw
- 03:10 PM Bug #15585 (Resolved): jewel: debian package: init.d script bug
- Script in master looks good now; presume it got backported as necessary.
- 03:08 PM Bug #16003 (Can't reproduce): test bug: objectstore tool export/import of only copy allowed pg to...
- 03:04 PM Revision 3b943b49 (ceph): Merge pull request #15032 from tchaikov/wip-doc-opts
- doc: add descriptions for mon/mgr options
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 03:01 PM devops Bug #19577 (Resolved): ship radosgw-admin in ceph-common package
- 02:56 PM Revision 7ff83a44 (ceph): doc: mention certain conf vars should be in global
- This is to make it apply whenever the radsogw-admin
command is run without specifying the instance name
Signed-off-b... - 02:29 PM Bug #19947: osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- /a/sage-2017-05-16_22:22:40-rados-wip-sage-testing2---basic-smithi/1186082
- 02:28 PM Bug #19427: common/LogClient.cc: 310: FAILED assert(num_unsent <= log_queue.size())
- This is still happening:...
- 02:23 PM RADOS Bug #19964 (Resolved): occasional crushtool timeouts
- ...
- 02:21 PM Bug #19963: LibRadosListNP.ListObjectsError
- https://github.com/ceph/ceph/pull/15138
- 02:21 PM Bug #19963 (Resolved): LibRadosListNP.ListObjectsError
- ...
- 02:16 PM Revision 9db24d55 (ceph): rgw: drop expat header in a couple of files
- Since it is already a part of rgw_xml
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 02:13 PM Revision b4a4416e (ceph): rgw: drop using namespace std in header files
- We're still having the include in include/type.h, so just sweeping
things under the rug for now
Signed-off-by: Abhis... - 02:11 PM Revision ef5265f1 (ceph): mon/Elector: call cancel_timer() in shutdown()
- instead of doing it manually.
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 12139ae529a49b6... - 02:11 PM Revision e3cba06b (ceph): mon: check is_shutdown() in timer callbacks
- introduce a helper class: C_MonContext, and initialize all timer events
using it, to ensure that they do check is_shu... - 02:10 PM Revision 9693b6bd (ceph): jewel: mon: add override annotation to callback classes
- The only purpose of this patch is to avoid merge conflicts while
cherry-picking commit 561cbded0c7e28231b1c7ce18663b8... - 02:02 PM Revision ea1b21d9 (ceph): mon/PaxosService: move classes to cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
(cherry picked from commit a4e979a41c7d3649cf70f9d0768015d7ff4aca8a) - 01:47 PM Revision 1869ed9b (ceph): mon/Paxos: move classes to .cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
(cherry picked from commit d21357a7e042424754d9ab41c134cae9e89945f9) - 01:43 PM Revision 18cf3023 (ceph): mon/Elector:move C_ElectionExpire class to cc file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
(cherry picked from commit c819596e59fd5f66b3258fedd1d10b20cf70f0a9) - 01:43 PM Revision fa33e760 (ceph): mon/Monitor: move C_Scrub, C_ScrubTimeout to .cc
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
(cherry picked from commit e58750127cbe8728f4047411904af3890966490f) - 01:38 PM Revision 73da4e19 (ceph): os/bluestore/KernelDevice: helpful warning when aio limit exhausted
- Suggested-by: Dan Van Der Ster <daniel.vanderster@cern.ch>
Signed-off-by: Sage Weil <sage@redhat.com> - 01:03 PM Revision a1328cde (ceph): pybind/rbd: fix crash if more than 1024 images in trash bin
- Signed-off-by: runsisi <runsisi@zte.com.cn>
- 12:48 PM rbd Bug #19962 (Resolved): Discard related IO should skip op if object map marks object as non-existent
- The discard-related ops should queue their completion if the object map is enabled and it detects that the object doe...
- 11:37 AM rgw Bug #19961 (New): luminous: rgw: leaked _shadow_ zero size tail objects if whole object size is m...
If s3 object size is multible of rgw_max_chunk_size
then after deletion and after gc completes
last _shadow_ obj...- 11:21 AM RADOS Bug #19960 (Resolved): overflow in client_io_rate in ceph osd pool stats
- luminous branch, v12.0.2
Output of ceph osd pool stats -f json contains overflowed values in client_io_rate sectio... - 11:20 AM CephFS Bug #19955 (Fix Under Review): Too many stat ops when MDS trying to probe a large file
- https://github.com/ceph/ceph/pull/15131
- 11:12 AM CephFS Bug #19955: Too many stat ops when MDS trying to probe a large file
- File size recovery should only happen when a client has failed to reconnect properly during the MDS restart. Is that...
- 03:29 AM CephFS Bug #19955 (Resolved): Too many stat ops when MDS trying to probe a large file
- When MDS recovers, it may emit tons of `stat` ops to OSDs trying to probe a large file, which as a result prevents cl...
- 11:18 AM Revision 618b9b3f (ceph): Merge pull request #15127 from tchaikov/wip-vstart-mgr-debug-ms
- vstart: "debug_ms=1" for mgr by default
Reviewed-by: John Spray <john.spray@redhat.com> - 11:17 AM rgw Bug #19959 (Resolved): luminous: rgw: s3 user stats not updated after radosgw-admin bucket rm --p...
- luminous branch, v12.0.2
After deletion of bucket with radosgw-admin with --purge-objects (with deletion of objects)... - 11:16 AM Linux kernel client Bug #19958 (Resolved): missing i_nlink check while converting a file handle to dentry
- xfstest generic/426 is failing due to a missing i_nlink check while converting a file handle to dentry. Here's the t...
