Activity
From 05/10/2013 to 06/08/2013
06/08/2013
- 11:00 PM CephFS Support #5285 (Closed): cephfs give permission to write files
- dup #5287
- 10:37 PM CephFS Bug #5287: the permission of file in CephFS
- so far the only solution is chmod
- 07:55 PM CephFS Bug #5287: the permission of file in CephFS
- Zheng Yan wrote:
> The short answer is no better solution so far. If a given node can mount the FS, it can access to... - 06:24 PM CephFS Bug #5287: the permission of file in CephFS
- The short answer is no better solution so far. If a given node can mount the FS, it can access to the data pool direc...
- 01:43 AM CephFS Bug #5287 (Resolved): the permission of file in CephFS
- Hi all,
I used the CephFS v0.56.3 to store VMs. There're 8 nodes of my cluster, and I mount the cephFS in every node... - 10:24 PM Bug #5200 (Resolved): mon: valgrind leaks
- 10:23 PM CephFS Bug #4832 (Resolved): mds: failed auth_unpin assert
- 09:39 PM Bug #5286 (Resolved): LibRadosCmd.PGCmd fails pg command test
- simpler fix in commit:81a786e9e52ad5168bb7024145ba11f98e35229b
- 08:43 AM Bug #5288 (Resolved): ceph.py: catch rados errors and print them nicely
- ubuntu@plana30:~$ ceph health
Traceback (most recent call last):
File "/usr/bin/ceph", line 1541, in <module>
... - 05:58 AM Revision 00eaf97d (ceph): librados.h: Fix up some doxygen problems
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 05:14 AM Revision e8300d0a (ceph): mds: fix filelock eval_gather
- Broken by a08d62045657713bf0a5372bf14136082ec3b17e
Reported-by: Yan, Zheng <yan.zheng@intel.com>
Signed-off-by: Sage... - 04:58 AM Revision 22532cc8 (ceph): ceph_manager: drop -- before --format=json arg
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:47 AM Revision 2b4157a7 (ceph): .gitignore: add 'ceph', now a generated file
- 04:20 AM Revision 028f1c70 (ceph): valgrind: more leveldb whitelisting
- 02:32 AM Revision a4994e3b (ceph): Support added for running scheduled tasks on virtual machines.
- This included:
A). changes made so that full path names on some files were used
(scheduled tasks started ... - 01:14 AM Linux kernel client Bug #5267: Kernal 3.2.0-23 crashed
- Thx very much, so quickly get reply made me glad. Maybe the kernel is too old, we will update ASAP.
I forget to upd... - 12:40 AM Revision 4eb8f898 (ceph): merged system_value for rpms
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:29 AM Revision 359f456a (ceph): ceph: old daemons output to outs and outbuf, combine
- When talking to old daemons, if a command succeeds, there may be
output on outs, outbuf, or both; combine them if the... - 12:28 AM Revision b3f38f3e (ceph): ceph: handle old OSDs as command destinations, fix status part of -w
- For osd tell or pg <pgid> commands, the CLI sends the command directly
to the OSD; if the OSDs are still old, the com... - 12:28 AM Revision 754301bb (ceph): support install task for fedora
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:24 AM Revision 05d1d027 (ceph): Merge pull request #352 from ceph/wip-4832
- mds: do not double-queue file recovery in eval_gather
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:20 AM Revision 11e1afd8 (ceph): ceph: add -v for version. Makefile processes ceph_ver.h
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:15 AM Revision 32b2f113 (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 12:13 AM Revision 7012d192 (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 12:12 AM Revision 5e5bd665 (ceph): Merge pull request #343 from dalgaaf/wip-da-SCA-cppcheck
- Reviewed-by: Sage Weil <sage@inktank.com>
06/07/2013
- 11:14 PM Bug #5286 (Fix Under Review): LibRadosCmd.PGCmd fails pg command test
- wip-5286
- 10:45 PM Bug #5286 (Resolved): LibRadosCmd.PGCmd fails pg command test
- ...
- 11:10 PM Revision fde536fa (ceph): osd: make scrub chunk size tunable
- It was hard-coded at 5. Make it range from 5-15 by default, for now.
We should still keep this smallish since this ... - 10:59 PM Revision 0bc731ea (ceph): test_filestore_idempotent: use obj name from source coll add
- Fixes: #5240
Reviewed-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:59 PM Revision 637e0ead (ceph): rados: --num-objects will now cause bench to stop after that many objects
- Reviewed-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com> - 10:04 PM CephFS Bug #4832: mds: failed auth_unpin assert
- aie.. thanks
- 09:36 PM CephFS Bug #4832: mds: failed auth_unpin assert
- that commit breaks filelock eval gather
- 05:23 PM CephFS Bug #4832 (Resolved): mds: failed auth_unpin assert
- commit:a08d62045657713bf0a5372bf14136082ec3b17e
- 10:00 PM Revision ed9af6cd (ceph): Merge branch 'wip-RhelInstall-wusui'
- 09:58 PM Revision 9d6141dd (ceph): Add RHEL support to teuthology
- Fix #4946
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 09:23 PM Revision 7e095077 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/messages/MMonProbe.h - 09:09 PM Revision 5047a4ff (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 09:09 PM Revision 3ea45533 (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 09:00 PM Revision c75760e3 (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 08:59 PM Revision bd12e81e (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 08:59 PM Revision b1d436e7 (ceph): rgw: add 'cors' to the list of sub-resources
- Fixes: #5261
Backport: cuttlefish
Add 'cors' to the list of sub-resources, otherwise auth signing
is wrong.
Signed-o... - 08:52 PM Revision ad3934e3 (ceph): rgw: handle deep uri resources
- In case of deep uri resources (ones created beyond a single level
of hierarchy, e.g. auth/v1.0) we want to create a n... - 08:52 PM Revision 8d55b87f (ceph): rgw: fix get_resource_mgr() to correctly identify resource
- Fixes: #5262
The original test was not comparing the correct string, ended up
with the effect of just checking the su... - 08:51 PM Revision 9a0a9c20 (ceph): rgw: add 'cors' to the list of sub-resources
- Fixes: #5261
Backport: cuttlefish
Add 'cors' to the list of sub-resources, otherwise auth signing
is wrong.
