Activity
From 06/21/2014 to 07/20/2014
07/20/2014
- 09:51 PM Bug #8752: firefly: scrub/repair stat mismatch
- Upgraded cluster to 0.80.4, restarted all components (previously MDS 0.80.2 could be still running), copied some data...
- 09:21 PM Revision ff15a43c (ceph): Merge pull request #2111 from ceph/wip-8174
- osd: add config for osd_max_object_name_len = 2048 (was hard-coded at 4096)
Reviewed-by: Haomai Wang <haomaiwang@gma... - 08:48 PM Bug #8886 (Closed): Miss some folders in PG's folder
- When put objects to a cluster, I checked the contents of directory /var/lib/ceph/osd/current/pg.xxx and found a probl...
- 06:18 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- I'm getting confident that this kernel bug always hit during deep-scrub.
I reproduced it several times just by start... - 02:48 PM Revision 2aa3edcb (ceph): os/FileStore: fix max object name limit
- Our max object name is not limited by file name size, but by the length of
the name we can stuff in an xattr. That w... - 02:18 PM Bug #8174 (Resolved): rados put of a long object name crashes the OSD process
- 09:36 AM CephFS Bug #8878: mds lock cycle (wip-objecter)
- This is going to be a bit of a project:
- fix every completion to take mds_lock
- .. and shunt every one off to... - 07:31 AM Bug #8885 (Resolved): SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-19_23:15:03-rados-wip-sage-testing-testing-basic-plana/37...
- 07:27 AM Bug #8884 (Can't reproduce): osd/OSD.cc: 6317: FAILED assert(p->second.empty()) in consume_map()
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-19_23:15:03-rados-wip-sage-testing-testing-basic-plana/37...
- 03:51 AM Revision 5049fc4c (ceph): rgw: dump prefix unconditionally
- As part of issue #8858, and to be more in line with S3, dump the Prefix
field when listing bucket even if bucket is e... - 03:51 AM Revision 7fdd6d94 (ceph): rgw: list extra objects to set truncation flag correctly
- Otherwise we end up returning wrong truncated value, and no data on the
next iteration.
Signed-off-by: Yehuda Sadeh ... - 03:51 AM Revision 1f8774e0 (ceph): rgw: account common prefixes for MaxKeys in bucket listing
- To be more in line with the S3 api. Beforehand we didn't account the
common prefixes towards the MaxKeys (a single co... - 03:51 AM Revision cb0a7ab8 (ceph): rgw: add NextMarker param for bucket listing
- Partially fixes #8858.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 924686f0b6593deff... - 03:51 AM Revision 34aa7086 (ceph): rgw: improve delmited listing of bucket
- If found a prefix, calculate a string greater than that so that next
request we can skip to that. This is still not t... - 03:51 AM Revision d027ff1b (ceph): utf8: export encode_utf8() and decode_utf8()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 49fc68cf8c3122c878ea9503c9c74d7046bc9c6f)
07/19/2014
- 08:56 PM Revision a2594a54 (ceph): osd/MemStore: handle collection_move_rename within the same collection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:56 PM Revision 8dd6b8f9 (ceph): os/MemStore: fix wrlock ordering checks
- We can't compare the shared_ptrs themselves; we need to compare the
addresses of the actual objects.
Signed-off-by: ... - 08:56 PM Revision 6f312b05 (ceph): os/MemStore: copy attrs on clone
- Backport: firefly
Signed-off-by: Sage Weil <sage@redhat.com> - 08:56 PM Revision f4bffece (ceph): ceph_test_objectstore: test memstore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:22 PM Revision 2dad906f (ceph): move ship_utilities to install task (from ceph test)
- No need to install ceph just to get daemon-helper, adjust-ulimits, etc..
These utilities are used by lots of tasks, n... - 03:19 PM Bug #8701 (Fix Under Review): osd: scrub found obsolete rollback obj
- the rgw suite, which reliably triggered this, is now passing. wip-8701 ready for review!
- 03:00 PM rgw Bug #8676: md5sum check failed during readwrite.py
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-19_13:59:16-rgw-wip-8701-testing-basic-plana/370152
- 09:30 AM Bug #8882 (Resolved): osd: osd tier remove ... leaves incomplete clones behind, confusing scrub
- ubuntu@teuthology:/a/teuthology-2014-07-18_02:32:01-rados-master-testing-basic-plana/368480
rados/thrash/{clusters/f... - 09:29 AM Bug #8881 (Duplicate): scrub 85.0 cf2b2318/foo15/3/test-rados-api-plana35-13313-11/85 expected cl...
- ubuntu@teuthology:/a/teuthology-2014-07-18_02:32:01-rados-master-testing-basic-plana/368448
ubuntu@teuthology:/a/teu... - 09:24 AM Messengers Bug #8880: msg/Pipe.cc: 1538: FAILED assert(0 == "old msgs despite reconnect_seq feature")
- Which daemon was this?
Looks like that commit does include the fix for #8504... :( - 09:10 AM Messengers Bug #8880 (Resolved): msg/Pipe.cc: 1538: FAILED assert(0 == "old msgs despite reconnect_seq featu...
- ubuntu@teuthology:/a/teuthology-2014-07-18_02:32:01-rados-master-testing-basic-plana/368391...
- 06:43 AM Bug #8680 (Resolved): crushtool should not send it's output to stderr
- This has been resolved in the master branch.
- 06:27 AM Revision dc6c9bf2 (ceph): libosd_types, libos_types, libmon_types
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 1c170776cb8c0266f0f54f049ed07bbdb9c9ab5e)
Conf... - 06:27 AM Revision 3d89380c (ceph): rgw: move a bunch of stuff into rgw_dencoder
- This will help out ceph-dencoder ...
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit b1a641f30... - 06:27 AM Revision c390ec4f (ceph): ceph-dencoder: don't link librgw.la (and rados, etc.)
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 34671108ce0b7597dba4f619732ecdb8933cda6e) - 06:18 AM Revision 7be91e8c (ceph): Revert "ceph.spec: move ceph-dencoder to ceph from ceph-common"
- This reverts commit 95f5a448b52db545a2b9bbad47fdb287254f93ea.
(cherry picked from commit 58cc894b3252a848ebc2169bcc49... - 06:18 AM Revision 04ad08a1 (ceph): Revert "debian: move ceph-dencoder to ceph from ceph-common"
- This reverts commit b37e3bde3bd31287b11c069062280258666df7c5.
(cherry picked from commit f181f78b7473260a717bc8ab4fc4... - 05:44 AM Revision 34671108 (ceph): ceph-dencoder: don't link librgw.la (and rados, etc.)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:39 AM Revision b1a641f3 (ceph): rgw: move a bunch of stuff into rgw_dencoder
- This will help out ceph-dencoder ...
Signed-off-by: Sage Weil <sage@redhat.com> - 05:33 AM Revision 1c170776 (ceph): libosd_types, libos_types, libmon_types
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:55 AM Revision 58cc894b (ceph): Revert "ceph.spec: move ceph-dencoder to ceph from ceph-common"
- This reverts commit 95f5a448b52db545a2b9bbad47fdb287254f93ea.
- 03:55 AM Revision f181f78b (ceph): Revert "debian: move ceph-dencoder to ceph from ceph-common"
- This reverts commit b37e3bde3bd31287b11c069062280258666df7c5.
- 02:43 AM devops Bug #8330: repodata on rpm repos do not list latest ceph-deploy (1.5.2)
- Still the same for ceph-deploy 1.5.9 on the rhel7 ceph-noarch repo.
ceph-deploy is the only package available. ceph-...
07/18/2014
- 11:51 PM Revision ad4a4e13 (ceph): unittest_osdmap: revert a few broken changes
- From commit 80ea6067f790b9431ae6744c38a034833e8ad4ab.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:56 PM Revision dc417e47 (ceph): rgw: list extra objects to set truncation flag correctly
- Otherwise we end up returning wrong truncated value, and no data on the
next iteration.
Signed-off-by: Yehuda Sadeh ... - 09:56 PM Revision d7209c11 (ceph): rgw: dump prefix unconditionally
- As part of issue #8858, and to be more in line with S3, dump the Prefix
field when listing bucket even if bucket is e... - 09:56 PM Revision 82d2d612 (ceph): rgw: account common prefixes for MaxKeys in bucket listing
- To be more in line with the S3 api. Beforehand we didn't account the
common prefixes towards the MaxKeys (a single co... - 09:55 PM Revision 924686f0 (ceph): rgw: add NextMarker param for bucket listing
- Partially fixes #8858.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:40 PM Revision b779e5ac (ceph): Removed upgrade-sequence to avoid failures (becasue 3-firefly-upgrade i...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:12 PM CephFS Bug #8878 (Resolved): mds lock cycle (wip-objecter)
- ...
- 08:47 PM Revision 4a63396b (ceph): rgw: fix decoding + characters in URL
- Fixes: #8702
Backport: firefly
Only decode + characters to spaces if we're in a query argument. The +
query argument... - 08:18 PM Revision 02a6c917 (ceph): rados/singleton-nomsgr/all/alloc-hint: enable xfs extsize for test
- This is off by default; enable it for this test.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:18 PM Revision 09a5974f (ceph): crushtool: Send output to stdout instead of stderr
- A lot of output was send to stderr instead of stdout and vise versa.
Error messages should go to stderr, but all oth... - 06:17 PM Revision b9463e34 (ceph): Merge pull request #2115 from ceph/wip-8811
- Make standby-replay MDSes much more careful about journal formats; both changing them and generally being aware.
Rev... - 05:49 PM Revision a24efaef (ceph): Merge pull request #61 from ceph/wip-no-mds
- clusters: Remove mds from default fixed-* configs
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:45 PM Revision 49fc68cf (ceph): utf8: export encode_utf8() and decode_utf8()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:45 PM Revision e6cf618c (ceph): rgw: improve delmited listing of bucket
- If found a prefix, calculate a string greater than that so that next
request we can skip to that. This is still not t... - 05:44 PM Revision bd3367ea (ceph): osd: add config for osd_max_attr_name_len = 100
- Set a limit on the length of an attr name. The fs can only take 128
bytes, but we were not imposing any limit.
Add ... - 05:44 PM Revision 7e0aca18 (ceph): osd: add config for osd_max_object_name_len = 2048 (was hard-coded at 4...
- Previously we had a hard coded limit of 4096. Objects > 3k crash the OSD
when running on ext4, although they probabl... - 05:44 PM Revision 7c0b2a05 (ceph): os: add ObjectStore::get_max_attr_name_length()
- Most importantly, capture that attrs on FileStore can't be more than about
100 chars. The Linux xattrs can only be 1... - 05:40 PM Revision ed3bc4c3 (ceph): osdc/Journaler: validate header on load and save
- Previously if the journal header contained invalid
write, expire or trimmed offsets, we would end up
hitting a hard-t... - 05:40 PM Revision 5438500a (ceph): mds: fix journal reformat failure in standbyreplay
- In the 0.82 release, standbyreplay MDS daemons would try
to reformat the jouranl if they saw an older version on
disk... - 05:40 PM Revision 8eef89e6 (ceph): doc: fix example s/inspect/journal inspect/
- Signed-off-by: John Spray <john.spray@redhat.com>
- 05:40 PM Revision e60dd0f6 (ceph): osdc: refactor JOURNAL_FORMAT_* constants to enum
- ...so that the upper limit doesn't have to be updated
by hand.
Signed-off-by: John Spray <john.spray@redhat.com> - 05:30 PM Revision 442c3fd5 (ceph): configure: do not link leveldb with everything
- Detect leveldb, but do not let autoconf blindly link it with everything on the
planet.
Signed-off-by: Dan Mick <dan.... - 05:30 PM Revision c1073e43 (ceph): ceph.spec: move ceph-dencoder to ceph from ceph-common
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 95f5a448b52db545a2b9bbad47fdb287254f93ea) - 05:30 PM Revision f4e9e0ef (ceph): debian: move ceph-dencoder to ceph from ceph-common
- It links against the world currently (notably leveldb). Not nice for the
client-side lib.
Signed-off-by: Sage Weil ... - 05:29 PM Revision 50936661 (ceph): Merge pull request #2104 from ceph/wip-dencoder
- move ceph-dencoder to ceph from ceph-common
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 05:27 PM Revision 094db116 (ceph): Merge pull request #2114 from ceph/wip-vstart
- vstart.sh: default to 3 osds
Not-NAKed-by: John Spray <john.spray@inktank.com> - 05:18 PM Revision a06df52a (ceph): clusters: Remove mds from default fixed-* configs
- Create a separate fixed-3-cephfs cluster config for
use in the filesystem tests.
Signed-off-by: John Spray <john.spr... - 05:00 PM Revision 18ca6b60 (ceph): test: add a missing semicolon
- Broke in df8f48628.
Signed-off-by: John Spray <john.spray@redhat.com> - 04:51 PM Revision 113c3656 (ceph): Merge pull request #2119 from ceph/wip-vstart-existing-mds
- Wip vstart existing mds
Reviewed-by: Sage Weil <sage@redhat.com> - 04:15 PM Revision df8f4862 (ceph): Merge pull request #2108 from kevincox/sizeint
- Fix size of network protocol intergers.
Reviewed-by: Sage Weil <sage@redhat.com> - 03:53 PM Revision 0cd02684 (ceph): qa: generalise cephtool for vstart+MDS
- Previously this test assumed no pre-existing
filesystem and no MDS running. Generalize it
to nuke any existing files... - 03:53 PM Revision b936a276 (ceph): mon/MDSMonitor: fix msg on idempotent `fs rm`
- Was outputting trailing "unrecognised command"
because we returned 0 instead of setting r=0.
Signed-off-by: John Spr... - 03:53 PM Revision bb5a574f (ceph): mon: carry last_failure_osd_epoch across `fs new`
- So that new MDSs in a new filesystem are guaranteed
to be up to date with anything we blacklisted
from a filesystem c... - 03:34 PM rgw Bug #8858 (Fix Under Review): NextMarker, Prefix missing from bucket list results
- 02:06 PM Bug #8851: Mon crash after update to 0.80.4
- Can you upload the full log of startup with crash?