- 10:49 AM CephFS Bug #19854: ceph-fuse write a big file,The file is only written in part
- hi zheng yan:
disable page cache at the client(fuse_disable_pagecache = true), problem disappear; - 09:14 AM rbd Backport #19957 (Resolved): jewel: rbd: Lock release requests not honored after watch is re-acquired
- https://github.com/ceph/ceph/pull/17385
- 09:06 AM CephFS Bug #19946 (Fix Under Review): CInode.cc: 2481: FAILED assert(s == nested_auth_pins)
- https://github.com/ceph/ceph/pull/15130
- 03:40 AM CephFS Bug #19946: CInode.cc: 2481: FAILED assert(s == nested_auth_pins)
- happens only when mds_debug_auth_pins is enabled. the new dirfrag hasn't been added to inode's frag map, which confus...
- 09:01 AM Revision 2c537ee7 (ceph): mds: fix CDir::merge() for mds_debug_auth_pins
- Fixes: http://tracker.ceph.com/issues/19946
Signed-off-by: "Yan, Zheng" <zyan@redhat.com> - 09:00 AM Revision fab6fc15 (ceph): Merge pull request #15103 from drunkard/master
- doc: minor fixes in radosgw/
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:58 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- revival of http://tracker.ceph.com/issues/15569 ?
- 08:54 AM Revision ae8eee2f (ceph): Merge pull request #15080 from hikycool/master
- doc: update the usage of 'ceph-deploy purge'
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:44 AM Revision e6be9335 (ceph): mon/MDSMonitor: respect mds_standby_for_rank config
- Signed-off-by: "Yan, Zheng" <zyan@redhat.com>
- 08:27 AM devops Bug #19937: ceph-common needs dependency to psmisc package (Ubuntu 16.04)
- Jewel using the latest available release:
# apt-cache policy ceph-common
ceph-common:
Installed: 10.2.7-1xenia... - 08:07 AM devops Bug #19937: ceph-common needs dependency to psmisc package (Ubuntu 16.04)
- @Burkhard: which version of Ceph are we talking about here?
- 08:14 AM Revision 4d66902e (ceph): mds: don't pin inodes in MDCache::export_pin_queue
- pinning inode can trigger assertion when replaying log
1: (()+0x560ceb) [0x55b263ff7ceb]
2: (()+0x115c0) [0x7fc039... - 07:29 AM Backport #18958 (Resolved): jewel: IPv6 Heartbeat packets are not marked with DSCP QoS - simple m...
- 07:29 AM Revision 966f2229 (ceph): Merge pull request #13450 from dreamhost/wip-18887-jewel
- jewel: msg: IPv6 Heartbeat packets are not marked with DSCP QoS - simple messenger
Reviewed-by: Josh Durgin <jdurgin... - 06:15 AM Bug #19900: osd crash during shutdown
- ...
- 12:31 AM Bug #19900: osd crash during shutdown
- This was actually a crash, from teuthology.log:...
- 04:47 AM rgw Bug #19956: radosgw Segmentation fault when service is restarted during lifecycle processing
- Yikes, same fault also happened when I pushed a new period map, which caused the 'realm reloader' to trigger. That ma...
- 04:25 AM rgw Bug #19956 (Resolved): radosgw Segmentation fault when service is restarted during lifecycle proc...
- ceph version 11.2.0 (f223e27eeb35991352ebc1f67423d4ebc252adb7),
1. Trigger a lifecycle gc run
2. Restart the ser... - 04:31 AM rgw Bug #19906: Random Segmentation fault thread_name:civetweb-worker
- I suspect this is the same as my crash: http://tracker.ceph.com/issues/19704 - though your offsets are different bec...
- 03:56 AM Revision d4195bb8 (ceph): rgw: rename s3_code to err_code for swift
- Signed-off-by: Guo Zhandong <guozhandong@cmss.chinamobile.com>
- 03:36 AM rgw Documentation #19953 (Duplicate): multisite.rst: update pool names in Pools section and describe ...
- 02:47 AM rgw Documentation #19953 (Duplicate): multisite.rst: update pool names in Pools section and describe ...
- 03:14 AM mgr Bug #19954 (Resolved): mgr key needs "mon 'allow *'" caps
- Prior to https://github.com/ceph/ceph/commit/5906e359bd and https://github.com/ceph/ceph/commit/6625fcd8fd, the mgr k...
- 02:41 AM Revision d05fdd38 (ceph): rgw: fix X-Object-Meta-Static-Large-Object in SLO download
- when download SLO objects, the response header "X-Object-Meta-Static-Large-Object" doesn't decode. Expect value is "T...
- 02:36 AM Revision 4b338ce9 (ceph): doc/rgw: remove fastcgi page and sample configs
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 02:31 AM Revision a6daa84d (ceph): vstart: "debug_ms=1" for mgr by default
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:31 AM rgw Bug #19951 (Resolved): rgw:SLO download response header "X-Object-Meta-Static-Large-Object" has 4...
- https://github.com/ceph/ceph/pull/15045
- 02:28 AM Revision cdf7a719 (ceph): print clusterinfo
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 01:19 AM Revision 5bc0e344 (ceph): common: Remove redundant includes
- Fixes: http://tracker.ceph.com/issues/19883 (Partially)
Signed-off-by: Jos Collin <jcollin@redhat.com> - 12:45 AM Bug #19950: ceph-deploy doesn't automatically create ceph-<number> in osd directory
- Additional info..
when I remove / comment this line in the ceph.conf... - 12:22 AM Bug #19950 (Closed): ceph-deploy doesn't automatically create ceph-<number> in osd directory
- Hi,
I used tro try to upgrade my existing Ceph cluster from Hammer to Jewel (10.2.7) in CentOS 7.3.1611.