Signed-o... - 08:13 PM Linux kernel client Bug #5267: Kernal 3.2.0-23 crashed
- Thx very much, so quickly get reply made me glad. Maybe the kernel is too old, we will update ASAP.
I forget to upd... - 09:35 AM Linux kernel client Bug #5267 (Won't Fix): Kernal 3.2.0-23 crashed
- please try kernel 3.4 or later.. we aren't backproting fixes as far back as 3.2!
- 07:39 PM CephFS Support #5285 (Closed): cephfs give permission to write files
- Hi all,
I used the CephFS v0.56.3 to store VMs. There're 8 nodes of my cluster, and I mount the cephFS in every n... - 06:05 PM Bug #4698: osd suicide timed out after 150
- log: ubuntu@teuthology:/a/teuthology-2013-06-07_01:30:04-upgrade-master-testing-basic/32963...
- 06:05 PM Revision f4f6758b (ceph): Merge branch 'wip-ceph-cli'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:58 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- 08:38 AM Bug #4179 (Fix Under Review): osd: memory leak during deep scrub on bobtail
- 05:41 PM Bug #5273 (Rejected): osd: ops waiting a long time for osdmaps
- sam points out that the 'waiting for osdmap' status is misleading here..
- 10:24 AM Bug #5273 (Rejected): osd: ops waiting a long time for osdmaps
- mark nelson is observing this.. diagnose and track down.
- 05:38 PM devops Bug #5248 (Need More Info): upstart: ceph-all job is starting too soon
- waiting to hear back from jamespage ... he's conferring with the upstart people
- 05:37 PM devops Bug #5194 (Need More Info): udev does not start osd after reboot on wheezy or el6 or fedora
- can you confirm whether 'partprobe /dev/...' will start the osd?
- 05:34 PM CephFS Bug #5236 (Resolved): mds assert when starting file scan
- no more failures, yay!
- 05:24 PM Documentation #5284: crushtool's manpage is very out of date
- see crushtool --help
- 05:24 PM Documentation #5284 (Closed): crushtool's manpage is very out of date
- 05:00 PM Revision 0b036ecd (ceph): osd: do not include logbl in scrub map
- This is a potentially use object/file, usually prefixed by a zeroed region
on disk, that is not used by scrub at all.... - 04:51 PM Revision dea8c2d1 (ceph): doc: Updated for glossary terms and added indexing.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:50 PM Revision 8e24328d (ceph): doc: Added indexing and did a bit of cleanup.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:54 PM Revision 03b12b8a (ceph): rados: add btrfs to osd powercycle tests
- So we can get some testing coverage on btrfs, and identify whether the
xfs corruption issues are related to the fs or... - 03:39 PM devops Bug #5283 (Won't Fix): Ceph-deploy can't handle /dev/disk/by-* device paths
- If you try to create a new osd with ceph-deploy using /dev/disk/by-* path instead of the /dev/* path the osd creation...
- 03:37 PM devops Feature #5282 (Closed): Get Dumpling into EPEL
- 03:35 PM devops Feature #4515 (Duplicate): packaging: create qemu packages with rbd enabled for centos 6
- Duplicates 4550
- 03:33 PM devops Documentation #5253 (Resolved): Update Pre-Flight docs to use ceph-deploy package
- 03:31 PM devops Feature #5015 (Resolved): ceph-deploy: push packages to all ceph repos
- 03:29 PM devops Feature #5019 (Resolved): arm: gitbuilder for ARM
- 03:28 PM devops Feature #5018: arm: ceph-deploy: push packages to ARM
- 03:26 PM rbd Feature #4834 (Resolved): Recompile/package qemu with new version of librbd to enable asynchronou...
- 02:56 PM devops Feature #5089 (Resolved): ceph-deploy install fails on arm
- It works.
Needed python-pushy and ceph-deploy built on arm added to the repos. - 02:54 PM devops Feature #5016: ceph-deploy: gitbuilders for release packages
- Opened ticket #5281 for the gitbuilder vms. This task may have fallen off the radar.
- 02:25 PM RADOS Feature #5280 (New): osd/client: messages should be tagged with the earliest sane map
- A client at epoch e should not have to wait for an osd to catch up to epoch e unless the mapping changed in epoch e. ...
- 02:17 PM Fix #5279 (In Progress): pipeline large object recovery
- currently pushes for large objects are syncronous: push->reply->push etc.
should be push->push->push
... - 02:17 PM rgw Bug #5262 (Resolved): rgw: can't access buckets with names that start with 'auth'
- Backported to cuttlefish in commit:bd12e81e48014024171c55f5984c9183c8e363cb and commit:c75760e39d8df5b1971343e9f9186f...
- 01:59 PM rgw Bug #5262 (Pending Backport): rgw: can't access buckets with names that start with 'auth'
- Fixed in next, commit:8d55b87f95d59dbfcfd0799c4601ca37ebb025f5. Fixed a related issue as well, commit:ad3934e335399f7...
- 02:15 PM Fix #4567 (Resolved): mon: refactor mon caps; allow restriction of key/value storage by prefix
- 02:15 PM Feature #3273: mon: simple dm-crypt key management
- - make sure ceph-deploy and chef can use this
- 02:06 PM Fix #5278 (Resolved): osd: smarter recovery for small objects
- 1) avoid collection move for single write pushes
2) maybe package multiple small objects at once? - 02:05 PM rgw Bug #5261 (Resolved): rgw: 'cors' is not regarded as a sub-resource
- Backported to cuttlefish in commit:b1d436e752c9c20e7dbff91b769cb2ba47383571
- 01:58 PM rgw Bug #5261 (Pending Backport): rgw: 'cors' is not regarded as a sub-resource
- Fixed in next branch, commit:9a0a9c205b8c24ca9c1e05b0cf9875768e867a9e.
Will backport to cuttlefish and update with c... - 10:46 AM rgw Bug #5261: rgw: 'cors' is not regarded as a sub-resource
- Yeah, tested it. I created a new functional test for it. Also, there's no CORS in bobtail, so we don't need it there.
- 10:29 AM rgw Bug #5261: rgw: 'cors' is not regarded as a sub-resource
- Well, that's a simple enough fix. Have you tested it yet?