By "temporarily resolved", do you mean it's working now, or does ... - 01:37 PM rgw Bug #8702 (Pending Backport): RadosGW incorrectly converting + to space in URLs
- 11:16 AM rgw Bug #8702: RadosGW incorrectly converting + to space in URLs
- ok, I see it now.
- 10:43 AM rgw Bug #8702: RadosGW incorrectly converting + to space in URLs
- We talked about this on the mailing list. I can reproduce this at will on apache as well.
Can you take a look at ... - 10:40 AM rgw Bug #8702: RadosGW incorrectly converting + to space in URLs
- The problem seem to be with the the web server itself here that doesn't send the REQUEST_URI url encoded as it should...
- 07:27 AM rgw Bug #8702: RadosGW incorrectly converting + to space in URLs
- See https://github.com/ceph/ceph/pull/2117
- 01:28 PM CephFS Bug #8876: kcephfs: hang on read of length 0
- got debug output from a resend, but not very helpful.. i think teh bug is in the striped read code, which happened lo...
- 01:27 PM CephFS Bug #8876 (Resolved): kcephfs: hang on read of length 0
- ...
- 01:13 PM Documentation #8875 (Resolved): `ceph-deploy new` needs to be called for every node, not just the...
- Hi guys,
Running into issue adding monitors. The initial monitor gets created successfully, but get below error ad... - 12:50 PM devops Feature #8868: Update Fedora to 0.80.5 packages with ceph-common
- The ceph-common split is now in the latest firefly. There are a few other cleanups (reducing dependencies) pending i...
- 11:07 AM devops Feature #8868 (Resolved): Update Fedora to 0.80.5 packages with ceph-common
- In order to push the Ceph client packages up into RHEL 7.1, we need to have the latest packages available in Fedora a...
- 11:44 AM devops Feature #8871 (Resolved): modify ceph-deploy to only install repo file and not install packages
- As a user, I want to update my repo files but not automatically install the packages.
Proposal: Add a switch to th... - 11:14 AM CephFS Feature #8869 (Resolved): MDS: support standby-replay on old-format journals
- Right now if we see an old-format journal and we're in standby-replay, we just hang around waiting for it to be conve...
- 11:14 AM rbd Bug #8821 (Fix Under Review): rbd: ceph.conf "rbd default format" woes
- https://github.com/ceph/ceph/pull/2112
- 10:01 AM Feature #7988 (Fix Under Review): Logs: Log every administrative action taken by a user
- https://github.com/ceph/ceph/pull/2118
- 08:22 AM Bug #5195: "ceph-deploy mon create" fails when adding additional monitors
- Still having this issue with firefly, is it possible it was re-introduced>?
see SUPPORT #8861 just opened. - 07:03 AM Bug #8865 (Resolved): cep osd setmaxosd doesn't check if osds exist
- this lets you destroy whole swaths of osds. i think we should make you 'ceph osd rm ...' first
- 05:38 AM Bug #8346: OSD crashes on master (FAILED assert(ip_op.waiting_for_commit.count(from)))
- It reproduced.
Setup details:
3 osd nodes (3 osds in each node)
3 monitors
rebooted the node with osds:6,7,... - 04:44 AM Revision 06a8f7b9 (ceph): configure: do not link leveldb with everything
- Detect leveldb, but do not let autoconf blindly link it with everything on the
planet.
Signed-off-by: Dan Mick <dan.... - 04:33 AM Revision 0193d3aa (ceph): AUTHORS
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:04 AM rgw Bug #8864 (Resolved): radosgw help doesn't seem to display some debug options
- Looks like radosgw has options like `--debug-rgw` & `--log-file`, but these don't seem to appear in the help or docum...
07/17/2014
- 11:48 PM Revision 681c399e (ceph): logrotate.conf: fix osd log rotation under upstart
- In commit 7411c3c6a42bef5987bdd76b1812b01686303502 we generalized this
enumeration code by copying what was in the up... - 11:46 PM Revision b3eebec5 (ceph): Merge pull request #2116 from ceph/wip-logrotate
- logrotate.conf: fix osd log rotation
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 11:40 PM Revision 14a9ca60 (ceph): logrotate.conf: fix osd log rotation under upstart
- In commit 7411c3c6a42bef5987bdd76b1812b01686303502 we generalized this
enumeration code by copying what was in the up... - 11:39 PM Revision b140ce9e (ceph): Re-enabled rgw tests, #8846 should be fixed now
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 11:08 PM Revision 794ec7fb (ceph): rgw: don't try to wait for pending if list is empty
- Fixes: #8846
Backport: firefly, dumpling
This was broken at ea68b9372319fd0bab40856db26528d36359102e. We ended
up ca... - 10:39 PM Revision eba43a9a (ceph): Fixed prints
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:21 PM Revision cbe9ee2c (ceph): Added prints
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:05 PM Revision c1896d56 (ceph): Fixed missed line
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:00 PM Revision be0330c5 (ceph): Removed 'firefly' branch name, upgrade step will be set to 'next' or '...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 08:56 PM Revision 7b342ef0 (ceph): doc: Add Note about European mirror in Quick Start
- 08:20 PM Bug #8863 (Resolved): osd: second reservation rejection -> crash
- I found bug#7624 resolved this problem?http://tracker.ceph.com/issues/7642? and the source code of OSDMonitor in 0.80...
- 08:05 PM Revision e75dd2e4 (ceph): remove suse service restarts
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 0f11aaeefd7e8b49f88607937aade6113eb... - 08:05 PM Revision 361c1f85 (ceph): remove ceph restarts on upgrades for RPMs
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit e3a5756f58ef5d07badf18ab08a26f47f7d... - 07:30 PM Revision 2c4f22fa (ceph): Merge pull request #2109 from ceph/wip-8849
- remove ceph restarts on upgrades for RPMs
Backport: firefly
Reviewed-by: Sage Weil <sage@redhat.com> - 07:09 PM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- Sage Weil wrote:
> Ok, it installs dumpling, upgrades to v0.80.1, then runs radosgw. Is there a way to work around ... - 04:45 PM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- Ok, it installs dumpling, upgrades to v0.80.1, then runs radosgw. Is there a way to work around thsi bug (which is i...
- 09:11 AM rgw Bug #8311 (New): No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testi...
- Marking as "new" as still see this problem in http://pulpito.front.sepia.ceph.com/teuthology-2014-07-16_19:12:01-upgr...
- 07:06 PM Revision 0f11aaee (ceph): remove suse service restarts
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 07:03 PM Revision e3a5756f (ceph): remove ceph restarts on upgrades for RPMs
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 06:30 PM Revision 04f040ad (ceph): Again fixed identations
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 05:52 PM Revision 2a82fd6a (ceph): Fixed indentation
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 05:14 PM Revision 4d6899c7 (ceph): qa/workunits/cephtool/test.sh: fix erasure_code_profile get test
- I broke this in ce9f12d7a2202948532fed9da4d763ed03f6b8fa (the pool isn't
type erasure).
Signed-off-by: Sage Weil <sa... - 04:49 PM Bug #8701 (In Progress): osd: scrub found obsolete rollback obj
- 04:39 PM rgw Bug #8846 (Pending Backport): radosgw on 0.80.4 crashes when doing a multi-part upload
- oops, we still need to do dumpling
- 04:32 PM rgw Bug #8846 (Resolved): radosgw on 0.80.4 crashes when doing a multi-part upload
- 03:28 PM Revision 2679a024 (ceph): Added print tasks
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:03 PM Bug #8835: rados mkpool doesn't error out for pools which are existing
- Hmm. That's probably fine, assuming it's wired up correctly (e.g., doesn't get blocked if the osdmap is up to date). ...
- 01:22 PM rbd Bug #8821: rbd: ceph.conf "rbd default format" woes
- Now works as expected; thanks, Josh.
- 01:20 PM Revision fe8c04f4 (ceph): Merge pull request #2113 from ceph/wip-8857
- mon/MDSMonitor: make legacy 'newfs' command idempotent
Reviewed-by: John Spray <john.spray@redhat.com> - 01:13 PM devops Support #8861 (Rejected): Deploying additional monitors fails.
- Hi GUys,
Pretty new to Ceph, need help in troubleshooting install.
Using Ubuntu 14.04 and Ceph firefly.
When ru... - 12:28 PM devops Bug #8849 (Pending Backport): rpm restarts daemons on upgrade
- 11:26 AM Bug #8860 (Resolved): ceph-disk issues with custom cluster name
- ceph-disk and the init script in some places ignores the custom cluster name...
- 08:24 AM Bug #8851: Mon crash after update to 0.80.4
- it can be temporarily resolved by this command?
-------------------------------------------------
ceph-kvstore-tool... - 07:10 AM rbd Bug #8859 (Closed): krbd crash while serving linux-lio iscsi: rbd_assert(img_request != NULL);
- We have Linux-HA configuring a pair of nodes to make highly-available iSCSI targets with Linux-LIO, and so it maps th...
- 06:23 AM CephFS Bug #8811: Journal corruption during upgrade to 0.82 with standby-replay daemons
- https://github.com/ceph/ceph/pull/2115
- 06:21 AM CephFS Bug #8811 (Fix Under Review): Journal corruption during upgrade to 0.82 with standby-replay daemons
- 06:20 AM Bug #8857 (Resolved): mon: mds newfs command is not idempotent
- Looks good to me. We may get questions from anyone who relied on the old behaviour of newfs to 'reset' a filesystem,...
- 04:49 AM rgw Bug #7796: RGW Keystone token auth fails with '411 Length Required' when Keystone using Apache/WSGI
- I also ran into this while trying to set up a test cluster. Never could figure out what went wrong until I finally st...
- 04:41 AM Bug #8801: Ceph monitors do not start after server restart
- We were able to reproduce the issue with the monitors by restarting the physical server. The Ceph configuration had d...
- 12:55 AM Revision ce9f12d7 (ceph): qa/workunits/cephtool/test.sh: test osd pool get erasure_code_profile
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:49 AM Revision e8ebcb79 (ceph): mon: OSDMonitor: add "osd pool get <pool> erasure_code_profile" command
- Enable us to obtain the erasure-code-profile for a given erasure-pool.
Signed-off-by: Ma Jianpeng <jianpeng.ma@intel... - 12:46 AM Revision 5ccfd37b (ceph): vstart.sh: default to 3 osds
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:34 AM Revision 7c0f1d8d (ceph): Commented out rgw tests
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 12:24 AM Revision 5f6b11a6 (ceph): mon/MDSMonitor: make legacy 'newfs' command idempotent
- We need to return success if we get a dup command. Simply check whether
the fs is already enabled with the same pool... - 12:03 AM Revision 53556815 (ceph): Disabled rwg tests for now to wait for fix for radosgw crash #8846
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
07/16/2014
- 10:28 PM Revision bf252c8d (ceph): Merge remote-tracking branch 'gh/next'
- 10:27 PM Revision b89ab5f7 (ceph): rgw: don't try to wait for pending if list is empty
- Fixes: #8846
Backport: firefly, dumpling
This was broken at ea68b9372319fd0bab40856db26528d36359102e. We ended
up ca... - 10:17 PM Revision 512c7aad (ceph): Merge pull request #2110 from ceph/wip-8846
- rgw: don't try to wait for pending if list is empty
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:58 PM Revision ba7ad44f (ceph): Merge pull request #2095 from onlyjob/rbdmap
- rbdmap: per-device post-map/pre-unmap hooks
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 09:34 PM Revision 19e68ac5 (ceph): rbd: respect rbd_default_* parameters
- Treat rbd_default_{format,order,stripe_unit,stripe_count} as defaults for
the usual arguments for specifying those pr... - 09:34 PM Revision 0f87c553 (ceph): librbd: use order-agnostic default stripe parameters
- This way the default striping style of splitting into
object-sized chunks still works with non-default orders
specifi... - 09:34 PM Revision e891a937 (ceph): rbd: remove accidental repeated option
- --stripe-count is already parsed above this
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 09:19 PM Revision 9588af31 (ceph): rgw: set data extra pool correctly
- When configuring multiregion zone, set the data extra pool
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry ... - 09:10 PM Revision 1bf07724 (ceph): Merge pull request #2107 from ceph/wip-set_layout
- Wip set layout
Reviewed-by: Greg Farnum <greg@inktank.com> - 08:57 PM Bug #8835: rados mkpool doesn't error out for pools which are existing
- Greg, the check is actually present in Objecter::create_pool() which is not hit(may be due to a stale osdmap?). I hav...
- 10:41 AM Bug #8835: rados mkpool doesn't error out for pools which are existing
- This is basically intended behavior; under some circumstances the message to the monitors can get "replayed" and ther...
- 03:35 AM Bug #8835: rados mkpool doesn't error out for pools which are existing
- Have a fix in place, would be sending out a pull request soon.
- 08:33 PM Revision f9f2417d (ceph): rgw: don't try to wait for pending if list is empty
- Fixes: #8846
Backport: firefly, dumpling
This was broken at ea68b9372319fd0bab40856db26528d36359102e. We ended
up ca... - 07:48 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- looks like a ABBA deadlock between ceph_connection->mutex and ceph_osd_client->request_mutex....
- 04:34 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- The problem is also very repeatable at our site as well. Attached is the kern.log file after running the requested c...
- 11:52 AM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Hi Zheng,
No problem, in our setup it's pretty easy to reproduce the error.
Please find the output attached. (... - 07:19 PM Revision 88f694dc (ceph): set the default log level to WARNING
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 420f0a471a31d1e56359ea642ed831e8a38... - 07:18 PM Revision 83477235 (ceph): Merge pull request #2106 from ceph/wip-8813
- eat up the level from logging output when not using the `-v` flag
Reviewed-by: Sage Weil <sage@redhat.com> - 06:15 PM Revision 7fb0f644 (ceph): Replace branch dumpling with firefly to fix capitalization issue 2048k ...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 06:11 PM rgw Bug #8858 (Resolved): NextMarker, Prefix missing from bucket list results
- S3 returns these when listing buckets; RGW does not. This breaks clients like GoodSync.