As I us...
05/16/2017
- 10:47 PM Revision a21d411c (ceph): osd: fix argument-dependent lookup of swap()
- because include/types.h has a 'using namespace std', the call to
::swap() had previously been selecting overloads fro... - 10:43 PM Revision 6c34a2c6 (ceph): qa: silence upgrade test failure
- The new fs setting standby_count_wanted is only avialable in luminous. Upgrade
tests were tripping on this.
Fixes: h... - 10:15 PM Bug #18522 (Pending Backport): mon: MAX AVAIL calcuation does not fact or in mon_osd_full_ratio
- 10:02 PM Revision 4b72940d (ceph): qa: fix float parse error in test_fragment
- 2017-05-16 17:45:30,663.663 INFO:__main__:run args=['./bin/ceph', 'daemon', 'mds.b', 'perf', 'dump', 'mds']
2017-... - 09:35 PM Bug #19877 (Resolved): check_past_interval_bounds assert after split
- 08:14 PM Bug #19877: check_past_interval_bounds assert after split
- https://github.com/ceph/ceph/pull/14989 merged
- 09:33 PM Revision 9da68431 (ceph): osd/PGLog: avoid pinning large buffers with ObjectModDesc
- Accidentally removed by 5e0ec06376f832d32a6b1af390f925a59b03798f.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:33 PM Revision 234a989d (ceph): osd: encode snaps more efficiently
- 1- encode into a sized buffer.
2- do not needlessly copy the set<> to a vector<> before encoding.
set<> and vector<> ... - 09:25 PM ceph-ansible Bug #19949 (New): ceph-ansible suite fails on jewel
- Run: http://pulpito.ceph.com/teuthology-2017-05-14_04:15:02-ceph-ansible-jewel-distro-basic-vps/
Logs: http://qa-pro... - 09:16 PM Revision 6ecb0329 (ceph): mon: add test for crush type down health warnings
- Signed-off-by: Neha Ojha <nojha@redhat.com>
- 08:47 PM Revision a07ad9fe (ceph): qa/suites/rados/thrash: add redirect test cases
- Signed-off-by: Myoungwon Oh omwmw@sk.com
- 08:44 PM Revision d44fd08a (ceph): src/test: RadosModel (redirected I/O test, Set/Unset Redirect)
- Signed-off-by: Myoungwon Oh omwmw@sk.com
- 08:38 PM Revision 402d747a (ceph): osd: handle IGNORE_REDIRECT
- Signed-off-by: Myoungwon Oh omwmw@sk.com
- 08:38 PM Revision 81a802c5 (ceph): librados: add op flag (IGNORE_REDIRECT)
- Signed-off-by: Myoungwon Oh omwmw@sk.com
- 08:35 PM Revision 2f96956b (ceph): osd/pglog: Remove loop through empty collection.
- Signed-off-by: J. Eric Ivancich <ivancich@redhat.com>
- 08:20 PM Revision 26df056e (ceph): Merge pull request #15087 from liewegas/wip-thrash-ec
- qa/suites/rados: fix ec thrashing
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:19 PM Revision 07ac91d4 (ceph): Merge pull request #15072 from liewegas/wip-crush-swap-bucket
- mon,crush: add 'osd crush swap-bucket' command
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Kefu Chai <... - 08:18 PM Revision 9187156b (ceph): Merge pull request #15069 from tchaikov/wip-inttypes-cleanup
- int_types.h: remove hacks to workaround old systems
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 08:17 PM Revision 98827f44 (ceph): Merge pull request #15057 from liewegas/wip-osd-choose-cleanup
- osd/PG: drop pre-firefly compat_mode for choose_*_acting
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Davi... - 08:16 PM Revision a49d9c56 (ceph): Merge pull request #15042 from badone/wip-redundant-headers-3
- common: Remove redundant includes
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:13 PM Revision 0e03291c (ceph): Merge pull request #14989 from liewegas/wip-19877
- osd: fix past_intervals base case by adding epoch_pool_created to pg_history_t
Reviewed-by: Josh Durgin <jdurgin@red... - 08:02 PM Bug #19948 (Resolved): LibRadosTwoPools[EC]PP.PromoteSnap
- ...
- 07:59 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- /a/yuriw-2017-05-15_22:59:10-rados-wip-yuri-testing_2017_5_16-distro-basic-smithi/1181575 (bluestore)
- 05:55 PM RADOS Bug #19943: osd: enoent on snaptrimmer
- Clone 269 was trimmed but it corresponds to a lot of other snapshots, so the object shouldn't be removed until all th...
- 04:04 PM RADOS Bug #19943 (Resolved): osd: enoent on snaptrimmer
- ...
- 07:58 PM Bug #19947 (Resolved): osd/PGLog.h: 1235: FAILED assert(miter->second.have == eversion_t())
- ...