And it's marked as needing a backport to cuttlefish, but... - 02:03 PM Fix #4840 (Resolved): mon: transition from old-style allow command to new command descriptions
- 02:02 PM Feature #5147 (Resolved): Display unique cluster ID in ceph status
- 01:54 PM Bug #5200 (In Progress): mon: valgrind leaks
- 01:35 PM Bug #5270: osd: crash in PG::peek_map_epoch()
- Very odd. That xattr is written atomically on pg collection creation and never overwritten thereafter.
- 01:29 PM rbd Feature #5005: cinder: switch rbd driver to use librbd instead of the cli tool
- Review: https://review.openstack.org/30792
Commit: http://github.com/openstack/cinder/commit/e2d0e1f479a56d60dc09ae9... - 11:32 AM rbd Feature #5005 (Resolved): cinder: switch rbd driver to use librbd instead of the cli tool
- 01:28 PM rbd Feature #5004: cinder: make rbd configuration easier to use
- Review: https://review.openstack.org/30791
Commit: http://github.com/openstack/cinder/commit/483b84e42b90f2ffe0a09f5... - 11:32 AM rbd Feature #5004 (Resolved): cinder: make rbd configuration easier to use
- 01:14 PM rgw Feature #5164: rgw: multisite: metadata push notifications: design blueprint
- 01:13 PM rgw Feature #4098 (Fix Under Review): rgw: multi-site: Global Bucket Namespace
- 01:13 PM rgw Feature #4329 (Fix Under Review): rgw: dr: updated buckets log: RESTful API
- 01:08 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- They are waiting a bit before the upgrade, however they recently reported back that they put together some custom rul...
- 01:03 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- I'd rather not to do a backport. Do we have a bobtail customer asking for this who can't/won't upgrade to Cuttlefish?
- 01:04 PM rgw Feature #5136 (Need More Info): rgw: revise user stats
- ?
- 01:00 PM rgw Feature #5169: Do not list swift containers when enumerating buckets using S3 API
- 12:58 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- 11:51 AM rbd Documentation #5212: doc: link to recommended kernel version from pages that describe using kerne...
- 11:42 AM rbd Feature #4013 (In Progress): rbd: openstack: extend nova boot api to support going from image to ...
- 11:42 AM rbd Feature #4017 (In Progress): rbd: openstack: simplify volume booting with new api
- 11:30 AM rbd Feature #5275 (Resolved): openstack: port always_use_volumes option to grizzly
- The folsom version is git://github.com/jdurgin/nova wip-volumes.
- 10:52 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I'll try commenting out the assert, and yes, we tried the snapshots feature of the MDS hours before the shutdown.
- 09:44 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- were you using the mds snapshots?
- 09:42 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- probably the workaround is to comment out that assert..
- 07:56 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Is it useful for me to keep the FS in this state much longuer, right now the FS is unusable. Is it possible to clear ...
- 10:20 AM devops Bug #5242 (Resolved): ceph-deploy: reports purgedata as invalid command when purge is not successful
- fixed the mirror!
- 09:47 AM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- any news here, tamil?
- 09:56 AM Bug #5272 (Duplicate): Updating ceph from 0.61.2 to 0.61.3 obviously changes tunables of existing...
- I'm running a ceph cluster with three server nodes, each running one MON, one MDS and three OSDs to provide CEPHFS st...
- 09:49 AM devops Bug #5263 (In Progress): Python Error While Installing ceph-deply on debian wheezy
- The version 1.0 pachages should not have included the test directory. I'm double checking the repos to ensure thaey...
- 09:35 AM Bug #5260 (Resolved): mon: FAILED assert(other->is_writeable()) from MDSMonitor on 0.61.2
- 08:47 AM Bug #4999 (Can't reproduce): monitor sync failure
- 08:34 AM Bug #5257 (Resolved): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- The prefork fix is backported to cuttlefish, so closing this one out then.
- 07:34 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Running without tcmalloc would be a very helpful data point, yes. You can get non-tcmalloc packages built for precis...
- 07:16 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- It turns out that the Debian wheezy libgoogle-perftools-dev package and ceph packages depends on libgoogle-perftools4...
- 05:44 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Sorry. s/Gary/Sage/
- 05:43 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Would it be helpful to try and build packages that don't use tcmalloc (using the --without-tcmalloc configure option)...
- 12:40 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- No, unfortunately the latest cuttlefish branch didn't fix it. We had another crash about 6 hours after we upgraded.
... - 04:38 AM Revision a08d6204 (ceph): mds: do not double-queue file recovery in eval_gather
- This fixes a specific case of double-queuing seen in #4832:
- client goes stale, inode marked NEEDSRECOVER
- eval ... - 03:08 AM Revision 3ac6ffe8 (ceph): Merge branch 'wip-ceph-cli' into master
- Conflicts:
src/include/rados/librados.h
src/librados/librados.cc
src/osdc/Objecter.cc
src/pybind/rados.py
Requir... - 01:46 AM Revision faa1ae76 (ceph): MDSMonitor: dead debugging code
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 3f7cac32 (ceph): ceph: improve error reporting on failure to connect to cluster
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 783b7ec8 (ceph): librados, ceph, rados.py: -EINVAL for create with null/invalid name
- Means setting defaults should be more careful throughout as well
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:46 AM Revision 2431bfb6 (ceph): librados: rados_X_command need to assemble a vector from char *cmd
- The old monitors take a vector with words split; new monitors don't
care, but the old ones do
Signed-off-by: Dan Mic... - 01:46 AM Revision b114e11a (ceph): ceph: refactor -s -> status to common code, pass childargs to old mons
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 44466815 (ceph): ceph: error and verbose message improvement
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:46 AM Revision 37a61028 (ceph): ceph: -v should mean version, not --verbose
- To be implemented soon with ceph_ver.h
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:46 AM Revision 24a5212d (ceph): ceph, librados, rados.py, librados tests: pass cmd as array
- Using ceph to pass commands to the old monitor requires the
message to have words in a vector; this means that we nee... - 01:46 AM Revision 7785fc53 (ceph): rados.py: make exception with errno string instead of int
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:44 AM Revision ead8d89d (ceph): ceph: fix up old-monitor handling
- Finish command after submitting to old monitor, rather than falling
through to new-command handling
Also, translate -... - 01:41 AM Revision 8108c952 (ceph): AuthMonitor: fix signed/unsigned comparison warning
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:41 AM Revision 366de90d (ceph): librados, rados.py: rados_create2: add clustername and future flags
- rados.py also gets "conf_defaults" dict for things you might want to
default in your app differently before ceph.conf... - 01:41 AM Revision 3720b64a (ceph): ceph: collect/use clustername, and set defaults like other utilities
- (defaults like log_to_stderr, err_to_stderr)
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 01:41 AM Revision b1588bd4 (ceph): ceph: catch/handle exceptions in admin socket commands
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:38 AM Revision f43c9745 (ceph): mon: upgrade auth database on leader
- If we are the leader, and the auth database has not yet been upgraded,
do so. The upgrade consists of translating ol... - 01:38 AM Revision f2177a4d (ceph): mon: AuthMonitor: remove dead code to avoid confusion
- AuthMonitor::election_finished() does nothing.