The NextMarker parameter ... - 06:07 PM Revision b8c443b4 (ceph): Fix get_hash() arg ordering
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:48 PM Revision 4b13caf5 (ceph): Use new git mirror for qemu-iotests
- Fixes: 8191
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cherry picked from commit ddf37d903f826f3e153d8009c... - 05:48 PM Revision 3f251024 (ceph): Support latest qemu iotest code
- Modified qemu-iotests workunit script to check for versions
that use the latest qemu (currently only Trusty). Limit ... - 05:43 PM Revision d0613784 (ceph): librbd: skip zeroes when copying an image
- This is the simple coarse-grained solution, but it works well in
common cases like a small base image resized with a ... - 05:23 PM Bug #8857 (Fix Under Review): mon: mds newfs command is not idempotent
- 05:14 PM Bug #8857 (Resolved): mon: mds newfs command is not idempotent
- ...
- 04:44 PM CephFS Bug #8811 (In Progress): Journal corruption during upgrade to 0.82 with standby-replay daemons
- This may be the result of a bug in the journal reformatting that occurs during upgrade, affecting systems using stand...
- 04:18 PM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- Even with the default chunk size, this can be triggered by performing a multipart upload consisting of a single small...
- 02:07 PM rgw Bug #8846 (Fix Under Review): radosgw on 0.80.4 crashes when doing a multi-part upload
- 09:42 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- Oh yes, I've raised it to 5M to avoid having each part of a multi-part generate 2 objects in rados.
- 09:40 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- Are you by any chance using a non-default chunk size?
- 08:11 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- Yes, it happens since ea68b9372319fd0bab40856db26528d36359102e as I reported on the ML. (and now realize I forgot to ...
- 08:08 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- Did that happen before (e.g., 0.80.3)? can you add:
debug ms = 1
debug rgw = 20
- 07:06 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- For more info, I'm doing a multipart upload and it crashes at the last part of the file. Two first part are 5M and th...
- 05:36 AM rgw Bug #8846: radosgw on 0.80.4 crashes when doing a multi-part upload
- ...
- 05:31 AM rgw Bug #8846 (Resolved): radosgw on 0.80.4 crashes when doing a multi-part upload
This is the tracelog (from a self compiled version since I started debugging this myself. However same exact issue ...- 03:25 PM rgw Bug #8632 (Need More Info): rgw: bucket listing with delimiter doesn't scale well
- 03:11 PM Revision 420f0a47 (ceph): set the default log level to WARNING
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:20 PM Bug #8174 (Fix Under Review): rados put of a long object name crashes the OSD process
- 02:17 PM Bug #8701: osd: scrub found obsolete rollback obj
- This is going to require some thought.
The basic problem is that because of filename length limitations, for long ... - 01:46 PM Bug #8852 (Need More Info): submodules not cecking out the right branch, jerasure does not compile
- Could you please add the log of the commands and their output ? It works for me on the current master:...
- 10:53 AM Bug #8852 (Won't Fix): submodules not cecking out the right branch, jerasure does not compile
- I noticed that after doing a "./do_autogen.sh" the compilation process breaks saying that "galois_init_default_field"...
- 01:33 PM devops Bug #8849 (Fix Under Review): rpm restarts daemons on upgrade
- Pull request opened https://github.com/ceph/ceph/pull/2109
- 12:39 PM devops Bug #8849 (In Progress): rpm restarts daemons on upgrade
- Greg: that might be Suse, as we are specifically looking for it for certain restart-related things in the Spec file. ...
- 10:14 AM devops Bug #8849: rpm restarts daemons on upgrade
- I'm all for changing this, but we want to be careful when doing so. It sounds familiar to me and I think maybe we set...
- 09:25 AM devops Bug #8849 (Resolved): rpm restarts daemons on upgrade
- 01:30 PM CephFS Bug #8177 (Resolved): Client: seg fault in verify_reply_trace on traceless reply
- I believe the fix that actually went into master is commit:334c43f54d31131c4970f43d7e43ebb43e6cd22d.
- 12:59 PM CephFS Bug #8576: teuthology: nfs tests failing on umount
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-09_23:10:02-knfs-next-testing-basic-plana/353010/
http://qa-p... - 12:34 PM Documentation #8854 (Closed): Clarify potential problems from ceph-deploy purgedata command when ...
- When running the ceph-deploy purgedata command on a storage node the command will end up making later installations a...
- 12:17 PM devops Bug #8813 (Resolved): ceph-disk list displays INFO messages rendering output hard to read
- in master, backported to firefly
- 10:50 AM rbd Bug #8821 (In Progress): rbd: ceph.conf "rbd default format" woes
- 09:59 AM Bug #8851 (Resolved): Mon crash after update to 0.80.4
- When I updated mon from 0.80.3 to 0.80.4, restart it then crashed
--------------------------------------------------... - 09:41 AM devops Bug #8850 (Can't reproduce): ceph-deploy tests fail during tar due to file changed; incomplete sh...
- ubuntu@teuthology:/a/teuthology-2014-07-15_19:08:01-ceph-deploy-dumpling-testing-basic-plana/363933
and others.
<... - 09:27 AM devops Bug #7391 (Resolved): ceph-deploy should pass the verbose flag to ceph-disk
- merged commit 7b0056b into ceph:master
- 06:39 AM devops Bug #7391 (Fix Under Review): ceph-deploy should pass the verbose flag to ceph-disk
- Pull request opened https://github.com/ceph/ceph-deploy/pull/216
- 08:42 AM rgw Bug #8848 (Resolved): "adjust-ulimits: command not found" in upgrade:firefly-firefly-testing-basi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-15_19:12:01-upgrade:firefly-firefly-testing-basic-...
- 08:22 AM rgw Bug #8847 (Can't reproduce): "Error initializing cluster client" in upgrade:firefly-firefly-testi...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-15_19:12:01-upgrade:firefly-firefly-testing-basic-...
- 05:23 AM Bug #8797: "ceph status" do not exit with python_2.7.8
- I believe that we should attempt to replicate the problem first as I know the Python ticket will get ignored unless t...
- 05:08 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- Some possibly related feedback from running master (aeaac69) on Fedora 20:
* Mons don't come up because they're tr... - 04:18 AM rbd Bug #8845 (Resolved): Flattening Clones of clone, results in command failure
- 1. Created clone of clone in below manner
Create a Pool i.e. pool1
create a rbd i.e.rbd1
create ... - 01:14 AM Revision 67b5193f (ceph): init-ceph: wrap daemon startup with systemd-run when running under systemd
- We want to make sure the daemon runs in its own systemd environment. Check
for systemd as pid 1 and, when present, u... - 01:11 AM Revision 3e0d9800 (ceph): init-ceph: wrap daemon startup with systemd-run when running under systemd
- We want to make sure the daemon runs in its own systemd environment. Check
for systemd as pid 1 and, when present, u...
07/15/2014
- 11:32 PM Revision 99dfaf7d (ceph): doc/release-notes: v0.80.4
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:32 PM Revision 911038ec (ceph): Merge pull request #2101 from ceph/wip-mds-session-asok-squash
- Provide client session handling and information via the admin socket.
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:27 PM Revision fccc6adb (ceph): Merge pull request #287 from ceph/wip-mds-sessions
- Wip mds sessions
- 10:22 PM Revision 443b782d (ceph): Merge pull request #288 from ceph/wip-upgrade-fix
- task/ceph: Make cephfs_setup cuttlefish-compatible
- 09:57 PM Revision d5a4998b (ceph): Merge pull request #291 from ceph/wip-rgw-pools
- rgw: set data extra pool correctly
Backport: next, firefly
Reviewed-by: Sage Weil <sage@redhat.com> - 09:32 PM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- I still see it on firefly;
http://pulpito.front.sepia.ceph.com/ubuntu-2014-07-15_21:01:54-upgrade:firefly-firefly-te... - 12:52 PM rgw Bug #8311 (Resolved): No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-...
- should be fixed now
- 09:07 PM Bug #8769 (Rejected): osd.3 crashed in upgrade:dumpling-x:stress-split-firefly---basic-multi suite
- not much to go on without the osd log; let's wait for it to reproduce.
- 08:56 PM Revision 80ea6067 (ceph): Fix size of network protocol intergers.
- This fixes the size of some integers that are visible in the network
protocol. There should be no change for machine... - 08:42 PM Revision 2f43cef0 (ceph): doc: Extended discussion for building docs on CentOS / RHEL.
- Fixes: #7722
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 08:40 PM Revision 124f97f2 (ceph): doc: Added a script to build docs on CentOS / RHEL.
- Fixes: #7722
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 08:02 PM Revision 63fb271b (ceph): rgw: set data extra pool correctly
- When configuring multiregion zone, set the data extra pool
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:35 PM Linux kernel client Bug #8798 (Won't Fix): The kernel of a server with Ceph hangs
- 07:30 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- when this happens again, execute 'echo t > /proc/sysrq-trigger' and upload the kernel message.
By the way, are the... - 07:23 PM Linux kernel client Bug #8818: IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- Hi,
We are experimenting exactly the same problem when running several concurrent dd operations to a kernel mounte... - 07:13 PM Revision 7c241cfa (ceph): 0.80.4
- 06:34 PM Revision 32bffa5a (ceph): Added client.0 upgrade step
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 06:22 PM Revision 2aea9deb (ceph): Commented out test.sh as failed tests: LibRadosMisc.Operate1PP can't wo...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 06:11 PM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- i think we fixed this by doing systemd-run from teh init script...
- 06:02 PM Revision 79da400d (ceph): Fix a bug where results_email was being ignored
- Referring to the setting in ~/.teuthology.yaml
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:02 PM Revision 7262effc (ceph): Merge pull request #290 from ceph/wip-deep-scrub
- task/ceph.py: deep-scrub instead of scrub
- 06:02 PM Revision 29c06f00 (ceph): Add and use new fetch() method
- The old fetch_branch() wasn't behaving properly with the ceph.com git
mirror. This method works with github.com and c... - 06:00 PM Bug #8752: firefly: scrub/repair stat mismatch
- Samuel Just wrote:
> Just fyi, this is a relatively harmless stat counting error. It shouldn't cause corruption.
... - 01:23 PM Bug #8752: firefly: scrub/repair stat mismatch
- Just fyi, this is a relatively harmless stat counting error. It shouldn't cause corruption. Not that I know how to ...
- 05:18 AM Bug #8752: firefly: scrub/repair stat mismatch
- If #8830 affect only XFS-based OSDs it is definitely not my case. All my OSDs are on Btrfs...
Objects from affected ... - 05:29 PM Feature #8844 (Resolved): asserts to log message to ceph log
- There are number of outstanding issues with stability of Ceph components: for example it is not unusual for OSDs to g...
- 05:28 PM Revision 26c49ec2 (ceph): task/ceph.py: deep-scrub instead of scrub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:09 PM RADOS Feature #8843 (New): ceph pg {deep-}scrub 20.\*
- Similar to command ...
- 05:08 PM Bug #7804 (Duplicate): backfill racing with a hitset object remove
- This looks like a dup of #7983, where we already fix backfill vs hit_set issues by deferring any hit_set_persist or t...
- 05:08 PM Revision 36441a27 (ceph): README: teuthology-suite
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:33 PM Revision cc754bae (ceph): Enabled tunables
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:10 PM Linux kernel client Feature #8842: CephFS kernel module for RHEL7.0 GA
- The kernel modules are available in the firefly rhel7 as well as rpm-testing.
Getting cephfs working is not someth... - 04:01 PM Linux kernel client Feature #8842 (Resolved): CephFS kernel module for RHEL7.0 GA
- Looks like we only have the libceph and RBD kernel modules for RHEL 7.0 GA at rpm-testing/rhel7.
We need to have ... - 04:10 PM Revision c8421651 (ceph): Changed restart order, mds after osd
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:31 PM CephFS Feature #8634 (Resolved): mds: admin commands list, evict, etc session
- commit:911038ecdbad5c19bd20ac0bd5a03dae53aa3175
- 03:30 PM Bug #8701: osd: scrub found obsolete rollback obj
- wip-8701 adds a test to store_test which reproduces the problem. The issue appears to be with collection_move_rename...
- 02:30 PM Bug #8701: osd: scrub found obsolete rollback obj
- Now I wonder whether it's the long object name.
- 02:23 PM Bug #8701: osd: scrub found obsolete rollback obj
- Actually, I appear to have already correctly handled the thing I mentioned above. Must be something else.
- 12:14 PM Bug #8701: osd: scrub found obsolete rollback obj
- more of these in the latest rgw master run...
/var/lib/teuthworker/archive/teuthology-2014-07-14_23:02:01-rgw-mast... - 02:21 PM devops Bug #6703 (Resolved): OSDs with dmcrypt fail to start at boot
- Merged into Ceph master branch with hash 31eefeb
- 02:12 PM devops Bug #7486 (Rejected): python-backports needs fixing for rhel
- 02:10 PM devops Bug #8513 (Can't reproduce): s3tests failed at bootstrap in the nightlies
- 02:08 PM devops Bug #8788 (Resolved): Rhel 7 ceph=deploy v1.5.7 for firefly fails to retrieve correct package - i...
- 02:04 PM devops Bug #8374 (Won't Fix): redhat-lsb is not recognized as a dependency in FC19
- 01:50 PM Bug #8588: In the erasure-coded pool, primary OSD will crash at decoding if any data chunk's size...
- Yeah, this needs to be handled better. The biggest problem is that the crash is on the primary rather than the repli...
- 01:44 PM Bug #8777: osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- this happened 3x on my wip-msgr run, too: ubuntu@teuthology:/a/sage-2014-07-12_17:17:39-rados:thrash-wip-msgr-testing...
- 01:41 PM Bug #8726: (firefly command on dumpling issue?) Error "'adjust-ulimits ceph-coverage /home/ubuntu...
- the thrashosds needs the primary-affinity: false (i think? check that syntax) in the yaml
- 01:41 PM Bug #8801: Ceph monitors do not start after server restart
- Can you provide logs for the monitor that doesn't start? Ideally with 'debug mon = 10'.
