Activity
From 06/05/2014 to 07/04/2014
07/04/2014
- 06:33 PM rgw Bug #8698 (Resolved): s3tests.functional.test_s3.test_multipart_upload failures on firefly
- 06:33 PM Bug #8738 (Pending Backport): divergent osdmaps crush tunables
- 05:51 PM Bug #8747: OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.start || s...
- I use my local build of 0.80.1 with commit:29ee6faecb9e16c63acae8318a7c8f6b14367af7 (from branch "firefly") applied y...
- 05:44 PM Bug #8747: OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.start || s...
- May be a duplicate of #8011
- 05:41 PM Bug #8747 (Duplicate): OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubbe...
- On 0.80.1 one OSD crashed several times as follows (full log attached):...
- 12:28 PM Revision c7937ff3 (ceph): doc: Fix a typo regarding requiretty for RHEL based platforms
- 05:19 AM Revision b1a4a7cb (ceph): rgw: set a default data extra pool name
- Fixes: #8585
Have a default name for the data extra pool, otherwise it would be empty
which means that it'd default t... - 12:36 AM Revision 276dbfc4 (ceph): Merge pull request #2058 from ceph/wip-refs
- refcount debugging for RefCountedObject
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Samuel J...
07/03/2014
- 11:32 PM Revision 2280c0ea (ceph): OSDMonitor: fix quorum_features comparison in check_cluster_features
- We need to see if there's a feature which is not in the quorum_features,
not if there are no features in common!
Sig... - 11:32 PM Revision 54af8104 (ceph): mon: check changes to the whole CRUSH map and to tunables against clust...
- When we change the tunables, or set a new CRUSH map, we need to make sure it's
supported by all the monitors and OSDs... - 09:47 PM CephFS Bug #8745 (Resolved): ceph-fuse: pjd link 78 failure
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-07-02_23:04:01-fs-next-testing-basic-plana/339949...
- 09:28 PM Revision b0da92b8 (ceph): msg/Message: use RefCountedObject ctor to set initial ref count
- Also, drop the useless assert in the dtor (the RefCountedObject dtor does
the same).
Signed-off-by: Sage Weil <sage@... - 09:28 PM Revision c0dcf3bf (ceph): common/RefCountedObject: make nref, cct private
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision c0ba58c4 (ceph): msg: debug refs on incoming Messages
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision 05474172 (ceph): common/RefCountedObject: optionally debug
- Introduce a 'refs' subsys for logging. Print log ref count inc and dec
for any RefCountedObject that gets a cct pass... - 09:28 PM Revision ff1521fc (ceph): common/RefCountedObject: optionally take initial ref count to ctor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision 45991c05 (ceph): common/RefCountedObject: assert nref == 0 in dtor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision fc8d1980 (ceph): osd: debug Session refs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision 242ee89c (ceph): msg: debug Connection refs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:28 PM Revision e6218568 (ceph): msg/Pipe: debug Pipe refs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:27 PM Revision dc1e425d (ceph): Merge pull request #2059 from ceph/wip-osd-dumpres
- osd: allow dumping reservation state via asok
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:03 PM Feature #8744 (Closed): Add VERBOSE to make check invocation
- Newer versions of automake (1.12.0b and later) have reworked make check output so that it, by default,
1) collect... - 09:00 PM Revision 303a9fdc (ceph): Merge pull request #2069 from thorstenb/thb-buildconvenience-1
- Automagically setup submodules on first run.
Reviewed-by: Sage Weil <sage@redhat.com> - 08:56 PM Revision 235c27ab (ceph): Merge pull request #2066 from thorstenb/wip-janitorial-clang-2
- [werror] Fix c++11-compat-reserved-user-defined-literal
- 08:46 PM devops Feature #8306: separate ceph.rpm into ceph and ceph-common
- The way the file is written now:
%{_bindir}/ceph
%{_bindir}/ceph-authtool
%{_bindir}/ceph-conf
%{_bindir}/ceph-... - 08:36 PM Revision 9973d980 (ceph): Merge pull request #2062 from somnathr/wip-sd-replicated-pg
- ReplicatedPG: Removed the redundant register_snapset_context call
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:36 PM Revision f21a0179 (ceph): Merge pull request #2064 from somnathr/wip-sd-share-map
- OSD: adjust share_map() to handle the case that the osd is down
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:35 PM Revision 3c03beb3 (ceph): Merge pull request #2065 from somnathr/wip-sd-optracker
- Pull request for optracker changes
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:34 PM Revision c44e1449 (ceph): Merge pull request #2063 from athanatos/wip-8691
- OSD: wake_pg_waiters after dropping pg lock
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:46 PM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- Same errors in this suite: http://pulpito.front.sepia.ceph.com/teuthology-2014-07-03_14:10:02-upgrade:dumpling-dumpli...
- 05:18 PM Bug #8741: osd: ec plugin leak
- 05:10 PM Bug #8741: osd: ec plugin leak
- The object is "allocated once per process":https://bitbucket.org/jimplank/jerasure/src/21de98383350e7c46e5ee329de2a93...
- 04:52 PM Bug #8741 (New): osd: ec plugin leak
- ...
- 04:34 PM Bug #8738 (Fix Under Review): divergent osdmaps crush tunables
- https://github.com/ceph/ceph/pull/2072
- 02:35 PM Bug #8738: divergent osdmaps crush tunables
- wip-7838-next has a patch on top of current "next" to resolve this by testing all CRUSH maps against the cluster feat...
- 10:22 AM Bug #8738 (Resolved): divergent osdmaps crush tunables
- 555ed048e73024687fc8b106a570db4f osd-20_osdmap.13258__0_4E62BB79__none
6037911f31dc3c18b05499d24dcdbe5c osd-23_osd... - 04:18 PM Revision b7eecd44 (ceph): Don't mess with ~/src/teuthology by default
- Setting 'automated_scheduling: True' in ~/.teuthology.yaml enables it.
Signed-off-by: Zack Cerza <zack.cerza@inktank... - 04:12 PM Revision 4881b2ed (ceph): Relocate teuthology checkouts to ~/src/
- Also use an underscore instead of a dash between 'teuthology' and the
branch name.
Signed-off-by: Zack Cerza <zack.c... - 03:10 PM Fix #8739 (New): erasure-code: use LRU to cache decoding matrix in jerasure
- https://github.com/ceph/ceph/blob/master/src/include/lru.h could be used in https://github.com/dachary/ceph/blob/wip-...
- 03:09 PM Revision 6934bbe1 (ceph): task/ceph_manager: generalize admin_socket calls
- This is so that tasks can access the admin sockets
of other service types such as the MDS.
Signed-off-by: John Spray... - 03:09 PM Revision 87383048 (ceph): run_tasks: catch malformed task case
- If you do something like this:
- foo:
- bar:
- baz
Then catching AttributeError is necessary for giving a somewhat
... - 03:09 PM Revision f6ec9589 (ceph): nuke: fix unmounted multiple fuse mount points
- It was trying to pass multiple paths to fusermount, but
it should instead invoke fusermount for each path.
Signed-of... - 03:09 PM Revision 6e19ba41 (ceph): task/ceph: add option to avoid doing scrub
- When iterating on test in development, it's useful
to be able to skip this step.
Signed-off-by: John Spray <john.spr... - 02:49 PM Documentation #8549: Ceph installation pre-flight problem with ssh-copy-id
- The instruction is to create passwordless ssh between the admin node and the ceph nodes. It sounds to me like you are...
- 02:00 PM Revision 10cdb29b (ceph): Merge pull request #2047 from dachary/wip-osd-config
- osd: improve tests for configuration updates
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com> - 02:00 PM Revision b9b498e6 (ceph): Merge pull request #2028 from ceph/wip-rgw-firefly
- rgw: a couple backports for firefly
Passed the rgw suite, modulo a python bootstrap issue.
sage-2014-07-01_09:50:22... - 12:40 PM Revision 5b97cd7f (ceph): Merge pull request #2036 from ceph/wip-osd-map-cache-size
- osd: allow osd map cache size to be adjusted at runtime
Reviewed-by: Loic Dachary <loic@dachary.org> - 09:29 AM Revision 72ac3c0a (ceph): Merge pull request #2068 from thorstenb/wip-janitorial-clang-4
- ceph_argparse_flag has no regular 3rd parameter.
Reviewed-by: Loic Dachary <loic@dachary.org> - 05:22 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- I have recreated everything from scratch and restored our backups. Initial crash-stress-tests ran fine. ("killall -9 ...
- 04:12 AM Bug #8601: erasure-code: default profile does not exist after upgrade
- "rebased and repushed":https://github.com/ceph/ceph/pull/1990
- 03:31 AM Revision 2226b91e (ceph): qa: support running under non privileged user
- If the test is run against a cluster started with vstart.sh (which is
the case for make check), the --asok-does-not-n... - 02:17 AM rgw Bug #7799: Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- This one looks exactly the same http://pulpito.ceph.com/loic-2014-07-02_22:04:23-upgrade:firefly-x:stress-split-maste...
- 01:22 AM rgw Bug #7799 (Can't reproduce): Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- It's not the same error, my bad
- 01:21 AM rgw Bug #7799: Errors in upgrade:dumpling-x:stress-split-firefly---basic-plana suite
- http://pulpito.ceph.com/loic-2014-07-02_23:05:05-upgrade:firefly-x:stress-split-firefly-testing-basic-vps/338941/
<p... - 01:42 AM Bug #8736 (Duplicate): thrash and scrub combination lead to error
- In http://pulpito.ceph.com/loic-2014-07-02_23:05:05-upgrade:firefly-x:stress-split-firefly-testing-basic-vps/338904/ ...
- 01:24 AM rgw Bug #8735 (Can't reproduce): TestAccountNoContainers fail in Firefly upgrade:firefly-x:stress-split
http://pulpito.ceph.com/loic-2014-07-02_23:05:05-upgrade:firefly-x:stress-split-firefly-testing-basic-vps/338941/
...- 12:55 AM Revision a501eb80 (ceph): Merge pull request #2061 from ceph/wip-8728
- qa/workunits/rest/test.py: make osd create test idempotent
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 12:44 AM Revision 55e297ad (ceph): Merge pull request #2046 from ceph/wip-8670
- mon: OSDMonitor: 'osd pool' - if we can set it, we must be able to get it
Reviewed-by: Loic Dachary <loic@dachary.or... - 12:42 AM Revision 3428b090 (ceph): Remove default results_server
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 12:39 AM Revision dbadcd0d (ceph): Allow setting results_email in teuthology.yaml
- (Instead of passing --email to teuthology-suite)
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 12:27 AM Revision 34a7b318 (ceph): Don't remove the teuthology repo if errors occur
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 12:26 AM Revision 97bf86c5 (ceph): Optionally, don't remove a repo when errors occur
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 12:17 AM Revision 63fd33e4 (ceph): Add another unit test
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
07/02/2014
- 10:51 PM Revision f7086d36 (ceph): Automagically setup submodules on first run.
- I mean, who's reading the README, anyway?
Signed-off-by: Thorsten Behrens <tbehrens@suse.com> - 10:49 PM devops Bug #8734 (Resolved): EPEL / Ceph.com package priority issues
- When following the Ceph.com manual configuration guide in our documentation you can fall into a trap if you have an E...
- 10:43 PM Revision 0c7c7223 (ceph): ceph_argparse_flag has no regular 3rd parameter.
- With clang warning: 'va_start' has undefined behavior with reference
types, noticing copy-paste mistake on ceph_argpa... - 10:43 PM Revision 909850eb (ceph): [werror] Fix c++11-compat-reserved-user-defined-literal
- c++11 readiness, avoid clash with
http://www.stroustrup.com/C++11FAQ.html#UD-literals
Signed-off-by: Thorsten Behren... - 10:18 PM Revision 2d083a79 (ceph): Merge pull request #45 from dachary/wip-ec-readwrite-firefly-x
- add erasure code workload to upgrade/firefly-x
- 08:51 PM Revision fde99e69 (ceph): OSD: adjust share_map() to handle the case that the osd is down
- The assert was hitting while OSd is waiting for becoming healthy
in handle_osd_map(). This can happen while io is goi... - 06:40 PM Bug #8733 (Resolved): OSD crashed at void ECBackend::handle_sub_read
- When took one OSD out (total 219 OSDs) to trigger recovery, 30 OSDs crashed after about 20min. All OSD crashed for sa...
- 06:35 PM Revision ddc04c83 (ceph): mon: OSDMonitor: 'osd pool' - if we can set it, we must be able to get it
- Add support to get the values for the following variables:
- target_max_objects
- target_max_bytes
- cache_target_... - 06:20 PM Revision 0392ddb6 (ceph): ReplicatedPG: Removed the redundant register_snapset_context call
- In the get_object_context(), the get_snapset_context is been called
and the register_snapset_context is already been ... - 06:06 PM Revision 2f089d8d (ceph): OpTracker: The optracker enabled/disabled check is added
- The optracker enabled/disabled check is now added in the
mark_event(const string&) interface.
Signed-off-by: Somnath... - 06:01 PM Revision 63be0f20 (ceph): OpTracker: use mark_event rather than _mark_event
- mark_event() interfaced changed to accept time and it is default
to 'now'. The mark_event is the wrapper function of ... - 05:53 PM Bug #8728 (Pending Backport): rest/test.py osd create not idempotent
- 01:06 PM Bug #8728: rest/test.py osd create not idempotent
- After Sage explained the retry/create problem, looks right to me...
- 10:36 AM Bug #8728 (Resolved): rest/test.py osd create not idempotent
- bc no uuid is passed we may create an extra osd id, which makes the tell test further down fail.
ubuntu@teutholog... - 05:51 PM Revision 5f2aa569 (ceph): fix create_pool_with_unique_name call to use profile name
- The hardcoded arguments are deprecated for the profile name. Create a
profile that matches the previous default argum... - 05:50 PM Revision 7cdfb05e (ceph): document create_pool erasure_code_profile_name argument
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 05:43 PM Bug #8670 (Pending Backport): Cache tiering parameters can not be displayed for a pool
- 05:40 PM Bug #8724 (Rejected): osd/ReplicatedPG.cc: 10278: FAILED assert(obc) in recover_backfill()
- sweet
- 12:24 PM Bug #8724: osd/ReplicatedPG.cc: 10278: FAILED assert(obc) in recover_backfill()
There are multiple simultaneous asserts. The objects involved in the backfill assert is benchmark_data_maetl_4884_...- 09:29 AM Bug #8724 (Rejected): osd/ReplicatedPG.cc: 10278: FAILED assert(obc) in recover_backfill()
- this was on a vstart cluster. log attached....
- 05:39 PM Revision bb3e1c92 (ceph): qa/workunits/rest/test.py: make osd create test idempotent
- Avoid possibility that we create multiple OSDs do to retries by passing in
the optional uuid arg. (A stray osd id wi... - 04:19 PM Revision 71182fd8 (ceph): Allow testing with online repos
- It is not the default.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 04:08 PM Revision cb7fdfb7 (ceph): Add a unit test simulating simultaneous checkouts
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:08 PM Revision 43c4595a (ceph): Add a couple unit tests for teuthology.parallel
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:50 PM Revision 0d1886cc (ceph): Merge pull request #47 from ceph/wip-multimds-pjd
- marginal/multimds: fuse_default_permissions = 1 for pjd
- 01:13 PM devops Feature #8120 (Resolved): RHEL7 GA kernel build
- This was delayed due to updating the rhel7 branch so it would work with newer clusters as the old one was over a year...
- 12:36 PM CephFS Tasks #8535: audit the journaler send-to-OSD ordering
- This looks fine — we send out the journal header at the same time as the blocks to write, but we update the write_pos...
- 10:34 AM Bug #8727: Firefly monitors send incompatible messages to older monitors
- Looks like the issue is that MForward's COMPAT version was set to 0 on b4fbe4f8; according to Sage that has the messe...
- 10:24 AM Bug #8727 (Resolved): Firefly monitors send incompatible messages to older monitors
- MForward got revved to a new version that requires Firefly monitors to decode. That doesn't work if you upgrade peons...
- 10:27 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- osd objectstore = keyvaluestore-dev
is so experimental, it's not even in our automated testing. I'm not really ve... - 10:07 AM Bug #7891: osd: leaked pg refs on shutdown
- teuthology-2014-07-01_02:30:37-rados-firefly-distro-basic-plana/337102
- 09:49 AM Bug #8726 (Resolved): (firefly command on dumpling issue?) Error "'adjust-ulimits ceph-coverage /...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-30_19:02:27-rbd-dumpling-testing-basic-plana/33528...
- 09:40 AM CephFS Bug #8725 (Resolved): mds crashed in upgrade:dumpling-x:stress-split-master-testing-basic-plana
- Logs are in http://qa-proxy.ceph.com/teuthology/ubuntu-2014-07-01_11:38:37-upgrade:dumpling-x:stress-split-master-tes...
- 07:02 AM CephFS Bug #8708: kcephfs: direct_io tests failing
- It's new regression in 3.16 rc. introduced by commit 2b777c9d (ceph_sync_read: stop poking into iov_iter guts)
- 06:01 AM Revision 44199d6a (ceph): mds: use mutex to protect log segment list
- prevent race between creating new log segment and trimming old
segment.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel... - 06:01 AM Revision 7e1deb6e (ceph): mds: defer encoding/submitting log events to separate thread
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:01 AM Revision 6d8ccdd6 (ceph): mds: add thread to encode/submit log events
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:04 AM Revision 70c0723f (ceph): osd: add dump_reservations asok command
- Allow an admin to inspect pending and in-progress reservations.
Backport: firefly
Signed-off-by: Sage Weil <sage@ink... - 04:49 AM Revision 64837106 (ceph): common/AsyncReserver: add dump()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:03 AM Revision 88cc7c0e (ceph): marginal/multimds: fuse_default_permissions = 1 for pjd
- pjd contains lots of test cases for file permission.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 12:40 AM Revision 9f06e2c1 (ceph): rgw: fix uninit ofs in RGWObjManifect::obj_iterator
- Valgrind picked this up:
<kind>UninitCondition</kind>
<what>Conditional jump or move depends on uninitialised va... - 12:38 AM Revision 5fd8b0d1 (ceph): rgw: if extra data pool name is empty, use data pool name instead
- Fixes: #8311
An empty pool name could be used as the extra data pool.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.co... - 12:35 AM Revision cbad09e1 (ceph): rgw: extend manifest to avoid old style manifest
- In case we hit issue #8269 we'd like to avoid creating an old style
manifest. Since we need to have parts that use di... - 12:35 AM Revision ea68b937 (ceph): rgw: don't allow multiple writers to same multiobject part
- Fixes: #8269
Backport: firefly, dumpling
A client might need to retry a multipart part write. The original thread
mi...
07/01/2014
- 11:47 PM Subtask #7363 (Rejected): erasure code: reduce the chunk size to a minimum
- 11:32 PM Support #7501 (Closed): Firefly - monitor hangs when ceating EC pool with latest code in master/f...
- This is obsolete now that firefly has been released.
- 11:18 PM Revision 9211bb5d (ceph): Merge pull request #280 from dachary/wip-erasure-code-profile
- add rgw.create_ec_pool default profile
- 11:16 PM Revision f285266a (ceph): Merge pull request #2056 from ceph/wip-8010
- Revert "mon: OSDMonitor: Refuse to delete CephFS pools"
Reviewed-by: Sage Weil <sage@redhat.com> - 11:15 PM Revision 21681531 (ceph): add rgw.create_ec_pool default profile
- the former arguments had defaults, the caller do not set them
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:13 PM Revision 9e81fc18 (ceph): mon: ensure HealthService warning(s) include a summary
- The low disk space check would change our status to HEALTH_WARN and include
a detail message, but no summary. We nee... - 11:13 PM Revision e96637c2 (ceph): mon: refactor check_health()
- Refactor the get_health() methods to always take both a summary and detail.
Eliminate the return value and pull that ... - 11:13 PM Revision 28584200 (ceph): mon: fix typos, punctuation for mon disk space warning(s)
- Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 98883f6308ce72f69a71feab29ef... - 11:12 PM Revision 4f066608 (ceph): mon/OSDMonitor: make down osd count sensible
- We currently log something like
1/10 in osds are down
in the health warning when there are down OSDs, but this is ... - 11:09 PM Revision 5e880228 (ceph): rados/thrash: set osd_max_backfill = 1 sometimes
- Hopefully this will help catch leaks in the recovery reservations.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:39 PM Revision 1d12dd77 (ceph): ls: make --archive-dir default to .
- This is how I use it 99% of the time.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:19 PM Revision 8649cbbc (ceph): Revert "qa/workunits/suites/fsx.sh: don't use zero range"
- This reverts commit 583e6e3ef7f28bf34fe038e8a2391f9325a69adf.
We're using a different fsx source, which doesn't supp... - 09:33 PM Bug #8722: osd: recovery op counting leak (dumpling)
- note that a pg query includes this:...
- 09:18 PM Bug #8722 (Won't Fix): osd: recovery op counting leak (dumpling)
- encountered pgs stuck during backfill, with rops=1 on the primary, no progress, and no blocked requests on the primar...
- 09:06 PM Revision 6a0dd1be (ceph): Revert "mon: OSDMonitor: Refuse to delete CephFS pools"
- This reverts commit c7d265a9b276aad5caf9b35f3ce8bc7bdd169f0f.
Because this pre-dates the `fs rm` command, this chang... - 09:01 PM Revision 693aa0dd (ceph): Merge pull request #275 from ceph/wip-replace-update-sh
- Replace update.sh functionality
- 08:08 PM Revision 149a3059 (ceph): Merge pull request #2055 from ceph/wip-8692
- mon: clear osd request queue latency info on down or up
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:03 PM CephFS Bug #8677: multimds: pjd failures
- https://github.com/ceph/ceph-qa-suite/commit/88cc7c0e2d3e2d37750759762edc7b7d7f00ca11
- 06:54 AM CephFS Bug #8677 (In Progress): multimds: pjd failures
- 07:55 PM CephFS Bug #8708: kcephfs: direct_io tests failing
- fixed by commit 8102ce75 (ceph: pass proper page offset to copy_page_to_iter() )
- 08:32 AM CephFS Bug #8708 (Resolved): kcephfs: direct_io tests failing
- teuthology-2014-06-29_23:01:50-kcephfs-next-testing-basic-plana/334012...
- 07:53 PM CephFS Bug #8719 (Duplicate): failed test_sync_io workunit
- 07:53 PM CephFS Bug #8719: failed test_sync_io workunit
- dup #8708
- 03:32 PM CephFS Bug #8719 (Duplicate): failed test_sync_io workunit
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-26_07:42:35-kcephfs-next-testing-basic-plana/327859/
http://q... - 07:42 PM Revision 9ce5ff96 (ceph): mon: clear osd request queue latency info on down or up
- It doesn't make sense to warn about slow requests on OSDs that are down;
clear those stats in the monitor when we see... - 06:49 PM Revision 3a6711f8 (ceph): Merge pull request #2054 from ceph/wip-fs-cmds-oops
- Apply some accidentally-dropped commits from the wip-fs-cmds branch to be a little friendlier and pass tests.
Review... - 06:21 PM Revision ec95ee25 (ceph): Rename suite_base to suite_dir
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:11 PM Revision f8c88a4b (ceph): OSD: wake_pg_waiters after dropping pg lock
- Otherwise, we dispatch_session_waiting while still holding the pg lock,
which is obviously wrong. Unfortunately, thi... - 05:45 PM Revision 434348aa (ceph): Add --suite-branch and --suite-base
- The former lets you specify a specific ceph-qa-suite branch to use for
testing. The latter lets you specify an as-is ... - 05:40 PM Revision e2b151d0 (ceph): mds: Update default FS name
- From 'default' to 'cephfs' so that it looks
at least vaguely meaningful.
Signed-off-by: John Spray <john.spray@redha... - 05:40 PM Revision 44eb2593 (ceph): qa: add a check for crash_replay_interval autoset
- ... that after a fs new on fresh pools, crash_replay_interval
is set to the default on the data pool.
Signed-off-by:... - 05:40 PM Revision 710561cb (ceph): mon/MDSMonitor: EC check in 'fs new' like newfs
- Signed-off-by: John Spray <john.spray@redhat.com>
- 05:40 PM Revision f62f7f57 (ceph): qa: update cephtool EC pools test to respect IDs
- ...of data and metadata pools which are no longer
constant.