PaxosService::election_finished() is the one being handled.
Signed-o... - 01:38 AM Revision afebad4f (ceph): auth: CephxKeyServer: add secrets_{begin,end}() getters
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 01:38 AM Revision 115bb933 (ceph): ceph: Remove connect/command timeouts; too risky for now
- Keep 10s timeout when connecting for help descriptions, however
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:35 AM Revision 5c308447 (ceph): doc: Updated with glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:29 AM Revision 8e13b38c (ceph): doc: Updated with glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:27 AM Revision 7116de35 (ceph): doc: Correction and index tags.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:26 AM Revision ae5aeb1c (ceph): doc: Updates for glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
06/06/2013
- 11:01 PM devops Feature #5018: arm: ceph-deploy: push packages to ARM
- Is this by any chance a duplicate ?
- 10:59 PM devops Feature #5089 (In Progress): ceph-deploy install fails on arm
- Needs a bit more testing.
- 10:57 PM devops Feature #5091 (In Progress): google-perftools for arm
- Need to verify that new upstream package build will work for us.
- 10:56 PM devops Feature #5092 (Closed): libatomic-ops for arm; or use gcc atomics instead
- This does not appear to be an issues. libatomicops is not supported on some arm architectures, but v7 is ok. Early ...
- 10:53 PM devops Feature #5015: ceph-deploy: push packages to all ceph repos
- ceph-deploy is being added to all the testing and named releases.
The is still some automation that could be appli... - 10:51 PM devops Feature #5088 (Resolved): ceph-deploy packages need to install on arm
- Completed. Arm version of ceph-deploy built and added to the repo.
- 10:49 PM devops Feature #5090 (Resolved): ceph-build: Need to support arm in the repos.
- Completed, It was just adding armhf to the architectures in the repo cofnig.
- 10:48 PM devops Feature #5016 (In Progress): ceph-deploy: gitbuilders for release packages
- Waiting for gitbuilder VMs to be instantiated.
- 10:42 PM Revision c9569804 (ceph): task/install.py: extraneous subscript in upgrade() for only some remotes
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:35 PM Bug #5270 (Resolved): osd: crash in PG::peek_map_epoch()
- ...
- 10:33 PM Bug #5269 (Resolved): osd: EEXIST on mkcoll
- ...
- 10:14 PM Revision ce2b686a (ceph): Merge pull request #347 from dalgaaf/wip-da-scripts
- Some smaller fixes for init-radosgw files
- 09:53 PM CephFS Bug #4832: mds: failed auth_unpin assert
- full log attached for posterity. see wip-4832
- 06:27 PM CephFS Bug #4832: mds: failed auth_unpin assert
- ...
- 07:23 AM CephFS Bug #4832: mds: failed auth_unpin assert
- ...
- 09:38 PM CephFS Fix #5268 (Closed): mds: fix/clean up file size/mtime recovery code
- from diagnosing #4832 (see the attached log) it looks like this code needs an overhaul:
* i don't think we should ... - 08:55 PM Revision 4bf75015 (ceph): mon: fix preforker exit behavior behavior
- In 3c5706163b72245768958155d767abf561e6d96d we made exit() not actually
exit so that the leak checking would behave f... - 08:55 PM Revision d398a185 (ceph): rados.py: correct some C types
- trunc was getting size_t instead of uint64_t, leading to bad results
in 32-bit environments. Explicitly cast to the d... - 08:20 PM Linux kernel client Bug #5267 (Won't Fix): Kernal 3.2.0-23 crashed
- I don't know how to descript it. The kernal crashed and the last output on the screen is in attached. Who can tell me...
- 06:58 PM Revision b394edc1 (ceph): doc/release-notes: v0.61.3
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:59 PM Revision 3d6eaf58 (ceph): doc: Added upstart syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:58 PM Revision 2d9a46c2 (ceph): doc: Added link to Upstart syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:00 PM devops Bug #5266 (Closed): the apt-get install instructions are missing an update
- http://ceph.com/docs/master/start/quick-start-preflight/
This section is missing the update:
wget -q -O- 'https... - 04:53 PM devops Documentation #5265: node-name is confusing. hostname is probably more accurate
- I think it might be helpful to have a section of the QSG that describes the basic networking requirements (i.e., host...
- 04:49 PM devops Documentation #5265 (Closed): node-name is confusing. hostname is probably more accurate
- http://ceph.com/docs/master/start/quick-ceph-deploy/
ceph-deploy new {node-name}
ceph-deploy new ceph-node
nod... - 04:28 PM Revision 4ee638cc (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 04:23 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- found it (probably):...
- 04:06 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- ...
- 04:21 PM Revision 595962aa (ceph): Merge branch 'wip_5154'
- Fixes: #5154
Reviewed-by: Sage Weil <sage@inktank.com> - 04:17 PM devops Bug #5263: Python Error While Installing ceph-deply on debian wheezy
- Adding package list just in case:
root@ceph-server:/mnt/my-cluster# dpkg -l
Desired=Unknown/Install/Remove/Purge/... - 04:14 PM devops Bug #5263 (Resolved): Python Error While Installing ceph-deply on debian wheezy
- While trying to install ceph-deploy on a new Debian 7.0/Wheezy with all the latest updates I got the following error:...
- 03:46 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- I updated my cluster from 0.61.2 to 0.61.3 and can tell a noticeable improvement. There are still some I/O stalls whi...
- 11:51 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- I've uploaded slowpeer-ceph-osd.2.log.bz2 (--debug-ms=1 --debug-filestore=5 --debug-osd=20) & slowpeer-osd2-ceph.log ...