- 01:39 PM Linux kernel client Bug #8806: libceph: must use new tid when watch is resent
- 01:37 PM CephFS Bug #8834 (Rejected): ceph client hang when copy files
- 12:43 AM CephFS Bug #8834: ceph client hang when copy files
- looks like the readdir memory allocation fail bug. It should be fixed in 3.14
- 12:26 AM CephFS Bug #8834: ceph client hang when copy files
- the client was running on ubuntu 14.04
Linux tc-host-2 3.13.0-24-generic #46-Ubuntu SMP Thu Apr 10 19:11:08 UTC 2014... - 12:23 AM CephFS Bug #8834 (Rejected): ceph client hang when copy files
- ceph client hang when copy files
I'm not familiar with Ceph, hope the attached syslog would give you some hints. - 01:37 PM Bug #8747: OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.start || s...
- Yeah, 8011 seems to be less dead then we thought, reopening.
- 01:36 PM Bug #8747 (Duplicate): OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubbe...
- see #8011
- 05:27 AM Bug #8747: OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.start || s...
- Although it takes up to an hour to reproduce I seems to have a reliable way to do so.
I shall be happy to capture de... - 01:36 PM Bug #8011: osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || soid >= scrubber.end)
- see #8747 for a log of this happening on 0.80.3
- 01:34 PM Bug #8646 (Resolved): OSD: assert in share_map() when marked down by an OSDMap
- 01:33 PM Bug #8714: we do not block old clients from breaking cache pools
- how about we return EPERM or EOPNOTSUPP on osd ops from clients w/o the caching features?
- 01:31 PM Bug #8642 (Duplicate): After Upgrade from Emperor to Firefly osd start (seemingly randomly) crashing
- dup of #8738, now fixed
- 01:29 PM Bug #8584 (Duplicate): OSD Crashing on firefly - Timeouts on starting again
- this look slike it was #8738
- 01:28 PM Revision 6c48d076 (ceph): doc: add cephfs layout documentation
- This clarifies how to deal with layouts in CephFS
using vxattrs. We can point people here if they
ask what they shou... - 01:26 PM Bug #8694: OSD crashed (assertion failure) at FileStore::_collection_move_rename
- This is probably a dup of 8733.
- 01:20 PM Bug #8691: osd: PG::_lock, OSD::pg_map_lock lock cycle
- 01:19 PM Bug #8643 (Closed): 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == ...
- 01:18 PM Bug #8532 (Need More Info): 0.80.1: OSD crash (domino effect), same as BUG #8229
- 01:12 PM Feature #7288 (Resolved): Deep-scrub throttle
- everything but the idea that the scrub timing could be randomized has been implemented. the prioritization will get ...
- 01:11 PM Feature #8580: Decrease disk thread's IO priority and/or make it configurable
- oh, we did backport the io priority
- 01:10 PM Feature #8580 (Resolved): Decrease disk thread's IO priority and/or make it configurable
- would rather not backport the ioprio stuff to dumpling. the sleep is there.
- 12:35 PM Bug #8830 (Resolved): deep scrub mismatches on rbd workload with alloc hints
- 12:30 PM Revision d91f028e (ceph): task: refactor kclient into KernelMount
- Additionally make both kclient and ceph_fuse
tasks yield a collection of CephFSMount
objects so that subsequent tasks... - 12:30 PM Revision 91e56bb9 (ceph): task/mds_journal_migration: only mount my client
- Pass explicit client ID list to ceph_fuse context so
that it doesn't try to mount all clients in the config,
in case ... - 12:30 PM Revision 8bb77ed9 (ceph): task: add mds_client_recovery
- This task exercises the CephFS session recovery
behavior.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:30 PM Revision 785a272b (ceph): task: fix admin_socket for non-int ids
- This was working for OSDs and for my config
where MDS happened to have numeric ID, but
in general service IDs are str... - 12:30 PM Revision 403ba2c8 (ceph): task/cephfs: use dedent for embedded python
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:30 PM Revision 9c8dd98a (ceph): task/kclient: remove redundant double loop
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:30 PM Revision 6cba4973 (ceph): task: create FuseMount class from ceph_fuse
- This is for use by other tasks that need filesystem
mounts under their own control.
Signed-off-by: John Spray <john.... - 12:20 PM Bug #8797: "ceph status" do not exit with python_2.7.8
- Fascinating info so far, Dmitry, thanks for your work on this. Anxious to see what the Python team thinks of the ass...
- 02:40 AM Bug #8797: "ceph status" do not exit with python_2.7.8
- http://bugs.python.org/issue21963
- 11:59 AM Revision d81d77dc (ceph): kclient: remove `kclient` workunit
- This only contained the file_layout.sh workunit, which
is going away.
Fixes: #8773
Signed-off-by: John Spray <john.... - 11:45 AM Revision af740ecd (ceph): cephfs: pool safety & print deprecation warning
- Print a message indicating to users that this tool
is now deprecated in favour of vxattrs.
Signed-off-by: John Spray... - 11:44 AM Revision d915ceb0 (ceph): update hadoop-wordcount test to be able to run on hadoop 2.x. The hadoo...
- A sample command to run the test on hadoop 2.x is
TESTDIR=/home/test HADOOP_HOME=/usr/lib/hadoop HADOOP_MR_HOME=/usr/... - 11:23 AM Revision cceab2b7 (ceph): qa: retire kclient-specific layout test
- `cephfs set_layout` was broken and is now deprecated
in favour of using xattrs for layout. Retire the
kclient-specif... - 11:04 AM devops Bug #7391: ceph-deploy should pass the verbose flag to ceph-disk
Example output with the changeset...- 09:36 AM devops Bug #8813: ceph-disk list displays INFO messages rendering output hard to read
- Started work on #7391 to address this from ceph-deploy's end.
- 06:16 AM devops Bug #8813 (Fix Under Review): ceph-disk list displays INFO messages rendering output hard to read
- PR opened https://github.com/ceph/ceph/pull/2106
- 08:46 AM devops Bug #8831 (Duplicate): ice1.2 on precise:ceph-deploy purge reports error
- Closing as duplicate of #8730
Was resolved in ceph-deploy 1.5.9 - 07:14 AM CephFS Feature #4583 (In Progress): libcephfs: add test that kills a client and verifies mds cleans it up
- 07:11 AM CephFS Bug #8257 (Resolved): 0.80~rc1: MDS segmentation fault
- ...
- 07:03 AM CephFS Bug #8118 (Closed): MDS crashes
- This got a non-zero response from the OSD while writing out a directory. That's generally not an MDS bug, and if it w...
- 06:55 AM CephFS Bug #6609 (Can't reproduce): teuthology rsync workunit failure
- 06:52 AM CephFS Bug #7613 (Need More Info): mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- 05:08 AM Bug #8835 (Resolved): rados mkpool doesn't error out for pools which are existing
- 'rados mkpool' doesn't seem to throw an error, for pools that are already existing.
<snip>
root#: rados mkpool ... - 12:02 AM Revision 95f5a448 (ceph): ceph.spec: move ceph-dencoder to ceph from ceph-common
- Signed-off-by: Sage Weil <sage@redhat.com>
- 12:00 AM Revision b37e3bde (ceph): debian: move ceph-dencoder to ceph from ceph-common
- It links against the world currently (notably leveldb). Not nice for the
client-side lib.
Signed-off-by: Sage Weil ...
07/14/2014
- 10:41 PM Revision aeaac69f (ceph): Merge pull request #2098 from ceph/wip-dump-new-crush
- crush: include CRUSH_V3, v2/v3 rules checks in dump_tunables()
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:39 PM Revision 7557a813 (ceph): XfsFileStoreBackend: default to disabling extsize on xfs
- This appears to be responsible for the deep scrub mismatches on some rbd
workloads.
Fixes: 8830
Signed-off-by: Samue... - 10:38 PM Revision ce72a3b5 (ceph): Merge pull request #2103 from ceph/wip-8830
- XfsFileStoreBackend: default to disabling extsize on xfs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:00 PM Revision 7a1f589a (ceph): Trying without tunables again
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:00 PM Revision ee7016a0 (ceph): Revert "Revert "rgw: if extra data pool name is empty, use data pool na...
- This reverts commit 0b6bd2545925b5e8a80d41de1fda13ffe9d30e2b.
We confused commit 5fd8b0d1639c67e355f0fc0d7e6d7036618... - 09:55 PM Revision 01cd3cdc (ceph): XfsFileStoreBackend: default to disabling extsize on xfs
- This appears to be responsible for the deep scrub mismatches on some rbd
workloads.
Fixes: 8830
Signed-off-by: Samue... - 09:43 PM Revision 0ee2d545 (ceph): Merge pull request #46 from ceph/wip-max-backfills
- rados/thrash: set osd_max_backfill = 1 sometimes
- 09:37 PM Revision aa5d4d31 (ceph): Merge pull request #58 from ceph/wip_add_v0.80.3
- Added v0.80.3 to the mix
- 09:35 PM Revision 69b2eba6 (ceph): Removed whitelist lines since it's not needed for version v0.80.3
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:27 PM Revision 0f367cee (ceph): Added v0.80.3 to the mix
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:16 PM Revision 657bd369 (ceph): Fix the incomplete substitute_placeholders() fix
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:48 PM Revision f557ac5f (ceph): Add a debug statement to reset_repo()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:30 PM Revision 56ad9575 (ceph): Be smarter about choosing branches
- Part of this is also about failing sooner, and not allowing invalid
configurations to enter the queue. This commit al... - 05:46 PM Revision fa42928d (ceph): Changed restart sequence
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 05:43 PM Revision a560519c (ceph): Merge pull request #2102 from ceph/wip-8823
- ceph_test_rados_api_tier: fix [EC] HitSet{Read,Write,Trim} tests
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:32 PM Revision 51a01c0d (ceph): Try diff restart
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:23 PM Revision a1b15674 (ceph): Merge pull request #2097 from sjahl/master
- doc: Fixes a broken link on the rados deploy osd page.
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 04:14 PM Revision fc597e5e (ceph): doc/release-notes: some additional warnings and recommendations against...
- Several users are having troubles related to the overhead of the data
rebalance from adjusting tunables.
Signed-off-... - 04:04 PM devops Bug #8831 (Duplicate): ice1.2 on precise:ceph-deploy purge reports error
- ...
- 03:41 PM Bug #8752: firefly: scrub/repair stat mismatch
- This appears unrelated to 8830. Probably a stat miscounting bug somewhere in the cache/tiering code.
- 03:40 PM Bug #8752 (New): firefly: scrub/repair stat mismatch
- Actually, maybe not. The naive interpretation doesn't have #8830 causing differences in file sizes...but maybe it cou...
- 03:19 PM Bug #8752 (Duplicate): firefly: scrub/repair stat mismatch
- almost certainly a dup of #8830. fix will hit the firefly branch shortly!
- 03:16 PM Bug #8752: firefly: scrub/repair stat mismatch
- No improvement with 0.80.3. I'm getting ~20 inconsistent PGs after every cycle of full "deep-scrub" (i.e. `ceph osd d...
- 03:37 PM Revision 6c05747d (ceph): task: move Filesystem class to shared location
- ...in preparation for tests other than mds_journal_migration
to use it.
Signed-off-by: John Spray <john.spray@redhat... - 03:35 PM Revision 47087ff7 (ceph): Fall back to master for suite_branch
- The reason for this is that last-in-suite jobs don't have suite_branch
or branch set. We just want to use master for ... - 03:24 PM Revision 18a3a09a (ceph): Added back tunables
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 03:08 PM Bug #8815 (Resolved): mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2
- 03:07 PM Bug #8747: OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.start || s...
- No improvement with 0.80.3 -- I'm still getting those crashes frequently on "deep-scrub" and "repair".
Sometimes two... - 03:04 PM Revision e17e9d85 (ceph): ceph_test_rados_api_tier: fix [EC] HitSet{Read,Write,Trim} tests
- The hit_set_ fields can only be set on tier pools as of
f131dfbaedf6f451572e7aa3a83f653912122953.
Fixes: #8823
Signe... - 01:28 PM Bug #8830 (Resolved): deep scrub mismatches on rbd workload with alloc hints
- 01:15 PM Revision a4ed3366 (ceph): mds: add `session ls` and `session evict` to asok
- These commands are intended to help admins deal
with MDSs during recovery, to identify troublesome
clients which may ... - 01:12 PM Revision b120a488 (ceph): common/admin_socket: remove dead code
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:12 PM Revision 52a2bc5f (ceph): mon: remove unused attribute notified_global_id
- Signed-off-by: John Spray <john.spray@redhat.com>
- 01:12 PM Revision 0e0be07f (ceph): client: include ID in mds_sessions asok
- So that an admin can map a ceph-fuse process
reliably to an entry in the MDS session list.
Signed-off-by: John Spray... - 12:33 PM devops Bug #8813 (In Progress): ceph-disk list displays INFO messages rendering output hard to read
- 12:09 PM rgw Bug #8702: RadosGW incorrectly converting + to space in URLs
- Looks like this is ultimately caused by line 1227 in rgw_rest.cc...
- 10:41 AM Bug #8823 (Resolved): Failing LibRadosTierPP.HitSetRead,Write,Trim
- 09:36 AM Support #8826 (Rejected): Attempt to set PG_NUM and PGP_NUM to 8192 on pool rbd causes OSDs to go...
- Based on other analysis in the private ticket, it looks like it's just hitting the fd limit; I think that's well-docu...
- 07:51 AM Support #8826 (Rejected): Attempt to set PG_NUM and PGP_NUM to 8192 on pool rbd causes OSDs to go...
- The customer is willing to modify pool rbd for its production usage but doing so generates an error message when issu...
- 05:30 AM CephFS Bug #8811: Journal corruption during upgrade to 0.82 with standby-replay daemons
- Hmmm. Aside from is_readable() giving inconsistent results, seems like this could happen if there was a bug that cau...
- 05:19 AM Revision bb47ff34 (ceph): osd: fix confusing debug output for op_applied
- Signed-off-by: Sage Weil <sage@inktank.com>
07/13/2014
- 10:19 PM Bug #8824 (Can't reproduce): osd: hung MOSDECSubOpWrite
- ubuntu@teuthology:/a/teuthology-2014-07-13_02:30:04-rados-next-testing-basic-plana/357668
see osd.2's log... - 08:52 PM Bug #8823: Failing LibRadosTierPP.HitSetRead,Write,Trim
- ah, it looks like these are from the mon change that prevents fetching/setting hit_set_* fields on non-tier pools.