Signed-off-by: John Spray <john.spray@redhat.com> - 05:40 PM Revision 82d3fcc7 (ceph): qa: Update data pool ID for vxattrs test
- Signed-off-by: John Spray <john.spray@redhat.com>
- 05:40 PM Revision c0ffa01f (ceph): mon: Set crash_replay_interval automatically
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:56 PM Revision 42a73500 (ceph): Use a test-specific name/email for the git calls
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:54 PM Bug #7999: osd: pgs share info that hasn't been persisted
- ubuntu@teuthology:/a/teuthology-2014-06-17_02:30:05-rados-firefly-distro-basic-plana/313395
- 04:42 PM Revision d6f17528 (ceph): Add more unit tests
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:22 PM Bug #7891: osd: leaked pg refs on shutdown
- Blessed[Gen]Context doesn't clean up the wrapped Context if the destructor is called. Running flab:/home/sage/src/te...
- 03:36 PM Bug #7891: osd: leaked pg refs on shutdown
- ubuntu@teuthology:/a/teuthology-2014-06-17_02:30:05-rados-firefly-distro-basic-plana/313621/remote
- 01:27 PM Bug #7891: osd: leaked pg refs on shutdown
- 04:14 PM CephFS Bug #8010 (Resolved): It's impossible to remove unused filesystem pools from a cluster
- 03:57 PM Feature #8307 (Resolved): Creating a pool with erasure code allows me to create invalid ec profil...
- 03:52 PM Bug #8349 (In Progress): env-vs-args unittest is racy
- 03:44 PM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- Any update on this problem ?
- 03:43 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- Samuel Just wrote:
> What kernel version are you using?
It's 3.14 as Yan Zheng suggested since I couldn't mount C... - 01:13 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- What kernel version are you using?
- 03:31 PM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- This happened while working on the suite. It is entirely possible that it was bugous to begin with.
- 11:10 AM Bug #8711 (Resolved): Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in ...
- h3. cuttlefish backward compatibility problem...
- 03:20 PM Revision b606456e (ceph): Merge pull request #277 from dachary/wip-erasure-code-profile
- erasure code profile: fix bugs found while testing manually
- 03:16 PM rgw Bug #8718 (Resolved): CORS OPTIONS request fails for presigned urls
- We are able to create a bucket and then apply a CORS configuration to the bucket. We are then able to create a pre-ge...
- 03:05 PM Revision 1eca89df (ceph): Merge pull request #2053 from dachary/wip-signed-warnings
- test: use 0U with gtest to avoid spurious warnings
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.... - 02:49 PM Revision e8d57b36 (ceph): Merge pull request #2052 from dachary/wip-vstart-wrapped
- qa: support running under non privileged user
Reviewed-by: Florent Flament <florent.flament@cloudwatt.com> - 02:32 PM CephFS Feature #8690: MDS: Allow some kind of recovery when pools are deleted out from underneath us
- Except that's not really sufficient; we'd need to identify it as a non-existent pool and deal with cases where the po...
- 02:11 PM CephFS Feature #8690: MDS: Allow some kind of recovery when pools are deleted out from underneath us
- Hmm, so to recover from this case I guess we could catch the case where we're writing to a data pool no longer exists...
- 02:29 PM Bug #8717 (Resolved): teuthology: valgrind leak checks broken for osd (at least)
- there is a leak of SEssion + Connection in the osd introduced by fast dispatch and teuthology isn't catching it.
- 02:22 PM Bug #8584: OSD Crashing on firefly - Timeouts on starting again
- Can you reproduce with
debug osd = 20
debug filestore = 20
debug ms = 1
? - 02:14 PM Revision d81c7d19 (ceph): Merge pull request #278 from ceph/wip-nullfs
- Support the new fs syntax.
Reviewed-by: Greg Farnum <greg@inktank.com> - 02:05 PM rbd Bug #8715 (Can't reproduce): "ceph_test_librbd_fsx: invalid option -- 'h'" error in teuthology-20...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-30_19:02:27-rbd-dumpling-testing-basic-plana/33528...
- 01:44 PM Revision c6041497 (ceph): add erasure code workload to upgrade/firefly-x
- copied from suites/rados/thrash/workloads/ec-readwrite.yaml
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:31 PM Bug #8614 (Can't reproduce): OSD keyring shifted
- The monitor shutdown because you ran out of disk space on the monitor disk.
You should free up space or move the m... - 01:25 PM Bug #8519: msgr: deadlock, blocked on SimpleMessenger::lock
- 01:23 PM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- Any update, Matthias?
BTW, I notice there is a clock skew on the mons; that can prevent you from seeing updates an... - 01:20 PM Bug #8582: Cluster very slow after upgrade to 80.1
- Any update here, Rens?
- 01:14 PM Bug #8346 (Can't reproduce): OSD crashes on master (FAILED assert(ip_op.waiting_for_commit.count(...
- 01:07 PM Bug #8691: osd: PG::_lock, OSD::pg_map_lock lock cycle
- 11:20 AM Bug #8691: osd: PG::_lock, OSD::pg_map_lock lock cycle
- 01:06 PM Bug #8692 (Resolved): mon: blocked request warnings for down osd (dumpling)
- 12:47 PM Bug #8692 (Fix Under Review): mon: blocked request warnings for down osd (dumpling)
- 11:02 AM Bug #8692: mon: blocked request warnings for down osd (dumpling)
- this eventually gets clear out for an out osd, once PGMonitor catches up. the request histogram isn't clear on osd d...
- 01:00 PM Bug #8714 (Resolved): we do not block old clients from breaking cache pools
- We got an email on ceph-users which implies that we are letting old kernel clients maul cache pools (by accessing bas...
- 12:34 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Ah, sorry, leveldb-based OSD just died again with "FAILED assert(start <= header.oid)" so perhaps "journal dio" did n...
- 12:25 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Something strange is going on. After this incident I've been running deep-scrub on all OSDs and some minor errors lik...
- 11:58 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Samuel Just wrote:
> Hmm, so you have snapshotting disabled on btrfs?
Yes. Otherwise eventually kernel crashes an... - 10:08 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Hmm, so you have snapshotting disabled on btrfs? Specifically what config options did you change to do that? I wond...
- 11:06 AM Messengers Bug #8504 (Resolved): msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- This doesn't actually require any backports. :)
Prior to the fast dispatch work, the pre_publish_lock was held by ... - 10:39 AM devops Bug #8710 (Resolved): undefined call to remoto.process after refactoring in osd.py
- Fixed in the master branch of ceph-deploy with hash 84932ca37769c42c47549896ad2e47263fd58c39
- 10:38 AM devops Bug #8710 (Resolved): undefined call to remoto.process after refactoring in osd.py
- After the refactoring in ceph-deploy to allow packaging it without vendoring libs, a call to remoto was done without ...
- 10:26 AM Revision bbb25244 (ceph): erasure-code: fix typo in create_pool argument name
- missing _name at the end
Signed-off-by: Loic Dachary <loic@dachary.org> - 10:21 AM Revision dd8f0980 (ceph): erasure-code: do not prepend 'ceph' to the erasure-code-profile command
- When used in the radosgw context, the 'ceph' string must be present but
when used in ceph_manager, the 'ceph' string ... - 10:19 AM Revision 2e5d1703 (ceph): erasure-code: str() to avoid + conversion errors
- if the value from the yaml file is an int, it must be converted into a
string bevore being concatenated with '='
Sig... - 09:58 AM Linux kernel client Bug #8464: krbd: deadlock
- I haven't seen this on nightly runs (the only place it seemed to pop up) in a while.
- 09:56 AM rbd Bug #8709: stale size reported by ioctl(BLKGETSIZE64) after librbd_resize() returns
- Happens rarely during long fsx -K runs.
- 09:54 AM rbd Bug #8709 (Resolved): stale size reported by ioctl(BLKGETSIZE64) after librbd_resize() returns
- 09:14 AM rbd Bug #8416 (Need More Info): Client Crash when try to map a volume (ubuntu)
- 08:30 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- A "firefly-x suite has been scheduled":http://pulpito.ceph.com/loic-2014-07-01_17:29:18-upgrade:firefly-x:stress-spli...
- 08:25 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- The "erasure code workload has been added to firefly-x":https://github.com/ceph/ceph-qa-suite/pull/45 and tested with...
- 07:41 AM Revision 917ef157 (ceph): test: use 0U with gtest to avoid spurious warnings
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:01 AM CephFS Bug #8255: mds: directory with missing object cannot be removed
- I think the remaining step is to eventually incorporate the ability to remove teh last trace of the damaged directory.
- 06:57 AM CephFS Feature #8634 (In Progress): mds: admin commands list, evict, etc session
- 06:49 AM CephFS Bug #8624 (Resolved): monitor: disallow specifying an EC pool as a data or metadata pool
- PR was merged 4f7e26f2befed9bd3a77ad5aee650c08ffd1a366
- 06:42 AM Revision 522174b0 (ceph): qa: support running under non privileged user
- If the test is run against a cluster started with vstart.sh (which is
the case for make check), the --asok-does-not-n... - 04:51 AM Revision 8697d6a1 (ceph): OSD: await_reserved_maps() prior to calling mark_down
- send_message_osd_cluster() et al are *trying* to protect their Connection
lookups (and not re-open zapped Connections... - 03:52 AM Revision d7f3c88d (ceph): Merge pull request #1942 from ceph/wip-fs-cmds
- Wip fs cmds
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:54 AM Revision 6f972060 (ceph): osd: allow osd map cache size to be adjusted at runtime
- Signed-off-by: Sage Weil <sage@inktank.com>
06/30/2014
- 11:50 PM Revision f4e69bae (ceph): Merge remote-tracking branch 'gh/next'
- 11:48 PM Revision f3c92145 (ceph): Merge pull request #2050 from ceph/wip-cephtool
- qa/workunits/cephtool/test.sh: sudo ceph daemon
- 11:46 PM Revision 0164f91d (ceph): Merge pull request #271 from dachary/wip-erasure-code-profile
- erasure-code: separate profile from pool creation
- 11:43 PM Revision 32d094a4 (ceph): Fix linter errors
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:41 PM Revision bcc09f93 (ceph): qa/workunits/cephtool/test.sh: sudo ceph daemon
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:40 PM Revision e431abd4 (ceph): Add a basic validation of the branch value
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:36 PM CephFS Bug #8677: multimds: pjd failures
- we has fuse_default_permissions = 0, it causes every permission check fail
- 06:49 AM CephFS Bug #8677: multimds: pjd failures
- ubuntu@teuthology:/a/teuthology-2014-06-26_07:42:59-multimds-next-testing-basic-plana$ teuthology-ls --archive-dir ....
- 11:23 PM Revision bfd82261 (ceph): Run unit tests offline
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:04 PM Revision b6a77d7f (ceph): Merge pull request #44 from ceph/wip-7032
- rados/singleton/all/thrash_cache_writeback_forward_none: thrash cache pool drain
- 10:31 PM Revision d890bd11 (ceph): Merge pull request #2049 from ceph/wip-fix-pglog-unittest
- PGLog: fix clear() to avoid the IndexLog::zero() asserts
Reviewed-by: Sage Weil <sage@redhat.com> - 09:50 PM Messengers Bug #8504 (Pending Backport): msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Merged to next in commit:8697d6a10ee822e8a032a559c78e211e2182799a
Unfortunately back porting it will require a lit... - 09:29 PM Revision b9f26eda (ceph): documentation typo
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:44 PM Revision 959f2b25 (ceph): PGLog: fix clear() to avoid the IndexLog::zero() asserts
- Introduced in:
c5b8d8105d965da852c79add607b69d5ae79a4d4
ac11ca40b4f4525cbe9b1778b1c5d9472ecb9efa
Signed-off-by: S... - 08:43 PM Revision 98e06176 (ceph): erasure-code: separate profile from pool creation
- Instead of being hard coded, the erasure code profile is read from yaml
as:
erasure_code_profile:
name: te... - 08:38 PM Revision 84635d8b (ceph): Merge pull request #233 from ceph/wip-background
- run something in the background
- 08:35 PM Revision 1cd80765 (ceph): daemon-helper: optional kill an entire process group
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:35 PM Revision 7e388c9f (ceph): background_exec: run something in the background
- This is a contextmanager task that will run some command in the background
for the duration of any subsequent tasks, ... - 08:34 PM Revision f8282df8 (ceph): rados/singleton/all/thrash_cache_writeback_forward_none: thrash cache p...
- Enable/disable cache pool against a running workload.
Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com> - 08:29 PM Revision 053c261e (ceph): rgw: set meta object in extra flag when initializing it
- As part of the fix for 8452 we moved the meta object initialization.
Missed moving the extra flag initialization that... - 08:23 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- http://qa-proxy.ceph.com/teuthology/gregf-2014-06-27_16:16:53-rados-wip-8504-testing-basic-plana/330510/
I think a... - 12:59 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- two nearly-identialy yamls hit this:
ubuntu@teuthology:/a/teuthology-2014-06-27_23:00:47-rgw-master-testing-basic-... - 08:13 PM Revision c8aac0de (ceph): Merge pull request #2003 from ferustigris/hotfix/rgw_memory_leaks
- RGW memory leaks have been fixed
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:11 PM Revision 45648c1f (ceph): Merge pull request #2041 from ceph/wip-map-unmap
- Wip map unmap
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:09 PM Revision f55bf956 (ceph): Merge pull request #2040 from ceph/wip-krbd-settle
- krbd: rework the unmap retry loop
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:08 PM Revision 25c9dfff (ceph): Merge pull request #2038 from ceph/wip-fsx-random-ctx
- test_librbd_fsx: use private RNG context
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 08:02 PM Revision 809fe7ea (ceph): Merge pull request #2048 from ceph/wip-8699
- rgw: fix uninit ofs in RGWObjManifect::obj_iterator
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:55 PM Revision e0d3b78b (ceph): rgw: fix uninit ofs in RGWObjManifect::obj_iterator
- Valgrind picked this up:
<kind>UninitCondition</kind>
<what>Conditional jump or move depends on uninitialised va... - 07:36 PM Revision 583e6e3e (ceph): qa/workunits/suites/fsx.sh: don't use zero range
- Zero range is not supported by cephfs.
Fixes: #8542
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from ... - 07:36 PM Revision d43e7113 (ceph): qa/workunits/suites/fsx.sh: don't use zero range
- Zero range is not supported by cephfs.
Fixes: #8542
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from ... - 07:35 PM Revision 9db124d9 (ceph): Merge pull request #2045 from ceph/wip-8542
- qa/workunits/suites/fsx.sh: don't use zero range
Reviewed-by: Greg Farnum <greg@inktank.com> - 07:28 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Samuel Just wrote:
> Hmm. I looked into the journal code. Each entry is checksumed, and the checksum actually incl... - 11:06 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Hmm. I looked into the journal code. Each entry is checksumed, and the checksum actually includes the uuid. Rewrit...
- 07:10 PM Revision 73b929ba (ceph): osd: improve tests for configuration updates
- Extract the default values from the actual configuration instead of
having them hardcoded. Also check that lowering t... - 06:23 PM devops Bug #8616 (Closed): after deploying ceph while testing calamari, rados operation hangs.
- This is working in later tests.
- 06:13 PM Bug #8694: OSD crashed (assertion failure) at FileStore::_collection_move_rename
- Greg Farnum wrote:
> Can you print the value of "r" in the _collection_move_rename frame?
From the backtrace above,... - 12:18 PM Bug #8694: OSD crashed (assertion failure) at FileStore::_collection_move_rename
- Can you print the value of "r" in the _collection_move_rename frame?
Do you have a full OSD log from when this hap... - 06:12 PM Revision c5b8d810 (ceph): Merge pull request #2026 from athanatos/wip-8438-master
- Wip 8438 master
Fixes: #8438
Backport: Firefly
Reviewed-by: Sage Weil <sage@inktank.com> - 06:11 PM Revision 830940bf (ceph): Merge pull request #2027 from athanatos/wip-7999-master
- Wip 7999 master
Fixes: #7999
Backport: Firefly
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Haomai Wang <h... - 06:09 PM devops Bug #8668 (Can't reproduce): ceph-deploy install on Rhel7 fails.
- THis appears to have gone away. I could believe that changes in the past week fixed this issue.
- 05:19 PM Revision 49c0b461 (ceph): Merge pull request #2014 from ceph/wip-scrub-dumpling
- osd: scrub priority updates for dumpling
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:10 PM Revision 5a61f449 (ceph): Split up repo helper into separate functions
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:11 PM Bug #8701: osd: scrub found obsolete rollback obj
- 2014-06-30 13:41:45.351861 1041a700 15 filestore(/var/lib/ceph/osd/ceph-0) remove 3.32s0_head/81920472/default.4106.5...
- 01:56 PM Bug #8701 (Resolved): osd: scrub found obsolete rollback obj
- ...
- 03:01 PM Revision ee0d322c (ceph): Merge pull request #1991 from dachary/wip-8307-erasure-code-profile-imp...
- erasure code profile implicit creation (firefly backport)
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 02:38 PM rgw Bug #8702 (Resolved): RadosGW incorrectly converting + to space in URLs
- (see also ceph-users mailing list thread titled 'Problem with RadosGW and special characters')
RadosGW is incorrec... - 02:24 PM RADOS Feature #8695: OSD: make osd_backfill_full_ratio respond to injectargs/whatever
- Okay, this value actually does respond to injectargs (it's re-read every time it's used), but I'm under the impressio...
- 08:54 AM RADOS Feature #8695: OSD: make osd_backfill_full_ratio respond to injectargs/whatever
- We had a discussion about revamping the config stuff during the giant CDS to address that; see
http://wiki.ceph.c... - 08:50 AM RADOS Feature #8695: OSD: make osd_backfill_full_ratio respond to injectargs/whatever
- I have another concern, how to know the option can be changed on runtime without viewing source?
- 08:28 AM RADOS Feature #8695 (New): OSD: make osd_backfill_full_ratio respond to injectargs/whatever
- Right now, it's just set up on boot up, but obviously there's interest in it being something you can change at runtime.
- 02:17 PM Revision a67c1c1c (ceph): erasure-code: OSDMonitor::get_erasure_code is a const
- If it is not, the non const version of OSDMap::get_erasure_code_profile
is called and a profile is created as a side ... - 02:17 PM Revision a7119c31 (ceph): erasure-code: pool create must not create profiles
- If a non existent profile is provided as an argument to osd pool create,
it must exit on error and not create the pro... - 02:05 PM Revision 2dec8a81 (ceph): qa/workunits/suites/fsx.sh: don't use zero range
- Zero range is not supported by cephfs.
Fixes: #8542
Signed-off-by: Sage Weil <sage@inktank.com> - 01:21 PM Feature #8475 (Fix Under Review): erasure-code: oversized objects when using the Cauchy technique
- "upgrade/firefly-x/stress-split":http://pulpito.ceph.com/loic-2014-06-27_18:45:37-upgrade:firefly-x:stress-split-wip-...
- 01:02 PM rgw Bug #8693 (Duplicate): rgw: doesn't not automatically detect stripe size
- #8442
- 10:01 AM rgw Bug #8693: rgw: doesn't not automatically detect stripe size
- Hello Sage,
I've juste done the dump: and my stripe_width is 4096. I've tried to put in my ceph.conf : rgw max c... - 09:23 AM rgw Bug #8693: rgw: doesn't not automatically detect stripe size
- The problem is probably that rgw's write stripe size isn't aligned with the rados pool. This will be fixed to happen...
- 01:01 PM rgw Bug #8699 (Pending Backport): rgw: uninit ofs in RGWObjManifest::obj_iterator
- 12:53 PM rgw Bug #8699 (Resolved): rgw: uninit ofs in RGWObjManifest::obj_iterator
- ubuntu@teuthology:/a/teuthology-2014-06-27_23:00:47-rgw-master-testing-basic-plana/331379...
- 12:45 PM rgw Bug #8698 (Resolved): s3tests.functional.test_s3.test_multipart_upload failures on firefly
- ubuntu@teuthology:/a/teuthology-2014-06-17_23:01:01-rgw-firefly-distro-basic-plana (s3tests failing)
ubuntu@teuthol... - 12:34 PM CephFS Bug #8542 (Resolved): kcephfs: fsx failure on read (expected 0's)
- 07:04 AM CephFS Bug #8542 (Fix Under Review): kcephfs: fsx failure on read (expected 0's)
- https://github.com/ceph/ceph/pull/2045
from our fsx's help:
-z: Do not use zero range calls
- 12:03 AM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- file system may choose to zero out the extent or do whatever which will result in reading zeros from the range *while...
- 12:12 PM devops Bug #8697: libcephfs_jni.so symlink does not get created in EL6 RPM
- Based on a conversation with joshd1 in IRC, it may be due to ldconfig not being run in the package specfile:
The r... - 12:09 PM devops Bug #8697 (Rejected): libcephfs_jni.so symlink does not get created in EL6 RPM
- The subpackage "libcephfs_jni1" apparently never creates the appropriate symlink to /usr/lib64/libcephfs_jni.so.
F... - 11:10 AM Feature #8389 (Pending Backport): osd: clean up old ec objects more aggressively
- 11:10 AM Feature #8480 (Pending Backport): modify scrub to detect/repair obsolete rollback objects
- 11:10 AM Bug #7999 (Pending Backport): osd: pgs share info that hasn't been persisted
- 11:10 AM Bug #8438 (Pending Backport): erasure code: object are not cleanup
- 10:38 AM Bug #8670: Cache tiering parameters can not be displayed for a pool
- Talked this over with Sam and not checking the nature of each pool when setting some of these variables is indeed a b...
- 09:53 AM Bug #8670 (Fix Under Review): Cache tiering parameters can not be displayed for a pool
- https://github.com/ceph/ceph/pull/2046
- 10:38 AM Bug #8696 (Resolved): mon: 'osd pool set' must take into account pool's nature when setting some ...
- There's no logic currently in place to disallow users from setting some variables on any pool regardless of the natur...
- 10:00 AM devops Bug #8581: DNS issues when resolving hosts
- Despite what that error message says right before that it shows a 'no route to host' which is not a DNS error:
<pr... - 05:38 AM devops Bug #8581: DNS issues when resolving hosts
- Still seeing DNS issues:...
- 09:40 AM Revision 3dfb596f (ceph): Merge pull request #2039 from dachary/wip-erasure-code-doc
- erasure-code: add definitions to the glossary
Reviewed-by: Florent Flament <florent.flament@cloudwatt.com> - 09:40 AM Revision 8be756a0 (ceph): task/ceph: Invoke newfs for CephFS as needed
- New ceph versions will no longer create the
CephFS pools and will not enable the filesystem
by default. This change ... - 09:40 AM Revision 641a2943 (ceph): task: update 'newfs' users to 'fs new'
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:38 AM Revision 7294e8c4 (ceph): test/qa: update for MDSMonitor changes
- Accomodate changes:
* data and metadata pools no longer exist by default
* filesystem-using tests must use `fs new`... - 09:38 AM Revision 96f4e782 (ceph): mds: journal-related debug messages
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:38 AM Revision 641b4195 (ceph): mds: Handle setting 'enabled' in upgrades
- Previously was always defaulting to disabled,
should be enabled if MDS map epoch is >1 (i.e.
if an MDS was ever start... - 09:38 AM Revision fc0f8bd1 (ceph): mon/MDSMonitor: s/enabled/get_enabled()/
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:38 AM Revision b7f09c2c (ceph): mon/MDSMonitor: fix incorrect comment
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:38 AM Revision 83f19064 (ceph): mon/MDSMonitor: log warning while MDS up but no FS
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:36 AM Revision ae5f1db4 (ceph): mon: add `ceph fs [new|rm|ls]`
- Signed-off-by: John Spray <john.spray@inktank.com>
- 09:36 AM Revision fd9c1fe6 (ceph): vstart: update for newfs/rmfs changes
- Signed-off-by: John Spray <john.spray@inktank.com>
- 09:35 AM Revision 1dfe913a (ceph): erasure-code: add definitions to the glossary
- and fix a typo
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:33 AM Revision f6d029df (ceph): mon: warn in newfs if crash_replay_interval=0
- This is the setting we would apply to data pools
created automatically, so notify the user if they're
failing to use ... - 09:33 AM Revision c442b0db (ceph): mon: enable deleting pools when FS disabled
- Signed-off-by: John Spray <john.spray@inktank.com>
- 09:33 AM Revision 6109cc98 (ceph): mon: stop MDSMonitor when FS disabled
- Where 'stopped' means ignoring beacons and
not performing 'tick' activities.