- 08:21 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- So, I've upgraded my whole cluster to cuttlefish git (7d549cb), mainly to address this issue. The treee I've installe...
- 02:16 PM rgw Bug #5262 (Resolved): rgw: can't access buckets with names that start with 'auth'
- 01:34 PM Revision 963a9c46 (ceph): init-radosgw*: add all sections to usage output
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:33 PM Revision 4ea24ae7 (ceph): init-radosgw*: add status
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:21 PM Revision 39fff6a1 (ceph): fix init-radosgw* to use the same indentation
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:47 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Sage Weil wrote:
> the problem:
>
> mon.1 and .2 had newer data, mon.0 had older data.
> mon.0 converts, waits t... - 11:16 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- the mon.1 log snippet...
- 11:15 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- the problem:
mon.1 and .2 had newer data, mon.0 had older data.
mon.0 converts, waits to join quorum
mon.1 conve... - 06:31 AM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- cephdrop:ceph-5257-mondirs.tar.bz2, fetched earlier today.
- 10:51 AM Feature #4982 (In Progress): OSD: namespaces pt 1 (librados/osd, not caps)
- 10:09 AM rgw Bug #5261 (In Progress): rgw: 'cors' is not regarded as a sub-resource
- 10:04 AM rgw Bug #5261 (Resolved): rgw: 'cors' is not regarded as a sub-resource
- 'cors' needs to be regarded as a sub-resource, otherwise auth signing is not being done correctly.
- 09:51 AM Bug #4976: osd powercycle triggers object corruption on xfs
- ubuntu@teuthology:/a/teuthology-2013-06-05_10:57:29-rados-cuttlefish-master-basic/31967
- 09:37 AM Bug #5154 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 09:29 AM Bug #4731 (Resolved): PG: don't write out pg epoch on every map activation
- 08:10 AM Bug #5246: mon crashing on pool/pg creation with wip-mon
- comments on gh
- 07:40 AM Revision 8f9b1470 (ceph): Merge branch 'wip-3527'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 07:23 AM Revision 4b80c5b9 (ceph): rados: Output client address in rados listwatchers request
- Add client entity_addr_t string to list of watchers rados interface
Signed-off-by: David Zafman <david.zafman@inktan... - 07:23 AM Revision 0cbc0a08 (ceph): osd: Add dump_watchers to osd admin socket to examine all watchers
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision 4eb576e3 (ceph): Add test_blacklist_self() librados function for test cases
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision a4dbfa31 (ceph): test: Add blacklisting to test_stress_watch
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision 0bd60f8e (ceph): osd: Add entity_addr_t to watch_info_t and Watch
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:23 AM Revision ab0da283 (ceph): osd: Drop watchers from blacklisted clients
- On blackist addition or populate ObjectContext
check watcher address against blacklist
Add dout() of the watcher's... - 07:23 AM Revision 3b0a44d9 (ceph): osd: Add dump_blacklist to admin socket
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:28 AM Bug #5255 (Resolved): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- 06:19 AM Bug #5260 (Resolved): mon: FAILED assert(other->is_writeable()) from MDSMonitor on 0.61.2
- Lack of logging doesn't help that much in assessing what may be going on, but the stack trace might prove itself usef...
- 06:09 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- All our OSD nodes have now been updated to packages built from the latest cuttlefish branch, commit 7d549cb82ab8e..
... - 01:27 AM Feature #3527 (Resolved): osd: blacklist should cancel outstanding watches from blacklisted client
- commit:8f9b1470dd50bab9fa85450306c274b1a70a672c
- 12:44 AM Revision 92d085f7 (ceph): mon: fix preforker exit behavior behavior
- In 3c5706163b72245768958155d767abf561e6d96d we made exit() not actually
exit so that the leak checking would behave f...
06/05/2013
- 11:09 PM Revision 91d54a8f (ceph): Merge remote-tracking branch 'gh/next-leaks' into next
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 10:09 PM Revision 5deece1d (ceph): PG: don't dirty log unconditionally in activate()
- merge_log and friends all take care of dirtying the log
as necessary.
Fixes: #5238
Signed-off-by: Samuel Just <sam.j... - 09:21 PM CephFS Bug #4832: mds: failed auth_unpin assert
- lgo is here flab:/home/sage/tmp/4832
- 09:21 PM CephFS Bug #4832: mds: failed auth_unpin assert
- it's getting recovered twice:...
- 09:02 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Faidon: can you send a tarball of your mon dirs? IIRC the old files are still present post-conversion, so we should ...
- 06:19 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- from the logs on cephdrop, this looks like a non-deterministic store conversion maybe? the quorum 0,1 is happily chu...
- 06:16 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- 05:39 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I just upgraded another box and I'm not observing the same behavior. OSDs are now down while PGs are upgrading. This ...
- 05:22 PM Bug #5257 (Need More Info): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- do you have a complete mon log for this? if not, can you capture one the next time around? that osd should have bee...
- 04:48 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- There seems to have been a monitor election (without me doing anything) exactly before the "141 up":...
- 04:36 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I'm sure nodown wasn't set. I didn't restart all mons at once, just 12 (one box) out of 141.
This is what "grep os... - 04:30 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- are you sure 'nodown' wasn't set? this upgrade happens in load_pgs(), long before the osd sends a message to the mon...
- 01:05 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- Just to give a sense of the size of the issue:...
- 12:54 PM Bug #5257: Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- This happened after a while:...
- 11:38 AM Bug #5257 (Resolved): Ceph OSD bobtail->cuttlefish upgrade goes backward in time with osdmap
- I upgraded ceph on one of my boxes (12 osds) and the osds came up, printing "183140 PGs are upgrading". During that t...
- 08:07 PM Revision 951fc2fa (ceph): OSD: resurrect a parent if it splits into the pg we want to create
- When attempting to create a new pg object in response to a
peering message, there are 3 cases:
1) That pg is currentl... - 07:58 PM Revision 5a53da3c (ceph): ceph-test: add ceph_test_rados_api_lock to packaging and qa
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:58 PM Revision 30733af9 (ceph): Makefile.am: add -ldl to unittest_pglog
- b70868e007ffa56e0eabf22b4ca836327c5f82d4 broke non-package builds on
ubuntu and debian. This fixes the problem, and i... - 07:58 PM Revision 02946e5e (ceph): qa: stop running xfstests 192 in qemu
- This test is unreliable in a vm since it relies on command timing for
checking access time.