- 07:51 PM CephFS Bug #19946: CInode.cc: 2481: FAILED assert(s == nested_auth_pins)
- Full MDS log: https://www.dropbox.com/s/skjrie44ngc27cj/mds.b.log.bz2
- 07:50 PM CephFS Bug #19946 (Resolved): CInode.cc: 2481: FAILED assert(s == nested_auth_pins)
- nested_auth_pins == 2
s == 1
2017-05-16 10:15:54.754892 7fea71adb700 -1 /home/dfuller/ceph/src/mds/CInode.cc:
I... - 07:39 PM Revision b540b429 (ceph): mon/OSDMonitor: introduce debug option to allow filestore for ec overwr...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:39 PM Revision b54da2e5 (ceph): doc: mention certain conf vars should be in global
- This is to make it apply whenever the radsogw-admin
command is run without specifying the instance name
Resolves: rh... - 06:37 PM Revision b2a9ad79 (ceph): doc: mention certain conf vars should be in global
- This is to make it apply whenever the radsogw-admin
command is run without specifying the instance name
Signed-off-b... - 06:05 PM Revision 38ba53d0 (ceph): Merge pull request #15113 from trociny/wip-unittest_librbd-cleanup
- test/librbd: unit tests cleanup
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 05:51 PM devops Bug #15872: Removing ceph packages should remove 'ceph' user and 'ceph' group as well
- *PR*: https://github.com/ceph/ceph/pull/15118
- 05:38 PM devops Bug #15872: Removing ceph packages should remove 'ceph' user and 'ceph' group as well
- I'm interested in fixing this and am working on a patch.
- 05:37 PM Bug #17689 (Resolved): upstart: race condition starting ceph-all jobs depending on network
- Fixed in https://github.com/ceph/ceph/pull/11631
- 04:36 PM Bug #17689: upstart: race condition starting ceph-all jobs depending on network
- Related: https://bugs.launchpad.net/bugs/1636322
- 04:54 PM RADOS Feature #19944 (Rejected): [RFE]: add option/support config persistence with ceph tell command
- we should have support in ceph itself to make the conf changes persist, ceph tell has good error checking mechanism a...
- 04:41 PM rgw Bug #19920: test_cls_rgw.sh FAILED ClsSDK.TestSDKCoverageReplay (2035 ms)
- also in http://qa-proxy.ceph.com/teuthology/teuthology-2017-05-15_05:00:21-smoke-master-testing-basic-vps/1178707/teu...
- 04:40 PM rbd Bug #19929 (Pending Backport): Lock release requests not honored after watch is re-acquired
- 04:40 PM Revision dbde7af1 (ceph): Merge pull request #15093 from dillaman/wip-19929
- librbd: reacquire lock should update lock owner client id
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 04:28 PM Revision e57ecb64 (ceph): qa/suites/rados/thrash: make sure osds have map before legacy scrub
- The OSDs must have a map reflecting the require_luminous flag in order
for the legacy conversion to happen. A quick ... - 03:54 PM Revision 978f1d3a (ceph): Merge pull request #10690 from ceph/wip-rgw-polymorphic-errors
- rgw: polymorphic error codes
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 03:17 PM rbd Bug #19636: upgrade:client-upgrade/{hammer,jewel}-client-x/rbd failing in kraken 11.2.1 integrati...
- Seems similar in http://pulpito.ceph.com/teuthology-2017-05-13_05:45:02-upgrade:client-upgrade-kraken-distro-basic-sm...
- 03:12 PM rbd Bug #19942 (Duplicate): "[ FAILED ] TestLibRBD.Metadata" in upgrade:client-upgrade-kraken-distr...
- Run: http://pulpito.ceph.com/teuthology-2017-05-13_05:45:02-upgrade:client-upgrade-kraken-distro-basic-smithi/
Job: ... - 03:11 PM Revision 60f90461 (ceph): Merge pull request #15096 from jcsp/wip-journalrepair-test
- qa: simplify TestJournalRepair
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 03:06 PM Bug #19598: "Unable to correct problems, you have held broken packages." in upgrade:hammer-jewel-...
- Suspect the same issue in upgrade:client-upgrade-kraken run:
http://qa-proxy.ceph.com/teuthology/teuthology-2017-05-... - 02:21 PM Bug #19598: "Unable to correct problems, you have held broken packages." in upgrade:hammer-jewel-...
- Also in http://pulpito.ceph.com/teuthology-2017-05-14_02:25:02-upgrade:hammer-jewel-x-kraken-distro-basic-smithi/
- 02:53 PM rgw Bug #19932 (Pending Backport): rgw_file: v3 write timer does not close open handles
- 02:29 PM Revision 8b2e41c0 (ceph): rgw_file: v3: fix write-timer action
- For now, unify with v4 write-on-close path, by calling
RGWFileHandle::close() on write-timer expire, since it will
ca... - 02:24 PM Bug #19414: ceph-deploy fails on ovh nodes
- Also in http://pulpito.ceph.com/teuthology-2017-05-13_05:55:02-ceph-deploy-kraken-distro-basic-ovh/
- 02:20 PM Revision 225bc600 (ceph): Merge pull request #15110 from tchaikov/wip-build-using-cmake
- doc: use do_cmake.sh instead of `cmake ..`
Reviewed-by: Sage Weil <sage@redhat.com> - 02:19 PM Revision e7d1d877 (ceph): Merge pull request #15023 from tchaikov/wip-cmdparse-constness
- cmdparse: more constness
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:53 PM Bug #19941 (Resolved): ceph-disk fails if OSD udev rule triggers prior to mount of /var
- Another "my OSDs don't come up on reboot" bug:
ceph-disk unconditionally calls setup_statedir() during initialisat... - 01:50 PM Revision 33494b27 (ceph): mon/MgrMonitor: s/digest_callback/digest_event/
- to be consistent with the rest of mon
Signed-off-by: Kefu Chai <kchai@redhat.com> - 01:50 PM Revision a80ff012 (ceph): mon/MgrMonitor: cancel timer before resetting it
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 01:50 PM Revision 9061c893 (ceph): mon/MgrMonitor: send digests only if is_active()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 01:50 PM Revision a850dc23 (ceph): mon/MgrMonitor: use mono clock to avoid potention issue introduced by t...