Signed-off-by: John Spray <john.spray@i... - 09:33 AM Revision 58674643 (ceph): mon: hide mdsmap in 'ceph status' if not enabled
- Previously we checked if the MDS map had ever been
updated (epoch > 1), now we have an explicit flag
for whether it's... - 09:30 AM Revision 90e6daec (ceph): osdmap: Don't create FS pools by default
- Because many Ceph users don't use the filesystem,
don't create the 'data' and 'metadata' pools by
default -- they wil... - 09:30 AM Revision 243963c1 (ceph): mon: don't require 'sure' flag for new fs
- Only prompt for --yes-i-really-mean-it if there
is an existing FS.
Signed-off-by: John Spray <john.spray@inktank.com> - 09:30 AM Revision ef7d1bc0 (ceph): doc: RPM instructions correction
- Signed-off-by: John Spray <john.spray@inktank.com>
- 09:30 AM Revision 8f7900a0 (ceph): mds: add 'enabled' flag to MDSMap
- When 'enabled' is false, the MDSMap is effectively
null. This allows Ceph clusters with no filesystem
or filesystem ... - 09:30 AM Revision 13305d5b (ceph): mds: no initial filesystem
- Because not everyone uses CephFS, we would
like to avoid initially creating any data/metadata
pools for CephFS.
To a... - 09:18 AM Revision fcdf2739 (ceph): mds: avoid comparing MutationRef with 0
- LLVM on OS X considers this == operator with an int
ambiguous: compare with an explicit MutationRef()
instead.
Signe... - 08:59 AM Revision e4737907 (ceph): krbd: rework the unmap retry loop
- The retry loop in the unmap path turned out to be insufficient for
doing long fsx -K runs. Replace it with a single ...
06/29/2014
- 09:31 PM Bug #8694 (Duplicate): OSD crashed (assertion failure) at FileStore::_collection_move_rename
- Most recently when the cluster was doing backfilling/recovery, we captured one OSD crash at FileStore::_collection_mo...
- 06:26 PM Revision 59d18ac2 (ceph): [RGW, memory leak] Memory leak in RGW has been fixed: deletion of alloc...
- Memory leaks detector report:
$ valgrind --leak-check=full /usr/bin/radosgw -c /etc/ceph/ceph.conf -n
client.radosg... - 06:26 PM Revision 8e5c9213 (ceph): [RGW, memory leak] Memory leak in RGW GC (losing pointer during allocat...
- Memory leaks detector report:
...
==117947== 11,725 (200 direct, 11,525 indirect) bytes in 25 blocks are definitely l... - 06:26 PM Revision 8706b74e (ceph): [RGW, memory leaks] Memory leak in RGW initialization (Inserting new co...
- Memory leaks detector report:
$ valgrind --leak-check=full /usr/bin/radosgw -c /etc/ceph/ceph.conf -n
client.radosg... - 05:58 PM Revision 16b14ea1 (ceph): map-unmap.sh: drop the get_id() logic
- Take advantage of the fact that 'rbd map' will now talk to udev and
output the device that got assigned by the kernel... - 05:58 PM Revision 9bcc19de (ceph): map-unmap.sh: fail if 'rbd rm' fails
- Fail if 'rbd rm' fails - most probably it'd fail with "image still has
watchers" and in that case it's a bug in the k... - 05:55 PM Revision abdb168c (ceph): test_librbd_fsx: use private RNG context
- It is at the core of fsx to be able to reproduce the exact op sequence
that lead to a failure. Use reentrant glibc R... - 04:32 PM Revision 9517ceab (ceph): os/FileStore: put SUPER usage in ifdef __linux__
- This is an update to take account of 9312c5e wherein
the FS_* enum was replaced by direct use of SUPER_MAGIC
macros.
... - 04:32 PM Revision b066e160 (ceph): common: move #include syscall into ifndef DARWIN
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:31 PM Revision 2db500b1 (ceph): client: handle missing O_RSYNC constant
- Although this is part of POSIX, it's missing on
OS X. #define it to zero in this case so that checks
for the flag wi... - 04:31 PM Revision 4b36074c (ceph): os/FileStore: move ZFS_SUPER_MAGIC in linux ifdef
- The __SWORD_TYPE for this line is linux-specific.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:31 PM Revision 656bc04d (ceph): common/Thread: add missing #include for pid_t
- On linux this worked by side effect from
pthread.h, but POSIX header for pid_t is
sys/types.h -- this is needed on OS... - 04:31 PM Revision b2bcf52a (ceph): ceph.in: handle DYLD_LIBRARY_PATH on OS X
- On OS X, the environment variable to override
to .libs is DYLD_LIBRARY_PATH instead of
LD_LIBRARY_PATH.
Signed-off-b... - 03:37 AM rgw Bug #8693 (Duplicate): rgw: doesn't not automatically detect stripe size
- Hello,
I'm trying to create a bucket on a erasure code pool with RGW and I have this errors:
2014-06-29 12:...
06/28/2014
- 08:58 PM Bug #8692 (Resolved): mon: blocked request warnings for down osd (dumpling)
- 2 ops are blocked > 65.536 sec
3 ops are blocked > 32.768 sec
1 ops are blocked > 32.768 sec on osd.36
2 ops are b... - 01:44 PM Revision 12079a7c (ceph): doc: dev: cache-pool.rst: fix typo s/objets/objects/
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 09:35 AM Bug #8691 (Resolved): osd: PG::_lock, OSD::pg_map_lock lock cycle
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-06-27_10:04:18-smoke-master-testing-basic-plana/329562...
- 08:54 AM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- We can support it, just not "preferably without issuing data IO". It needs to iterate over the range and zero the ra...
- 08:38 AM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- There is no way we can support it
/*
* FALLOC_FL_ZERO_RANGE is used to convert a range of file to zeros preferab... - 07:08 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Although recovery was extremely frustrating experience for me due to all those spontaneous OSD crashes I may have fou...
- 06:48 AM Bug #8670: Cache tiering parameters can not be displayed for a pool
- funny thing, those parameters can be set on any pool regardless of their nature.
Is this by design or a bug? - 06:26 AM CephFS Feature #8690: MDS: Allow some kind of recovery when pools are deleted out from underneath us
- CephFS was practically unusable until I applied the following patch to MDS:...
06/27/2014
- 09:57 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- I'm a bit sceptical of your analysis. I have some confidence in my systems. Due to concerns regarding data integrity ...
- 04:34 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- It's not really practical to do that, partly because it would result in the pool becoming unusable anyway. You appea...
- 03:43 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- First let's focus on the original issue please. Some hours later I was able to start OSD that were previously dying w...
- 10:18 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- If you can reproduce that crash, please attach a log with
debug osd = 20
debug filestore = 20
debug ms = 1 - 12:02 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Hi Samuel,
As advised I introduced ... - 09:35 PM CephFS Feature #8690 (New): MDS: Allow some kind of recovery when pools are deleted out from underneath us
- I had a secondary (cache) pool once connected to CephFS directory as follows:...
- 08:42 PM Revision 6b948075 (ceph): Use corrected tube_name
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:41 PM Revision 85833067 (ceph): Return corrected tube_name
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:34 PM Revision 491999be (ceph): Use teuthology.beanstalk
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:33 PM Revision 4689467a (ceph): PG: pass OpRequestRef by ref to avoid refcounting overhead
- Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
- 08:27 PM Revision 1f59e405 (ceph): Merge remote-tracking branch 'upstream/master' into wip-8438-master
- Conflicts:
src/osd/ECMsgTypes.cc - 08:25 PM Revision 953c33ed (ceph): osd/: plumb rollback_trim_to through interfaces and messages
- We simply trim the roll back info up to min_last_complete_ondisk
since we cannot correctly rollback past that point a... - 08:25 PM Revision d48a737a (ceph): osd/: in scrub, check for and remove obsolete rollback objs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:25 PM Revision ac11ca40 (ceph): PGLog: add rollback_info_trimmed_to_riter to IndexedLog and use in PG
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:25 PM Revision 62027ec9 (ceph): doc/release-notes: v0.82
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:23 PM Revision 3ec07cdc (ceph): Merge pull request #43 from dachary/wip-firefly-x
- add upgrade/firefly-x based on dumpling-x
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yuri Weinstein <yur... - 08:20 PM Revision d56b59de (ceph): add upgrade/firefly-x based on dumpling-x
- It is a s/dumpling/firefly/ mostly. With the exception of
rados/test-upgrade-firefly.sh which is dumpling specific.
... - 08:16 PM Revision 3ceafcf3 (ceph): mon: fix set cache_target_full_ratio
- It was a noop because it was incorrectly using the variable n. Add a
test to protect against regression.
http://trac... - 07:55 PM Revision eb3963f8 (ceph): Merge branch 'next'
- 07:55 PM Revision 7fae9412 (ceph): rgw: allocate enough space for bucket instance id
- Fixes: #8608
Backport: dumpling, firefly
Bucket instance id is a concatenation of zone name, rados instance id,
and a... - 06:09 PM Revision 2207ed12 (ceph): PGLog: fix logging whitespace in trim
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:06 PM Revision af4970ca (ceph): OSDMap: avoid passing pg_t by value
- Passing pg_t param by cons ref for avoiding copies.
Signed-off-by: Somnath Roy <somnath.roy@sandisk.com> - 05:54 PM Revision f48a0333 (ceph): Merge remote-tracking branch 'upstream/master' into wip-7999-master
- Conflicts:
src/os/KeyValueStore.h - 05:51 PM Revision d72eec03 (ceph): PG: block outgoing peering messages until the last interval is durable
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:51 PM Revision f9f89be3 (ceph): PG: add machinery to temporarily buffer outgoing recovery messages
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:50 PM Revision f7498124 (ceph): os/: add async flush_commit() method to Sequencer and implementations
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:48 PM Revision 0debfe11 (ceph): OSD: pass param by ref to avoid copying overrhead
- passing OpRequestRef, OSDMapRef by ref to avoid refcounting overhead
and in some cases passing structures by const re... - 05:11 PM Revision 5bb608c6 (ceph): Merge pull request #42 from ceph/wip-smoke
- upgrade: fix dumpling tests
- 04:25 PM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- So...we need to implement that functionality, don't we? Just knowing the problem isn't a resolution, if we're no long...
- 04:21 PM Revision 55b65d62 (ceph): Document checkout_repo()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:18 PM Revision 25a40677 (ceph): Drop a "fix" for a bug that probably never existed
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision b16c48a8 (ceph): Also handle teuthology repo checkouts
- Our shell script did this also.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 04:14 PM Revision 807d6fd7 (ceph): Use 'ceph-qa-suite.git' for the repo name
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision abd35908 (ceph): Add unit tests for repo_utils
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision f5bed55d (ceph): Improve missing branch detection and logging
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision a4c3a025 (ceph): Add a note about teuthology scheduling
- Specifically, that we always schedule using the master branch.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 04:14 PM Revision 5e3c13de (ceph): Use a more informative variable name for dest_path
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision 93fd6b89 (ceph): Move repo checkout code to new module repo_utils
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision 484693c2 (ceph): Fix linter errors
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision 6e3e6693 (ceph): Generalize error message
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:14 PM Revision 88d26e4a (ceph): Handle ceph-qa-suite checkouts
- Previously we had an internally-maintained shell script that did this.
Signed-off-by: Zack Cerza <zack.cerza@inktank... - 04:07 PM Revision 7d2388b4 (ceph): Merge pull request #274 from dachary/wip-facet
- document how to specify a facet in teuthology-suite
- 04:04 PM Revision 09baca9f (ceph): document how to specify a facet in teuthology-suite
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:16 PM RADOS Fix #8687 (New): OSD: preemptively clean up incoming Connections from dead OSDs
- If we get an incoming Connection from a dead OSD, but never actually receive a Message from it, we never kill the Con...
- 03:14 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Okay, and after more discussion (thanks Sage!), the "Messenger bug" is the same as the OSD bug — the surviving OSD ot...
- 02:50 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Of course the lookup is supposed to be protected by the map reservation system, but since we're doing mark_down prior...
- 02:41 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- get_con_osd_cluster might be okay, since a marked_down Connection won't send any outgoing messages, which is what we ...
- 02:20 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- OSD bug:
1) In handle_osd_map(), we need to wait until nobody is using a (previously-)reserved map prior to doing an... - 01:49 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Greg Farnum wrote:
> So it looks like osd.4 called mark_down on the addr-based interface and nuked the Pipe from han... - 03:05 PM Bug #8512 (Duplicate): osd crashed at Pipe::reader in firefly
- Drat, I am wrong again. Stupid messenger-interface-related bugs. :(
- 02:56 PM Bug #8512: osd crashed at Pipe::reader in firefly
- While the symptom is the same, this is actually a separate issue from the one I noted in #8504 (although the analysis...
- 10:21 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Yeah, reproducing on a clean cluster would probably be a good next step.
- 03:52 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- today, we had further network problems and inconsistent pg count is still increasing:...
- 07:45 AM Revision 55ed85b1 (ceph): mds: introduce sequence number for log events
- Use the sequence number to index log segments. Later commit will defer
encoding/submitting log events to separate thr... - 07:45 AM Revision 1f3fbc90 (ceph): mds: print sequence number of log segment
- 07:45 AM Revision 0690078c (ceph): mds: pass finish context to MDlog::submit_entry()
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 07:45 AM Revision a17462c8 (ceph): mds: add get_metablob() to log events
- later commits will use it to get EMetaBlob and update EMetaBlob's
event sequence number.
Signed-off-by: Yan, Zheng <... - 06:07 AM Feature #8071 (Resolved): erasure-code: simplify jerasure initialization
- Was merged before testing it individually.
- 05:11 AM Bug #8680 (Resolved): crushtool should not send it's output to stderr
- Currently crushtool sends it output to stderr instead of stdout.
Shouldn't this be fixed? - 04:44 AM RADOS Feature #8679 (New): improve logging statements
- As discussed at some point, one of the annoyances is to have very cryptic logging messages (cryptic to those who have...
- 01:57 AM Revision 21955d72 (ceph): MOSDOpReply: Constructor initialization list is used to instantiate mem...
- constructor initialization list is modified to initialize ops,oid,pgid with
copy constructor instead of assignment op... - 01:53 AM Revision 44db3d04 (ceph): MOSDOpreply: The functions are returned by const ref and parameters pas...
- get_oid,get_pg,get_replay_version,get_user_version are returning by reference and
corresponding setter is accepting p... - 01:35 AM Revision 1c93c61c (ceph): MOSDOp: The functions are returned by const ref and parameters passed b...
- get_snapid(),get_snap_seq,get_pg,get_object_locator,get_version are returning
by reference and the corresponding sett...
06/26/2014
- 11:15 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- the cluster is in really bad shape, which happend basically before i switched the config options. we are now trying t...
- 05:19 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Are you seeing different results now?
- 11:08 PM Revision 3c636018 (ceph): rgw: allocate enough space for bucket instance id
- Fixes: #8608
Backport: dumpling, firefly
Bucket instance id is a concatenation of zone name, rados instance id,
and a... - 11:06 PM Revision 5f66a2c9 (ceph): rgw: allocate enough space for bucket instance id
- Fixes: #8608
Backport: dumpling, firefly
Bucket instance id is a concatenation of zone name, rados instance id,
and a... - 07:43 PM Revision 94e1b776 (ceph): Merge pull request #2035 from ceph/wip-da-SCA-20140623
- Fix for SCA and CID issues
Reviewed-by: Sage Weil <sage@redhat.com> - 06:37 PM Revision ad81a98e (ceph): Revert "ceph-disk: Enable creating multiple osds per dev"
- This reverts commit 200d0ae9c6e6701c06310230e180d4e739865bfe.
This breaks ceph-disk. See #8644. Reverting for now.... - 06:33 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Samuel Just wrote:
> Dropping the pool containing pg 14.7 would be an option.
I was afraid you would say that... ... - 06:29 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Samuel Just wrote:
> Are you certain that you have never had cephfs writing directly to this pool?
Yes, absolutel... - 06:25 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Dropping the pool containing pg 14.7 would be an option. At what version did you start using this pool? I think I r...
- 06:10 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Are you certain that you have never had cephfs writing directly to this pool? I have a theory for the size mismatch,...
- 05:40 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Thanks for your help and explanations, Samuel.
Samuel Just wrote:
> No, you are using erasure coding with M=K=2. ... - 05:34 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- No, I guess it looks like a cephfs block. Is this cephfs with caching? Or somehow cephfs without caching?
- 05:18 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- No, you are using erasure coding with M=K=2. You will need at least two osds to recover the pg. That part is correc...
- 02:09 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- I need more help here please. OSD.11 is still crashing as soon as it started. Earlier I've set it "out" so it have li...
- 01:32 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- All journals are on ext4@SSD. I'll disable "journal aio" but I don't understand how journal can be an issue. There we...
- 11:28 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- All of your journals are on ext4? Or the journals on btrfs osds are btrfs?
- 09:08 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Try disabling journal aio. I've seen similar behavior on another ticket with those kernel versions. I think somethi...
- 06:14 PM Revision e02957db (ceph): test: use (unsigned)0 with gtest to avoid spurious warnings
- Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 06:05 PM Revision 4aadddc3 (ceph): Merge pull request #2034 from ceph/wip-osd-ints
- osd: fix int -> int32_t in misc encoded structures
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:38 PM CephFS Bug #8677 (Resolved): multimds: pjd failures
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-06-26_07:42:59-multimds-next-testing-basic-plana$ teut...
- 04:52 PM Revision 1c0dc1ce (ceph): smoke: add rbd fsx + thrashing
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:51 PM Revision f8df9bd2 (ceph): scratchtool.c: cleanup do_rados_getxattrs()
- Cleanup error path to reduce code duplication.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:46 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- The one I originally reported is much simpler:
osd.0 got marked down
osd.1 called mark_down and then forgot about i... - 03:21 PM Messengers Bug #8504: msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Okay, so the crashed OSD (osd.5) was marked down by the other endpoint (osd.4). Then osd.5 reconnected to osd.4, whic...
- 10:54 AM Messengers Bug #8504 (In Progress): msgr: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Not a bug we introduced, but the existing patch only fixes the bug on the accept side. These crashes are on the conne...
- 04:46 PM Revision 3fa6dd21 (ceph): smoke: add a mon thrash test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:44 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- Samuel Just wrote:
> Where in the docs did you see that bit?
I also followed what Greg told me in his reply to my... - 04:35 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- Samuel Just wrote:
> I think you need add-cache rather than set-overlay.
Based on the following link, I need to s... - 11:12 AM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- Where in the docs did you see that bit?
- 11:12 AM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- I think you need add-cache rather than set-overlay.
- 04:44 PM Revision 64ec775f (ceph): smoke: add some rados osd thrashing test
- ec, caching, snaps
Signed-off-by: Sage Weil <sage@inktank.com> - 04:43 PM Revision e99eba9a (ceph): smoke: specify fs on each run
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:28 PM CephFS Bug #8542 (Resolved): kcephfs: fsx failure on read (expected 0's)
- ceph_fallocate() does not recognize FALLOC_FL_ZERO_RANGE
- 04:13 PM Revision 4e9c2c1b (ceph): osd: fix pg_stat_t int -> int32_t
- Still 4 bytes on i386 and x86_64.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:13 PM Revision 238b1a3f (ceph): osd: fix pg_shard_t int -> int32_t
- Still 4 bytes on i386 and x86_64.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:11 PM Revision 709f0c47 (ceph): osd: fix pg_interval_t int -> int32_t
- Still 4 bytes on i386 and x86_64.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:08 PM rgw Bug #8676 (Duplicate): md5sum check failed during readwrite.py
- ubuntu@teuthology:/a/teuthology-2014-06-26_07:41:24-rgw-next-testing-basic-plana/327692...
- 03:47 PM Revision 959d664b (ceph): Merge pull request #2032 from sponce/wip-fixstriperoni386
- Wip fixstriperoni386
Reviewed-by: Sage Weil <sage@redhat.com> - 03:40 PM Revision f5a72b75 (ceph): Added a couple of ASSERTS for avoiding coverity to complain about the p...
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 03:40 PM Revision a5f9a091 (ceph): Fixed build on 32 bits platforms
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 03:33 PM Revision cf16dfc7 (ceph): Merge pull request #2030 from ceph/wip-xattr-fix
- mds: set xattr_version to 0 if replay doesn't contain xattrs
Reviewed-by: Sage Weil <sage@redhat.com> - 02:52 PM RADOS Bug #8675 (Won't Fix): Unnecessary remapping/backfilling?
- A little experiment: on my cluster I marked two OSDs from different hosts as "out".
After some time when remapping f... - 02:11 PM Revision 84d7971c (ceph): log the command that is being run with subprocess
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit e189a668285f9ab73116bc19f9df1cc5154... - 01:10 PM Feature #8674: osd: cache tier: avoid promotion on first read
- Greg Farnum wrote:
> This naively sounds like a terrible idea — you still have maintain metadata on the object (so y... - 01:08 PM Feature #8674: osd: cache tier: avoid promotion on first read
- This naively sounds like a terrible idea — you still have maintain metadata on the object (so you know it's the secon...
- 01:05 PM Feature #8674 (Resolved): osd: cache tier: avoid promotion on first read
- Earlier we proposed adding a new 'read-forward' mode that never promotes on reads (which may make sense for flash). ...
- 12:48 PM Bug #8344: Upstart scripts silently fail when asok missing
- I saw this with Emperor and Firefly running on Ubuntu Raring. Perhaps it only affects Raring, similar to #7188.
- 11:34 AM Bug #8344 (Can't reproduce): Upstart scripts silently fail when asok missing
- I tried reproducing this both on master and on dumpling and couldn't make it happen. I could see any problems when t...
- 11:37 AM Bug #8521 (Can't reproduce): osd: hung LibRadosListECPP.ListObjectsPP
- 11:36 AM Bug #8644: 624ae21833 breaks ceph-disk
- I reverted the commit for now. John, care to take a look? I hit the same problem as well on a mira (using ceph-depl...
- 11:30 AM Bug #8660 (Closed): pg in forever "down+peering" state
- Also, this is almost certainly not a bug, but rather a consequence of 8643. We don't go active with fewer than M osd...
- 09:09 AM Bug #8660: pg in forever "down+peering" state
- Attach an actual osdmap (ceph osd getmap -o /tmp/map)
- 11:13 AM Bug #8611 (Duplicate): osd/ReplicatedPG.cc: 2348: FAILED assert(p != snapset.clones.end())
- 11:10 AM Bug #8520 (Can't reproduce): osd: segv in PushOp::print()
- Haven't seen it recur lately, marking can't reproduce.
- 11:10 AM Bug #8673 (Resolved): s3tests.functional.test_s3.test_multipart_upload failed in teuthology-2014-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-26_08:02:03-upgrade:dumpling-x:parallel-firefly---...
- 11:03 AM Feature #7792: leveldb 1.12.0 for rhel
- The history of 1.12 on Centos/RHEL has been that it breaks. There were aspersions cast on one of the patches from a F...
- 02:41 AM Feature #7792: leveldb 1.12.0 for rhel
- Which RHEL version will be using 1.12? I thought this was about providing something newer than the old/buggy 1.7 in e...
- 10:13 AM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- Not really. The ondisk files on the osds correspond to rados objects. You can work from that back to blocks in the ...
- 07:10 AM Bug #8603 (Resolved): ceph-disk should not hide commands that go through subprocess
- Backported/cherrypicked to Firefly with commit 84d7971
- 05:33 AM Revision 93df7daf (ceph): mds: set xattr_version to 0 if replay doesn't contain xattrs
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:06 AM Revision c2ffad34 (ceph): Merge pull request #2019 from ceph/wip-refactor-cephtool-test
- qa/workunits/cephtool/test.sh: refactor and make it modular (yey! \o/)
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:20 AM Bug #7593: Disk saturation during PG folder splitting
- Pull request as per comment 8 - https://github.com/ceph/ceph/pull/2031
- 03:22 AM Revision 046c9769 (ceph): common/fd.cc: fix possible out-of-bounds write
- Read max 'sizeof(target) - 1' to not write out of bound
later on the 'target[r] = 0;' call in case we read the
full P... - 02:40 AM Revision 605d1805 (ceph): mount.ceph.c: fix strdup related memory leak
- CID 1219611 (#1 - 5): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable saw_name going out of scope
leaks the ... - 01:49 AM Revision 7f7e56c6 (ceph): scratchtool.c: fix resource leak and error handling
- Check the result of rados_ioctx_create()before using io_ctx.