Signed-off-by: Josh Durg... - 07:58 PM Revision 68ccf8eb (ceph): Add RADOS API lock tests
- Add tests for the advisory locking API calls.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Signed-off-by: Fili... - 07:48 PM Revision d8415663 (ceph): Add RADOS lock mechanism to the librados C/C++ API.
- Add functions to the librados C/C++ API, to take advantage and utilize the
advisory locking system offered by RADOS.
... - 07:05 PM devops Feature #5214: Kernel gitbuilders for rpm distros
- This needed centos 6.4 .I know it said 6.3 or 6.4 but we already needed 6.4 cloud-init support for other things so it...
- 06:45 PM Revision 6f78b6e0 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 06:44 PM Revision d9703117 (ceph): doc: Added key and ceph repository to ceph-deploy install.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:10 PM Revision 92b1e398 (ceph): v0.61.3
- 05:59 PM Bug #5256: Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- Cephdrop now has 5256-ceph-mon.ms-be1005.log.gz, 5256-ceph-mon.ms-fe1001.log.gz, 5256-ceph-mon.ms-fe1003.log.gz.
T... - 01:50 PM Bug #5256 (In Progress): Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- 11:29 AM Bug #5256 (Resolved): Upgraded bobtail->cuttlefish mon crashes, then can't resume the conversion
- ...
- 05:33 PM Revision c76838f6 (ceph): osd: Style corrections
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:33 PM Revision 89524eb5 (ceph): osd: Fix usage of commands supported by TestOpsSocketHook::test_ops()
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:33 PM Revision 7acf3de6 (ceph): cls,msg: Fix use of set_in4_quad() to set a entity_addr_t
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:31 PM Revision 7d549cb8 (ceph): os/LevelDBStore: only remove logger if non-null
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit ce67c58db7d3e259ef5a8222ef2ebb1febbf7362)
Fixe... - 03:53 PM Revision a99435d0 (ceph): mon: fix leak of loopback Connection
- The accessor returns a reference. Instead of taking+dropping it each
time, take one ref in Monitor ctor and release ... - 03:53 PM devops Bug #5259 (Duplicate): osd create command fails inconsistently on ubuntu
- ubuntu@teuthology:/a/teuthology-2013-06-05_01:01:15-ceph-deploy-master-testing-basic/31847...
- 03:43 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Okay so I tried duplicating this again today. And now I can't. I think it was due to an iptables issue at first, but ...
- 03:42 PM Revision 08bb8d51 (ceph): messages/MMonHealth: remove unused flag field
- This was initialized in (one of) the ctor(s), but not encoded/decoded,
and not used. Remove it. This makes valgrind... - 03:34 PM Revision 4974b29e (ceph): messages/MMonProbe: fix uninitialized variables
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com> - 03:11 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- Don't know since we don't have a design; but probably not as I suspect it will require a (very minor) format change/e...
- 03:06 PM rgw Feature #5218: rgw: make bucket removal "atomic"
- When fixed, will this be backported to bobtail?
- 02:21 PM devops Bug #5258 (Resolved): ceph-deploy: forgetkeys command could delete existing keyring files without...
- From an admin point of view, it would be nice to have 'forgetkeys' command to delete only existing keyring files and ...
- 01:51 PM Bug #5240: run_seed_to_range failed, probably fdcache
- 2013-06-05T04:21:14.657 INFO:teuthology.orchestra.run.err:2013-06-05 04:21:58.389650 7faabeffd700 10 filestore(b) tru...
- 12:31 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- ...
- 12:30 PM Bug #4179: osd: memory leak during deep scrub on bobtail
- as Sam requested, here is the perf dump for each osds on the cluster...
- 11:40 AM Bug #5255: 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- Just tested this and it works as expected.
- 10:39 AM Bug #5255: 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- backported with commit commit:7d549cb82ab8ebcf1cc104fc557d601b486c7635
- 10:29 AM Bug #5255 (Pending Backport): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- Sage had already created a patch for this but it's only on next (commit:ce67c58db7d3e259ef5a8222ef2ebb1febbf7362).
... - 10:27 AM Bug #5255 (In Progress): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- 10:04 AM Bug #5255 (Resolved): 0.56.6 -> cuttlefish tip (to be .3), mon crashes on boot
- I upgraded my first mon from 0.56.6 to cuttlefish tip as of now (8544ea7) and it crashes on boot with:...
- 11:32 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- For the slow peering case, I think the first problem is that we unconditionally dirty the log in activate(). Since m...
- 07:51 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Looking more closely it appears that for the qa job the problem is just that the recovery gets very low priority due ...
- 07:50 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Stefan Priebe wrote:
> Hi sage is this related to my one? http://tracker.ceph.com/issues/5232
Only sort of.. one ... - 10:32 AM Fix #5232 (In Progress): osd: slow peering due to pg log rewrites
- 07:34 AM Bug #4999: monitor sync failure
- No, I meant I had hit the original issue again, where a sync failed
due to timeout (see updates 2,3)
I haven't be... - 04:14 AM Bug #5205: mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_addresses()
- Thanks Adam, this provides great insight on what's going on.
- 12:46 AM Revision e4eb4aa2 (ceph): teuthology-lock --summary: allow --machine-type=all
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:24 AM Revision 8c23d8cb (ceph): dev/rbd-diff: make formats into bullet lists (solves linebreak probs)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:22 AM Revision ff8f9d30 (ceph): rados: only 1 client for objectcacher stress test
- Otherwise these may step on each other.
06/04/2013
- 11:39 PM Revision 051f477a (ceph): Merge pull request #346 from ceph/wip-5233
- rados.py: correct some C types
- 11:20 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- Hi sage is this related to my one? http://tracker.ceph.com/issues/5232
- 04:49 PM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- the health checks was a red herring. wait_for_recovery calls assert, but the other thread(s) finish before we see th...
- 09:26 AM Bug #5238: osd: slow recovery (uselessly dirtying pg logs during peering)
- I think this might be a teuthology problem: i can't find any ceph process running on the cluster when it hangs. tryi...
- 11:11 PM Revision 188ae890 (ceph): ceph_manager: don't say you have no arguments and then list them
- Calling ceph pg dump --format=json works better without -- before pg
(how did this work before?...)