- 08:51 PM Bug #8823 (Resolved): Failing LibRadosTierPP.HitSetRead,Write,Trim
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-13_13:58:27-rados-master-testing-basic-plana/357922
and ... - 08:46 PM Bug #8822: osd: hang on shutdown, spinlocks
- ...
- 08:45 PM Bug #8822 (Resolved): osd: hang on shutdown, spinlocks
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-07-13_02:30:04-rados-next-testing-basic-plana/357857
... - 02:12 AM rbd Bug #8821 (Resolved): rbd: ceph.conf "rbd default format" woes
- `/usr/bin/rbd` have few errors with "rbd default format".
With the following in "/etc/ceph/ceph.conf":...
07/12/2014
- 11:54 PM Revision 18900a15 (ceph): Removed tunables temporarily for testing
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 01:04 PM Revision 586d3ee3 (ceph): doc: Fixes a broken link on the rados deploy osd page.
- Signed-off-by: Stephen Jahl <stephenjahl@gmail.com>
- 06:13 AM Feature #8538 (Resolved): Functionality to have rbdmap also mount after mapping an image
- Merged. Thanks, Sage.
- 12:01 AM Revision 79f3f674 (ceph): Merge pull request #1999 from yuyuyu101/keyvaluestore-cache
- Keyvaluestore cache
Reviewed-by: Samuel Just <sam.just@inktank.com>
07/11/2014
- 11:39 PM Revision 7afd50fb (ceph): Merge pull request #57 from ceph/wip-test-post-file
- test ceph-post-file
Reviewed-by: Greg Farnum <greg@inktank.com> - 11:39 PM Revision d24fa335 (ceph): Merge pull request #2096 from ceph/wip-test-post-file
- qa/workunits/post-file.sh
Reviewed-by: Greg Farnum <greg@inktank.com> - 11:00 PM Revision 447f849f (ceph): doc/release-notes: v0.80.3
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Revision 3150bba8 (ceph): rados: test ceph-post-file
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:33 PM Revision 29f20b7e (ceph): qa/workunits/post-file.sh
- Test ceph-post-file.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:07 PM Revision 50957875 (ceph): Merge pull request #2090 from ceph/wip-nuke-dlist
- nuke dlist
Reviewed-by: Greg Farnum <greg@inktank.com> - 10:06 PM Revision 96653bb2 (ceph): Merge pull request #2089 from lpabon/lpabon_readforward
- Support for READFORWARD in the caching tier
Reviewed-by: Sage Weil <sage@redhat.com> - 10:06 PM Revision 50c6b83a (ceph): Merge pull request #2093 from theanalyst/doc/format-fix
- doc: minor format fix for radosgw admin docs
- 10:02 PM Revision 94d40b5e (ceph): Merge pull request #2042 from ceph/wip-port-fixes
- Portability updates
Reviewed-by: Sage Weil <sage@redhat.com> - 10:00 PM Revision 1fd89cea (ceph): Merge pull request #2086 from ceph/wip-8696
- mon: OSDMonitor: limit tier-specific pool set/get on non-tier pools
Reviewed-by: Sage Weil <sage@redhat.com> - 09:59 PM Revision 636a899f (ceph): Merge pull request #2091 from ceph/wip-kinetic-os
- prototype kinetic osd backend
Reviewed-by: Sage Weil <sage@redhat.com> - 09:56 PM Revision 49e5c8ec (ceph): Merge remote-tracking branch 'gh/next'
- 09:42 PM Revision e1fc96f7 (ceph): Merge pull request #2071 from somnathr/wip-sd-cpu-optimized
- Wip sd cpu optimized
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:22 PM Linux kernel client Bug #8818 (Resolved): IO Hang on raw rbd device - Workqueue: ceph-msgr con_work [libceph]
- While conducting dd read and write tests to a raw rbd device for baseline performance tests we experience an IO hang....
- 09:01 PM Revision f70677c3 (ceph): Merge branch 'wip_stable_upgrade2' into firefly
- 09:00 PM Revision 0b0f5668 (ceph): upgrade/firefly: ignore crush tunables on upgrade
- ..then adjust them
Signed-off-by: Sage Weil <sage@redhat.com> - 09:00 PM Revision 499e3ff7 (ceph): upgrade/firefly: upgrade to firefly, not dumpling
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:00 PM Revision e0caeb6d (ceph): upgrade/firefly: do intermediate s3tests on original test set
- The later s3-tests fail on early firefly point releases.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:00 PM Revision 96103c0c (ceph): upgrade/firefly: ignore mon scrub errors from early firefly versions
- See #8815
Signed-off-by: Sage Weil <sage@redhat.com> - 09:00 PM Revision f82efd08 (ceph): upgrade/firefly: don't use overrides
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:00 PM Revision 14e78204 (ceph): Added upgrade tests - stable
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:00 PM Revision b2364eb9 (ceph): upgrade/firefly: consolidate into a single collection
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:00 PM Revision ab7f52ef (ceph): suites/upgrade/firefly: test rgw at the end
- ...and do all final tests for all runs
Signed-off-by: Sage Weil <sage@redhat.com> - 09:00 PM Revision f5fc55f9 (ceph): upgrade/firefly: upgrade mds after osd
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:00 PM Revision 8b73b98b (ceph): upgrade/firefly: fix final steps
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:55 PM Revision c68b5fc9 (ceph): Add a flag to dump the entire job body.
- ... with a warning.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 08:40 PM Revision 4f61db90 (ceph): Add missing placeholder
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:18 PM Revision dcd22a53 (ceph): Add a --dry-run flag to teuthology-schedule
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:17 PM Revision c9e1e82d (ceph): rbdmap: per-device post-map/pre-unmap hooks
- There are cases when automatic (un-)mounting of file system on RBD is not
enough. Some services may need to be starte... - 08:13 PM Revision fb7d5a3a (ceph): Merge pull request #2094 from ceph/wip-8815
- mon: avoid scrub noise due to divering OSDMap encoding versions
Reviewed-by: Greg Farnum <greg@inktank.com> - 07:44 PM Revision 0ccee819 (ceph): Don't drop the rest of os.environ
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:20 PM Revision f8658deb (ceph): Use os.path.expanduser() instead of os.environ
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:15 PM Revision b6c7ba29 (ceph): Fix typo
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:14 PM Revision 0ad10586 (ceph): Fix lock paths
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:06 PM Revision 7418de93 (ceph): Use the ceph_branch if suite_branch isn't found
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:31 PM Revision c93da05b (ceph): osd/osd_types: be pedantic about encoding last_force_op_resend without ...
- The addition of the value is completely backward compatible, but if the
mon feature bits don't match it can cause mon... - 06:29 PM Revision 712d5d1e (ceph): osd/osd_types: remove useless encode_compat local var for pg_pool_t::en...
- This is left over from db3fd1152a87f8f152facdf141f8367296b371df
when we made the HitSet stuff incompat, but that beha... - 06:21 PM Revision 50dc8f0d (ceph): Merge pull request #56 from ceph/wip-pjd
- multimds: fix pjd fuse_default_permissions
Reviewed-by: Greg Farnum <greg@inktank.com> - 06:21 PM Revision fe1d476a (ceph): marginal: fix pjd overrides for fuse_default_persmissions
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:13 PM Revision bc1c12a4 (ceph): multimds: fix pjd overrides for fuse_default_permissions
- Set the default (off) in the ceph task directly, so that there is only a
single overrides field that reenables. Othe... - 05:59 PM Revision b693c402 (ceph): Merge pull request #289 from ceph/split_prep
- Split prep
- 05:20 PM Revision f9d0e8ff (ceph): Merge pull request #2088 from guangyy/wip-8733
- Fix the PG listing issue which could miss objects for EC pool
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:14 PM Revision a129e85c (ceph): 0.80.3
- 04:41 PM Revision 9547a7f3 (ceph): Discourage modifying defaults in instances
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:33 PM Revision 4a6352e3 (ceph): Don't use double underscores
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:03 PM Revision bf048976 (ceph): Merge pull request #2092 from onlyjob/rbdmap
- rbdmap: per-device mount (Closes: #8538)
Reviewed-by: Sage Weil <sage@redhat.com> - 03:55 PM Revision a924606d (ceph): Run tests for base class in subclass tests
- Also remove test_defaults() since it was a bad idea.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 03:26 PM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- How come we did not see these errors for awhile, and now do in brand new upgrade/firefly?
- 01:54 PM rgw Bug #8311: No pool name error in ubuntu-2014-05-06_21:02:54-upgrade:dumpling-dumpling-testing-bas...
- this causes a similar failure in upgrade/firefly when mon_thrash tries to run:...
- 02:58 PM Bug #8696 (Pending Backport): mon: 'osd pool set' must take into account pool's nature when setti...
- 02:54 PM Bug #8701: osd: scrub found obsolete rollback obj
- I think the reason for this is that scrub waits for inflight modifications to the specified range, but the obsolete o...
- 02:22 PM Revision 50e93c21 (ceph): qa/workunits: cephtool: adjust pool name where missing as it has changed
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:58 PM Revision cf94cf35 (ceph): crush: include CRUSH_V3, v2/v3 rules checks in dump_tunables()
- Backport: firefly
Signed-off-by: Sage Weil <sage@inktank.com> - 01:56 PM rgw Bug #8442: rgw: does not detect/adapt to erasure pool stripe size
- 12:33 PM Revision daadff4c (ceph): doc: minor format fix for radosgw admin docs
- Missing backtick fixed
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com> - 11:23 AM CephFS Bug #8677 (Resolved): multimds: pjd failures
- 11:23 AM CephFS Bug #8677: multimds: pjd failures
- Should be resolved by commit:50dc8f0dda6ea2beeb1a05a8423b747baa9d1d4d in the ceph-qa-suite repo.
- 11:08 AM devops Cleanup #7722 (In Progress): Make /admin/build-doc distro independent
- I have a first cut of it done. I had to use fedora packages for ditaa, but verified that it works.
- 10:49 AM Bug #8733 (Pending Backport): OSD crashed at void ECBackend::handle_sub_read
- 09:50 AM Revision b844ec93 (ceph): rbdmap: per-device mount (Closes: #8538)
- `/etc/init.d/rbdmap start` was doing `mount -a`. Although (arguably)
`mount -a -O _netdev` could be less disruptive, ... - 09:42 AM Bug #8815: mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2
- The problem is we added the pool_op_resent to pg_pool_t encoding, but didn't encoding conditionally based on teh feat...
- 09:19 AM Bug #8815 (Resolved): mon: scrub error (osdmap encoding mismatch?) upgrading from 0.80 to ~0.80.2
- ubuntu@teuthology:/a/sage-2014-07-10_20:55:57-upgrade:firefly-firefly-testing-basic-plana/353414
description: upgr... - 09:00 AM Bug #8797: "ceph status" do not exit with python_2.7.8
- Please be advised that this issue appears to be a regression in Python 2.7.8 (see details in the Debian bug report).
- 03:23 AM Feature #8538 (Fix Under Review): Functionality to have rbdmap also mount after mapping an image
- "mount -a" behaviour strikes me as incorrect. Not only we mount unrelated file systems but also there is a risk to do...
- 12:59 AM Revision 02683ac6 (ceph): rbd.cc: Check io-size avoid floating point exception.
- In func do_bench_write if io_size is zero,it can cause floating point execption.
Signed-off-by: Jianpeng Ma <jianpen... - 12:30 AM Revision cdd4d040 (ceph): fix typos
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 12:02 AM Revision 6cd34573 (ceph): qa/workunits: cephtool: cleanup after pool creation
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
07/10/2014
- 11:17 PM Revision f131dfba (ceph): mon: OSDMonitor: limit tier-specific pool set/get on non-tier pools
- Fixes: 8696
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 11:17 PM Revision 64bdf6c9 (ceph): osd: pg_pool_t: clear tunables on clear_tier()
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:17 PM Revision 8e5a8daf (ceph): mon: OSDMonitor: be scary about inconsistent pool tier ids
- We may not crash your cluster, but you'll know that this is not something
that should have happened. Big letters mak... - 11:17 PM Revision df594495 (ceph): qa/workunits: cephtool: split get/set on tier pools from get/set tests
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:17 PM Revision 9fea033f (ceph): qa/workunits: cephtool: test get/set on both tier and non-tier pools
- Make sure gets and sets of tiering-specific variables succeed on tier
pools and fail on non-tier pools.
Signed-off-b... - 11:17 PM Revision 49db6767 (ceph): qa/workunits: cephtool: test erroneous 'tier remove'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:17 PM Revision 704b0a33 (ceph): qa/workunits: cephtool: pool needs to be a tier to be used as such
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:56 PM Revision caa65c39 (ceph): Added steps to cover for 'ceph osd crush tunables firefly'
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 10:35 PM Revision 49725e08 (ceph): Add src_base_path to defaults.
- Defaults to ~/src
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 10:35 PM Revision 9257b870 (ceph): Use config.src_base_path
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:35 PM Revision 24b44cbe (ceph): Clone ceph-qa-suite and add it to PYTHONPATH
- So that teuthology runs can find their tasks
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 10:35 PM Revision 8b6e8243 (ceph): Tweak fetch_teuthology_branch()
- Specifically, make it match fetch_qa_suite()'s behavior.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 10:35 PM Revision 9e5338f8 (ceph): Add test for config substitution
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:35 PM Revision 0f69e3d4 (ceph): Use a dict for a job template instead of a string.
- This makes later modifications far easier.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 10:35 PM Revision 70d87bda (ceph): Update existing unit test, and add another.
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:35 PM Revision c886a936 (ceph): Make teuthology.config *far* more robust
- In addition to parsing its configuration from a yaml file, it can now be
created from a dict. It can also be dumped a... - 10:35 PM Revision fb97e85a (ceph): Use the new JobConfig object
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:35 PM Revision c105827d (ceph): Store the suite_branch in the job config
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:35 PM Revision 46b48c9b (ceph): Remove unused import
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:17 PM Revision 1a4bde2b (ceph): Fix install_except_hook()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 09:53 PM Revision 277cc10e (ceph): Added dumpling-firefly-x upgrade suite per http://tracker.ceph.com/issu...