Free io_ctx where needed. Fix messages at the end of tes... - 12:50 AM Revision bdb13460 (ceph): scratchtool.c: fix resource leak
- CID 1219612 (#1 - 3): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable iter going out of scope leaks the
stor... - 12:00 AM Revision 67255435 (ceph): qa/workunits: cephtool: delete unnecessary function calls
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:00 AM Revision 5c4616e1 (ceph): qa/workunits: cephtool: set +e for the tcmalloc tests
- Avoids failing the tests when tcmalloc is not present
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 12:00 AM Revision 4b0809a1 (ceph): qa/workunits: cephtool: only run heap profiler test if tcmalloc enabled
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:00 AM Revision 802290d6 (ceph): osd: OSD: better explanation on 'max_count' calculation for 'osd bench'
- 'max_count' is the maximum number of bytes that we are to allow for an
'osd bench' command. This value is a hard-cap... - 12:00 AM Revision 48e38ac6 (ceph): qa/workunits: cephtool: fix 'osd bench' test
- Commit 7dc93a9651f602d9c46311524fc6b54c2f1ac595 fixed an incorrect
behavior with the OSD's 'osd bench' value hard-cap... - 12:00 AM Revision f4184086 (ceph): qa/workunits: cephtool: cleanup state after erasure-code-profile test
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:00 AM Revision 5d26575e (ceph): qa/workunits: cephtool: allow running individual tests
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:00 AM Revision 946bd0da (ceph): qa/workunits: cephtool: disable bash debug when not running tests
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
06/25/2014
- 11:57 PM Revision 780424df (ceph): qa/workunits: cephtool: add/remove comments
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:55 PM Revision 3d14a96f (ceph): qa/workunits: cephtool: split into properly indented functions
- The test was a big sequence of commands being run and it has been growing
organically for a while, even though it has... - 11:52 PM Revision 04658b7b (ceph): qa/workunits: cephtool: move test line to where it's more appropriate
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:51 PM Revision db6cc133 (ceph): qa/workunits: cephtool: split into functions
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:51 PM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- I realize I have not given you much information. I have been busy restoring backups to other locations. I will come b...
- 02:10 PM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- We still need more complete logging from a crash to help diagnose.
- 11:37 PM Revision d2f17c74 (ceph): Merge pull request #1863 from ceph/wip-rgw-manifest-iter
- rgw: reduce calls to rgw_obj.set_obj()
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:14 PM Revision 8a5e0034 (ceph): Merge pull request #2021 from ceph/wip-da-fix-make-check
- Fixes to get "make check" run on SUSE v2
Reviewed-by: Sage Weil <sage@redhat.com> - 10:12 PM Bug #8121: ReplicatedBackend::build_push_op() should handle a short read or assert
- I got this assert in ReplicatedBackend::build_push_op .
Steps Followed:
sudo ceph pg map 3.151
osdmap e1274 pg... - 09:54 PM Revision 291d4484 (ceph): rgw: fetch object attrs on multipart completion
- Fixes: #8452
Backport: firefly
This fixes a regression following a code cleanup.
Signed-off-by: Yehuda Sadeh <yehuda... - 09:54 PM Revision 2fd808fe (ceph): rgw: check appropriate entity permission on put_metadata
- Fixes: #8428
Backport: firefly
Cannot use verify_object_permission() to test acls, as the operation
here might eithe... - 09:52 PM Revision 15360a90 (ceph): ceph-disk: partprobe before settle when preparing dev
- Two users have reported this fixes a problem with using --dmcrypt.
Fixes: #6966
Tested-by: Eric Eastman <eric0e@aol.... - 09:49 PM Revision d1afeb38 (ceph): XfsFileStoreBackend: call ioctl(XFS_IOC_FSSETXATTR) less often
- No need to call ioctl(XFS_IOC_FSSETXATTR) if extsize is already set to
the value we want or if any extents are alloca... - 09:49 PM Revision 7b8e5c99 (ceph): mon: Fix default replicated pool ruleset choice
- Specifically, in the case where the configured
default ruleset is CEPH_DEFAULT_CRUSH_REPLICATED_RULESET,
instead of a... - 09:33 PM Revision 25a4a874 (ceph): rgw: calc md5 and compare if user provided appropriate header
- Fixes: #8436
Backport: firefly
This was broken in ddc2e1a8e39a5c6b9b224c3eebd1c0e762ca5782. The fix
resurrects and o... - 09:31 PM Revision ad18a45a (ceph): rgw: calculate user manifest
- Fixes: #8169
Backport: firefly
We didn't calculate the user manifest's object etag at all. The etag
needs to be the m... - 09:30 PM Revision 6aa7f7ee (ceph): librados: simplify/fix rados_pool_list bounds checks
- We were not breaking out of the loop when we filled up the buffer unless
we happened to do so on a pool name boundary... - 08:39 PM Revision 4e68ac34 (ceph): Merge pull request #2001 from dachary/wip-tiermsg
- mon: test that pools used in tiers cannot be removed
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:35 PM Revision c6ac1b7f (ceph): Merge pull request #1938 from dachary/wip-8071
- erasure-code: remove jerasure internals dependencies
- 08:30 PM Revision 971950bd (ceph): Merge pull request #2025 from ceph/wip-disable-static
- do_autogen.sh: --disable-static
Reviewed-by: Loic Dachary <loic@dachary.org> - 08:24 PM Revision 3226a85f (ceph): Merge pull request #1967 from yuyuyu101/kvstore-fix-set-alloc-hint
- Make KeyValueStore not use expected_write_size
Reviewed-by: Sage Weil <sage@redhat.com> - 08:23 PM Revision 39530536 (ceph): test/ceph-disk.sh: fix for SUSE
- On SUSE 'which' returns always the full path of (shell) commands and
not e.g. './ceph-conf' as on Debian. Add check a... - 08:23 PM Revision be70c1ff (ceph): osdmaptool/test-map-pgs.t: fix escaping to fix run
- Run failed always running into the '|| cat $OUT' case due
to bad escaping of '\t'. This is caused by different shells... - 08:19 PM Revision dc1a4dfd (ceph): Revert "Give meaningful error when submodules are not checked out"
- This reverts commit 87f9dbaf78ee040bbe0f56d2ada5299b150916b2.
This breaks the gitbuilders. Maybe it needs the base ... - 08:15 PM Revision 96955351 (ceph): Make <poolname> in "ceph osd tier --help" clearer.
- The ceph osd tier --help info on the left always says <poolname>.
It is unclear which one to put <tierpool> on the ri... - 07:42 PM Revision 2ba03e08 (ceph): Merge pull request #1982 from accelazh/firefly-fix-issue-8256
- Make <poolname> in "ceph osd tier --help" clearer (fix issue 8256).
Reviewed-by: Loic Dachary <loic@dachary.org> - 06:54 PM Revision 667a223f (ceph): Update unit tests to reflect renamed function
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision e1597a03 (ceph): No need to explicitly return None here
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision ba1eae98 (ceph): Add more docstrings
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision f4321b05 (ceph): Skip the kernel stanza if the branch passed is '-'
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision e7323da5 (ceph): Swap order of job_id and run_name when deleting
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 2e18fddb (ceph): Only delete jobs that match the pattern
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 1be15edb (ceph): Use the return value of schedule_suite()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 26fdef0a (ceph): Split prepare_and_schedule() out of main()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 89b38dd3 (ceph): Don't schedule an email job if email isn't set
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 15317083 (ceph): Add default results_email
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 356ab7e0 (ceph): Do everything that schedule_suite.sh does
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 91c73859 (ceph): Raise ScheduleFailError even if not sending email
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision b6cb3f8c (ceph): Add lots of unit tests for teuthology.suite
- More to come...
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:54 PM Revision fd13a18c (ceph): With dry_run, quote any individual args
- So that individual commands can be copied and pasted
in order to execute them individually.
Signed-off-by: Zack Cerz... - 06:54 PM Revision 173c7b84 (ceph): Fix bug where the base yaml wasn't being merged
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 6df3b134 (ceph): Remove schedule_suite.sh
- Its entire functionality is now provided by teuthology-schedule.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:54 PM Revision 743edd6b (ceph): Fix a couple linter errors
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 7082a3df (ceph): Add a few more docstrings and a debug statement
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 1ccbff8d (ceph): Refactor collection scheduling out of main()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision f5af797c (ceph): Port to docopt
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 43505b2a (ceph): Only allow scheduling one suite per call.
- Also remove all traces of the extra and confusing term 'collection'
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:54 PM Revision ef9638a2 (ceph): Remove 'template' feature
- Neither Sage nor I could find anything that used it
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:54 PM Revision 4fed92c0 (ceph): Silence connection pool logging
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision d14c44f4 (ceph): Add functions for querying gitbuilder repos
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 675f087b (ceph): Take machine_type instead of worker
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 0aabafd6 (ceph): 'and' is a thing
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision d92f5385 (ceph): Remove unused functions
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 19d73071 (ceph): Don't reread the entire yaml file...
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision b790c4da (ceph): Tweak usage formatting
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:54 PM Revision 3b69efa2 (ceph): Organize arguments into logical sections
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:35 PM Revision 381aac54 (ceph): Merge pull request #1978 from adamcrume/master
- OSD bug fix and developer error message
Reviewed-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision 1b9805d9 (ceph): Merge pull request #2023 from adamcrume/wip-8661
- doc: Fix malformed parameters in librados.h
Reviewed-by: Sage Weil <sage@redhat.com> - 06:30 PM Revision 50dc2462 (ceph): OSD::calc_priors_during: handle CRUSH_ITEM_NONE correctly
- Fixes: #8507
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 0bd6f6797c69af9aff851033c57... - 06:29 PM Revision a53bcf23 (ceph): OSD::calc_priors_during: fix confusing for loop bracing (cosmetic)
- Confusing lack of braces is confusing.
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit ... - 06:14 PM Revision 394d5123 (ceph): Merge pull request #1958 from jdurgin/wip-rbd-ro
- qa: add script to test krbd setting ro/rw ioctl
Reviewed-by: Sage Weil <sage@redhat.com> - 06:11 PM Revision 5ed892aa (ceph): Merge branch 'wip-mon-sanity-checks'
- Reviewed-by: Sage Weil <sage@redhat.com>
- 06:10 PM Revision 76361b80 (ceph): mon: simplify output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:05 PM Revision 4958786c (ceph): Merge commit '4225e2f6c9f69682d0e7288d7809851b61a17c70'
- Conflicts:
PendingReleaseNotes
Reviewed-by: Sage Weil <sage@redhat.com> - 06:05 PM Revision 178e6f0f (ceph): rados.cc: fix pool alignment check
- Only check pool alignment if io_ctx is initialized.
Introduced in 304b08a23a3db57010078046955a786fe3589ef8
Fixes: #8... - 05:55 PM Revision 31b59d66 (ceph): Merge pull request #1973 from ceph/wip-8593
- mon: fix up health warnings
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:53 PM Revision ef736f53 (ceph): osd: fix filestore perf stats update
- Update the struct we are about to send, not the (unlocked!) one we will
send the next time around.
Backport: firefly... - 05:53 PM Revision a9f97f8c (ceph): osd: fix filestore perf stats update
- Update the struct we are about to send, not the (unlocked!) one we will
send the next time around.
Backport: firefly... - 05:52 PM Revision 589d9d76 (ceph): Merge pull request #1980 from ceph/wip-osd-stats
- osd: move osd_stat tracking into OSDService; fix minor bug
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:50 PM Revision 31721eef (ceph): Merge pull request #2006 from ceph/wip-8603
- log the command that is being run with subprocess
Reviewed-by: Sage Weil <sage@redhat.com> - 05:48 PM Revision a7e1ad42 (ceph): Merge pull request #1969 from ceph/wip-vstart-conf
- vstart.sh: echo CEPH_{CONF,KEYRING} exports if necessary
Reviewed-by: Sage Weil <sage@redhat.com> - 05:34 PM Revision 6a461a2d (ceph): Merge pull request #2022 from ceph/wip-mon-perf
- mon: shut down perfcounters last
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:27 PM Revision 385fd6c5 (ceph): do_autogen.sh: --disable-static
- This will make builds go ~2x as fast when developing.
Reported-by: Luis Pabon <lpabon@redhat.com>
Signed-off-by: Sag... - 05:02 PM Revision 25466839 (ceph): Merge pull request #1944 from athanatos/wip-8396
- Move the waiting_for_pg list down into the Sessions, and coordinate the updates so that we don't get races
between th... - 04:48 PM rgw Bug #8608 (Pending Backport): rgw: bucket instance id is truncated
- 04:47 PM Revision 14085f42 (ceph): 0.82
- 04:24 PM Revision eb16198f (ceph): Merge pull request #2024 from dachary/wip-8630-inject-enxio
- osd: workaround race condition in tests
Reviewed-by: Sage Weil <sage@redhat.com> - 04:11 PM Revision 152bbd6a (ceph): osd: workaround race condition in tests
- Trying to "ceph tell" a newly created OSD sometime triggers an
ENXIO. The OSD creation function used for test scripts... - 03:45 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- The problem gotten worse, see #8660 which is probably another manifestation of this issue...
Samuel Just wrote:
>... - 02:26 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- I think 248520c7/100001015d5.00000000/head//14 was inconsistently updated (pg 14.7). You can probably clear this iss...
- 03:43 PM Revision cb740b39 (ceph): mon: shut down perfcounters last
- In particular, remove_all_sessions updates the perfcounter stats, so we
need to stop those after.
Signed-off-by: Sag... - 03:38 PM Revision 524700fd (ceph): doc: Fix malformed parameters in librados.h
- Fixes parameters for rados_write_op_operate and rados_aio_write_op_operate
Fixes: #8661
Signed-off-by: Adam Crume <... - 03:23 PM Bug #8670 (Resolved): Cache tiering parameters can not be displayed for a pool
- Hi,
ceph version 0.80.1 (a38fe1169b6d2ac98b427334c12d7cf81f809b74)
When creation a cache tiering scheme, some p... - 03:06 PM Feature #8523 (Fix Under Review): pool quota: Should have get-quota
- 03:04 PM Revision 56cad1a8 (ceph): libcephfs/test.cc: fix use after free
- Don't call ceph_shutdown() after ceph_release().
CID 1219651 (#1 of 1): Use after free (USE_AFTER_FREE)
17. deref_... - 03:04 PM Revision a5c704b2 (ceph): RadosStriperImpl.cc: catch exception by reference
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:04 PM Revision 6d798639 (ceph): rgw/rgw_rados.h: use static_cast instead of c-style cast
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 02:54 PM Revision e0f94138 (ceph): Merge pull request #1996 from dachary/wip-mailmap
- mailmap updates
reviewed-by individual commits - 02:51 PM devops Bug #6966 (Resolved): ceph-disk: prepare --dmcrypt failing
- 02:48 PM Bug #8373 (Resolved): Pool creation defaults to ruleset 0 even if it doesn't exist
- 02:48 PM Bug #8241 (Resolved): XfsFileStoreBackend tries to set extsize but may get EINVAL
- 02:29 PM Bug #8346: OSD crashes on master (FAILED assert(ip_op.waiting_for_commit.count(from)))
- Please enable
debug osd = 20
debug filestore = 20
debug ms = 1
reproduce, and attach the log. - 02:27 AM Bug #8346: OSD crashes on master (FAILED assert(ip_op.waiting_for_commit.count(from)))
- Even in my setup of 8 nodes : with 3 osd in each node, got the same assert:
Steps to reproduce:
While IO was goin... - 02:28 PM Bug #8447 (Resolved): librados: buffer overflow in rados_pool_list
- 02:01 PM Bug #8613 (Duplicate): ENOENT from ceph_test_rados
- 01:58 PM Bug #8361 (Can't reproduce): osd/osd_types.h: 2868: FAILED assert(rwstate.empty())
- 01:48 PM Feature #8605 (Resolved): mon: add sanity checks on configurables
- 01:40 PM Feature #8231: ceph filestore dump improvements
- 01:36 PM Feature #7515: mon: 'osd crush reweight-subtree <name> <weight>'
- commit:47028874e2403ce54918b3b1d78f2f61dd14251d
- 01:36 PM Feature #7515 (Resolved): mon: 'osd crush reweight-subtree <name> <weight>'
- 01:35 PM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- 01:35 PM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- upgrade tests mixed cluster with and without
- 01:31 PM Feature #7792: leveldb 1.12.0 for rhel
- 1.12 is in Fedora, which is what RHEL will be using. Can we close this?
- 01:13 PM Revision 5d7add93 (ceph): Merge pull request #2017 from ceph/wip-8654
- Fix #8654 - OSD.cc: parse LSB data via lsb_release
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dacha... - 01:06 PM Revision 0b3a3987 (ceph): osd/OSD.cc: parse lsb release data via lsb_release
- Use lsb_release tool to be portable since parsing /etc/lsb-release
is not the same between different distributions. T... - 12:54 PM devops Bug #8668 (Can't reproduce): ceph-deploy install on Rhel7 fails.
- Running -- ceph-deploy install vpm017...
- 12:46 PM Bug #8630 (Need More Info): test osd-config.sh ENXIO
- "workaround":https://github.com/ceph/ceph/pull/2024
- 08:37 AM Bug #8630: test osd-config.sh ENXIO
- "failure log (full)":http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-raring-amd64-basic/log.cgi?log=e0f94138...
- 12:43 PM Feature #8307 (Fix Under Review): Creating a pool with erasure code allows me to create invalid e...
- 12:36 PM CephFS Bug #8622: erasure-code: rados command does not enforce alignement constraints
- Needs to be backported along with https://github.com/ceph/ceph/pull/2020 which fixes a bug introduced by the fix :-/
- 11:41 AM Bug #8507 (Resolved): OSD: failing to create PG (when splitting?) in rados/test.sh
- 11:30 AM Documentation #8661 (Resolved): Parameter documentation malformed for rados_write_op_operate and ...
- 08:33 AM Documentation #8661 (Resolved): Parameter documentation malformed for rados_write_op_operate and ...
- The documentation in src/include/rados/librados.h for rados_write_op_operate and rados_aio_write_op_operate uses bad ...
- 11:20 AM Bug #8610 (Duplicate): osd: calc_priors_during doesn't ignore CRUSH_ITEM_NONE
- 11:14 AM Bug #7999 (Fix Under Review): osd: pgs share info that hasn't been persisted
- 11:14 AM Feature #8480 (Fix Under Review): modify scrub to detect/repair obsolete rollback objects
- 11:14 AM Feature #8389 (Fix Under Review): osd: clean up old ec objects more aggressively
- 11:14 AM Bug #8438 (Fix Under Review): erasure code: object are not cleanup
- 11:11 AM Bug #8659 (Resolved): ceph-deploy doesn't write 'name' key to a custom_repo
- Fixed in ceph-deploy master:...
- 11:06 AM Bug #8652 (Resolved): rados rmpool broken
- 10:53 AM Bug #8593 (Pending Backport): mon: down but in osds in health warning calc is wrong
- 10:49 AM Bug #8603 (Pending Backport): ceph-disk should not hide commands that go through subprocess
- 10:39 AM Bug #8519: msgr: deadlock, blocked on SimpleMessenger::lock
- Giving this to Sam, as he didn't like my proposed solution. Downgrading from "Urgent" as we have yet to reproduce thi...
- 10:01 AM Bug #8505 (Resolved): OSD osd/OSD.cc: 6222: FAILED assert(p->second.empty())
- Merged into master as of commit: 25466839589813047c975e44e67e14f34e32139e
- 10:00 AM Bug #8396 (Resolved): osd: message delayed in Session misdirected after split
- Merged into master as of commit: 25466839589813047c975e44e67e14f34e32139e
- 04:51 AM Bug #8660: pg in forever "down+peering" state
- I've resetted "reweight" value for two OSDs to '1' and now
"sudo ceph pg map 14.7" shows:... - 04:38 AM Bug #8660 (Closed): pg in forever "down+peering" state
- On 0.80.1 one PG somehow stuck in "down+peering" state for a very long time (hours).
OSD.4 repeatedly logs
<pre... - 01:45 AM Revision 391d2411 (ceph): Merge pull request #2020 from ceph/wip-fix-rados-tool
- rados.cc: fix pool alignment check
Reviewed-by: Sage Weil <sage@inktank.com> - 01:23 AM Revision d7350a37 (ceph): rados.cc: fix pool alignment check
- Only check pool alignment if io_ctx is initialized.
Introduced in 304b08a23a3db57010078046955a786fe3589ef8
Fixes: #8... - 12:57 AM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- Zheng Yan wrote:
> you can try removing that assertion from the source code, than recompile ceph.
Thanks for your...
06/24/2014
- 11:00 PM Revision e5c565d3 (ceph): Merge remote-tracking branch 'origin/next'
- 10:49 PM Revision 4f7e26f2 (ceph): Merge pull request #2005 from ceph/wip-8624
- mon: MDSMonitor: do not allow ec pools to be used for data or metadata
Reviewed-by: Loic Dachary <loic@dachary.org>
... - 10:06 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Adding remaining logs (can attach only 10 files at once)...
- 09:57 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Here are detailed logs. This time osd.11 crashed as described. I tried to take affected OSD out and the error just mo...
- 07:20 PM Bug #8659 (Resolved): ceph-deploy doesn't write 'name' key to a custom_repo
- yum likes to have the 'name' field in a repo, but custom_repo does not attempt to set it, even if it gets a keyword. ...
- 07:12 PM Revision d6f30231 (ceph): FileStore: make _clone() copy spill out marker
- Previously we were not doing so, and that resulted in unpredictable loss
of xattrs from the client's perspective.
Si... - 07:12 PM Revision b758fd5f (ceph): FileStore: set XATTR_NO_SPILL_OUT when creating new files.
- Fixes: #8205
Backport: firefly
Signed-off-by: Greg Farnum <greg@inktank.com>
(cherry picked from commit e3b995e1567f... - 06:32 PM CephFS Bug #2825: File lock doesn't work properly
- the file was opened in O_APPEND mode. client needs to ask for file size before each write
- 08:25 AM CephFS Bug #2825: File lock doesn't work properly
- Yeah, please open a new ticket; this one's been closed for a while. :)
- 05:19 PM Revision 77670aea (ceph): thrashers/mapgap.yaml: ignore osd_map_cache_size warning
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:07 PM Revision 3134a320 (ceph): If archive_base is None, use config's
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:47 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- David Zafman wrote:
> When I was experimenting with tiering during development, I ran into this issue when the value... - 04:42 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- I have only 128 in that tier1-cache pool. Based on what you are saying, setting target_max_objects to 10 times greate...
- 04:34 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
When I was experimenting with tiering during development, I ran into this issue when the value of target_max_object...- 02:05 PM devops Feature #6986 (Closed): Build packages containing RBD and CephFS kernel modules for installation ...
- Superceded by 8120
- 02:04 PM devops Feature #8120: RHEL7 GA kernel build
- Ian hit me up about this. I am working on getting this done today.
- 02:02 PM devops Feature #8120: RHEL7 GA kernel build
- We need to publish the Ceph kernel modules for 7.0 GA on ceph.com
- 01:53 PM devops Feature #8656 (Duplicate): Update Ceph packages in Fedora
- Depedency: http://tracker.ceph.com/issues/8306
Once the ceph/ceph-common split has been made on the ceph.com RPMs,... - 01:49 PM devops Feature #8306: separate ceph.rpm into ceph and ceph-common
- Can you please document in this ticket what the contents of ceph-common are, thanks.
- 12:41 PM Bug #8654: Parsing /etc/lsb-release for OSD metadata is not portable
- Output from lsb_release -a:
$ lsb_release -a
LSB Version: core-2.0-noarch:core-3.2-noarch:core-4.0-noarch:c... - 12:40 PM Bug #8654 (Resolved): Parsing /etc/lsb-release for OSD metadata is not portable
- Using /etc/lsb-release to get information about the distro is not recommended since it's not portable.
Example: ca... - 12:30 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- i am running 3.14.7 at the moment, since there were some bugs with the cephfs kernel client, which forced me to upgra...
- 12:04 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Interestingly, 3.14.4 appears to have some changes to fs/aio.cc.
- 11:55 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Journal and storage are on the the same hard drive. used lvm to create a lv for the Journal and another lv for normal...
- 11:52 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Each journal is on it's own block device? Or on a partition?
- 11:50 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- okay, so i am disabling aio and fiemap. regarding Journal files: i checked again and i am only using block devices as...
- 11:49 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- There probably is a ceph bug in here somewhere, but I think most of your trouble is related to your environment someh...
- 11:48 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- http://tracker.ceph.com/issues/2535 seems to be the reason why fiemap defaults to disabled. You may want to disable ...
- 11:43 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- no, i am not using ceph-deploy, since there was no version for gentoo. so i used the following commands to init new o...