Signed-off-by: D... - 10:35 PM Revision 09a796d7 (ceph): doc: Removed ceph-deploy git, and added ceph-deploy packages.
- fixes: #5253
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:35 PM Revision d1e2e7b6 (ceph): doc: Modified pre-flight checklist for ceph-deploy packages.
- fixes: #5253
- 10:33 PM Revision 72a6767e (ceph): doc: Added title. Suppresses no title warning messages.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:11 PM Bug #5205: mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_addresses()
- I've also encountered this problem, running 0.61.2 on CentOS 6.4 (uname 2.6.32-220.el6.x86_64 #1 SMP Tue Dec 6 19:48:...
- 08:48 PM Revision 891641e8 (ceph): messages/MMonProbe: remove unused fields
- These fields are no longer used. We already bumped the mon internal
protocol in 5d7dd5ab67922b10351c3c7f57865d2c3e681... - 08:23 PM Revision 6dd7d469 (ceph): rados.py: correct some C types
- trunc was getting size_t instead of uint64_t, leading to bad results
in 32-bit environments. Explicitly cast to the d... - 08:13 PM Revision 6f8b53a0 (ceph): ceph: cleanup: accept --conf *and* -c; suppress stderr if no outs
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:13 PM Revision 24a270a1 (ceph): librados, rados.py: add rados_create2/init2
- librados clients, particularly the ceph tool, need to be able
to specify a full 'name'; rados_create enforced 'client... - 08:12 PM Revision ee0913c2 (ceph): Merge remote-tracking branch 'origin/master' into wip-ceph-cli
- Conflicts:
src/mon/OSDMonitor.cc
src/osd/OSD.cc
src/osd/ReplicatedPG.cc - 08:08 PM Revision 85576dba (ceph): Revert "mds: initialize rejoins_pending"
- This reverts commit 05a57bdd1289a63dcf2d4ca2f0dd3d73aff684ac.
Supplanted by d7fb9b173a163eb2318af5832456f0f236f716fd. - 08:08 PM Revision 0c4ca2ae (ceph): mds: allow purging "dirty parent" stray inode
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 08:08 PM Revision d7fb9b17 (ceph): mds: initialize some member variables of MDCache
- I added some member variables to class MDCache, but forget to
initialize them.
Fixes: #5236
Signed-off-by: Yan, Zhen... - 08:08 PM Revision bbdefe34 (ceph): Merge remote-tracking branch 'gh/next'
- 07:40 PM CephFS Bug #3681: kclient fsx fails nightly
- I think this has already been fixed (a cap revoke bug in the MDS code). When handling truncate request, current MDS ...
- 07:39 PM Revision 38d3c3cb (ceph): Merge pull request #340 from dachary/wip-5213
- PGLog::merge_old_entry unit tests
Reviewed-by: Sam Just <sam.just@inktank.com> - 07:38 PM Revision 8d948f61 (ceph): Merge pull request #327 from dachary/wip-pg_missing_t-tests
- unit tests for pg_missing_t
Reviewed-by: Sam Just <sam.just@inktank.com> - 07:36 PM Revision 96559465 (ceph): OSD: remove created argument from get_or_create_pg()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:36 PM Revision 15a5e099 (ceph): OSD: make get_or_create_pg handle_pg_peering_evt
- handle_pg_peering_evt() includes checking for splitting
and unlocking the pg.
Signed-off-by: Samuel Just <sam.just@i... - 07:36 PM Revision d605eafd (ceph): OSD: add pgid and res_map to DeletingState
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:07 PM Revision 64b3e833 (ceph): Revert "mds: allow purging "dirty parent" stray inode"
- This reverts commit b8f1cb978944a616b69150fdbb3a6b978d75b1dc.
- 06:07 PM Revision 05a57bdd (ceph): mds: initialize rejoins_pending
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:05 PM Revision c2169147 (ceph): Revert "mds: initialize some member variables of MDCache"
- This reverts commit 2d655bde8de9ad255d63718768558399cacd7068.
- 05:44 PM Bug #4999: monitor sync failure
- Jim, you mean you hit the leveldb error again? can you post a complete log for that? The one in the original report...
- 05:42 PM Revision ce67c58d (ceph): os/LevelDBStore: only remove logger if non-null
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:37 PM Revision cdf5785c (ceph): test_filestore_idempotent: make newly created objects globally unique
- The filestore requires hobjects to be globally unique.
Fixes: #5240
Signed-off-by: Samuel Just <sam.just@inktank.com... - 05:13 PM Bug #5246 (Fix Under Review): mon crashing on pool/pg creation with wip-mon
- pushed a simplification of the is_readable/writeable checks to wip-mon
- 08:33 AM Bug #5246: mon crashing on pool/pg creation with wip-mon
- Postponed but not forgotten.
- 07:46 AM Bug #5246 (Resolved): mon crashing on pool/pg creation with wip-mon
- this is using wip-mon when the cluster is first being setup during pool creation. OSDs were (possibly unrelated) goi...
- 04:42 PM Revision 713719a0 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 04:40 PM Bug #5233 (Resolved): python rados tests induce bad filestore truncate on arm
- commit:051f477
- 01:59 PM Bug #5233 (Fix Under Review): python rados tests induce bad filestore truncate on arm
- Added #5252 for the osd error handling part.
- 04:39 PM Revision 8544ea75 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 04:38 PM Revision 8bbd0370 (ceph): Merge pull request #344 from ceph/wip-5220
- Reviewed-by: Sage Weil <sage@inktank.com>
- 04:07 PM Revision 3ec763c4 (ceph): ceph: fix valgrind grep output parsing
- When you pass a single file to zgrep you don't get the filename prefix,
which confuses the split line a few lines down. - 03:56 PM Feature #5147: Display unique cluster ID in ceph status
- oh.. yeah, it's a uuid, e.g. "3cbff3a6-18f6-42e8-8940-febea7eb4282"
also, i didn't backport the change to cuttlefi... - 03:55 PM Feature #5147 (Need More Info): Display unique cluster ID in ceph status
- Can you please confirm the format of the unique string? PS have requested it being something easy to communucate over...