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 01:43 PM mgr Bug #19940 (Resolved): client.admin not granted mgr caps on upgrade (was: mgr access denied on pg...
- 12:39 PM mgr Bug #19940 (Fix Under Review): client.admin not granted mgr caps on upgrade (was: mgr access deni...
- https://github.com/ceph/ceph/pull/15112
- 12:12 PM mgr Bug #19940: client.admin not granted mgr caps on upgrade (was: mgr access denied on pg dump)
- Found it. client.admin now needs the mgr 'allow *' cap.
This fixes it:... - 12:04 PM mgr Bug #19940: client.admin not granted mgr caps on upgrade (was: mgr access denied on pg dump)
- ...
- 11:58 AM mgr Bug #19940 (Resolved): client.admin not granted mgr caps on upgrade (was: mgr access denied on pg...
- This is a newly deployed master test cluster running ceph-12.0.2-1185.g3155335.el7.x86_64.
Once per minute our mgr... - 01:43 PM Revision 035c3984 (ceph): Merge pull request #15112 from jcsp/wip-19940
- ceph-create-keys: update client.admin if it already exists
Reviewed-by: Sage Weil <sage@redhat.com> - 01:07 PM Revision fc286d61 (ceph): Merge pull request #15097 from linuxbox2/wip-rgwfile-write3
- rgw_file: v3: fix write-timer action
- 12:46 PM mgr Bug #17738 (Duplicate): Deadlock when shutdown() is called while still in init()
- 12:42 PM Revision f2337d1b (ceph): 12.0.3
- 12:39 PM Revision c0c64433 (ceph): test/librbd: make unit tests pass when cache is disabled
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:39 PM Revision c065cbdb (ceph): test/librbd: TestMockImageRemoveRequest gmock warnings
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 12:32 PM Revision 63855e38 (ceph): doc: add hyperlink on ACL settings
- The link listed at bottom but never used, I think it's missed by author.
Signed-off-by: Drunkard Zhang <gongfan193@g... - 12:28 PM Revision 82332b7a (ceph): ceph-create-keys: update client.admin if it already exists
- This means that anyone who de-privileges their client.admin
user will find that it gets resets with full privileges a... - 12:20 PM Revision 0f811b3d (ceph): doc: typo fixes in doc/radosgw/multisite
- Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
- 11:08 AM RADOS Bug #19939 (Resolved): OSD crash in MOSDRepOpReply::decode_payload
Seen on kcephfs suite, running against test branch based on Monday's master....- 11:00 AM CephFS Bug #19934: ceph fs set cephfs standby_count_wanted 0 fails on jewel upgrade
- ...
- 02:19 AM CephFS Bug #19934 (Resolved): ceph fs set cephfs standby_count_wanted 0 fails on jewel upgrade
- ...
- 10:54 AM Revision ba6e5e8d (ceph): doc: use do_cmake.sh instead of `cmake ..`
- user could be confused at seeing errors like:
src/CMakeLists.txt:644 (add_subdirectory): The source directory /src/l... - 10:00 AM CephFS Bug #19892 (Fix Under Review): Test failure: test_purge_queue_op_rate fails
- 09:52 AM CephFS Bug #19893 (Resolved): test_rebuild_simple_altpool fails
- 09:51 AM Revision 3155335c (ceph): Merge pull request #15094 from fullerdj/wip-djf-19893
- qa/cephfs: Fix for test_data_scan
Reviewed-by: John Spray <john.spray@redhat.com> - 09:45 AM CephFS Feature #19362 (Resolved): mds: add perf counters for each type of MDS operation
- 09:45 AM Revision 71e3a853 (ceph): Merge pull request #14938 from michaelsevilla/f19362
- mds: add perf counters for file system operations
Reviewed-by: John Spray <john.spray@redhat.com> - 09:43 AM CephFS Bug #19890 (Resolved): src/test/pybind/test_cephfs.py fails
- 09:24 AM CephFS Feature #19820 (Resolved): ceph-fuse: use userspace permission check by default
- 09:21 AM Bug #16910: cluster takes 30 mins to detect node down and meanwhile rbd is unresponsive
- Dear Martin,
we were in the same condition (30 mins to detect node down and meanwhile rbd is unresponsive);
We have... - 09:15 AM Revision 5efad43e (ceph): Merge pull request #15018 from ukernel/wip-19890
- pybind: fix open flags calculation
Reviewed-by: John Spray <john.spray@redhat.com> - 09:14 AM CephFS Bug #19755 (Pending Backport): MDS became unresponsive when truncating a very large file
- 09:13 AM Revision ea4a165f (ceph): Merge pull request #14769 from ukernel/wip-19755
- osdc/Filer: truncate large file party by party
Reviewed-by: John Spray <john.spray@redhat.com> - 09:05 AM Revision 9d2d032e (ceph): ceph: simplify CInode::maybe_export_pin()
- move most works into MDBalancer::handle_export_pins(), this simplifies
the code a lot.
Another reason for this chang... - 08:43 AM Revision 6473b793 (ceph): qa/cephfs: disable mds_bal_frag for TestStrays.test_purge_queue_op_rate
- directory fragmentation generates extra osd ops, which affects checks
in the test.