- 11:43 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- I wonder whether the nfs hangs are interfering somehow with the journal aio stuff, you might try disabling aio.
- 11:42 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Are you using journal_force_aio?
- 11:40 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Was it ceph-deploy?
- 11:36 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- most journals are on local block devices /dev/sda -> /dev/vg/ceph-journal, some few are still on files, but also loca...
- 11:14 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Is it true that your inconsistencies are correlated with network congestion which would also cause the nfs root to hang?
- 11:14 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- How did you deploy the cluster originally?
- 11:13 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Possibly? I've never seen a ceph cluster behave anything like this. Are your osd journals on the nfs root?
- 10:35 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- can the pg info and logs be corrupt, even if all pgs are active+clean and a deep-scrub on all osds runs through witho...
- 08:34 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- I think your pg info and logs at some point became badly corrupted for some pgs. I think that is causing the asserts...
- 12:11 PM Fix #8205 (Resolved): FileStore: properly fill in XATTR_NO_SPILL_OUT tag
- in firefly branch now
- 10:49 AM Bug #8646: OSD: assert in share_map() when marked down by an OSDMap
- Steps to reproduce:
Ceph cluster with 8 nodes, 3 osds per node.
While Client Io was going on, run command: ceph... - 10:45 AM Bug #8507 (Pending Backport): OSD: failing to create PG (when splitting?) in rados/test.sh
- 10:25 AM Bug #7891: osd: leaked pg refs on shutdown
- Steps to reproduce:
setup 8 nodes , 3 osds per node.
While Io was going on and cluster was also in rebalancing st... - 10:11 AM Bug #8652: rados rmpool broken
- wip-fix-rados-tool
- 10:09 AM Bug #8652 (Resolved): rados rmpool broken
- It's the pool alignment thing introduced in 304b08a23a3db57010078046955a786fe3589ef8
- 08:32 AM CephFS Bug #8651 (Need More Info): crashing mds in an active-active mds setup
- The MDS got blacklisted, presumably because it got overloaded and stopped heartbeating the monitor or its MDS peers. ...
- 02:15 AM CephFS Bug #8651 (Won't Fix): crashing mds in an active-active mds setup
- 2 active mds, crashing while writing 4 rsync streams to it with cephko
{ "mdsmap": { "epoch": 1428,
"flags"...
06/23/2014
- 11:48 PM Revision 378b5add (ceph): qa/workunit: cephtool: test mds newfs and add_data_pool with ec pools
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:48 PM Revision 2b007c25 (ceph): mon: MDSMonitor: print pool name along with id during 'newfs' errors
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:29 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- for testing purposes, i installed btrfs on osd.63 to osd.69 since 2014-05-28 and on osd.57 since 2014-05-13. snapshot...
- 04:39 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Have you been running the xfs/btrfs mix the whole time?
- 02:11 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- as you can see from the attached logfile (pg07f1-errors.txt.gz), there was only one assert on the osds which are rela...
- 12:57 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- after the initial bugreport, i repaired all pgs made a deep scrub on all osds, after which all pgs were active+clean,...
- 12:23 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- When did those things happen?
- 11:34 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- - pg 0.7f1 incomplete on [1,66,28]
- determined from logs, that there were missing files from shard 1 and 66 on osd.... - 11:16 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Why was there an rsync? Can you explain the sequence of events?
- 11:13 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- osd.66 and osd.1 (before my rsync from osd.28) had no subdirectory structure. the few files left on these hosts were ...
- 11:09 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- osd 66 has also a bad copy, only osd 28 had the copy containing the corresponding file. osd.66 is btrfs, while osd.28...
- 10:51 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Can you dump the xattrs on that file?
- 10:47 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- shard 66 here is osd 66. You mean that ./DIR_1/DIR_F/DIR_7/DIR_F/100001fa418.000014ed__head_9FDFF7F1__0 exists on os...
- 10:12 PM Revision d6f68132 (ceph): mon: MDSMonitor: do not allow ec pools to be used for data or metadata
- Fixes: #8624
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:09 PM Revision 20a1664b (ceph): common: LogClient: output to derr (i.e., dout(-1)) on CLOG_ERROR
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:09 PM Revision 98043608 (ceph): mon: Monitor: observe conf changes and report on unsage option values
- Fixes: #8605
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:08 PM Revision ec73888f (ceph): mon: Monitor: sanitize options at start
- Make sure some options have sane values.
Fixes: #8605
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:07 PM Revision 87f9dbaf (ceph): Give meaningful error when submodules are not checked out
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 10:06 PM Revision 58212b12 (ceph): osd: Only normalize extent if op uses extent
- Code in ReplicatedPG was reading and modifying ceph_osd_op.extent,
even though that is a member of a union and only v... - 09:41 PM Revision 4225e2f6 (ceph): osd: remove OSD-specific leveldb options
- OSDs will now rely on 'leveldb_*' config options. We do keep however
leveldb's log enabled for OSDs by passing 'leve... - 09:35 PM Revision 9655c7e8 (ceph): Support installing ceph kernels from gitbuilder on rpm machines.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 09:35 PM Revision 6a741914 (ceph): Remove unused variables and functions.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 09:35 PM Revision b2a5bdf2 (ceph): Added requested comment.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 08:59 PM Revision 52b147c8 (ceph): ceph-mon: override 'leveldb_*' config options for the monitor
- 'leveldb_*' options are currently used both by the monitor and the osd.
However, the monitor has quite different requ... - 08:26 PM Revision bb2ed23d (ceph): erasure-code: verify that rados put enforces alignment
- http://tracker.ceph.com/issues/8622 refs: #8622
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from c... - 08:26 PM Revision dece6506 (ceph): enforce rados put aligment
- Signed-off-by: Lluis Pamies-Juarez <lluis.pamies-juarez@hgst.com>
(cherry picked from commit 304b08a23a3db57010078046... - 06:43 PM CephFS Bug #2825: File lock doesn't work properly
- I've been using 0.80.1 on a vanilla 3.10.33 kernel. I am seeing this issue and can reproduce it reliably using the te...
- 06:28 PM Revision d42d19df (ceph): mon: MonitorDBStore: remove mon-specific leveldb options.
- From this point onward, users should use leveldb's options and add them
to the appropriate config sections of their c... - 06:25 PM Revision 235f4ca6 (ceph): Merge pull request #1998 from ceph/wip-disk-ioprio
- osd: allow io priority for (background) disk threadpool to be set
Backport: firefly, dumpling
Reviewed-by: Samuel Ju... - 06:24 PM Revision 9844885d (ceph): mon: DataHealthService: s/mon_leveldb_size_warn/mon_data_size_warn/
- Make the option name independent from the store mechanism used underneath.
Signed-off-by: Joao Eduardo Luis <joao.lu... - 06:08 PM Revision 66b0b0e6 (ceph): Merge pull request #2015 from ceph/wip-8610
- osd: ignore CRUSH_ITEM_NONE in compat_must_dispatch_immediately
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:47 PM Revision 57c5d058 (ceph): osd: ignore CRUSH_ITEM_NONE in compat_must_dispatch_immediately
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:59 PM CephFS Bug #8648: Standby MDS leaks memory over time
- I believe we're leaking CInodes in open_root_inode et al.
- 01:28 PM CephFS Bug #8648 (Resolved): Standby MDS leaks memory over time
- I've discovered in my Ceph cluster that the MDS overtime will leak memory. In my case it usually takes a week two or ...
- 04:55 PM Revision 203318b8 (ceph): osd/OSDMap: do not require ERASURE_CODE feature of clients
- Just because an EC pool exists in the cluster does not mean tha tthe client
has to support the feature:
1) The way c... - 04:55 PM Revision 6340b14b (ceph): osd/OSDMap: make get_features() take an entity type
- Make the helper that returns what features are required of the OSDMap take
an entity type argument, as the required f... - 04:54 PM Revision 400fa88f (ceph): Avoid extra check for clean object
- We needn't to check clean object via buffer state, skip the clean object.
Signed-off-by: Haomai Wang <haomaiwang@gma... - 04:09 PM Revision f3176843 (ceph): Merge pull request #1979 from ceph/wip-backfill-priority
- osd: improve backfill prioritization
Reviewed-by: Samuel Just <sam.just@inktank.com> - 04:08 PM Revision 5708727d (ceph): Merge pull request #1994 from dachary/wip-8599-ruleset-emperor
- mon: pool set <pool> crush_ruleset must not use rule_exists (emperor backport)
Reviewed-by: Sage Weil <sage@inktank.... - 04:03 PM Revision d9073f48 (ceph): osd: allow io priority to be set for the disk_tp
- The disk_tp covers scrubbing, pg deletion, and snap trimming
Signed-off-by: Sage Weil <sage@inktank.com> - 04:01 PM Revision a2b49110 (ceph): common/io_priority: wrap ioprio_set() and gettid()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:01 PM Revision 1b874102 (ceph): common/Thread: allow io priority to be set for a Thread
- Ideally, set this before starting the thread. If you set it after, we
could potentially race with create() itself.
... - 04:01 PM Revision dd6badcb (ceph): common/WorkQueue: allow io priority to be set for wq
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:56 PM Revision c3393434 (ceph): Merge remote-tracking branch 'gh/wip-misc-fixes'
- Conflicts:
src/mon/Monitor.cc
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.org> - 03:24 PM Bug #8641: Cache tiering agent cannot flush or evict objects during the benchmark
- Samuel Just wrote:
> How did you initially set target_max_objects, please provide more detail.
The attachment is ... - 10:39 AM Bug #8641 (Need More Info): Cache tiering agent cannot flush or evict objects during the benchmark
- How did you initially set target_max_objects, please provide more detail.
- 03:15 PM Revision b24ee497 (ceph): Merge pull request #2009 from kevincox/election-int
- Use sized integer.
Reviewed-by: Sage Weil <sage@inktank.com> - 03:09 PM Revision 0b78592a (ceph): Merge pull request #272 from ceph/release
- Create a python package for teuthology
- 01:24 PM CephFS Bug #8622 (Pending Backport): erasure-code: rados command does not enforce alignement constraints
- Loic - this needs to be backported to Firefly.
- 01:07 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- It is still necessary.
- 12:24 PM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- Here is the first log from affected OSD with increased verbosity, captured since start to crash.
Attaching logs from... - 10:36 AM Bug #8643 (Need More Info): 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.leng...
- Please reproduce with
debug osd = 20
debug filestore = 20
debug ms = 1
on all osds and attach those logs. - 11:44 AM Bug #8614: OSD keyring shifted
- My cluster is down right now, please help.
2014-06-23 11:42:25.117964 7fc0d4cf3700 1 mon.gfsnode5@0(leader).paxos... - 11:14 AM Bug #8610 (Pending Backport): osd: calc_priors_during doesn't ignore CRUSH_ITEM_NONE
- 11:09 AM Bug #8646 (Resolved): OSD: assert in share_map() when marked down by an OSDMap
- ...
- 10:15 AM Bug #8593 (Fix Under Review): mon: down but in osds in health warning calc is wrong
- 10:15 AM Bug #8556 (Resolved): CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- 09:20 AM Revision 8700aa0e (ceph): test/libradosstriper/striping.cc: fix potential memory leak
- Fix for:
[src/test/libradosstriper/striping.cc:138]: (error) Allocation with
getObjName, stat doesn't release it
Si... - 08:50 AM Revision 2a8c1e22 (ceph): MDCache.cc: init 'umaster::ls' with NULL in contructor
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:23 AM Revision da03e9eb (ceph): MDCache.h: init 'umaster::safe' in constructor
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 08:17 AM Revision 2210ee3c (ceph): test/objectstore/store_test.cc: prefer ++operators for iterators
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 07:57 AM Revision cd123947 (ceph): Merge pull request #2011 from dachary/wip-osd-bench
- osd: tests for osd bench
Reviewed-by: Huang Jun <hjwsm1989@gmail.com> - 07:10 AM Revision 3e93d4a1 (ceph): osd: tests for osd bench
- Check that the safeguards against timeouts work as expected and that the
default hardcoded values are valid.
Signed-... - 07:05 AM Bug #7593: Disk saturation during PG folder splitting
- Guang Yang wrote:
> Sage Weil wrote:
> > At a high level, sure, if you know ahead of time how many objects per PG y... - 04:43 AM Bug #8644 (Rejected): 624ae21833 breaks ceph-disk
- git bisect shows 624ae21833 breaks ceph-disk
Seems it tries to create partition one, which has already been create... - 04:15 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- sean redmond wrote:
> Ilya Dryomov wrote:
> > Just in case, the fix you are running with is now in 3.14. However w... - 04:05 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Ilya Dryomov wrote:
> Just in case, the fix you are running with is now in 3.14. However we
> are still working on... - 03:27 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- Olivier Bonvalet wrote:
> I haven't got this problem anymore, it seems really stable for me now. Thanks !
>
> I t... - 12:24 AM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- Almost no crashes, as i suspected. I had one osd going down, but I could find no crash in the logs.
But now my sys...
06/22/2014
- 10:49 PM Bug #8642: After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- The crashes seem recovery related. Things have calmed down very much as recovery settled down/stopped. We had a crash...
- 10:02 AM Bug #8642 (Need More Info): After Upgrade from Emperor to Firefly osd start (seemingly randomly) ...
- Can you attach a longer segment of the log file that includes the backtrace and failed assertion?
Also, if you can... - 09:45 PM Bug #3286: librbd, kvm, async io hang
- I met the same problem.
Fio hangs in a linux-3.15.0 when using direct and sync.
ceph version :0.80.1(release) - 04:07 PM Bug #8643 (Closed): 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == ...
- OSD (0.80.1) crashed and became unusable ever since due to similar crash soon after restart:...
- 12:01 PM Feature #8605 (In Progress): mon: add sanity checks on configurables
- also, making this twofold:
- monitors spit out warnings if in-memory config options do not pass the sanity checks.
... - 10:01 AM Support #8462: related to integrity of objects
- These questions are all specifically related to rgw, right?
06/21/2014
- 03:06 PM Revision 791a6b95 (ceph): Merge pull request #1974 from hjwsm1989/osd-bench
- Fix EINVAL err when use "ceph tell osd.* bench"
Reviewed-by: Loic Dachary <loic@dachary.org> - 03:18 AM Bug #8642 (Duplicate): After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- I upgraded our ceph cluster from Emperor to Firefly today. After the upgrade I changed "tunables to optimal" and chan...
- 02:13 AM Bug #8641 (Can't reproduce): Cache tiering agent cannot flush or evict objects during the benchmark
- I set target_max_objects to 1000, but it does not evict objects during creation of workload. It does not even start a...
06/20/2014
- 08:53 PM Revision 74be320a (ceph): Use sized integer.
- Signed-off-by: Kevin Cox <kevincox@kevincox.ca>
- 06:43 PM Revision 82d3a3dc (ceph): smoke-tests -> smoke
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:42 PM Revision 28a2253a (ceph): smoke: remove old smoke suite
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:06 PM Revision a312f9af (ceph): Update setup.py
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:45 PM Revision 31eefebd (ceph): Merge pull request #1961 from ceph/wip-6703
- support dmcrypt partitions when activating
Reviewed-by: Loic Dachary <loic@dachary.org> - 05:15 PM Revision 4ca12b40 (ceph): common/WorkQueue: allow io priority to be set for wq
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5e4b3b1f1cb870f39fc7cfb3adeae93e078d9057)
Con... - 05:15 PM Revision c9b3067f (ceph): common/Thread: allow io priority to be set for a Thread
- Ideally, set this before starting the thread. If you set it after, we
could potentially race with create() itself.
... - 05:15 PM Revision 0796057f (ceph): common/io_priority: wrap ioprio_set() and gettid()
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 705713564bebd84ad31cc91698311cf2fbd51a48)
Con... - 05:10 PM Revision c46fe8e9 (ceph): osd: introduce simple sleep during scrub
- This option is similar to osd_snap_trim_sleep: simply inject an optional
sleep in the thread that is doing scrub work... - 05:05 PM Revision 2cb19172 (ceph): Merge pull request #2007 from GRyall/master
- doc: Fixed Typo in pools documentation - replaced '-' with '_' in eg
Reviewed-by: John Wilkins john.wilkins@inktank.com - 04:54 PM Revision 66a5f3b9 (ceph): doc: Fixed Typo in pools documentation - replaced '-' with '_' in examp...
- 03:39 PM Revision 5cd50a42 (ceph): Allow killing jobs by passing a 'jobspec'.
- See teuthology-kill --help
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 03:14 PM Revision e189a668 (ceph): log the command that is being run with subprocess
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 11:12 AM Feature #8639 (Resolved): mon: dispatch messages while blocked waiting for IO
- There's a blueprint for this at https://wiki.ceph.com/Planning/Blueprints/Submissions/mon%3A_dispatch_messages_while_...
- 11:11 AM RADOS Tasks #8638 (New): mon: test rocksdb performance
- Test how the monitors behave with rocksdb compared to leveldb.
- 11:10 AM Tasks #8637 (New): leveldb: initial inquiries on how we can improve leveldb
- Go into leveldb and check how and where we can improve leveldb to behave better under our workload.
- 10:49 AM CephFS Feature #8636 (Resolved): mds/libcephfs: read only mount
- 10:42 AM Feature #8635 (Resolved): add scrub, snap trimming, should be items in the OpWQ with cost/priority
- 10:42 AM CephFS Feature #8634 (Resolved): mds: admin commands list, evict, etc session
- 10:38 AM Feature #8633: allow writes before recovering a replica
- should respect min_size
- 10:31 AM Feature #8633 (Duplicate): allow writes before recovering a replica
- 10:33 AM CephFS Feature #7352 (Resolved): mds: make classes encode/decode-able
- 10:14 AM Bug #8603 (Fix Under Review): ceph-disk should not hide commands that go through subprocess
- Pull request opened: https://github.com/ceph/ceph/pull/2006
- 10:12 AM rgw Bug #8632 (Resolved): rgw: bucket listing with delimiter doesn't scale well
- 08:35 AM CephFS Bug #8624 (Fix Under Review): monitor: disallow specifying an EC pool as a data or metadata pool
- https://github.com/ceph/ceph/pull/2005
- 06:53 AM CephFS Bug #8624 (In Progress): monitor: disallow specifying an EC pool as a data or metadata pool
- 08:26 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- there were more and more inconsistencies with missing files and i am unsure how to repair them. for example there wer...
- 08:23 AM Revision 41c536f9 (ceph): mailmap: Dominik Hannen affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 AM Revision a58fbf79 (ceph): mailmap: Colin Mattson affliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:23 AM Revision 1cdea987 (ceph): mailmap: Walter Huf name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:23 AM Revision efefbfd1 (ceph): mailmap: koleosfuscus affiliation
- Patrick McGarry, Sage Weil and Loic Dachary know who this nickname
belongs to
Signed-off-by: Loic Dachary <loic@dach... - 08:23 AM Revision 78cbac43 (ceph): mailmap: Dmitry Smirnov name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:23 AM Revision 2eddee73 (ceph): mailmap: Sylvain Munaut affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:23 AM Revision 43442953 (ceph): mailmap: Sushma Gurram affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 AM Revision 06734f19 (ceph): mailmap: Stephen F Taylor affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 AM Revision 009f01dc (ceph): mailmap: Sahid Orentino Ferdjaoui name normalization
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:23 AM Revision 4222f29e (ceph): mailmap: Wei Luo affiliation
- and name normalization
Reviewed-by: Wei Luo <luowei@yahoo-inc.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 AM Revision 3716f588 (ceph): mailmap: Lluis Pamies-Juarez affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 AM Revision 1f96cb72 (ceph): mailmap: Harpreet Dhillon affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:22 AM Revision 22c028d0 (ceph): mailmap: Red Hat acquires InkTank
- Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:21 AM Revision c2701723 (ceph): mailmap: Sebastien Ponce affiliation
- Reviewed-by: Sebastien Ponce <sebastien.ponce@cern.ch>
Signed-off-by: Loic Dachary <loic@dachary.org> - 07:57 AM devops Bug #7598: ceph-disk-activate error with ceph-deploy
- You cannot activate a device without calling prepare first. So if you are encountering an issue when activating witho...
- 07:52 AM Revision 39a4b781 (ceph): mon: test that pools used in tiers cannot be removed
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:49 AM Revision 2c8ff50f (ceph): Merge pull request #1997 from ceph/wip-tiermsg
- mon: name instead of id in "has tiers" message
Reviewed-by: Loic Dachary <loic@dachary.org> - 07:06 AM rgw Bug #7499 (Resolved): rgw: bucket unlink / link isn't working
- Fixed, commit:008663aac8b49be669c4694e97a7d4d6219572a1
- 02:17 AM rbd Bug #5876 (Resolved): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_reque...
- Should be fixed by commit 0f2d5be792b0 ("rbd: use reference counts for image requests"), which went into 3.16-rc1.
- 02:17 AM rbd Bug #8378 (Resolved): krbd: Kernel oops in rbd_img_obj_callback
- Should be fixed by commit 0f2d5be792b0 ("rbd: use reference counts for image requests"), which went into 3.16-rc1.
- 02:17 AM rbd Bug #7125 (Resolved): Assertion failure in rbd_img_obj_callback()
- Should be fixed by commit 0f2d5be792b0 ("rbd: use reference counts for image requests"), which went into 3.16-rc1.
- 02:14 AM Bug #8630: test osd-config.sh ENXIO
- tried to...
- 12:07 AM Bug #8630: test osd-config.sh ENXIO
- The problem did not show when run again, it is a race condition.
- 02:08 AM rbd Bug #6628 (Fix Under Review): krbd: BUG during ceph_osdc_stop() sometimes when rbd_add() fails
- wip-remove-osd-6628
- 12:52 AM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- Hi Greg,
Sorry for the late reply.
We were just trying to simulate some potential disk error here, so we artif...
06/19/2014
- 11:32 PM Bug #8630 (Resolved): test osd-config.sh ENXIO
- "gitbuilder on raring":http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-raring-amd64-basic/log.cgi?log=97772c...
- 09:25 PM Revision 09d02abe (ceph): Revert "rados: Fix cache_flush, cache_try_flush, cache_evict and add hi...
- cache_evict is kinda broken at the moment due to snapdir nonsense. I'm reverting this
test for now until it's fixed ... - 06:11 PM Revision fc772d73 (ceph): Add a couple tests for teuthology.schedule
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:39 PM Revision 363496ad (ceph): osd: use appropriate json types instead of stream when dumping info
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:39 PM Revision 1de9071d (ceph): osd/osd_types.cc: dump correct pg_log_entry_t member variable
- We were dumping 'version' twice: for 'version' and 'prior_version'. We
do have a member variable called 'prior_versi... - 05:16 PM Revision 97772c2f (ceph): mon: name instead of id in "has tiers" message
- Instead of "Pool foo has tiers 1 2" print
"Pool foo has tiers bar baz".
Signed-off-by: John Spray <jspray@redhat.com> - 04:06 PM Revision 34ba8faf (ceph): Merge pull request #1988 from dachary/wip-warnings
- test: fix -Wsign-compare warnings
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com> - 03:53 PM Revision 4d5469ac (ceph): osd: ECMsgTypes: dump json bools instead of strings
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:52 PM Revision 3f0ea951 (ceph): osd: have 'tid' dumped as a json unsigned int where appropriate
- Most of the places dumping it would dump it as a string. Others as an int.
Just a couple would dump it as an unsigned... - 03:41 PM Revision 708776cc (ceph): Merge pull request #1993 from dachary/fix_ut
- autotools: avoid check_SCRIPTS duplication
Reviewed-by: Wei Luo <luowei@yahoo-inc.com> - 03:31 PM Revision debaf615 (ceph): mon: dump 'epoch' as json unsigned instead of int
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:05 PM Revision 1a120e98 (ceph): mon: PGMonitor: dump 'epoch' as json int instead of string
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 02:59 PM Revision 317cf95f (ceph): mon: OSDMonitor: dump 'up' as json array instead of string
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 02:56 PM Revision b7ff3933 (ceph): mon: OSDMonitor: dump 'acting' as json array instead of string
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 02:28 PM Bug #8629 (Resolved): cache_evict needs to prevent make_writeable from creating a snapdir
- 01:10 PM Revision 78f94a90 (ceph): mailmap: Ailing Zhang affiliation
- and name normalization
Signed-off-by: Loic Dachary <loic@dachary.org> - 12:32 PM Revision f9eb77b1 (ceph): Merge pull request #1995 from sjahl/master
- doc: Fixed an incorrect flag in radosgw admin docs.