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 08:24 PM Revision 026b127a (ceph): doc/changelog/v0.80.2: include tag
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:23 PM Revision 59c00e5f (ceph): os: add prototype KineticStore
- Implement the KeyValueDB interface using libkinetic_client,
and allow it to be configured as the backend for the KeyV... - 08:06 PM Bug #8814: ceph-disk list fails in lxc container
- Attached a patch which fixes it.
It makes the assumption that if the device is not present, then it's a full disk... - 08:04 PM Bug #8814: ceph-disk list fails in lxc container
- Some more details on the container setup:...
- 07:18 PM Bug #8814 (Won't Fix): ceph-disk list fails in lxc container
- Certainly not an urgent or big issue, but we use lxc containers for our continuous integration system and have issues...
- 08:05 PM Bug #8797: "ceph status" do not exit with python_2.7.8
- This bug prevent Ceph daemons from starting...
Debian "testing" is already affected since python already propagated ... - 02:17 PM Bug #8797: "ceph status" do not exit with python_2.7.8
- Looks like librados thread is active (not terminated) in "rados.py" and `ceph` is waiting for it indefinitely... I'm ...
- 07:54 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- It may be more likely to happen during deep-scrub...
Any ideas?
- 07:00 PM Revision 74f5e5e9 (ceph): PG::op_must_wait_for_map: pass the epoch rather than the map
- have_same_or_newer_map is also modified to accept epoch instead of
map.
Signed-off-by: Somnath Roy <somnath.roy@sand... - 06:32 PM Revision 3c3cdcb2 (ceph): Don't execute network-using tests by default
- Set TEST_ONLINE to use them.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> - 06:30 PM Revision 60f27a26 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 06:30 PM Revision 98f92d84 (ceph): doc: Added CentOS/RHEL install for git.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:06 PM Revision 1d48f66a (ceph): Don't use master as the default teuthology branch
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 05:54 PM Revision 115c0785 (ceph): rgw: modelines
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:37 PM Revision 8589c108 (ceph): rgw: fix RGWObjManifestRule decoder
- Only decode the new field if it is a new struct.
Fixes: #8804
Backport: firefly
Signed-off-by: Sage Weil <sage@inkta... - 05:36 PM Revision c4afaf9d (ceph): rgw: fix RGWObjManifestRule decoder
- Only decode the new field if it is a new struct.
Fixes: #8804
Backport: firefly
Signed-off-by: Sage Weil <sage@inkta... - 05:04 PM rgw Bug #8436 (Resolved): rgw: ignores provided md5 for object upload
- 05:03 PM rgw Bug #8428 (Resolved): rgw: can't set bucket acls via swift api
- 05:03 PM rgw Bug #8452 (Resolved): S3 multipart upload ignores request headers
- 05:02 PM rgw Bug #8442 (Resolved): rgw: does not detect/adapt to erasure pool stripe size
- 05:01 PM rgw Bug #8699 (Resolved): rgw: uninit ofs in RGWObjManifest::obj_iterator
- 04:58 PM devops Bug #8813: ceph-disk list displays INFO messages rendering output hard to read
- I think we should make a -v verbose flag and hide this output by default, but let ceph-deploy ask for it?
- 04:51 PM devops Bug #8813 (Resolved): ceph-disk list displays INFO messages rendering output hard to read
- Version: 0.80.1
ceph-disk list displays INFO messages in stderr rendering output really difficult to read. The onl... - 03:50 PM Revision cbc73f71 (ceph): task/ceph: Make cephfs_setup cuttlefish-compatible
- Signed-off-by: John Spray <john.spray@redhat.com>
Fixes: #8711 - 03:05 PM Revision 0839e2a6 (ceph): doc: Added keyring location note to resolve pull abandoned pull request...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 02:01 PM Revision 4692257c (ceph): nuke dlist
- No users.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:43 AM Bug #8803 (Duplicate): "[ERR] 3.1s0 scrub stat mismatch" in rados-firefly-distro-basic-plana suite
- 08:50 AM Bug #8803 (Duplicate): "[ERR] 3.1s0 scrub stat mismatch" in rados-firefly-distro-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-08_02:30:04-rados-firefly-distro-basic-plana/34953...
- 11:30 AM CephFS Bug #8811 (Resolved): Journal corruption during upgrade to 0.82 with standby-replay daemons
- Two different ceph-users reports of hitting this issue on v0.82:...
- 11:09 AM Documentation #5987 (Resolved): document requirement for monitor host time sync
- I have peppered the docs with notes on this now.
http://ceph.com/docs/master/start/quick-ceph-deploy/?highlight=n... - 11:06 AM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- ubuntu@teuthology:/a/teuthology-2014-07-08_02:30:04-rados-firefly-distro-basic-plana/349535
- 10:51 AM CephFS Bug #8807: multimds: kernel_untar_build.sh is failing to remove all files
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:18:14-multimds-master-testing-basic-plana/349066/
http:... - 10:35 AM CephFS Bug #8807 (Closed): multimds: kernel_untar_build.sh is failing to remove all files
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:18:14-multimds-master-testing-basic-plana/349156/
<pr... - 10:48 AM CephFS Bug #8810 (New): mds: get_up_osd_features() is referencing invalid memory?
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:18:14-multimds-master-testing-basic-plana/349194/
<pr... - 10:46 AM CephFS Bug #8809 (Can't reproduce): uclient: memory leak
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:18:14-multimds-master-testing-basic-plana/349184/
The... - 10:38 AM rgw Bug #8804 (Resolved): rgw: DELETE failure on 0.80.2
- 09:09 AM rgw Bug #8804 (Resolved): rgw: DELETE failure on 0.80.2
- - put object on 0.80.1
- upgrade radosgw, osds to 0.80.2
- delete object -> error:... - 10:35 AM CephFS Bug #8808 (Resolved): multimds: stale NFS file handle on delete
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:18:14-multimds-master-testing-basic-plana/349129/
Thi... - 10:31 AM CephFS Bug #8677: multimds: pjd failures
- It looks like the override statement you added isn't sticking, Zheng. I assume the one in ceph-fuse.yaml that enables...
- 10:22 AM Linux kernel client Bug #8806: libceph: must use new tid when watch is resent
- This results in hard to track failures, because of an unfinished TODO...
- 10:13 AM Linux kernel client Bug #8806 (Resolved): libceph: must use new tid when watch is resent
- The following can happen:
- kernel client sends watch request
- it is processed, watch is set up, watch->connect(... - 09:12 AM Linux kernel client Bug #8798: The kernel of a server with Ceph hangs
- yes, kernel rbd clients suffer the same deadlock
- 05:31 AM Linux kernel client Bug #8798: The kernel of a server with Ceph hangs
- Thank you for the reply.
We use XFS for the OSD file system and do not use CephFS, but OCFS2 over RBD (kernel rbd... - 05:22 AM Linux kernel client Bug #8798: The kernel of a server with Ceph hangs
- you run OSD daemon and kernel client on the same machine, it's deadlock prone. Read following link for more informat...
- 03:51 AM Linux kernel client Bug #8798 (Won't Fix): The kernel of a server with Ceph hangs
- We have two separate Ceph installations with five servers. Each machine
has four disks. Two of the disks on each mac... - 05:05 AM Bug #8801 (Can't reproduce): Ceph monitors do not start after server restart
- We have two separate Ceph installations with five servers each.
Sometimes when a server is restarted the Ceph monito... - 04:29 AM rgw Feature #8800 (Rejected): Radosgw-agent on pypi.python.org
- It would be nice to have radosgw-agent on Pypi. It makes the code easily reusable (e.g. it can be put in the requirem...
- 02:34 AM Revision a3e5c6d6 (ceph): Add random_cache.hpp to Makefile.am
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:58 AM Bug #8625: EC pool - OSD creates an empty file for op with 'create 0~0, writefull 0~xxx, setxattr...
- We further locate the root cause for this issue, for the head object, there are several op transactions radosgw send ...
- 01:33 AM devops Bug #8788: Rhel 7 ceph=deploy v1.5.7 for firefly fails to retrieve correct package - install fails
- After a yum-update -y this morning a new version of ceph-deploy was installed. this is version 1.5.8
this version wo... - 01:15 AM Revision c930a1f1 (ceph): Work around an apparent binding bug (GCC 4.8).
- A reference to h->seq passed to std::pair ostensibly could not bind
because the header structure is packed. At first... - 01:15 AM Revision 16ef1ed5 (ceph): Convert ConnectionRef explicitly to bool.
- Signed-off-by: Matt Benjamin <matt@linuxbox.com>
- 01:15 AM Revision ebbdb3cc (ceph): Add required spacing after string literals (PRIu64).
- The common formatting for these 64bit types is not C++ 2011
clean.
Signed-off-by: Matt Benjamin <matt@linuxbox.com>
... - 01:15 AM Revision 79e37618 (ceph): Remove some not-resolving make_pair() invocations.
- There's nothing wrong with make_pair(), but there is some type
resolution issue in these instances, at least with GCC... - 01:15 AM Revision f51f162e (ceph): test: fix make_pair() for c++11
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 01:05 AM Revision 228760ce (ceph): Fix the PG listing issue which could miss objects for EC pool (where th...
- Backport: firefly
Signed-off-by: Guang Yang (yguang@yahoo-inc.com) - 12:54 AM Bug #8694: OSD crashed (assertion failure) at FileStore::_collection_move_rename
- I am not sure if this bug is related with http://tracker.ceph.com/issues/8733, but the failure pattern is quite simil...
- 12:18 AM Revision bd6ba100 (ceph): doc: Clean up formatting, usage and removed duplicate section.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:12 AM Revision 15d5b514 (ceph): doc/release-notes: v0.80.2
- Signed-off-by: Sage Weil <sage@redhat.com>
07/09/2014
- 11:30 PM Bug #8797 (Resolved): "ceph status" do not exit with python_2.7.8
- As reported in
https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=754341
after upgrade to python 2.7.8 "`cep... - 11:27 PM Revision 7e3ad1a6 (ceph): Merge pull request #1905 from leseb/doc-rbd-icehouse
- doc: rbd icehouse updated. Need to remove duplicate section.
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 11:05 PM Revision 8a0e498c (ceph): Merge pull request #2087 from theanalyst/doc/typo-fix
- doc: Fixing a few typos in docs
Reviewed-by: John Wilkins <john.wilkins@inktank.com> - 09:20 PM rgw Bug #8698 (Resolved): s3tests.functional.test_s3.test_multipart_upload failures on firefly
- 07:32 PM Revision 198236d6 (ceph): 0.80.2
- 07:05 PM Revision 0b6bd254 (ceph): Revert "rgw: if extra data pool name is empty, use data pool name instead"
- This breaks multipart uploads on firefly, though not on master.
Revert for now so we can release 0.80.2.
This revert... - 05:53 PM Revision 6a231eca (ceph): Revert "enable kernel debugging on kclient fsx runs"
- This reverts commit c883e310f32509579e827ed03c4ee28b491e5140.
We don't want the extra debugging any more.
Signed-off... - 05:52 PM Revision 29c2bb2a (ceph): Revert "qa: add an fsx run which turns on kernel debugging"
- This reverts commit 29c33f0c057acc4e0f4e5022c97553a2dc095b21.
We don't need the debugging any more, and having two se... - 05:49 PM Revision c15e5241 (ceph): Revert "qa: add an fsx run which turns on kernel debugging"
- This reverts commit 29c33f0c057acc4e0f4e5022c97553a2dc095b21.
We don't need the debugging any more, and having two se... - 03:22 PM CephFS Bug #8574: teuthology: NFS mounts on trusty are failing
- http://pulpito.ceph.com/teuthology-2014-07-07_23:10:01-knfs-master-testing-basic-plana/349016/
- 03:19 PM CephFS Bug #8576: teuthology: nfs tests failing on umount
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_23:10:01-knfs-master-testing-basic-plana/349023/
http://qa... - 03:14 PM CephFS Bug #8773 (In Progress): failing cephfs set_layout tests
- I know John looked at this yesterday and was proceeding, though I don't remember if it was based on nuking cephfs or ...
- 11:53 AM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- This is a cuttlefish error...
- 10:15 AM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- Ok.
- 10:04 AM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- Loic - could you please take another look at this?
- 09:49 AM devops Bug #8788 (Resolved): Rhel 7 ceph=deploy v1.5.7 for firefly fails to retrieve correct package - i...
- OS: RHEL7 all packages update to latest
Ceph deploy version 1.5.7
issue:
Incorrect package download attempted wh... - 06:38 AM CephFS Feature #8786 (Resolved): ceph kernel module for el7
Is there a reason why kmod-ceph is not available any more in the rpms, and also commented out in the sources?
T...- 06:26 AM Bug #8785 (Resolved): valgrind tcmalloc false positive (firefly)
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-08_16:54:40-rgw-wip-rgw-firefly-3-testing-basic-plana/349...
- 06:25 AM rgw Bug #8784 (Resolved): rgw: completion leak
- ...
- 05:48 AM Revision 2217f2bd (ceph): doc: fix a typo in quickstart doc
- * doc/start/documenting-ceph.rst: s/along side/alongside
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gma... - 05:48 AM Revision 7a0ea798 (ceph): doc: fix a few typos in radosgw docs
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:45 AM Revision d0892831 (ceph): doc: fix a few typos in rados docs
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:35 AM Revision cc5c33f5 (ceph): doc: fix a few typos in the dev docs
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:28 AM Revision e23ed9b7 (ceph): doc: fix a few typos in rbd docs
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:17 AM Revision d693d7bf (ceph): doc: Fix a few typos in the install docs
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 04:58 AM Revision bb881e53 (ceph): doc: fix a few typos in architecture page
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 04:57 AM Revision fcbdd2fe (ceph): doc: Fix a typo in the rbd man page
- 's/specifially/specifically'
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com> - 04:27 AM Bug #8733: OSD crashed at void ECBackend::handle_sub_read
- https://github.com/ceph/ceph/pull/2088
- 02:53 AM Revision ef117fef (ceph): Use submit_transaction_sync to make change durable
- submit_transaction will use asynchronous write operation, there is no journal
for keyvaluestore so we need to make it... - 02:53 AM Revision 6ff5fedb (ceph): Add random cache and replace SharedLRU in KeyValueStore
- SharedLRU plays pool performance in KeyValueStore with large header cache size,
so a performance optimized RandomCach... - 12:56 AM Revision a2164e73 (ceph): Merge pull request #2029 from ceph/wip-8523
- mon: OSDMonitor: add 'osd pool get-quota' command
Reviewed-by: Sage Weil <sage@redhat.com>
07/08/2014
- 11:25 PM Revision deed546e (ceph): Merge pull request #2085 from ceph/wip-7891
- osd: fix pg ref leaks on shutdown
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:13 PM Revision c0dc245b (ceph): osd: cancel agent_timer events on shutdown
- We need to cancel all agent timer events on shutdown. This also needs to
happen early so that any in-progress events... - 11:12 PM Revision e299357e (ceph): osd: separate cleanup from PGBackend::on_change()
- The generic portion of on_change() cleaned up temporary on-disk objects
and requires a Transaction. The rest is clea... - 11:12 PM Revision cafceae6 (ceph): osd: clear PGBackend state on shutdown
- This was leaking state on shutdown whenever there were in-flight repops
that were canceled.