Fixes: http://tracker.ceph.com/is... - 08:38 AM devops Bug #19937 (In Progress): ceph-common needs dependency to psmisc package (Ubuntu 16.04)
- 07:07 AM devops Bug #19937 (Duplicate): ceph-common needs dependency to psmisc package (Ubuntu 16.04)
- ceph-common includes a logrotate script that uses killall to inform ceph daemons to reopen their logfiles.
killall... - 08:14 AM Revision e6af68c3 (ceph): doc: change reference to internal link
- Signed-off-by: Drunkard Zhang <gongfan193@gmail.com>
- 07:32 AM Bug #14900: hammer: A massive crush OSD daemons in cache tier pool
- I get the same condition. Do you check out the reason ?
- 07:15 AM devops Bug #19938: Duplicate logrotate entries if ceph-base and ceph-common are installed (Ubuntu 16.04)
- (fingers were too fast...)
Colocating rados gateway and osd on the same host, ceph-common and ceph-base are instal... - 07:10 AM devops Bug #19938 (Resolved): Duplicate logrotate entries if ceph-base and ceph-common are installed (Ub...
- 06:45 AM Revision b6aafc27 (ceph): rgw-multisite: fix the problem of rgw website configure 'RedirectAllReq...
- Signed-off-by: yuliyang <yuliyang@cmss.chinamobile.com>
- 06:42 AM Revision cad4cffb (ceph): msg/async: add perf counter for msgr thread to know lat distribute
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:08 AM Revision 71c3fd4b (ceph): msg/async: remove unused perf counter
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 05:33 AM Revision da4c026f (ceph): rgw: Searching for error codes and dumping output based on protocol flags.
- The previous commit uses dynamic allocation to search for s3/ swift specific
error codes and dump the results. In ord... - 05:22 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- Tim Serong wrote:
> Sorry, I'm not explaining myself clearly. What I meant was;
>
> - At some time in the past, ... - 03:42 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- Sorry, I'm not explaining myself clearly. What I meant was;
- At some time in the past, commands in python module... - 05:02 AM Revision b92c8359 (ceph): Latest Changes based on comments:
- https://github.com/ceph/ceph/pull/10736#discussion_r116404207
https://github.com/ceph/ceph/pull/10736#discussion_r116... - 04:39 AM Revision a7c171b7 (ceph): msg/async: avoid was_session_reset involving outcoming_bl operation
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 04:35 AM Revision b640ded8 (ceph): polymorphic error codes.
- make set_req_state_err a method of req_state
get rid of params.perr; it's never used
rgw - polymorphic error object... - 04:29 AM Revision c70b3562 (ceph): msg/async: make sure write_message work in own thread
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 04:27 AM Revision cf4a73a8 (ceph): msg/async: remove write_lock on outcoming_bl and write_message
- since we only write_message within own thread, we could free outcoming_bl
without lock protection. then it could huge... - 02:41 AM Bug #19931: osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has ref count of 2'
- ...
- 02:39 AM RADOS Bug #19936 (New): filestore ENOTEMPTY
- ...
- 02:36 AM Bug #19935 (Resolved): scrub test should not be run with d-luminous/at-end
- /a/sage-2017-05-15_17:07:41-rados-wip-sage-testing2---basic-smithi/1180549...
05/15/2017
- 11:36 PM Bug #19884: support Debian stretch
- Be sure not to ignore the discussion in the Debian bug; there's good info there
- 11:06 PM rgw Bug #19932 (Fix Under Review): rgw_file: v3 write timer does not close open handles
- https://github.com/ceph/ceph/pull/15097
- 09:37 PM rgw Bug #19932 (Resolved): rgw_file: v3 write timer does not close open handles
- When a v3 write timer expires, it completes the current write as required, but does not clear the FLAG_OPEN or FLAG_S...
- 10:08 PM Revision 47c949d6 (ceph): rgw: remove fastcgi from default rgw frontends
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 09:37 PM Revision ce6ecb55 (ceph): rgw_file: v3: fix write-timer action
- For now, unify with v4 write-on-close path, by calling
RGWFileHandle::close() on write-timer expire, since it will
ca... - 09:31 PM CephFS Bug #19734 (Resolved): mds: subsystems like ceph_subsys_mds_balancer do not log correctly
- 09:31 PM Revision 6f1bf0dd (ceph): Merge pull request #15052 from batrick/i19734
- mds: use debug_mds for most subsys
Reviewed-by: John Spray <john.spray@redhat.com> - 09:27 PM Revision 2350555f (ceph): qa: simplify TestJournalRepair
- This was sending lots of metadata ops to MDSs to persuade
them to migrate some subtrees, but that was flaky. Use
the... - 09:14 PM Revision 18321c69 (ceph): ceph-disk: separate ceph-osd --check-needs-* logs
- It is using the OSD id zero but have nothing to do with OSD zero and
this is confusing to the user. The log themselve... - 08:40 PM CephFS Bug #19893 (Fix Under Review): test_rebuild_simple_altpool fails
- https://github.com/ceph/ceph/pull/15094
- 08:01 PM Revision 7f659e10 (ceph): qa/cephfs: Fix for test_data_scan
- Don't assume that test_data_scan will be run on exactly 2 MDS nodes.
Fixes: http://tracker.ceph.com/issues/19893
Sig... - 07:10 PM Bug #19931 (Resolved): osds abort on shutdown with assert(peering_queue.empty()) or 'pgid X has r...
- These have been happening consistently against the rgw:multisite suite, which sets 'wait-for-scrub: false'.