- 12:02 PM Bug #8628: Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- Now I understand better. It will require someone more familiar with the code than I am to figure this one out.
- 11:58 AM Bug #8628: Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- No, I was adding tracepoints to the function and saw the bug.
- 11:52 AM Bug #8628: Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- Did you run into a problem related to this ?
- 11:24 AM Bug #8628: Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- I don't think it can be done reliably through the API. It might be possible by sending a specially crafted message t...
- 10:00 AM Bug #8628: Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- Would it be possible to create these conditions using the API ? It cannot be unit tested, unfortunately. But it may b...
- 09:13 AM Bug #8628 (Resolved): Bad ceph_osd_op.extent union access in ReplicatedPG::do_osd_ops
- ReplicatedPG::do_osd_ops reads and modifies ceph_osd_op.extent regardless of the operation, and therefore regardless ...
- 11:44 AM Revision d2e852e2 (ceph): doc: Fixed an incorrect flag in radosgw admin docs.
- Example use a "--gen-key" flag, which doesn't exist. Changed it to
"--gen-access-key".
Signed-off-by: Stephen Jahl <... - 11:11 AM Bug #8606 (Closed): JSON output normalization for "num_in_osds"
- This has been fixed in 790dda9c, which is went go out with 0.77. Current version does not suffer from this.
- 09:19 AM Revision 3138f2a9 (ceph): mon: pool set <pool> crush_ruleset must not use rule_exists
- Implement CrushWrapper::ruleset_exists that iterates over the existing
rulesets to find the one matching the ruleset ... - 07:54 AM Revision 741ad3ff (ceph): autotools: avoid check_SCRIPTS duplication
- The check_SCRIPTS content must be added to EXTRA_DIST, otherwise it will
not be included by make dist and it won't be... - 07:38 AM Revision c3678ad8 (ceph): Merge pull request #1992 from luowei62/fix_ut
- Fix dist package run unit test failed.
Reviewed-by: Loic Dachary <loic@dachary.org> - 06:13 AM Revision 5fee8078 (ceph): Merge pull request #1989 from dachary/wip-8622-rados-alignment
- tests: prevent gitbuilder trigger in test-erasure-code.sh
Reviewed-by: Lluis Pamies-Juarez <lluis@pamies.cat> - 04:27 AM Feature #8071: erasure-code: simplify jerasure initialization
- "tests queued":http://pulpito.ceph.com/loic-2014-06-19_13:26:46-rados-wip-8071-testing-basic-plana/
no clue why qu... - 04:00 AM Revision c0d78c62 (ceph): Fix dist package run unit test failed.
- Signed-off-by: Wei Luo <luowei@yahoo-inc.com>
06/18/2014
- 10:09 PM Revision b3ace76d (ceph): tests: prevent gitbuilder trigger in test-erasure-code.sh
- Use the INFO keywork instead of WARNING so that gitbuilder does not
confuse this with a warning worth fixing.
Signed... - 10:02 PM Revision 3a9c0fcd (ceph): test: fix -Wsign-compare warnings
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:21 PM Revision 15f03388 (ceph): Merge pull request #1987 from dachary/wip-8622-rados-alignment
- erasure-code: verify that rados put enforces alignment
Reviewed-by: Lluis Pamies-Juarez <lluis@pamies.cat> - 09:13 PM Revision b46c4056 (ceph): erasure-code: verify that rados put enforces alignment
- http://tracker.ceph.com/issues/8622 refs: #8622
Signed-off-by: Loic Dachary <loic@dachary.org> - 09:12 PM Revision 65005572 (ceph): Merge pull request #1983 from dachary/wip-osd-config
- tests: remove spurious and harmless find command
Reviewed-by: Florent Flament <florent.flament@cloudwatt.com> - 09:01 PM Revision 7182b455 (ceph): Merge pull request #1984 from llpamies/wip-8622
- enforce rados put aligment
Reviewed-by: Loic Dachary <loic@dachary.org> - 06:32 PM Revision 6aa3440d (ceph): Merge pull request #1943 from athanatos/wip-8507
- Wip 8507
Reviewed-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision e6466aa9 (ceph): Merge pull request #1986 from ceph/wip-scrub-sleep
- osd: introduce simple sleep during scrub
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:09 PM Revision 48ed75b8 (ceph): Merge pull request #1985 from concubidated/master
- ReplicatedPG: Fix 'ajusted' typo
Reviewed-by: Sage Weil <sage@inktank.com> - 05:56 PM Revision c35ceef5 (ceph): ReplicatedPG: 'ajusted' typo
- Signed-off-by: <Tyler Brekke> tyler.brekke@inktank.com
- 05:26 PM Revision de2c085c (ceph): rgw-admin: Fix the 'show log' command
- Fixes: #8553
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Sylvain Munaut <s.munaut@whatever-company... - 05:00 PM Revision 304b08a2 (ceph): enforce rados put aligment
- Signed-off-by: Lluis Pamies-Juarez <lluis.pamies-juarez@hgst.com>
- 04:34 PM Feature #8307: Creating a pool with erasure code allows me to create invalid ec profile names.
- "pending backport":https://github.com/ceph/ceph/pull/1991
- 03:49 PM Bug #8601 (Fix Under Review): erasure-code: default profile does not exist after upgrade
- "need review":https://github.com/ceph/ceph/pull/1990
- 02:08 PM CephFS Bug #8622: erasure-code: rados command does not enforce alignement constraints
- Would you have time to review / try this : https://github.com/ceph/ceph/pull/1987 ?
- 02:05 PM CephFS Bug #8622 (Resolved): erasure-code: rados command does not enforce alignement constraints
- This is fine, great work :-)
- 10:01 AM CephFS Bug #8622: erasure-code: rados command does not enforce alignement constraints
- Loic,
I had some problems squashing the commits and I created a new pull request:
https://github.com/ceph/ceph/pu... - 09:20 AM CephFS Bug #8622 (In Progress): erasure-code: rados command does not enforce alignement constraints
- 01:58 PM Revision 8d9201fd (ceph): tests: remove spurious and harmless find command
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 11:28 AM Revision 3ad451ef (ceph): Make <poolname> in "ceph osd tier --help" clearer.
- The ceph osd tier --help info on the left always says <poolname>.
It is unclear which one to put <tierpool> on the ri... - 10:30 AM rgw Bug #8553 (Resolved): rgw: log show broken
- Merged, commit:de2c085c0f53c1d06acc8a968666006624f939ad
- 10:17 AM rgw Bug #8585 (Resolved): rgw suite failures on master
- Merged, commit:b2542f8e880e45bb6d052f13eb3ef6a7c61e4cd4
- 09:13 AM Feature #8580 (In Progress): Decrease disk thread's IO priority and/or make it configurable
- 08:02 AM Bug #8625 (Resolved): EC pool - OSD creates an empty file for op with 'create 0~0, writefull 0~xx...
- When we tested radosgw against EC pool, we found that for the head strip written from radosgw, it always create two p...
- 02:16 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- Yes that worked on 3.14.1 kernel on Ubuntu 14.04 (mix of 32, 64 bit and wifi and ethernet). Great work on CephFS and ...
- 12:02 AM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- Zheng Yan wrote:
> you can try removing that assertion from the source code, than recompile ceph.
Thanks for the ...
06/17/2014
- 11:58 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- you can try removing that assertion from the source code, than recompile ceph.
- 11:44 PM CephFS Bug #8623 (Won't Fix): MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtu...
- 11:28 PM CephFS Bug #8623 (New): MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual voi...
- So the only way to use CephFS on EC pool is to stack CephFS on cache pool on top of EC pool? Will it work?
I got m... - 11:01 PM CephFS Bug #8623 (Won't Fix): MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtu...
- Yeah, EC pools need to be used underneath a cache pool (limited validation) or for RGW storage. CephFS definitely won...
- 09:16 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- I think EC pool does not support block storage either, because it does not support seeky write.
- 07:44 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- Zheng Yan wrote:
> EC pool does not support truncate operation. One option is make MDS return (Operation not support... - 07:14 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- EC pool does not support truncate operation. One option is make MDS return (Operation not supported) when client want...
- 06:52 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- Thanks for quick reply.
Zheng Yan wrote:
> osd_op_reply(169108 100000cfe98.00000000 [trimtrunc 2@0] v0'0 uv0 ondi... - 06:32 PM CephFS Bug #8623: MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtual void C_MD...
- osd_op_reply(169108 100000cfe98.00000000 [trimtrunc 2@0] v0'0 uv0 ondisk = -95 ((95) Operation not supported))
Thi... - 06:17 PM CephFS Bug #8623 (Won't Fix): MDS crashes (unable to access CephFS) / mds/MDCache.cc: In function 'virtu...
- All of a sudden I found all three MDS servers down and not starting (crashing):...
- 11:00 PM CephFS Bug #8624 (Resolved): monitor: disallow specifying an EC pool as a data or metadata pool
- Apparently you can, and things go horribly wrong when the MDS or clients try to write to it.
- 09:47 PM Revision 4afffb4a (ceph): osd: fix filestore perf stats update
- Update the struct we are about to send, not the (unlocked!) one we will
send the next time around.
Backport: firefly... - 09:47 PM Revision cdca7b71 (ceph): osd: move osd_stat into OSDService
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:35 PM Revision d20da8de (ceph): osd: add osd_min_recovery_priority tunable
- Add a tunable to control the minimum priority recovery item that we will
grant a reservation for. The priority is lo... - 09:35 PM Revision 0985ae71 (ceph): osd: prioritize backfill based on *how* degraded
- Instead of prioritizing all degraded PGs equally, prioritize those that
have the fewest acting members (the most degr... - 09:35 PM Revision b65ceb68 (ceph): common/AsyncReserver: add a min_priority knob
- To do reserve items that are < the min priority. Default to 0.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:56 PM Revision 0e7a9792 (ceph): osd: fix word sizes in MBackfillReserve
- Fix these fields to 32 bits.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:27 PM CephFS Bug #8622: erasure-code: rados command does not enforce alignement constraints
- I created a pull request for the second option.
https://github.com/ceph/ceph/pull/1981/
- 05:43 PM CephFS Bug #8622: erasure-code: rados command does not enforce alignement constraints
- After some debugging it seems to me that the problem is that rados client reads ands sends data in chunks of size (1<...
- 03:55 PM CephFS Bug #8622 (Resolved): erasure-code: rados command does not enforce alignement constraints
- Original title for the record : "EC pool fails for certain (k,m) combinations for >4MB objs"
Steps to reproduce th... - 05:47 PM Revision c4e8451c (ceph): osd: introduce simple sleep during scrub
- This option is similar to osd_snap_trim_sleep: simply inject an optional
sleep in the thread that is doing scrub work... - 05:39 PM Revision af503402 (ceph): Merge pull request #1968 from ceph/wip-ceph-isatty
- ceph: output prompt only if stdin is tty
Reviewed-by: Sage Weil <sage@inktank.com> - 04:27 PM Revision 7b580a2f (ceph): mon: Monitor: complex code deduplication algorithm applied to tick()
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:21 PM Revision 0ed1fe64 (ceph): mon: Monitor: rework tick() so we don't calculate the same thing over a...
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:06 PM Revision ef8a1281 (ceph): support dmcrypt partitions when activating
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:51 AM CephFS Fix #7564 (Duplicate): synchronize MDS and client times in a way that makes pjd happy even under ...
- 06:49 AM CephFS Feature #3727 (Resolved): mds: refactor EMetablob encoding paths
- 06:49 AM CephFS Feature #8386 (Resolved): mds: use client (instead of mds) ctime/mtime
- 05:20 AM CephFS Bug #8575 (Rejected): linux kernel: possible circular locking dependency detected
- 05:12 AM Revision 7dc93a96 (ceph): Fix EINVAL err when use "ceph tell osd.* bench"
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 05:06 AM rgw Bug #8553: rgw: log show broken
- In case you haven't traced this already, I have had this patch in my local tree for some time and forgot to post it.
- 04:58 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- I thing I found the buggy code, but it has been changed in 3.14 kernel. please try 3.14 kernel or the attached patch.
- 01:28 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- Kernel is 3.13.0. Happens with 32 or 64 bit. Here's part of the log from just before the error (last line has the err...
- 04:09 AM rgw Bug #8621: civetweb frontend fails authentication if URL has special chars
- The problem is that civetweb only give the url-decoded URI in the @struct mg_request_info@. I don't see how you can g...
- 02:31 AM rgw Bug #8621 (Resolved): civetweb frontend fails authentication if URL has special chars
- For example trying to initiate a multipart to a 'test:multi' key.
Logs from an attempt through fast cgi :... - 12:01 AM Revision 55a97787 (ceph): mon/OSDMonitor: make down osd count sensible
- We currently log something like
1/10 in osds are down
in the health warning when there are down OSDs, but this is ... - 12:01 AM Revision 98883f63 (ceph): mon: fix typos, punctuation for mon disk space warning(s)
- Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com> - 12:01 AM Revision 82e47db8 (ceph): mon: refactor check_health()
- Refactor the get_health() methods to always take both a summary and detail.
Eliminate the return value and pull that ... - 12:01 AM Revision 3ed7f2dd (ceph): mon: ensure HealthService warning(s) include a summary
- The low disk space check would change our status to HEALTH_WARN and include
a detail message, but no summary. We nee...
06/16/2014
- 10:58 PM Bug #8620 (Won't Fix): rest/test.py occasional failure (dumpling)
- (i suspect this affects master, too?)
ubuntu@teuthology:/a/teuthology-2014-06-16_19:00:48-rados-dumpling-testing-b... - 10:08 PM Revision ab12a036 (ceph): Merge pull request #1947 from ceph/wip-import-purge
- Wip import purge
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:52 PM Bug #8589: scrub error with leveldb backend
- Maybe we hint it(http://tracker.ceph.com/issues/8612)
- 08:09 PM Revision 5146cb06 (ceph): Merge pull request #1971 from ceph/wip-ec-hitset
- ceph_test_rados_api_tier: disable LibRadosTierECPP::HitSetWrite
Reviewed-by: Loic Dachary <loic@dachary.org> - 08:04 PM Revision 9cc1a758 (ceph): Merge pull request #1970 from dachary/wip-erasure-code-profile-default
- Revert "erasure-code: create default profile if necessary"
- 08:01 PM Bug #8582 (Need More Info): Cluster very slow after upgrade to 80.1
- 09:37 AM Bug #8582: Cluster very slow after upgrade to 80.1
- Can you look at something like iostat or iotop to see if the disks are busy or not? Are the ceph-osd procs using a l...
- 07:57 PM Revision c5b5ed67 (ceph): ceph_test_rados_api_tier: disable LibRadosTierECPP::HitSetWrite
- Disable this test until hitget-get reliably works on EC pools (currently
it does not, and this test usually passes on... - 07:41 PM Revision 0bb0095b (ceph): Revert "erasure-code: create default profile if necessary"
- This reverts commit 360de6adf24ef9a1287d169416d5e9bbb72afbec.
Conflicts:
src/mon/OSDMonitor.cc - 07:28 PM Revision 1c724651 (ceph): osd: verify osd config sanity checks
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:28 PM Revision f53bed1b (ceph): mon/OSDMonitor: fix build error
- This broke with 360de6adf24ef9a1287d169416d5e9bbb72afbec.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:14 PM devops Bug #8616 (Closed): after deploying ceph while testing calamari, rados operation hangs.
- After deploying ceph while testing the ICE installation process, I ran the following:
sudo rados -p data put myobj... - 06:56 PM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- can you enable debugging mode (echo module ceph +p > /sys/kernel/debug/dynamic_debug/control) on cephfs. I suspect th...
- 06:21 PM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- which version of kernel ?
- 02:32 PM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- With a single cephfs client machine, I had no problems.
With two client machines, my tests failed again (missed read... - 11:57 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- Yes - I have two ceph-osd machines and 4 cephfs client machines, all running Ubuntu 14.04 and the Ceph versions from ...
- 08:15 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- Are all of the running ceph-osd daemons 0.80? Is the client cephfs or rbd?
- 12:58 AM Bug #7371: libceph: tid 36856 reply has 196608 bytes we had only 147456 bytes ready
- I'm seeing this on Ubuntu 14.04 (Ceph 0.80).
- 05:16 PM Revision 84948517 (ceph): Merge pull request #1951 from sahid/ut-lru
- Adds tests to include/lru.h + fixes small issues
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Sage Weil... - 04:35 PM Revision a0689ecc (ceph): Merge pull request #1954 from dachary/wip-8307-erasure-code-profile-imp...
- erasure code profile implicit creation
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:30 PM Revision e0315268 (ceph): Merge pull request #1964 from ceph/wip-osd-configs
- osd: add sanity check/warning on a few key configs
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:29 PM Revision 11ce9119 (ceph): Merge pull request #1966 from dachary/wip-erasure-code-profile-default
- DNM: erasure-code: create default profile if necessary
Reviewed-by: Sage Weil <sage@inktank.com> - 04:27 PM Revision 3cf01a0e (ceph): Merge pull request #1963 from dachary/wip-8599-ruleset-dumpling
- mon: pool set <pool> crush_ruleset must not use rule_exists (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com> - 04:25 PM Revision f290a021 (ceph): Merge pull request #1962 from dachary/wip-8599-ruleset-firefly
- mon: pool set <pool> crush_ruleset must not use rule_exists (firefly)
Reviewed-by: Sage Weil <sage@inktank.com> - 04:19 PM Revision ec422a94 (ceph): Make conf_file optional
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:17 PM Revision 4bd1b5e2 (ceph): PendingReleaseNotes: note about keyvaluestore-dev on-disk format change
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:13 PM Revision d3d60af4 (ceph): Merge pull request #1941 from yuyuyu101/wip-8564
- Fix write operation on a deleted object in the same transaction(KeyValueStore)
Reviewed-by: Sage Weil <sage@inktank.... - 03:01 PM Bug #8519: msgr: deadlock, blocked on SimpleMessenger::lock
- wip-8519-osd-unblocking
I'll schedule a suite once it's going on the gitbuilders. Should add unit tests for the ne... - 02:33 PM Bug #8614 (Can't reproduce): OSD keyring shifted
- Hello,
Env:
1 host = mon, mds, admin for ceph-deploy
4 hosts = osd server
I troubleshooted an OSD being down ... - 02:32 PM Bug #8613 (Duplicate): ENOENT from ceph_test_rados
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-06-16_02:30:04-rados-master-testing-basic-plana/310274...
- 02:30 PM Bug #8612: osd: scrub mismatch, overcount on objects
- 02:29 PM Bug #8612 (Can't reproduce): osd: scrub mismatch, overcount on objects
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-06-16_02:30:04-rados-master-testing-basic-plana
310... - 02:28 PM Bug #8611 (Duplicate): osd/ReplicatedPG.cc: 2348: FAILED assert(p != snapset.clones.end())
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-06-16_02:30:04-rados-master-testing-basic-plana/310038...
- 02:16 PM Bug #8610 (Duplicate): osd: calc_priors_during doesn't ignore CRUSH_ITEM_NONE
- ubuntu@teuthology:/a/teuthology-2014-06-15_02:30:07-rados-next-testing-basic-plana/308761...
- 01:54 PM Revision d93e74e7 (ceph): common: Enforces the methods lru_pin() and lru_unpin()
- If lru_*pin() is called twice, the counter will be incr/decr
incorrectly since it will count more/less pinned objects... - 01:54 PM Revision d48ed68a (ceph): common: Fixes issue with lru_clear() + add new test
- The method lru_clear() must set attribute lru_num to zero
after lru_top, lru_bot and lru_mid are reseted. indeed, lru... - 01:54 PM Revision 62aa5c5c (ceph): common: Adds simple tests to verify good behavior
- Adds new tests to the lib include/lru.h to verify methods
insert_*.
Signed-off-by: Sahid Orentino Ferdjaoui <sahid.f... - 01:35 PM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/teuthology-2014-06-15_02:30:07-rados-next-testing-basic-plana/308538 (btrfs)
the problem in ... - 12:13 PM Bug #8595: osd: client op blocks until backfill starts (dumpling)
Both
6f975e35a1e29a01347e4a6709b54a0422e063dd
and
3d0d69fed09675fc466f6c5b2736ba674923823d
look like they need ...- 11:42 AM devops Bug #8403 (Resolved): Fedora 20 needs to be supported with repos
- FC20 repos are now available http://ceph.com/rpm-firefly/fc20/
- 11:39 AM Feature #8391: sysvinit does not support custom cluster names
- ceph-deploy now refuses to install on sysvinit systems when custom cluster names are passed in.
This issue is left... - 11:37 AM devops Bug #8572 (Resolved): ceph-release missing from new FC20 repo
- This was fixed a few days ago.
- 11:32 AM RADOS Feature #8609: Improve ceph pg repair
- +1 I think this is really important and would reduce the amount of time I spend managing my cluster.
- 11:20 AM RADOS Feature #8609 (New): Improve ceph pg repair
- At the moment, ceph uses the primary copy to repair an inconsistent pg. This is not always a good choice, if there ha...
- 10:58 AM rgw Bug #8608 (Resolved): rgw: bucket instance id is truncated
- The bucket instance id is a concatenation of the zone name, the rados (client) instance id, and a running atomic coun...
- 10:18 AM Bug #8606 (Closed): JSON output normalization for "num_in_osds"
- JSON output in ceph -s -f json shows the property of j["osdmap"]["osdmap"]["num_in_osds"] as a quoted string and not ...
- 10:01 AM Feature #8307 (Pending Backport): Creating a pool with erasure code allows me to create invalid e...
- 10:01 AM Feature #8307 (Resolved): Creating a pool with erasure code allows me to create invalid ec profil...
- 09:27 AM Bug #8601 (Pending Backport): erasure-code: default profile does not exist after upgrade
- 09:25 AM Bug #8599 (Resolved): Fix check of ruleset id on pool update
- 09:12 AM Revision 64f62326 (ceph): ceph: output prompt only if stdin is tty
- In loop mode, output prompt only if stdin is tty, i.e. if we are
interactive.
Signed-off-by: Ilya Dryomov <ilya.dryo... - 09:12 AM rbd Bug #8564 (Resolved): osd cannot be restarted when leveldb is used as backend
- 09:10 AM Revision 2eb1f55a (ceph): vstart.sh: rename conf variable to conf_fn
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 09:10 AM Revision 8d1cb8ba (ceph): vstart.sh: echo CEPH_{CONF,KEYRING} exports if necessary
- If CEPH_DIR is not PWD, echo export statements for CEPH_{CONF,KEYRING}.
Signed-off-by: Ilya Dryomov <ilya.dryomov@in... - 08:41 AM Feature #8605 (Resolved): mon: add sanity checks on configurables
- add a check_config() type method to the config observer and init to verify that important config tunables (like timeo...
- 06:35 AM Bug #8603 (Resolved): ceph-disk should not hide commands that go through subprocess
- ceph-disk currently does not tell you any commands that go through subprocess unless the command
fails, in which cas... - 06:30 AM Revision 18f58074 (ceph): Make KeyValueStore not use expected_write_size
- expected_write_size in set_alloc_hint isn't the mean of name, now it's just the
size of object. It's not suitable for... - 02:18 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- i am still having problems with the cluster, but this time there is a growing number of inconsistencies, which starte...
06/15/2014
- 02:54 PM Revision 360de6ad (ceph): erasure-code: create default profile if necessary
- http://tracker.ceph.com/issues/8601
Signed-off-by: Loic Dachary <loic@dachary.org> - 02:06 PM devops Bug #8602 (Rejected): ceph fedora package is missing erasure code libraries
- See https://bugzilla.redhat.com/show_bug.cgi?id=1109594
- 09:56 AM Revision 1fb45741 (ceph): Merge pull request #1960 from dachary/wip-test-kill-race
- tests: prevent kill race condition
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 07:58 AM Bug #8601 (Fix Under Review): erasure-code: default profile does not exist after upgrade
- "work in progress":https://github.com/ceph/ceph/pull/1966
- 06:44 AM Bug #8601 (Resolved): erasure-code: default profile does not exist after upgrade
- h3. Workaround
Create the *default* profile, after upgrading to firefly, with... - 04:30 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- With this applied to 0.80.1 and erasure pool is in use, all OSDs log ...
- 03:17 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- I just want to say thanks for this change. Backport is trivial and now I can finally use erasure pool with kernel RBD...
06/14/2014
- 05:30 PM Revision f3ec7d0b (ceph): osd: add sanity check/warning on a few key configs
- Warn when certain config values are set to bad values.