Fixes: #7891
Signed-off-... - 11:12 PM Revision ef40737e (ceph): osd: s/applying repop/canceling repop/
- The 'applying' language dates back to when we would wait for acks from
replicas before applying writes locally. We d... - 09:20 PM Bug #8733: OSD crashed at void ECBackend::handle_sub_read
- Here is the latest founding:
From erasure coding, there is a new struct ghobject_t to represent an object in CEPH.... - 05:33 AM Bug #8733: OSD crashed at void ECBackend::handle_sub_read
- to correct my last comment:
The marker for the next round listing is not the last one of current object list. So w... - 08:00 PM Revision b16b64eb (ceph): Support for READFORWARD in the caching tier
- READFORWARD caching policy uses writeback for writes
and redirects reads to the back end starage tier.
Signed-off-by... - 06:45 PM Revision 7756a136 (ceph): Merge remote-tracking branch 'gh/next'
- 06:33 PM Revision 714a9bb5 (ceph): mon: OSDMonitor: add 'osd pool get-quota' command
- Enables us to obtain current quotas for a given pool.
Fixes: #8523
Signed-off-by: Joao Eduardo Luis <joao.luis@inkt... - 06:33 PM Revision b927c0de (ceph): qa/workunits: cephtool: test for 'osd pool {get,set}-quota'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:07 PM Bug #8696 (Fix Under Review): mon: 'osd pool set' must take into account pool's nature when setti...
- https://github.com/ceph/ceph/pull/2086
- 05:55 PM Feature #8523 (Resolved): pool quota: Should have get-quota
- 05:25 PM Revision abb59ace (ceph): Merge pull request #2076 from cernceph/wip-wbthrottle-perfcounters
- decrement WBThrottle perfcounters in clear_object
Reviewed-by: Samuel Just <sam.just@inktank.com> - 05:06 PM Revision 9426c4fa (ceph): Merge pull request #2083 from ceph/wip-8727.firefly
- messages: MForward: fix compat version
Reviewed-by: Sage Weil <sage@redhat.com> - 05:05 PM Revision e553c341 (ceph): Merge pull request #2082 from ceph/wip-8727
- messages: MForward: fix compat version
Reviewed-by: Sage Weil <sage@redhat.com> - 04:42 PM Revision 4733178c (ceph): messages: MForward: fix compat version
- A while ago we bumped the head version and reset the compat version to 0.
Doing this so happens to make the messenger... - 04:32 PM Bug #8717: teuthology: valgrind leak checks broken for osd (at least)
- tcmalloc defeats valgrind's leak checks. we do need notcmalloc after all.
- 04:23 PM Bug #7891 (Pending Backport): osd: leaked pg refs on shutdown
- 03:31 PM Bug #7891: osd: leaked pg refs on shutdown
- This correlates with the applying in-progress repops:...
- 04:08 PM devops Feature #5847 (Resolved): Build own versions of most recent leveldb for all supported platforms.
- I have a new jenkins job with files available at:
http://jenkins.ceph.com/job/leveldb-testing/
This contains le... - 03:46 PM Revision c92feebb (ceph): messages: MForward: fix compat version
- A while ago we bumped the head version and reset the compat version to 0.
Doing this so happens to make the messenger... - 03:39 PM Bug #8726: (firefly command on dumpling issue?) Error "'adjust-ulimits ceph-coverage /home/ubuntu...
- Same on http://pulpito.front.sepia.ceph.com/teuthology-2014-07-07_19:00:04-rados-dumpling-testing-basic-plana/
- 03:28 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- Sage Weil wrote:
> Are there a lot of snapshots on the RBD image(s) mapped by this host?
None. RBD image format v... - 09:39 AM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- Are there a lot of snapshots on the RBD image(s) mapped by this host?
- 02:27 PM Bug #8777 (Resolved): osd/PGLog.h: 88: FAILED assert(rollback_info_trimmed_to_riter == log.rbegin())
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_02:32:01-rados-master-testing-basic-plana/34716...
- 02:24 PM Bug #8776 (Won't Fix): osd: runaway memory on dumpling
- specific osd in a large cluster eats ram when started (normal is 1-2 gb, it hits 8 before the host starts swapping an...
- 02:05 PM Bug #8711: Error "ceph --format=json-pretty osd lspools" is "unrecognized command" in cuttlefish
- Same on http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-04_19:33:03-upgrade:dumpling-x:parallel-firefly---basi...
- 01:36 PM Fix #6075 (Rejected): ceph.client.admin.keyring doesn't allow read to non-root users
- The admin keyring should remain with those permissions as they give superuser access to the cluster.
I think that ... - 12:26 PM Fix #6075 (Fix Under Review): ceph.client.admin.keyring doesn't allow read to non-root users
- Pull request opened https://github.com/ceph/ceph/pull/2084
- 12:40 PM rgw Bug #8608 (Resolved): rgw: bucket instance id is truncated
- backported to dumpling in commit:3c63601888c5c825f33ffc6797474eb8dc6935a4
- 11:14 AM devops Bug #8772 (Duplicate): ceph-deploy calamari connect fails when multiple hosts are listed.
- Fixed in 8671
- 09:42 AM devops Bug #8772 (Duplicate): ceph-deploy calamari connect fails when multiple hosts are listed.
- "ceph-deplpy install" works successfully on a list of hosts.
"ceph-deploy calamari connect" fails on the second host... - 10:55 AM CephFS Feature #4138 (In Progress): MDS: forward scrub: add functionality to verify disk data is consistent
- Starting on this now.
- 10:47 AM CephFS Bug #8576: teuthology: nfs tests failing on umount
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-06_23:10:01-knfs-next-testing-basic-plana/346584/
http://qa-p... - 10:43 AM CephFS Bug #8574: teuthology: NFS mounts on trusty are failing
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-04_23:10:02-knfs-master-testing-basic-plana/343743/
http://qa... - 10:24 AM CephFS Bug #8574: teuthology: NFS mounts on trusty are failing
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-06_23:10:01-knfs-next-testing-basic-plana/346574/
- 10:24 AM CephFS Bug #8574: teuthology: NFS mounts on trusty are failing
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-06_23:10:01-knfs-next-testing-basic-plana/346581/
http://qa-p... - 10:36 AM CephFS Bug #8773 (Resolved): failing cephfs set_layout tests
- ...
- 10:15 AM Bug #8771 (Resolved): Error setting "set_max_mds 0" in rados-master-testing-basic-plana suite
- fixed in master yesterday
- 09:18 AM Bug #8771 (Resolved): Error setting "set_max_mds 0" in rados-master-testing-basic-plana suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_02:32:01-rados-master-testing-basic-plana/34701...
- 10:14 AM Bug #8770 (Resolved): "unexpected keyword argument 'ec_pool'" error in teuthology-2014-07-07_02:3...
- fixed this already
- 09:02 AM Bug #8770 (Resolved): "unexpected keyword argument 'ec_pool'" error in teuthology-2014-07-07_02:3...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-07_02:32:01-rados-master-testing-basic-plana/34699...
- 10:03 AM Bug #8727 (Resolved): Firefly monitors send incompatible messages to older monitors
- 09:47 AM Bug #8727 (Fix Under Review): Firefly monitors send incompatible messages to older monitors
- wip-8727 (https://github.com/ceph/ceph/pull/2082) && wip-8727.firefly (https://github.com/ceph/ceph/pull/2083)
- 09:51 AM rbd Bug #6628 (Resolved): krbd: BUG during ceph_osdc_stop() sometimes when rbd_add() fails
- 08:05 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- still everything running ok, as indicated by a deep-scrub of all pgs. very strange.
i just read, that setting tuna... - 07:58 AM Bug #8769 (Rejected): osd.3 crashed in upgrade:dumpling-x:stress-split-firefly---basic-multi suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-07-05_19:55:01-upgrade:dumpling-x:stress-split-firefl...
- 04:08 AM Revision 59379a45 (ceph): Merge pull request #2081 from ceph/wip-osd-leaks
- osd: fix several memory leaks from fast dispatch
Reviewed-by: Samuel Just <sam.just@inktank.com> - 12:03 AM Bug #8758: PGs get stuck in “replay”, but drop it upon osd restarts
- ceph pg <PGid> query shows PGs stuck in active+replay+degraded state have that set in their primary state. Replicas,...
07/07/2014
- 11:29 PM Bug #8733: OSD crashed at void ECBackend::handle_sub_read
- As described above, this crash happens when failing to read part of object on
peer OSD because this part doesn't exi... - 11:17 PM Revision aefbac5e (ceph): osd: fix session leak when waiting on map
- We don't want to leak the Session if this Session is already waiting on
a map.
Introduced by eb30f88c942d80cbc951d4d... - 11:17 PM Revision 0bf4f652 (ceph): osd: clear sessions_waiting_on_map on shutdown
- Wake up these ops and drop the Session refs on shutdown.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:59 PM Bug #8176: Change target_max_objects/target_max_bytes has no immediate effect
- This was fixed in a97129f19789cd3a5c81667059fdac5c120bdbe6 where ReplicatedPG::on_pool_change() was added and called ...
- 10:37 PM Revision ca1dc3c9 (ceph): Merge pull request #2037 from ceph/wip-async-log
- MDS: Encode log events in a separate thread from main execution.
This is a first small step in multi-threading the M... - 10:12 PM Revision 17ad0831 (ceph): osd: clear Sessions for loopback Connections on shutdown
- Starting with the fast dispatch patches, we are calling the handle_connect
on loopback. Make sure we zap them on shu... - 10:11 PM Revision 231fe1b6 (ceph): Revert "OSD: move waiting_for_pg into Session"
- This reverts commit ecda2fef8ce982df3581a3b47ba74ae581d82479.
This leaves Session* refs indefinitely in the map.
Th... - 10:08 PM Revision 7262d29f (ceph): watch-suite.sh: new syntax
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:52 PM Revision 083f9fe4 (ceph): Merge pull request #2080 from ceph/wip-8306-rebase
- Wip 8306 rebase
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 09:49 PM Revision b81a2777 (ceph): ceph.spec.in: add bash completion file for radosgw-admin
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
(cherry picked from commit b70096307130bcbac176704493a63c5d039d3edc) - 09:40 PM Revision 4649d7e9 (ceph): ceph.spec.in: rhel7-related changes:
- udev rules: /lib -> /usr/lib
/sbin binaries move to /usr/sbin or %{_sbindir}
Signed-off-by: Sandon Van Ness <sandon@... - 09:40 PM Revision 38a9566e (ceph): Fix/add missing dependencies:
- - rbd-fuse depends on librados2/librbd1
- ceph-devel depends on specific releases of libs and libcephfs_jni1
- librbd... - 09:35 PM Revision b82c9e15 (ceph): Merge pull request #276 from dachary/wip-typo
- documentation typo
- 09:35 PM Revision 62f82c3d (ceph): Merge pull request #282 from ceph/wip-jcsp-misc
- Wip jcsp misc
- 09:32 PM Revision 733c89dc (ceph): ceph.spec.in: whitespace fixes
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
(cherry picked from commit ec8af52a5ede78511423a1455a496d46d580c6... - 09:27 PM Revision 21b03bc9 (ceph): ceph.spec.in: split out ceph-common as in Debian
- Move files, postun scriptlet, and add dependencies on ceph-common
where appropriate
Signed-off-by: Sandon Van Ness <... - 09:27 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- With rbd client on kernel (3.14.9 and earlier) I'm still getting those errors on one machine every day (~once a day o...
- 09:10 PM Revision aa1be2e3 (ceph): OSD: fix debug logging output
- The snapmapper and infos statements were backwards. Now they aren't.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:07 PM Bug #8717: teuthology: valgrind leak checks broken for osd (at least)
- 05:13 PM Bug #8717 (Fix Under Review): teuthology: valgrind leak checks broken for osd (at least)
- https://github.com/ceph/ceph-qa-suite/pull/51
- 09:06 PM Bug #7995 (Resolved): osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- 05:11 PM Bug #7995 (Fix Under Review): osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_ref...
- https://github.com/ceph/ceph/pull/2081
I suspect the original incidents for this bug were triggered by a different... - 08:24 PM Revision 469c003e (ceph): Merge pull request #285 from ceph/wip-8750-jcsp
- task/ceph: move set_max_mds into cephfs_setup
Reviewed-by: Sage Weil <sage@redhat.com> - 08:23 PM Revision 0f742995 (ceph): Merge pull request #2078 from ceph/wip-8751
- test: generalise default_pools in test_rados
Reviewed-by: Sage Weil <sage@redhat.com> - 08:12 PM Revision 235e4c7d (ceph): ceph.spec.in: rhel7-related changes:
- udev rules: /lib -> /usr/lib
/sbin binaries move to /usr/sbin or %{_sbindir}
Signed-off-by: Sandon Van Ness <sandon@... - 08:12 PM Revision b7009630 (ceph): ceph.spec.in: add bash completion file for radosgw-admin
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 08:12 PM Revision 5d192ed4 (ceph): Make the archive dir a positional argument
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 08:12 PM Revision 7cf81322 (ceph): Fix/add missing dependencies:
- - rbd-fuse depends on librados2/librbd1
- ceph-devel depends on specific releases of libs and libcephfs_jni1
- librbd... - 08:11 PM Revision ec8af52a (ceph): ceph.spec.in: whitespace fixes
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 08:09 PM Revision e131b9d5 (ceph): ceph.spec.in: split out ceph-common as in Debian
- Move files, postun scriptlet, and add dependencies on ceph-common
where appropriate
Signed-off-by: Sandon Van Ness <... - 08:02 PM Revision 0fa0e2ec (ceph): Merge pull request #279 from ceph/wip-ls
- ls: make --archive-dir default to .