An exa... - 06:12 PM Bug #19877 (Fix Under Review): check_past_interval_bounds assert after split
- 06:11 PM Bug #19899 (Resolved): bluestore: FAILED assert(num_running == 0) in aio_wake()
- 05:47 PM Revision 880dde8e (ceph): Merge pull request #15091 from ceph/luminous
- merge v12.0.2 release tag
- 05:43 PM Revision 6de3e184 (ceph): mds: add perf counters for file system operations
- Shows the types of operations that clients are doing by adding counters to the
spot where the MDS responds to clients... - 04:36 PM mgr Bug #19919: mgr: ImportError: No module named cherrypy
- This is going to go away either when the rest module gets ripped out (due to new rest module), or when we start pulli...
- 04:32 PM mgr Bug #19919: mgr: ImportError: No module named cherrypy
- Also see in run http://pulpito.ceph.com/teuthology-2017-05-13_03:25:02-upgrade:kraken-x-master-distro-basic-smithi/
... - 04:25 PM Revision 6db74cf1 (ceph): Merge pull request #15079 from ztczll/master
- mailmap: ztczll affiliation
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:13 PM rbd Bug #19929 (Fix Under Review): Lock release requests not honored after watch is re-acquired
- *PR*: https://github.com/ceph/ceph/pull/15093
- 02:35 PM rbd Bug #19929 (Resolved): Lock release requests not honored after watch is re-acquired
- After the watch fails, the lock owner client id is cleared and the re-acquire process is started. If the re-acquire i...
- 04:12 PM Revision 21ce5e16 (ceph): librbd: reacquire lock should update lock owner client id
- Fixes: http://tracker.ceph.com/issues/19929
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 03:47 PM Revision 27ba6cbb (ceph): msg/async: remove send message inline option
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 03:46 PM Revision 1156747d (ceph): doc: add new cn ceph mirror to doc and mirroring
- Signed-off-by: Shengjing Zhu <zsj950618@gmail.com>
- 03:28 PM Bug #19883: Remove redundant includes
- https://github.com/ceph/ceph/pull/15086
https://github.com/ceph/ceph/pull/15169
https://github.com/ceph/ceph/pu... - 02:50 PM Revision 5dc97198 (ceph): librbd: optimize copy-up to add hints only once to object op
- Fixes: http://tracker.ceph.com/issues/19875
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 02:22 PM Revision 80038f50 (ceph): qa/suites/rados/threas-erasure-code-*: fix luminous facet
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:21 PM Revision 8fdbeb5b (ceph): qa/suites/rados/thrash-erasure-code-overwrites: fix
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:03 PM Revision bd58423b (ceph): Merge pull request #15081 from tchaikov/wip-fio-readme
- fio: update README.md so only the fio ceph engine is built
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 01:46 PM CephFS Bug #19892: Test failure: test_purge_queue_op_rate fails
- Let's tweak the numbers on this test to get more consistent behaviour (more files), or maybe set the concurrent purge...
- 01:38 PM Revision 2b6b1b5b (ceph): doc/dev/perf_counters: update docs for new friendly properties
- Note that histograms are not yet documented.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision caf3367a (ceph): common/perf_counters: histograms are counters
- The histogram is a histogram of counters (not guages), so set the COUNTER
bit. (This only matters because we expose ... - 01:38 PM Revision 76211dc1 (ceph): common/perf_counters: make 'perf schema' more friendly
- The raw bits are pretty hard to interpret and the documentation isn't
super easy to find. Expose a string descriptio... - 01:38 PM Revision 0a8c444f (ceph): common/perf_counters: rename histogram adder method
- Specifically, it's a u64 counter histogram.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:15 PM Revision aa613862 (ceph): mon/OSDMonitor: add 'osd crush swap-bucket' command
- Swap contents of two crush buckets. Do it safely by default so that
the origin bucket has to be an orphan (unless fo... - 01:15 PM Revision abe64b45 (ceph): crush: add crush_alg_name
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:15 PM Revision 4c61bf3d (ceph): mon/OSDMonitor: require force flag is swap-bucket alg types differ
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:15 PM Revision 5f795631 (ceph): crush: implement swap_bucket
- Swap contents between buckets.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:44 PM rbd Bug #19907 (Pending Backport): rbd-mirror: admin socket path names collision
- 12:43 PM Revision 6b863620 (ceph): Merge pull request #15048 from trociny/wip-19907
- rbd-mirror: resolve admin socket path names collision
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:25 PM CephFS Bug #19891 (Resolved): Test failure: test_full_different_file
- 12:21 PM Revision 17f669a8 (ceph): Merge pull request #15026 from ukernel/wip-19891
- qa/suites/fs: reserve more space for mds in full tests
Reviewed-by: John Spray <john.spray@redhat.com> - 12:18 PM CephFS Bug #19828 (Resolved): mds: valgrind InvalidRead detected in Locker
- 12:18 PM CephFS Bug #19903 (Resolved): LibCephFS.ClearSetuid fails
- 12:18 PM Revision a1e51dfc (ceph): Merge pull request #15039 from ukernel/wip-19903
- client: fix UserPerm::gid_in_group()
Reviewed-by: John Spray <john.spray@redhat.com> - 12:17 PM Revision 897b5f5b (ceph): Merge pull request #15035 from batrick/quiet-mds-grow-shrink
- qa: silence spurious insufficient standby health warnings
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 12:16 PM Revision d63962f1 (ceph): Merge pull request #14991 from ukernel/wip-19828
- mds: fix use-after-free in Locker::file_update_finish()
Reviewed-by: John Spray <john.spray@redhat.com> - 12:16 PM Revision 0f250a88 (ceph): Merge pull request #14978 from cernceph/dvanders_quota
- client: client_quota no longer optional
Reviewed-by: John Spray <john.spray@redhat.com> - 11:27 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- Tim Serong wrote:
> Sorry, my mistake. I was confusing this for a problem we had at one point where invoking comman... - 11:04 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- Sorry, my mistake. I was confusing this for a problem we had at one point where invoking commands defined in the pyt...