Backport: firefly, dumpling
Signed-off-by: Sage Weil <sage@in... - 01:44 PM RADOS Support #8600 (Closed): MON crashes on new crushmap injection
- The crush map contains the following rule
rule ssd {
ruleset 1
type replicated
min_size 1
max_size 10
step... - 11:05 AM Revision c3400853 (ceph): mon: pool set <pool> crush_ruleset must not use rule_exists
- Implement CrushWrapper::ruleset_exists that iterates over the existing
rulesets to find the one matching the ruleset ... - 10:56 AM Revision d02d46e2 (ceph): mon: pool set <pool> crush_ruleset must not use rule_exists
- Implement CrushWrapper::ruleset_exists that iterates over the existing
rulesets to find the one matching the ruleset ... - 07:59 AM Revision 8fd2fc1a (ceph): osd: 'status' admin socket command
- Basic stuff, like what state is the OSD in, and what osdmap epoch are
we on.
Signed-off-by: Sage Weil <sage@inktank.... - 04:07 AM Bug #8599: Fix check of ruleset id on pool update
- "dumpling backport":https://github.com/ceph/ceph/pull/1963
- 03:23 AM Bug #8599 (Fix Under Review): Fix check of ruleset id on pool update
- The individual commits fixing this in master cannot be conveniently cherry-picked because the CrushWrapper::ruleset_e...
- 01:51 AM Bug #8599 (Resolved): Fix check of ruleset id on pool update
- h3. Workaround
Use the rule_id instead of the ruleset. The rule_id for a given ruleset can be found with: ... - 01:24 AM Revision 82c54795 (ceph): Merge pull request #1949 from ceph/wip-7774-3
- Wip 7774 3
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
06/13/2014
- 11:30 PM Revision f7c093e9 (ceph): Merge pull request #1915 from ceph/wip-8452-2
- rgw: set meta object in extra flag when initializing it
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:03 PM Bug #8598 (Can't reproduce): Monitor performance during intensive operations
- Problem: During times of intensive operations such as deep scrubbing, monitors are observed coming in and out of quor...
- 08:30 PM Revision 57224194 (ceph): init-ceph: continue after failure doing osd data mount
- If we are starting many daemons and hit an error, we normally note it and
move on. Do the same when doing the pre-mo... - 08:30 PM Revision 32349245 (ceph): init-ceph: continue after failure doing osd data mount
- If we are starting many daemons and hit an error, we normally note it and
move on. Do the same when doing the pre-mo... - 08:26 PM Bug #8595: osd: client op blocks until backfill starts (dumpling)
- commit:6f975e35a1e29a01347e4a6709b54a0422e063dd fixed it in emperor, but not intentionally.
- 08:23 PM Bug #8595: osd: client op blocks until backfill starts (dumpling)
- we are hitting this:...
- 07:20 PM Bug #8595 (Resolved): osd: client op blocks until backfill starts (dumpling)
- observed on congress. logs at cephstore7098:~sage
- 06:47 PM Revision 0cb6b719 (ceph): Add .ropeproject to .gitignore
- I use a vim plugin that creates lots of directories with that name
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 05:13 PM RADOS Feature #8594: Monitor multi-thread awareness
- The monitor is essentially single threaded right now. If that's causing specific performance issues it would be good ...
- 05:00 PM RADOS Feature #8594 (New): Monitor multi-thread awareness
- -First noticed by a support customer in firefly while starting OSDs, creating this as a tracking issue initially unti...
- 04:14 PM Revision e5a291ef (ceph): Fix for bug #6700
- When preparing OSD disks with colocated journals, the intialization process
fails when using dmcrypt. The kernel fail... - 03:39 PM Bug #8593 (Resolved): mon: down but in osds in health warning calc is wrong
- it is just comapring numbers, so if there are up + out osds it is wrong
int num_up_osds = osdmap.get_num_up_osds... - 01:29 PM Bug #8554 (Resolved): sysvinit script stops if it hits a mount error
- 12:59 PM Revision 4786a485 (ceph): osd: remove non const get_erasure_code_profile
- It is not used and will unexpectedly create a new entry if selected when
the const version is intended.
Signed-off-b... - 12:46 PM Revision a1c13c57 (ceph): tests: prevent kill race condition
- When trying to kill a daemon, keep its pid in a variable instead of
retrieving it from the pidfile multiple times. It... - 10:56 AM Revision 3c638111 (ceph): erasure-code: OSDMonitor::get_erasure_code is a const
- If it is not, the non const version of OSDMap::get_erasure_code_profile
is called and a profile is created as a side ... - 10:56 AM Revision 6bf8183f (ceph): erasure-code: consistent argument parsing for profiles
- Remove the = from the goodchars of the erasure_code_profile argument of
osd pool create so that it is consistent with... - 10:56 AM Revision 5c1f9aae (ceph): osd: improve osd pool create error message readability
- Add std::endl to separate independent error messages related to erasure
code.
Signed-off-by: Loic Dachary <loic@dach... - 10:56 AM Revision ff2eb234 (ceph): erasure-code: pool create must not create profiles
- If a non existent profile is provided as an argument to osd pool create,
it must exit on error and not create the pro... - 10:39 AM Revision acd6ebb0 (ceph): qa: set +x on cephfs_journal_tool_smoke
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:39 AM Revision 0d63cf24 (ceph): qa: extend cephfs_journal_tool_smoke
- To provide coverage for the 'import' command
resulting in the same contents as before an
export/import cycle.
Signed... - 10:39 AM Revision 381163c2 (ceph): tools/cephfs: Clean up waits in Dumper
- Remove some LOC by using C_SaferCond.
Signed-off-by: John Spray <john.spray@inktank.com> - 10:39 AM Revision ac057999 (ceph): tools/cephfs: error handling in journal_export
- Was failing on unreadable journal even if
only trying to do an import.
Was calling messenger destructor without init... - 10:39 AM Revision ee487b42 (ceph): tools/cephfs: Purge trailing objects during import
- Reviewed-by: Gregory Farnum <greg@inktank.com>
Signed-off-by: John Spray <john.spray@inktank.com> - 09:50 AM Feature #7238 (Fix Under Review): erasure code : implement LRC plugin
- 09:44 AM Feature #7238: erasure code : implement LRC plugin
- the "job died":http://qa-proxy.ceph.com/teuthology/loic-2014-06-12_15:38:27-rados-wip-7238-lrc-testing-basic-plana/30...
- 09:07 AM Feature #7238: erasure code : implement LRC plugin
- none of the "failed":http://pulpito.ceph.com/loic-2014-06-12_15:38:27-rados-wip-7238-lrc-testing-basic-plana/ are rel...
- 08:51 AM Feature #7238: erasure code : implement LRC plugin
- One job "died":http://qa-proxy.ceph.com/teuthology/loic-2014-06-12_15:38:27-rados-wip-7238-lrc-testing-basic-plana/30...
- 09:13 AM Bug #6700 (Resolved): ceph-disk prepare fails to set up an encrypted disk
- Backported commit 6733947 to Firefly.
- 08:34 AM Feature #8071: erasure-code: simplify jerasure initialization
- "Fail to run the rados test suite":http://pulpito.ceph.com/?branch=wip-8071 probably a teuthology local problem, inve...
- 08:33 AM devops Bug #6703 (Fix Under Review): OSDs with dmcrypt fail to start at boot
- Pull request opened: https://github.com/ceph/ceph/pull/1961
- 06:22 AM devops Bug #6703 (In Progress): OSDs with dmcrypt fail to start at boot
- 05:18 AM devops Bug #4887 (Resolved): ceph-disk list: Doesn't list properly devices using dm-mapper
- This is now no longer a problem in master. However, there are two related issues that might prevent someone from bein...
- 01:02 AM Revision 1781e7f1 (ceph): Merge pull request #1955 from ceph/wip-8585
- rgw: set a default data extra pool name
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
06/12/2014
- 11:45 PM Revision da2c72a8 (ceph): Merge pull request #1933 from ceph/wip-8556
- osd: do not require EC feature bit from clients.
Reviewed-by: Greg Farnum <greg@inktank.com> - 11:45 PM Revision 3fe1699f (ceph): osd/OSDMap: do not require ERASURE_CODE feature of clients
- Just because an EC pool exists in the cluster does not mean tha tthe client
has to support the feature:
1) The way c... - 11:44 PM Revision 250677c9 (ceph): osd/OSDMap: make get_features() take an entity type
- Make the helper that returns what features are required of the OSDMap take
an entity type argument, as the required f... - 09:36 PM Revision e29beff3 (ceph): erasure-code: remove jerasure internals dependencies
- Use the galois_init_default_field() function instead of implementing it
in the init function of the ErasureCodeJerasu... - 08:14 PM Revision 894f3724 (ceph): Merge pull request #1957 from ceph/wip-doc-os-recommendations
- doc: Updated the OS Recommendations for Firefly.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 07:48 PM Revision e720314a (ceph): doc: Updated the OS Recommendations for Firefly.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:35 PM Revision 2e3302cc (ceph): doc: Updated the example configuration.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:34 PM Revision 5a31df21 (ceph): doc: Updated doc for more recent versions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:23 PM Revision 09d3f916 (ceph): Add [--] to usage statement
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:37 PM Revision 1e18d85b (ceph): Merge pull request #1939 from ceph/wip-mon
- mon: a few basic perfcounter guages
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:57 PM Revision a5857e3d (ceph): Merge pull request #1956 from ceph/wip-fsx-sizeof
- test_librbd_fsx: fix sign-compare gcc warning
Reviewed-by: Sage Weil <sage@inktank.com> - 04:43 PM Bug #8556 (Pending Backport): CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- 02:36 PM Feature #8071: erasure-code: simplify jerasure initialization
- "backport merged":https://bitbucket.org/jimplank/jerasure/pull-request/23/add-galois_init_default_field-error-code/diff
- 02:11 PM Bug #8519: msgr: deadlock, blocked on SimpleMessenger::lock
- Unfortunately we didn't think to save the crash data, so it's all gone now. :(
But as I look at this again alongsi... - 01:32 PM Revision 2eab1c15 (ceph): Update RBD doc for OpenStack
- Some updates from Icehouse, best practice configurations and
explanations.
Signed-off-by: Sébastien Han <sebastien.h... - 01:16 PM Bug #8592 (Can't reproduce): sgdisk no longer likes `--change-name` when creating partitions
- When using `--change-name` on the same call when creating the partition sgdisk complains like:...
- 01:13 PM Bug #8591 (Resolved): ceph-disk incorrectly colocates journal when using dm-crypt
- If not specifying the journal it fails:
Note: slightly more verbose output from ceph-disk was tweaked to see actua... - 01:12 PM RADOS Feature #6421 (New): FileStore: Op unit tests
- I pushed what I had to wip-filestore-test, but I don't remember any of it any more.
- 12:52 PM CephFS Bug #8576: teuthology: nfs tests failing on umount
- teuthology-2014-06-09_23:02:09-knfs-master-testing-basic-plana/303822/
teuthology-2014-06-09_23:02:09-knfs-master-te... - 12:46 PM Documentation #8549: Ceph installation pre-flight problem with ssh-copy-id
- I think that the ssh-copy-id may work if there is a .ssh/authorized_keys file already set up on the 'copy to' machine
- 12:41 PM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- This is some kind of on-disk corruption on the replica that you're seeing?
I think you're probably right, as we're n... - 12:23 PM Revision 87650d43 (ceph): Merge pull request #1948 from steveftaylor/6700
- Fix for bug #6700
Reviewed-by: Alfredo Deza <alfredo.deza@inktank.com> - 10:55 AM Cleanup #8590 (New): better error reporting from ceph-disk
- It is *very* difficult to understand what the actual error may be when ceph-disk fails.
This is an example output... - 10:37 AM Revision a290d349 (ceph): test_librbd_fsx: fix sign-compare gcc warning
- {read,write}bdy are signed, sizeof returns unsigned, gcc complains.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktan... - 09:03 AM Bug #6700 (Pending Backport): ceph-disk prepare fails to set up an encrypted disk
- let's backport this to firefly
- 05:22 AM Bug #6700 (Resolved): ceph-disk prepare fails to set up an encrypted disk
- Pull request https://github.com/ceph/ceph/pull/1948
Merged to master branch of Ceph with hash 87650d4 - 07:27 AM Bug #8589: scrub error with leveldb backend
- use 'dd' command to test single rbd performance
- 02:55 AM Bug #8589: scrub error with leveldb backend
- Hi xinxin,
Could give some tips like what operations you did, and the cluster info - 01:41 AM Bug #8589 (Resolved): scrub error with leveldb backend
- when ceph cluster began to scrub , ceph cluster became unhealthy , several pgs is active+clean+inconsistent,
clu... - 07:01 AM CephFS Fix #5399 (Resolved): timestamp changes on replayed mds request (pjd link 71)
- commit:f81c53a716f43c8a36d6b2aea88cbebe961502d8
- 06:40 AM Feature #7238: erasure code : implement LRC plugin
- "rados suite":http://pulpito.ceph.com/loic-2014-06-12_15:38:27-rados-wip-7238-lrc-testing-basic-plana/ testing "the r...
- 05:26 AM devops Bug #4887: ceph-disk list: Doesn't list properly devices using dm-mapper
- There are two components here that will fix this. First is issue #6700 which had a PR but was not reviewed.
It jus... - 05:00 AM Feature #8475 (Fix Under Review): erasure-code: oversized objects when using the Cauchy technique
- "the rados test suite is ok":http://pulpito.ceph.com/loic-2014-06-10_11:39:56-rados-wip-8475-testing-basic-plana/ wit...
- 03:24 AM Revision e287f02a (ceph): Merge pull request #1937 from yuyuyu101/keyvaluestore-strip-size
- Add strip size and set_alloc_hint op support for KeyValueStore
Reviewed-by: Sage Weil <sage@inktank.com> - 01:57 AM devops Bug #7598: ceph-disk-activate error with ceph-deploy
- osd create works without any problem. It's only activate that fails.
- 01:12 AM Feature #8580: Decrease disk thread's IO priority and/or make it configurable
- I've done some fio testing to motivate this further. The fio config below should simulate the case where the journal ...
- 12:31 AM Revision 40c48bca (ceph): qa: add script to test krbd setting ro/rw ioctl
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
06/11/2014
- 11:50 PM Revision b2542f8e (ceph): rgw: set a default data extra pool name
- Fixes: #8585
Have a default name for the data extra pool, otherwise it would be empty
which means that it'd default t... - 11:11 PM Revision 94c8f70e (ceph): doc: Made mention of "incomplete" status.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:59 PM Revision 027e75cb (ceph): Merge pull request #1953 from ceph/wip-xattr-spillout
- Enable and fix the existing xattr spillout code.
Reviewed-by: Sage Weil <sage@inktank.com> - 09:29 PM Revision b8709ec0 (ceph): Merge pull request #1897 from somnathr/wip-sharded-threadpool
- Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 08:44 PM Revision c883e310 (ceph): enable kernel debugging on kclient fsx runs
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:40 PM Revision 29c33f0c (ceph): qa: add an fsx run which turns on kernel debugging
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:27 PM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- Rather than crashing the OSD, it is better to fail the request, and possibly marking the PG as inconsistent. Even bet...
- 08:06 PM Bug #8588 (Duplicate): In the erasure-coded pool, primary OSD will crash at decoding if any data ...
- In the EC pool, if any data chunk's size is changed due to some reason, this will make the total size retrieved from ...
- 07:39 PM Revision 8bc25bf5 (ceph): Merge pull request #41 from ceph/wip-rados-op-fixes
- rados: Fix cache_flush, cache_try_flush, cache_evict and add hit_set_lis...
- 05:48 PM Revision e3b995e1 (ceph): FileStore: set XATTR_NO_SPILL_OUT when creating new files.
- Fixes: #8205
Backport: firefly
Signed-off-by: Greg Farnum <greg@inktank.com> - 05:48 PM Revision 7267a37d (ceph): FileStore: remove dead code
- This case wasn't reachable when it was introduced, and it's still not.
Signed-off-by: Greg Farnum <greg@inktank.com> - 05:48 PM Revision fbe6009f (ceph): FileStore: do not use user_only in collection_getattrs
- There's no particular reason why any of the callers of collection_getattrs
want to avoid looking at Ceph's internal x... - 05:48 PM Revision bb4e3a9f (ceph): FileStore: remove user_only options from getattrs through the ObjectSto...
- This sort of awareness belongs at a higher level in the stack -- as
evidenced by nobody using the option at this leve... - 05:48 PM Revision f9787224 (ceph): FileStore: remove the user_only param from _fgetattrs
- Nobody sets it to true, so remove it!
Signed-off-by: Greg Farnum <greg@inktank.com> - 05:47 PM Revision 239476a9 (ceph): FileStore: make _clone() copy spill out marker
- Previously we were not doing so, and that resulted in unpredictable loss
of xattrs from the client's perspective.
Si... - 05:47 PM Revision af8052bd (ceph): Add xattr test to ceph_test_objectstore
- Add xattr synthetic test to test ObjectStore xattr related interfaces.
Signed-off-by: Haomai Wang <haomaiwang@gmail.... - 04:50 PM rgw Bug #8585 (Fix Under Review): rgw suite failures on master
- 04:21 PM rgw Bug #8585: rgw suite failures on master
- Failures are all (except for some intermittent) with EC backend. I guess it's related to the fix to #8311. Beforehand...
- 08:48 AM rgw Bug #8585 (Resolved): rgw suite failures on master
- teuthology-2014-06-09_23:00:50-rgw-master-testing-basic-plana for the latest
- 03:54 PM Fix #8205 (Pending Backport): FileStore: properly fill in XATTR_NO_SPILL_OUT tag
- This is in master now, but we'll need to backport to Firefly after it's been through some nightlies. (Unless we don't...
- 03:35 PM rgw Bug #8587 (Resolved): rgw: subuser object not created correctly
- An object with a empty name is created. Might be related to pool not existing before creating the user.
- 01:55 PM Feature #8307 (Fix Under Review): Creating a pool with erasure code allows me to create invalid e...
- "need review":https://github.com/ceph/ceph/pull/1954
- 10:10 AM Feature #8307 (In Progress): Creating a pool with erasure code allows me to create invalid ec pro...
- 09:32 AM Feature #8307: Creating a pool with erasure code allows me to create invalid ec profile names.
- OSDMonitor::get_erasure_code() is calling OSDMap::get_erasure_code_profile(), which according to gdb ends up hitting ...
- 11:26 AM rgw Bug #8586 (Resolved): Missing Swift API Header causes RadosGW to segfault
- When submitting a CORS request via the Swift API a segmentation fault can occur if the "Origin" header is missing.
... - 10:04 AM Feature #8343: please enable data integrity checking (by default) / silent data corruption
- Dmitry Smirnov wrote:
> Greg Farnum wrote:
> > it sounds like you used incorrect replicas as the authoritative sour... - 07:57 AM Feature #8343: please enable data integrity checking (by default) / silent data corruption
- Greg Farnum wrote:
> it sounds like you used incorrect replicas as the authoritative sources for the repairs you ran... - 08:39 AM Fix #6278: osd: throttle snap trimming
- Olivier Bonvalet wrote:
> Sorry for noise, one precision please : if I want to throttle to N io per OSD, the correct... - 07:24 AM Bug #8584 (Duplicate): OSD Crashing on firefly - Timeouts on starting again
- Besides the Crashing of OSD's on firefly with the following error in theyre logfiles:...
- 07:18 AM rgw Bug #8583: rgw: admin ops create user API can not determine existing user
- Sent a pull request to fix it: https://github.com/ceph/ceph/pull/1950
Please help to review it. - 07:08 AM rgw Bug #8583 (Resolved): rgw: admin ops create user API can not determine existing user
- Version: Firefly 0.8.0
Reproduce Steps:
1) Failed to create a user only with uid
PUT /admin/user?format=json&uid... - 06:08 AM Revision c616358f (ceph): rgw: chain binfo_cache to multiple cache entries
- Need to chain it to both the entry point and to the instance.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:08 AM Revision d9fac9c6 (ceph): rgw: chain to multiple cache entries in one call
- This ensures that chained cache entries that depend on more than one raw
cache entry (bucket info cache depends on bo... - 06:08 AM Revision ab764f38 (ceph): rgw: an infrastructure for hooking into the raw cache
- Extend the RGWCache so that we can chain other caches to it so that when
data is invalidated it notifies them.
Signe... - 06:08 AM Revision a2f6709f (ceph): rgw: user info uses cache chaining
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:08 AM Revision 7e81185b (ceph): rgw: bucket info uses cache chaining
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:08 AM Revision eaff42f3 (ceph): rgw: cache decoded user info
- Instead of accessing the raw user info data, cache the decoded
structure.
Signed-off-by: Yehuda Sadeh <yehuda@inktan... - 06:08 AM Revision 7fb6a3d6 (ceph): rgw: cache bucket info
- This is really a partial implementation, so should only be used for
testing.
Signed-off-by: Yehuda Sadeh <yehuda@ink... - 06:07 AM devops Bug #4887 (In Progress): ceph-disk list: Doesn't list properly devices using dm-mapper
- 05:56 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- 05:45 AM Bug #8582 (Can't reproduce): Cluster very slow after upgrade to 80.1
- Last week we've upgraded to firefily 80.1 on a production cluster (3 nodes, 18 osds). Upgrade went fine but the speed...
- 05:40 AM devops Bug #8581 (Can't reproduce): DNS issues when resolving hosts
- There have been consistent DNS errors where some hosts cannot be resolved and end up causing
failures with ceph-depl... - 01:10 AM Revision 0bbeeee3 (ceph): PG: Added a const spg_t member to the PG class
- The const spg_t member is been insantiated from constructor
and now get_pgid() can reference this to return a spg_t i... - 12:45 AM Revision 85e491fb (ceph): doc: Added a tip to install NTP when running multiple monitors.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:44 AM Revision d37ef6ab (ceph): doc: Added additional background to address additional states.
- Covers 1-node cluster issues, fewer OSDs than replicas, and
active + clean + inconsistent states in greater detail.
... - 12:42 AM Revision b7f6147c (ceph): doc: Added background discussion to clock settings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:26 AM Feature #8580 (Resolved): Decrease disk thread's IO priority and/or make it configurable
- PG scrubbing (and other "background" activities) should not consume IOPS if there are client IOs to be performed. The...
06/10/2014
- 11:43 PM Revision ecbb0056 (ceph): OSD: The thread pool variable name changed
- The variable names are more meaningful now. op_tp -> osd_tp and
op_sharded_tp -> osd_op_tp
Signed-off-by: Somnath Ro... - 11:19 PM rgw Feature #7774 (Fix Under Review): rgw: cache decoded user and bucket info
- 09:06 AM rgw Feature #7774 (In Progress): rgw: cache decoded user and bucket info
- 11:02 PM Revision 2a5d83d2 (ceph): ShardedTP: The config option changed
- The config option for sharded threadpool is changed to
osd_op_num_threads_per_shard instead of osd_op_num_sharded_poo... - 10:24 PM Revision a0e48b8b (ceph): ShardedTP: Changes related to conforming to Ceph coding guidelines
- Signed-off-by: Somnath Roy <somnath.roy@sandisk.com>
- 09:16 PM Bug #8578 (Can't reproduce): teuthology: OSD thrasher killing OSDs which hold the sole copies of PGs
- ubuntu@teuthology:/a/gregf-2014-06-09_22:28:53-rados-wip-xattr-spillout-testing-basic-plana/303486
For example:
<... - 07:40 PM Revision f69f2dff (ceph): Automatically watch 'multi' tube if tube_name
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:20 PM Revision 2e3f4bc6 (ceph): doc: Fixed typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:56 PM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- /teuthology-2014-05-30_23:02:02-kcephfs-master-testing-basic-plana/283020/
- 06:46 PM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- /a/teuthology-2014-06-01_23:02:07-kcephfs-next-testing-basic-plana/285055
- 06:10 PM CephFS Bug #8542: kcephfs: fsx failure on read (expected 0's)
- teuthology-2014-06-06_23:01:56-kcephfs-master-testing-basic-plana/297431/
- 06:42 PM Revision 67339470 (ceph): Fix for bug #6700
- When preparing OSD disks with colocated journals, the intialization process
fails when using dmcrypt. The kernel fail... - 06:22 PM CephFS Bug #8576 (Resolved): teuthology: nfs tests failing on umount
- Just a sample:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-02_23:02:20-knfs-master-testing-basic-plana/28... - 06:19 PM CephFS Bug #8575 (Rejected): linux kernel: possible circular locking dependency detected
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-06-02_23:02:20-knfs-master-testing-basic-plana/289526/
Not sur... - 06:00 PM CephFS Bug #8574 (Resolved): teuthology: NFS mounts on trusty are failing
- It looks like there are some changes to the settings which make Trusty's default NFS server settings incompatible wit...