- 07:32 PM Revision 08fa16ba (ceph): common: seq_read_bench argument order changed
- The argument order for seq_read_bench in src/common/obj_bencher.h has
been changed to match the argument order in obj... - 07:06 PM Revision bc1550ad (ceph): Merge pull request #286 from ceph/wip-results-timeout
- suite: change default results_timeout to 9h (from 6h)
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:20 PM Revision 4d7c09ee (ceph): suite: default to 9h results_timeout
- 6h isn't enough for xfstests.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:19 PM Revision cca5841c (ceph): test: generalise default_pools in test_rados
- Instead of fragile assumptions about what pools
do or do not exist by default, simply use what
exists at test setup t... - 05:13 PM devops Feature #8306 (Resolved): separate ceph.rpm into ceph and ceph-common
- 02:51 PM devops Feature #8306 (Pending Backport): separate ceph.rpm into ceph and ceph-common
- 04:40 PM Revision dbee797d (ceph): Merge pull request #2057 from ceph/wip-8593-firefly
- mon: backport health check improvements
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:39 PM rgw Bug #8698: s3tests.functional.test_s3.test_multipart_upload failures on firefly
- It's only failing multiregion tests on ec pools now, but I don't see anything obvious missing that fixed this in mast...
- 04:07 PM Revision 768d48f6 (ceph): Merge pull request #2074 from onlyjob/docs
- doc: mention kernel support for rbd format 2
Reviewed-by: Sage Weil <sage@redhat.com> - 04:04 PM Revision a2337474 (ceph): Merge pull request #2077 from ceph/wip-8754
- tests: don't depend on 'data' pool in rbd test
Reviewed-by: Sage Weil <sage@redhat.com> - 03:18 PM Bug #8758: PGs get stuck in “replay”, but drop it upon osd restarts
- Hummm, it looks like you're right: we start a replay period (which is time-based, 30s by default) as we go active and...
- 02:55 PM Bug #8758: PGs get stuck in “replay”, but drop it upon osd restarts
- 1. will do
2. my concern is that the replay bit appears to be lost because of a restart. say, osds 0, 1 and 2 (all ... - 01:41 PM Bug #8758: PGs get stuck in “replay”, but drop it upon osd restarts
- That's a good summary; see PG::may_need_replay(). I glanced over this and it looks like the PG is placed on the OSD's...
- 09:45 AM Bug #8758 (Need More Info): PGs get stuck in “replay”, but drop it upon osd restarts
- Two things:
1. When the PG gets stuck in replay next time, can you do a 'ceph pg <pgid> query' and see if the OSD ... - 07:39 AM Bug #8758 (Won't Fix): PGs get stuck in “replay”, but drop it upon osd restarts
- Sometimes, after restarting all OSDs (which I often do when I want them to recover quickly, since otherwise my memory...
- 03:05 PM rgw Bug #8766 (Resolved): multipart minimum size error should be EntityTooSmall
- This is already in the code as ERR_TOO_SMALL, but is reported to stop any response instead of sending the error on fi...
- 03:02 PM Bug #8396: osd: message delayed in Session misdirected after split
- reverting
- 03:02 PM Bug #8505: OSD osd/OSD.cc: 6222: FAILED assert(p->second.empty())
- Sage is reverting it, borken
- 02:45 PM Revision a7a631d1 (ceph): tests: don't depend on 'data' pool in rbd test
- Since we removed the default 'data' and 'metadata' pools,
tests which need a pool should create it themselves.
Signe... - 02:14 PM Bug #8349: env-vs-args unittest is racy
- 01:45 PM Bug #8349: env-vs-args unittest is racy
- breaking my branch builds today.
- 02:12 PM Fix #6075: ceph.client.admin.keyring doesn't allow read to non-root users
- 02:10 PM rgw Documentation #8764: multipart upload has a minimum size
- This is part of the S3 spec...?
http://docs.aws.amazon.com/AmazonS3/latest/API/mpUploadUploadPart.html
> Each part ... - 01:37 PM rgw Documentation #8764 (Closed): multipart upload has a minimum size
- Someone ran into a mysterious error on multipart uploads on the mailing list, which turned out to be because they wer...
- 02:05 PM Revision cf5f5351 (ceph): doc/release-notes: clarify CRUSH notes about tunables
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:02 PM Revision d84d7204 (ceph): decrement WBThrottle perfcounters in clear_object
- We observed that the WBThrottle perfcounters are leaking upwards
at a rate of around 50-100 ios_dirtied per day. The ... - 01:59 PM Bug #8320 (Resolved): heartbeat timeouts too low for vps machines
- added ~teuthology/vps.yaml and added it as an arg for all the vps scheduled suites. sets the heartbeat grace to 40s ...
- 01:54 PM Revision 7e3fb06a (ceph): Merge pull request #2075 from ceph/wip-8745
- mds: use client-provided time stamp for user-visible file metadata
Reviewed-by: Sage Weil <sage@redhat.com> - 01:24 PM CephFS Tasks #8535 (Closed): audit the journaler send-to-OSD ordering
- 01:22 PM Bug #8750 (Resolved): ceph mds set_max_mds 0 fails
- 01:21 PM Bug #8751 (Resolved): rados/test_python.sh: FAIL: test_rados.TestRados.test_list_pools
- 10:35 AM Bug #8751 (Fix Under Review): rados/test_python.sh: FAIL: test_rados.TestRados.test_list_pools
- https://github.com/ceph/ceph/pull/2078
- 01:05 PM rgw Documentation #8763 (Closed): document multiregion bucket placement configuration
- When a bucket is created the request can specify the region or placement target its objects will be stored in.
Doc... - 01:02 PM rgw Bug #8762 (Closed): swift api support chart is out of date
- http://ceph.com/docs/master/radosgw/swift/
- 01:02 PM rgw Bug #8761 (Closed): s3 api support chart is out of date
- http://ceph.com/docs/master/radosgw/s3/
- 12:44 PM Revision 18e556b0 (ceph): task/ceph: move set_max_mds into cephfs_setup
- Move the calculation of active MDS count out
of the generic service setup and into the
filesystem setup.
Fixes: #875... - 10:30 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- everything was still running good today, but i guess we had not much load the last days. i run my stress test again w...
- 10:18 AM Bug #8532: 0.80.1: OSD crash (domino effect), same as BUG #8229
- Anything new? Would you consider reenabling fiemap to see whether that makes the issues come back?
- 09:55 AM Bug #8754 (Resolved): rbd tests depend on 'data' pool
- Fix merged @ https://github.com/ceph/ceph/commit/a2337474f524044a1b7e5d728a49398d25f69322
- 05:28 AM Bug #8754: rbd tests depend on 'data' pool
- Failure occurs in context of suites/rbd/singleton, was working in other contexts because there is a redundant 'mds.a'...
- 05:25 AM Bug #8754 (Resolved): rbd tests depend on 'data' pool
- ...
- 09:39 AM Bug #8593: mon: down but in osds in health warning calc is wrong
- backported to firefly. i don't think we should touch dumpling with this.
- 09:38 AM Bug #8593 (Resolved): mon: down but in osds in health warning calc is wrong
- 08:17 AM Revision 16df4c3e (ceph): mds: use client-provided time stamp for user-visible file metadata
- Fixes: #8745
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 07:30 AM CephFS Bug #8757 (Won't Fix): no need to hold write lock on hardlink's dir while creating anchortable entry
- I've finally figured out why creating hardlink farms takes so long with up to 0.80: we take a write lock on the dir t...
- 06:55 AM CephFS Bug #8749 (Duplicate): knfs: EBUSY on umount
- 06:55 AM CephFS Bug #8748 (Duplicate): knfs: mount failure
- 06:52 AM CephFS Bug #8708 (Resolved): kcephfs: direct_io tests failing
- 06:52 AM CephFS Bug #8745 (Resolved): ceph-fuse: pjd link 78 failure
- 01:16 AM CephFS Bug #8745: ceph-fuse: pjd link 78 failure
- 06:08 AM Revision 73b2928a (ceph): Remove exclusive lock on GenericObjectMap
- Now most of GenericObjectMap interfaces use header as argument not the union of
coll_t and ghobject_t. So caller shou... - 06:08 AM Revision d1049794 (ceph): Add Header cache to KeyValueStore
- In the performance statistic recently, the header lookup becomes the main time
consuming for the read/write operation... - 01:08 AM rgw Bug #8233: Installation & Documentation broken for Ubuntu Trusty 14.04 - rgw
- I've got exactly the same error for Ubuntu Saucy (13.10).
- 12:54 AM Bug #8753 (Resolved): PG::activate assert failed when recover finished
-60> 2014-06-28 14:19:50.353700 7f9a354d8700 0 -- 10.1.16.72:6805/35913 >> 10.1.16.83:6812/1038272 pipe(0x3d389...
07/06/2014
- 09:21 PM Bug #7891: osd: leaked pg refs on shutdown
- ubuntu@teuthology:/var/lib/teuthworker/archive/sage-2014-07-05_19:34:55-rados-wip-msgr-testing-basic-plana/344755
- 06:13 PM Revision f3145e98 (ceph): ceph.conf: drop min pg per osd warning
- With only the rbd pool getting created this needs to be dropped
Signed-off-by: Sage Weil <sage@inktank.com> - 06:02 PM Revision 5860c3f9 (ceph): Merge pull request #281 from dachary/wip-lost-unfound
- fix create_pool_with_unique_name call to use profile name
Reviewed-by: Sage Weil <sage@redhat.com> - 11:01 AM Bug #8750: ceph mds set_max_mds 0 fails
- https://github.com/ceph/teuthology/pull/283
- 03:34 AM Bug #8752 (Can't reproduce): firefly: scrub/repair stat mismatch
- Two dozen PGs are in "active+clean+inconsistent" state.
Attempted "ceph pg repair" reports fixed error(s) but next s... - 03:03 AM Bug #8747 (New): OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.star...
- Re-opening as I just reproduced the issue. Sorry.
This happened again (probably) on attempt to repair inconsistent P... - 01:54 AM CephFS Feature #8690: MDS: Allow some kind of recovery when pools are deleted out from underneath us
- Yes, "data_cache" was a tiered cache pool but EC pool behind it was dropped as well.
IMHO recovery shouldn't bee t... - 01:27 AM Bug #8643: 0.80.1: OSD crash: osd/ECBackend.cc: 529: FAILED assert(pop.data.length() == sinfo.ali...
- This issue is no longer happening since when I dropped broken pool.
To close this bug I'd suggest to drop assert, sk... - 01:01 AM Revision 62ead223 (ceph): remove stray dirs
- These appear to be copies of samba/*
Signed-off-by: Sage Weil <sage@inktank.com> - 12:59 AM Revision 8920c4ba (ceph): remove stray workload dir
07/05/2014
- 09:43 PM Revision 6d6039a5 (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... - 09:43 PM Revision 0a8d194f (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... - 09:42 PM Bug #8747 (Closed): OSD crash on scrub:osd/ReplicatedPG.cc: 5297: FAILED assert(soid < scrubber.s...
- I found that two OSDs of 12 were running 0.80.1 without backported patch from #8011.
Interesting to note that the af... - 09:32 PM Bug #8750 (Fix Under Review): ceph mds set_max_mds 0 fails
- 02:42 PM Bug #8750: ceph mds set_max_mds 0 fails
- teuthology-2014-07-04_23:00:02-rbd-master-testing-basic-plana/343495
- 02:41 PM Bug #8750 (Resolved): ceph mds set_max_mds 0 fails
- 08:54 PM Bug #8751 (Resolved): rados/test_python.sh: FAIL: test_rados.TestRados.test_list_pools
- ...
- 07:15 PM Bug #8701: osd: scrub found obsolete rollback obj
- teuthology-2014-07-04_23:02:01-rgw-master-testing-basic-plana/343571
teuthology-2014-07-04_23:02:01-rgw-master-testi... - 03:15 PM Revision a49c6122 (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... - 02:41 PM Bug #8738 (Resolved): divergent osdmaps crush tunables
- 02:40 PM CephFS Bug #8749 (Duplicate): knfs: EBUSY on umount
- ubuntu@teuthology:/a/teuthology-2014-07-04_23:10:02-knfs-master-testing-basic-plana/343740
- 02:39 PM CephFS Bug #8748 (Duplicate): knfs: mount failure
- Command failed on plana18 with status 32: 'sudo mount -o
rw,hard,intr,nfsvers=4
plana24.front.sepia.cep... - 09:27 AM Revision c0806bbd (ceph): doc: mention kernel support for rbd format 2
- Signed-off-by: Dmitry Smirnov <onlyjob@member.fsf.org>
- 08:15 AM rgw Bug #8698: s3tests.functional.test_s3.test_multipart_upload failures on firefly
- ubuntu@teuthology:/a/sage-2014-07-04_22:49:56-rgw-firefly-testing-basic-plana/343404
after merging wip-rgw-firefly-2 - 07:53 AM Bug #7986: 3.1s0 scrub stat mismatch, got 2041/2044 objects, 0/0 clones, 2041/2044 dirty, 0/0
- ubuntu@teuthology:/a/sage-2014-07-03_22:15:01-rados-firefly-testing-basic-plana/340820
- 04:18 AM Revision dd5b60b4 (ceph): Merge remote-tracking branch 'gh/next'
- 04:18 AM Revision 828ce405 (ceph): Merge pull request #2073 from ceph/wip-rgw-firefly-2
- rgw: more firefly backports
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 01:35 AM Revision 50a21833 (ceph): Merge pull request #2072 from ceph/wip-8738-next
- Patch up the CRUSH map compatibility guards
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Joao Eduardo L...
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...
Also available in: Atom