- 07:23 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- Tim Serong wrote:
> This problem doesn't occur in master. I believe it was fixed by https://github.com/ceph/ceph/co... - 09:33 AM Backport #19926 (In Progress): jewel: mon crash on shutdown, lease_ack_timeout event
- https://github.com/ceph/ceph/pull/15083
- 08:16 AM Backport #19926 (Resolved): jewel: mon crash on shutdown, lease_ack_timeout event
- https://github.com/ceph/ceph/pull/15083
- 09:32 AM Backport #19928 (Resolved): kraken: mon crash on shutdown, lease_ack_timeout event
- https://github.com/ceph/ceph/pull/15084
- 08:58 AM rgw Bug #19927 (New): rgw-multisite: slave zone can not redirect website configure request to metadat...
hi,
when i make website configure request to slave zone rgw, and get website configure from master zone,but i ca...- 08:53 AM Revision 9609d789 (ceph): doc: update the usage of 'ceph-deploy purge'
- Now it refuses to purge data directly before remove ceph package.
So update the order between commands when using it.... - 08:13 AM Revision 1a0a89de (ceph): fio: update README.md so only the fio ceph engine is built
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:10 AM Revision 43a55828 (ceph): Merge pull request #15044 from lixiaoy1/master
- test/fio_ceph_objectstore: fix fio plugin build failure by engine_data
Reviewed-by: Casey Bodley <cbodley@redhat.com... - 08:04 AM CephFS Bug #19854: ceph-fuse write a big file,The file is only written in part
- Zheng Yan wrote:
> can you reproduce this issue? (errors in the client.log are normal, they shouldn't cause this iss... - 07:24 AM CephFS Bug #19854: ceph-fuse write a big file,The file is only written in part
- Zheng Yan wrote:
> can you reproduce this issue? (errors in the client.log are normal, they shouldn't cause this iss... - 07:12 AM CephFS Bug #19854: ceph-fuse write a big file,The file is only written in part
- hi zheng yan:
reproduce this issue is easy, but I don't know what specific logs need to be opened at the client an... - 07:57 AM Linux kernel client Bug #19275 (Resolved): stable-writes flag gets reset underneath rbd since 4.4
- In 4.4.68, 4.9.28, 4.10.16 and 4.11.1.
- 07:55 AM Linux kernel client Feature #17524 (Resolved): krbd: support disabling auto-exclusive lock transition logic
- Done in 4.12.
- 07:13 AM Revision c003d900 (ceph): mailmap:ztczll affiliation
- Signed-off-by: zhanglei <243290414@qq.com>
- 06:39 AM rgw Tasks #16784 (Fix Under Review): RADOSGW feature requires FCGI which no longer has an upstream so...
- 03:06 AM Revision 3e138f88 (ceph): Merge pull request #15076 from atheism/atheism-mailmap
- mailmap: Weibing Zhang mailmap affiliation
- 02:50 AM Revision ade9fec9 (ceph): Merge pull request #15007 from ztczll/master
- test/objectstore/: Check put_ref return value
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 02:50 AM Revision a869c9a5 (ceph): Merge pull request #15021 from runsisi/wip-fix-writefull
- osd/PrimayLogPG: update modified range to include the whole object size for write_full op
Reviewed-by: Sage Weil <sa... - 02:49 AM Revision d53127a2 (ceph): Merge pull request #15046 from ukernel/wip-osdmap-encode
- osd/OSDMap: bump encoding version for require_min_compat_client
Reviewed-by: Sage Weil <sage@redhat.com> - 02:48 AM Bug #19595: mgr: segv in msgr thread, with no core
- /a/sage-2017-05-12_14:53:12-rados-wip-sage-testing---basic-smithi/1171581
05/14/2017
- 05:12 AM Revision 1624b063 (ceph): mailmap: Weibing Zhang mailmap affiliation
- Signed-off-by: Weibing Zhang <atheism.zhang@gmail.com>
- 02:06 AM Bug #19925: Bluestore osd crashes on start
- I've just noticed that i'm running 10.2.7, and there have been a lot of enhancements to Bluestore since then. I thoug...
- 01:56 AM Bug #19925 (Closed): Bluestore osd crashes on start
- I'm seeing an issue very similar to that seen in #16278 - whereby a Bluestore OSD crashes upon start with the followi...
05/13/2017
- 10:05 AM Feature #10036 (Resolved): osd tree to show primary-affinity value
- 10:02 AM Feature #10036 (In Progress): osd tree to show primary-affinity value
- 07:59 AM Backport #17385 (In Progress): jewel: ceph cli: Rados object in state configuring race
- 04:58 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- This problem doesn't occur in master. I believe it was fixed by https://github.com/ceph/ceph/commit/9988a564d8
- 04:24 AM mgr Feature #19885: `ceph tell mgr help` failed on Kraken
- well, I found the command "get_command_descriptions" in source that used in OSD/MON module. I will take over this tic...
- 02:20 AM Revision 9a44857a (ceph): int_types.h: remove hacks to workaround old systems
- Signed-off-by: Kefu Chai <kchai@redhat.com>
Also available in: Atom