- 03:24 PM Feature #8343: please enable data integrity checking (by default) / silent data corruption
- Sorry for dropping this...it sounds like you used incorrect replicas as the authoritative sources for the repairs you...
- 01:55 PM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- I am having a lot of trouble trying to relate the ssh connection with how we start the daemon and the subsequent fail...
- 12:18 PM Revision 15ae765e (ceph): Merge pull request #270 from ceph/wip-schedule-suite
- Refactor teuthology.schedule...
- 09:51 AM devops Bug #8572 (Resolved): ceph-release missing from new FC20 repo
- ...
- 09:22 AM rbd Feature #8569: RBD Mirroring::
- 09:22 AM rbd Feature #8569 (Duplicate): RBD Mirroring::
- http://wiki.ceph.com/Planning/Blueprints/Giant/rbd%3A_journaling
- 09:22 AM rbd Bug #8416: Client Crash when try to map a volume (ubuntu)
- FWIW, I'm pretty sure this is a known bug in kernels ~3.5, which manifests as a crash on 'rbd map' if the kernel miss...
- 09:21 AM rbd Feature #7923: Openstack: backup from in-use volume instead of from detached volume
- Josh to write up more detailed blueprint for implementation
- 09:06 AM Bug #8241 (Pending Backport): XfsFileStoreBackend tries to set extsize but may get EINVAL
- 08:31 AM Revision 6c4c1b71 (ceph): Merge pull request #1945 from dachary/wip-warnings
- tests: fix signess warning
Reviewed-By: Christophe Courtaut <christophe.courtaut@gmail.com> - 06:30 AM Feature #7288: Deep-scrub throttle
- Would it be possible to add an nscrubs limit which works across the cluster?, for example at the pool level: osd_pool...
- 02:39 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- "rados suite":http://pulpito.ceph.com/loic-2014-06-10_11:39:56-rados-wip-8475-testing-basic-plana/
- 01:34 AM Feature #8475: erasure-code: oversized objects when using the Cauchy technique
- 01:37 AM Linux kernel client Bug #8568 (Closed): libceph: kernel BUG at net/ceph/osd_client.c:885
- Kernel panic after kill all OSD deamons at the same time.
All kernels.
Jun 10 10:12:34 client01 kernel: [ 1113.39...
06/09/2014
- 11:51 PM rbd Bug #8564: osd cannot be restarted when leveldb is used as backend
- Are you mean PR 1941 for bug fix and 1649 for performance purpose?
If so, yes - 10:48 PM rbd Bug #8564: osd cannot be restarted when leveldb is used as backend
- hi haomai , is https://github.com/ceph/ceph/pull/1941 PR the fix for this bug , while https://github.com/ceph/ceph/pu...
- 04:30 AM rbd Bug #8564 (Fix Under Review): osd cannot be restarted when leveldb is used as backend
- 04:29 AM rbd Bug #8564: osd cannot be restarted when leveldb is used as backend
- Hi xinxin,
Thanks for your report, you hint a known bug which will solved in (https://github.com/ceph/ceph/pull/16... - 02:47 AM rbd Bug #8564 (Resolved): osd cannot be restarted when leveldb is used as backend
- hi all , recently i enabled leveldb as filestore backend, after restarting my cluster , an osd is crashed, from the l...
- 11:31 PM Revision 78610b03 (ceph): Remote 'delete' and 'show' features
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:31 PM Revision 78dbc369 (ceph): Refactor teuthology.schedule...
- ... to separate the assembling of the job config from the scheduling of
the job. Also port its argument parsing to do... - 11:30 PM Revision b2f0ddad (ceph): Remove unused import
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:06 PM Revision a4923f5b (ceph): fix compilation warnings
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:22 PM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- Yeah. I'm actually not sure why it would be sending out rados xattr requests on restart unless you'd lost clients, bu...
- 05:53 PM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- I observe the slow requests with ceph -w, or watching osd log files.
(i) The mds getxattr parent requests during r... - 03:55 PM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- Can you talk about cases (i) and (ii) in a little more detail? And how you're observing the delayed xattr requests?
- 03:40 PM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- I like the notion of being able to recover at least part of the tree structure from data pools alone. Maybe the opti...
- 10:19 AM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- My concern with this is that part of the point is to provide a way to recover data into the hierarchy even if we've l...
- 09:41 PM Revision a405c228 (ceph): Merge pull request #268 from ceph/wip-5400
- Support installing ceph kernels from gitbuilder on rpm machines.
- 08:43 PM Revision 3d1df3aa (ceph): Better variable names.
- As suggested by review.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> - 05:41 PM Revision 558249c5 (ceph): rgw: cut short object read if a chunk returns error
- Fixes: #8289
Backport: firefly, dumpling
When reading an object, if we hit an error when trying to read one of
the ra... - 04:46 PM Revision dbf984e9 (ceph): Disable "fix" for corrupt repo detection
- It's causing more problems than it's solving at this point
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 03:37 PM Bug #7804: backfill racing with a hitset object remove
- ubuntu@teuthology:/a/gregf-2014-06-02_14:44:16-rados-wip-sharded-threadpool-testing-basic-plana/287095
- 02:43 PM Documentation #8536 (Resolved): Ceph-deploy install on Centos and RHEL
- There were comments on the master branch, but not on Firefly or Dumpling. I've added the comments there too.
- 02:22 PM Revision 2e5c697f (ceph): Use correct cwd
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:31 PM Bug #7891: osd: leaked pg refs on shutdown
- http://qa-proxy.ceph.com/teuthology/gregf-2014-06-02_14:44:16-rados-wip-sharded-threadpool-testing-basic-plana/287448/
- 12:29 PM Revision 47028874 (ceph): Merge pull request #1872 from ceph/wip-reweight-tree
- mon: add 'osd crush reweight-tree ...'
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 11:30 AM Revision 63cc7f97 (ceph): Add test for objectstore
- Add remove then write object in a transaction.
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> - 11:20 AM Revision 50c8fee8 (ceph): Fix write operation on a deleted object in the same transaction
- If the following op happened:
touch obj
delete obj
write obj
KeyValueStore will fail at "write" operation.
Signed-o... - 11:20 AM Revision 737c13e1 (ceph): Remove SequencerPosition from KeyValueStore
- Now KeyValueStore expects kv backend to ensure consistency and there is unusable
for KeyValueStore to store a Sequenc... - 11:16 AM Revision 2fe1a057 (ceph): Merge pull request #1940 from vshankar/doc-fix
- doc: fix typo in erasure coding section
Reviewed-by: Loic Dachary <loic@dachary.org> - 09:34 AM Revision ef065156 (ceph): doc: fix typo in erasure coding section
- Signed-off-by: Venky Shankar <vshankar@redhat.com>
- 09:10 AM Revision 25200521 (ceph): Merge pull request #1936 from ceph/wip-8554
- init-ceph: continue after failure doing osd data mount
Reviewed-by: Loic Dachary <loic@dachary.org> - 09:08 AM devops Bug #7598: ceph-disk-activate error with ceph-deploy
- One of the differences here is that you cannot call 'activate' without doing a 'prepare' first.
This behavior woul... - 05:46 AM Revision 1080e7a3 (ceph): Add upper limit to the write size of set_alloc_hint in KeyValueStore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:15 AM Bug #8554 (Pending Backport): sysvinit script stops if it hits a mount error
- 04:12 AM Revision a948ce2f (ceph): Merge pull request #1931 from ceph/wip-7068-dumpling
- Wip 7068 dumpling
Reviewed-by: Sage Weil <sage@inktank.com> - 03:18 AM Revision 6a7e2014 (ceph): init-ceph: continue after failure doing osd data mount
- If we are starting many daemons and hit an error, we normally note it and
move on. Do the same when doing the pre-mo... - 02:24 AM Feature #8071: erasure-code: simplify jerasure initialization
- "jerasure merged in master":https://bitbucket.org/jimplank/jerasure/commits/1b30a37c9f75df371cf4deaedfde6b843933b4f0 ...
06/08/2014
- 10:36 PM CephFS Feature #8563: mds: permit storing all metadata in metadata pool
- I like this idea too, but currently have no time to implement it.
- 09:57 PM CephFS Feature #8563 (New): mds: permit storing all metadata in metadata pool
- (this had originally been filed as issue #8230, which was hijacked into an unrelated issue)
I'm speaking specifica... - 10:02 PM Revision 24853e0d (ceph): Merge pull request #1913 from sahid/dist
- Populate AUTHORS and ChangeLog for a distributed package
Reviewed-by: Loic Dachary <loic@dachary.org> - 09:13 PM rgw Feature #8562 (Resolved): rgw: Conditional PUT on ETag
- The object versioning has not been implemented yet in RGW. But there are some use cases that different sources concur...
- 09:11 PM Bug #7068 (Resolved): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.size())...
- 03:56 PM Revision 1f99cdae (ceph): mon: gather perf stats on elections
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:56 PM Revision 8f36d96f (ceph): mon: gather perf stats on session adds, removes, counts
- I found myself wanting to know this on a running cluster.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:24 AM Feature #8071 (Fix Under Review): erasure-code: simplify jerasure initialization
- "need review":https://github.com/ceph/ceph/pull/1938
- 10:03 AM Feature #8071: erasure-code: simplify jerasure initialization
- "pending pull request on jerasure":https://bitbucket.org/jimplank/jerasure/pull-request/22/add-galois_init_default_fi...
- 09:07 AM Feature #8071 (In Progress): erasure-code: simplify jerasure initialization
- 07:11 AM Feature #7238 (Fix Under Review): erasure code : implement LRC plugin
06/07/2014
- 06:03 PM Revision ecda2fef (ceph): OSD: move waiting_for_pg into Session
- This way, we can handle pg splits atomically with ms_fast_dispatch.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 04:22 PM Revision db19040e (ceph): Merge pull request #1934 from sahid/patch-1
- Fix two typos with "dependencies"
- 02:48 PM Revision e217488f (ceph): Merge pull request #269 from ceph/wip-radosfix
- rados: Add hit_set_list missing from possible op weights
- 02:45 PM Revision b7c1e351 (ceph): Update to reflect relocated get_jobs()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:57 AM Revision 1f40c356 (ceph): Add set_alloc_hint test to ceph_test_objectstore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 10:57 AM Revision 5dd9b2ae (ceph): Make KeyValueStore support set_alloc_hint op
- Add a new config let KeyValueStore support configurable strip size.
set_alloc_hint op can affect the strip size of th... - 06:25 AM Revision b0c66a71 (ceph): doc: Fixes spelling errors on README
- Signed-off-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com>
- 06:16 AM Revision c5841fac (ceph): Merge pull request #1899 from yuyuyu101/kvstore-osd-perf
- Make KeyValueStore support "ceph osd perf" command
Reviewed-by: Sage Weil <sage@inktank.com> - 06:12 AM Revision dacc0acf (ceph): Merge pull request #1912 from yuyuyu101/keyvaluestore-sparse-read-bug
- Fix keyvaluestore fiemap bug
Reviewed-by: Sage Weil <sage@inktank.com> - 04:56 AM rbd Bug #8529 (Resolved): vm get killed when leveldb backend enable
- 01:13 AM Revision f5d3f3ea (ceph): Merge branch 'wip-libradosstriper'
- https://github.com/ceph/ceph/pull/1186
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 01:12 AM Revision d160ce23 (ceph): Implementation of the radosstriper interface.
- The user facing API is implemented in libradosstriper.cc and the backend in RadosStriperImpl.cc.
Details on how the c... - 01:12 AM Revision fa01ca65 (ceph): Added unit test suite for the Rados striping API.
- This includes tests for standard io and asynchronous io, similar to what is tested in the rados tests.
In addition, i... - 01:12 AM Revision 910d73c4 (ceph): Added RPM and debian packaging for libradosstriper, creating a new pack...
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
06/06/2014
- 11:05 PM Bug #8554 (Fix Under Review): sysvinit script stops if it hits a mount error
- tested fix on the original node and it works.
- 06:53 AM Bug #8554 (Resolved): sysvinit script stops if it hits a mount error
- ...
- 10:30 PM Revision 875e2d24 (ceph): rados: Add hit_set_list missing from possible op weights
- For the future help keep in sync with test/osd/TestRados.cc by listing
in order of op_types in that code.
Signed-off... - 10:05 PM Feature #8560 (Resolved): mon: instrument paxos
- Add perf counters for paxos internals, like
- restarts
- commit
- commit txn size in bytes (average)
- commit t... - 09:33 PM Revision e057f38a (ceph): Merge pull request #1926 from nereocystis/librados-write-full
- doc: Use write_full for C++ example
- 09:16 PM Revision 91045942 (ceph): Merge pull request #1935 from ceph/wip-flag-known-redirs
- osdc/Objecter: mark all ops as known-if-redirected
Reviewed-by: Sage Weil <sage@inktank.com> - 09:15 PM Revision 2a7de824 (ceph): Move teuthology-ls's implementation to ls.py
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:45 PM Revision a6c34e47 (ceph): osdc/Objecter: mark all ops as known-if-redirected
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 08:20 PM Revision 036e8072 (ceph): Merge pull request #1891 from ceph/wip-8380-b
- osdc/Objecter: flag ops that have been redirected
- 05:50 PM Revision 9db846b7 (ceph): Merge pull request #1930 from ceph/wip-set-extsize-fix
- Wip set extsize fix
Backport: firefly
Reviewed-by: Sage Weil <sage@inktank.com> - 05:01 PM Revision 87e7ff0e (ceph): Fix corrupt repo detection
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:19 PM Revision 3b44f08f (ceph): Merge pull request #1922 from ceph/wip-os-rename
- os: rename get_*() -> decode_*()
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@cloudwatt.com> - 03:55 PM Revision 273c502b (ceph): tasks: Use '_' instead of '-' in names
- Python modules are not allowed to contain hyphens
in the name. Using hyphens only works here because
we're using low... - 03:45 PM Revision 95a464a4 (ceph): Merge remote-tracking branch 'origin/wip-8269-dumpling' into dumpling
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 01:30 PM Bug #8556 (Fix Under Review): CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- 10:52 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- Hmm, so splitting OSDMap::get_features() into a get_features_client() and get_features_server()?
- 10:44 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- We talked about this in core standup and the consensus is currently to just drop the EC requirement for clients entir...
- 10:40 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- Not really. The course of action I had in mind was to make an exception for the EC bit in the kernel (i.e. ignore th...
- 10:18 AM Bug #8556: CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- RBD is the *only* storage system which can really identify a given client instance as communicating with only a singl...
- 10:13 AM Bug #8556 (Resolved): CEPH_FEATURE_OSD_ERASURE_CODES feature bit
- Currently OSDs require CEPH_FEATURE_OSD_ERASURE_CODES feature for the clients to be able to connect to the OSDs. Thi...
- 11:51 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- I ran a grep through all the osd logfiles searching for failed asserts and attached the output. The oldest logfiles a...
- 11:38 AM Revision bc3b30ed (ceph): XfsFileStoreBackend: call ioctl(XFS_IOC_FSSETXATTR) less often
- No need to call ioctl(XFS_IOC_FSSETXATTR) if extsize is already set to
the value we want or if any extents are alloca... - 11:32 AM Revision 750b1db6 (ceph): XfsFileStoreBackend: nuke redundant goto in set_extsize()
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 09:15 AM Bug #8555 (Can't reproduce): PUT osd/pool/rename?srcpool=data2&destpool=data3: 400 (dumpling)
- 2014-06-05T23:00:20.443 INFO:teuthology.task.workunit.client.0.out:[10.214.132.18]: PUT osd/pool/rename?srcpool=data2...
- 08:08 AM Revision 479a67e0 (ceph): creating smoke-tests suite to include basic tests from all modules
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 08:06 AM rbd Bug #6385 (Resolved): run_xfstests.sh: doesn't work with newly-organized upstream tests
- 08:05 AM Bug #8241 (Fix Under Review): XfsFileStoreBackend tries to set extsize but may get EINVAL
- With the fix applied we shouldn't see this message anymore, so I've
left the priority intact. The other known cause... - 07:52 AM Revision e25e33e2 (ceph): Merge pull request #1928 from nereocystis/pool-pg-fix-spelling
- doc: Descrption => Description
Reviewed-by: Loic Dachary <loic@dachary.org> - 04:23 AM devops Bug #7598: ceph-disk-activate error with ceph-deploy
- My issue (as stated above in comment #4) is resolved.
I discovered that i was using a broken ceph.rpm coming from th... - 01:53 AM Revision 524a155e (ceph): rgw: reduce calls to rgw_obj.set_obj()
- default manifest iterator construction did unneeded init of rgw_obj.
Also add a smarter copy constructor to RGWObjSta... - 01:24 AM Revision 3dae48c7 (ceph): rados: Fix cache_flush, cache_try_flush, cache_evict and add hit_set_list
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 12:10 AM Revision e31d3fe0 (ceph): doc: Descrption => Description
- Correct spelling error.
Signed-off-by: Kevin Dalley <kevin@kelphead.org>
06/05/2014
- 11:48 PM Revision 0ca43d83 (ceph): doc: Use write_full for C++ example
- Latest version of librados uses write_full when writing entire object.
Should the documentation mention that the met... - 09:39 PM rgw Bug #8553 (Resolved): rgw: log show broken
- ...
- 08:03 PM Revision 0bd6f679 (ceph): OSD::calc_priors_during: handle CRUSH_ITEM_NONE correctly
- Fixes: #8507
Signed-off-by: Samuel Just <sam.just@inktank.com> - 07:11 PM Bug #8551 (Resolved): init-ceph: small drives can end up with defaultweight = 0.00
- init-ceph calculates the default weight of an OSD with...
- 07:08 PM Revision 624ae218 (ceph): Merge pull request #1859 from ceph/wip-multipartition
- ceph-disk: Enable creating multiple osds per dev
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 07:07 PM Revision 825db505 (ceph): Added requested comment.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 07:04 PM Revision 242d9de4 (ceph): Remove unused variables and functions.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 07:03 PM Revision a63ee379 (ceph): Merge remote-tracking branch 'gh/next'
- 07:02 PM Revision 16e2ed0d (ceph): Merge pull request #1925 from ceph/wip-i386-atomic
- fix i386 atomic64_t
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:59 PM Revision 2081c992 (ceph): include/atomic: make 32-bit atomic64_t unsigned
- This fixes
In file included from test/perf_counters.cc:19:0:
./common/perf_counters.h: In member function ‘std::pair... - 06:58 PM Revision 64e99d81 (ceph): ceph-objectstore-test: fix warning in collect_metadata test
- In file included from test/objectstore/store_test.cc:33:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::... - 06:48 PM rgw Bug #8550 (Resolved): rgw: need to reduce calls to rgw_obj.set_obj()
- This is a placeholder bug for pull request #1863.
- 06:41 PM Revision a79a787b (ceph): doc: Added requiretty comment to preflight checklist.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:34 PM Revision 5c5eb21f (ceph): doc: Added Disable requiretty to quick start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:29 PM Revision 34d9b2bc (ceph): doc: Added Disable requiretty commentary.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:44 PM Documentation #8549 (Closed): Ceph installation pre-flight problem with ssh-copy-id
- http://ceph.com/docs/master/start/quick-start-preflight/#ceph-node-setup
The use of ssh-copy-id in the above docum... - 05:07 PM Revision f92d7bb6 (ceph): Fixed missing include of assert.h in RWLock interface
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 05:07 PM Revision 8c124910 (ceph): Fixed usage of rhel_version in spec file : it should have been rhel
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 05:07 PM Revision 62064f38 (ceph): Added const qualifiers for the layout argument of file_to_extents and o...
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 05:07 PM Revision 7ceeb9f8 (ceph): Completed librados documentation of rados_write_op_cmpxattr and rados_r...
- Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch>
- 05:07 PM Revision e1ad0bf6 (ceph): Added a striper interface on top of rados called radosstriper.
- This interface allows to manipulate striped objects stored in a rados cluster with a standard open/read/write/stat/cl...
- 05:07 PM Revision b9a35b3c (ceph): Extracted RadosXattrIter from librados.cc into independent .h anc .cc f...
- This makes this interface usable by clients of librados.
Signed-off-by: Sebastien Ponce <sebastien.ponce@cern.ch> - 04:19 PM Revision aede8328 (ceph): os: rename get_*() -> decode_*()
- These methods have side-effects: they move the decode iterator *and*
return a value. Rename them to avoid confusion ... - 03:33 PM Revision 5bb078f9 (ceph): Populate ChangeLog when distribute
- Generates ChangeLog from git history for a
distributed package.
Signed-off-by: Sahid Orentino Ferdjaoui <sahid.ferdj... - 03:33 PM Revision b22cc850 (ceph): Populate AUTHORS when distribute
- Adds a complete list of contributors in a
distributed package.
Signed-off-by: Sahid Orentino Ferdjaoui <sahid.ferdja... - 01:48 PM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- attempting to reproduce
- 12:06 PM rgw Bug #8539: civetweb backend responds with a body when a HEAD request yields an error
- Here you go.
- 10:57 AM rgw Bug #8539: civetweb backend responds with a body when a HEAD request yields an error
- This fix seems fine to me. Can you resend it with a proper description and a Signed-off-by line?
- 08:05 AM rgw Bug #8539 (Resolved): civetweb backend responds with a body when a HEAD request yields an error
- So for example, doing a HEAD on a non-existent key will yield a 404, along with a Content-Length: 79 (which is allowe...
- 10:55 AM rgw Bug #8540 (Rejected): ERROR: s3tests.functional.test_s3.test_multipart_upload
- It fails on the new test for 8452, but the version running here is before the fix for it was merged. Closing.
- 08:55 AM rgw Bug #8540 (Rejected): ERROR: s3tests.functional.test_s3.test_multipart_upload
- all (?) of the s3-tests tests on master failed like so:...
- 10:35 AM Feature #8546 (New): add nonce/sequence number associating the several pg metadata keys which are...
- If they don't match, we have a indication that the pg metadata is inconsistent. At that point, there are some option...
- 09:48 AM CephFS Bug #8541 (Duplicate): [WRN] client.4131 released lease on dn 1000000016c/l72 which dne" in clust...
- oh, i missed that this was dumpling. won't fix!
- 09:44 AM CephFS Bug #8541: [WRN] client.4131 released lease on dn 1000000016c/l72 which dne" in cluster log
- So do we want to try and backport, or can we close this?
- 09:03 AM CephFS Bug #8541 (Duplicate): [WRN] client.4131 released lease on dn 1000000016c/l72 which dne" in clust...
- http://pulpito.ceph.com/teuthology-2014-06-02_19:03:01-fs-dumpling-testing-basic-plana/288497/
same symptom as #5871 - 09:35 AM Documentation #8536: Ceph-deploy install on Centos and RHEL
- Actually, these comments are reasonably prominent in the master branch in both the preflight and in the quick start, ...
- 09:30 AM rbd Bug #8543 (Rejected): run_xfstests: mkdir: cannot create directory `//var/lib/xfstests/common': F...
- cool thanks!
- 09:26 AM rbd Bug #8543: run_xfstests: mkdir: cannot create directory `//var/lib/xfstests/common': File exists
- The problem is this...
- 09:14 AM rbd Bug #8543 (Rejected): run_xfstests: mkdir: cannot create directory `//var/lib/xfstests/common': F...
- ...
- 09:13 AM CephFS Bug #8542 (Resolved): kcephfs: fsx failure on read (expected 0's)
- ...
- 07:24 AM rgw Bug #8517 (Duplicate): Can't initiate multipart upload in firefly branch.
- 12:37 AM rgw Bug #8517: Can't initiate multipart upload in firefly branch.
- Duplicates #8311 ... I can't close it myself.
- 04:53 AM Bug #8254 (Resolved): Not logging missing_on_shards properly
- 12:49 AM rbd Bug #8184 (Resolved): krbd: make sure we have latest osdmap on 'rbd map'
- 12:49 AM Bug #8530 (Resolved): make tags broken by dummy.cc
- 12:36 AM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- Oh damn, I reported #8517 which turns out to be a duplicate of this.
However I used the bucket.get_data_extra_pool... - 12:32 AM Revision 7c2c8da2 (ceph): Merge pull request #1918 from ceph/wip-da-SCA-20140604
- Some new fixes for gcc and cppcheck warnings/issues
Reviewed-by: Sage Weil <sage@inktank.com>
Also available in: Atom