- 03:27 PM Revision b226e117 (ceph): os/LevelDBStore: fix merge loop
- We were double-incrementing p, both in the for statement and in the
body. While we are here, drop the unnecessary el... - 03:09 PM devops Documentation #5253 (Resolved): Update Pre-Flight docs to use ceph-deploy package
- update pre-flight info at http://ceph.com/docs/master/start/ to instruct users to download ceph-deploy package, which...
- 03:04 PM Bug #5225 (Rejected): arm: rbd fsx test failed on the arm set up
- fsx allocates the entire image size in memory. We just need to decrease the image size to make it work on these machi...
- 01:59 PM Bug #5252 (Resolved): osd: EINVAL from truncate causes osd to crash
- If a rados client sends a truncate operation that exceeds the maximum file size, truncate/ftruncate(2) will return EI...
- 01:15 PM Bug #4976: osd powercycle triggers object corruption on xfs
- this is looking more like an xfs bug to me.. sent something to the list.
i also think it is new in 3.9. need to tr... - 12:49 PM Bug #5239 (Need More Info): osd: Segmentation fault in ceph-osd / tcmalloc
- 09:36 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- this is either heap corruption, or a buggy tcmalloc, i think.
are there known problsm with wheezy's tcmalloc versi... - 09:36 AM Bug #5239: osd: Segmentation fault in ceph-osd / tcmalloc
- Gary, can you please take a look at this?
- 12:34 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- I'm running a single MDS on the same server as a MON and a ODS. We're not using the FS very much, just testing, this ...
- 12:16 PM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Can you provide the output of "ceph -s" as well, please. And start up an MDS daemon after setting "debug mds = 20" an...
- 11:19 AM CephFS Bug #5250: ceph-mds 0.61.2 aborts on start
- Full log at pastebin.com : http://pastebin.com/9YPMjw0t
- 11:18 AM CephFS Bug #5250 (Can't reproduce): ceph-mds 0.61.2 aborts on start
- After rebooting the whole cluster using the "shut the braker off" method, I had some BTRFS corruption which was fixed...
- 12:32 PM Bug #5247 (Resolved): upgrade suite is hanging
- tested on '0.63-229-g64b3e83-1precise' [sha1: 64b3e833f62f2538ffd7bd565d968decf6584691]
- 12:19 PM Bug #5247: upgrade suite is hanging
- error seen is ...
- 10:47 AM Bug #5247: upgrade suite is hanging
- 09:27 AM Bug #5247 (Resolved): upgrade suite is hanging
- has gottne hung the last 2-3 nights
- 12:27 PM Bug #5251 (Can't reproduce): wrong node messages in mds log
- when upgrading from bobtail to next branch, seeing repeated wrong node messages in the osd logs....
- 11:43 AM Revision b70868e0 (ceph): unit tests for PGLog::merge_old_entry
- The tests covers 100% of the LOC of merge_old_entry. It is broken down
in 13 cases to enumerate all the situations it... - 10:57 AM Bug #5163: filestore: ENOTEMPTY on object removal
- Can we get a recursive ls of 2.363_head on that osd?
- 10:50 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- what happens if you do 'ceph-disk-active /dev/sdb1' (or whatever the xfs patition is)? what about 'partprobe /dev/sd...
- 10:44 AM Bug #5240 (Resolved): run_seed_to_range failed, probably fdcache
- 10:26 AM RADOS Feature #5249 (Resolved): mon: support leader election configuration
- Right now, monitor election is handled by selecting the monitor with the lowest IP that can reach enough peers. This ...
- 10:02 AM devops Bug #5248 (Resolved): upstart: ceph-all job is starting too soon
- The current ceph-all job specifies the following:
start on (local-filesystems and net-device-up IFACE!=lo)
This c... - 09:49 AM Bug #5237 (Duplicate): filestore idempotent tester failure
- 09:39 AM rbd Bug #5220 (Resolved): test_ls_snaps segfaults on the arm test setup
- 09:37 AM CephFS Bug #5236: mds assert when starting file scan
- 09:33 AM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- this is definitely using hte wrong version of ceph-deploy.. discover is not a command any more. somehow pulling from...
- 08:42 AM rgw Bug #5245: Frequent 500s from radosgw
- Yes, there is a single radosgw process:...
- 07:58 AM rgw Bug #5245: Frequent 500s from radosgw
- Can you verify that you only have a single gateway running on that socket, and that the process id does not change wh...
- 07:51 AM rgw Bug #5245: Frequent 500s from radosgw
- This is my Apache config:...
- 07:30 AM rgw Bug #5245: Frequent 500s from radosgw
- Could it be that you let apache spawn the gateways by itself? Or maybe running multiple gateways over the same socket...
- 02:32 AM rgw Bug #5245 (Can't reproduce): Frequent 500s from radosgw
- Hi,
I have roughly 30 clients talking simultaneously to radosgw over 1Gbps link. I use boto library on the client ... - 08:33 AM Bug #5215 (Resolved): mon: hang during sync with mon thrashing
- commit:eb6d5fcf994d2a25304827d7384eee58f40939af
- 07:17 AM Bug #5215 (In Progress): mon: hang during sync with mon thrashing
- Managed to trigger this using the following job:...
- 04:07 AM Revision f6f4f8f7 (ceph): librados cmd tests: mon_status comes to stdout, not stderr
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision fbfdd51a (ceph): ceph: backward-compatibility hack: blank line before JSON output
- Many JSON commands (osd dump, et. al.) used to print a status
line first before the actual output; this has been fixe... - 04:07 AM Revision 51a887a2 (ceph): Add ceph_test_rados_api_cmd to the ceph-test package
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 18f2f194 (ceph): test/librados: remove "set_auid" pool tests
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 21a1c4d3 (ceph): mon: fix POOL_OP_AUID_CHANGE
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision a4b824cd (ceph): PGMonitor: fix pg dump and dump_stuck
- dump needed to default to format plain, not json
dump_stuck was not doing format = plain correctly (coredumping)
Sig... - 04:07 AM Revision 8c674800 (ceph): ceph: various cleanups
- - make base class valid() do useful work
- remove valid from CephPoolname; pool need not exist for create
- add --u... - 04:07 AM Revision 5e90e6c8 (ceph): mon/MonCap: set text in set_allow_all()
- This will let the cap encode/decode to the same value.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:07 AM Revision 0bec7e13 (ceph): mon/MonCap: fix setting of text in parse()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision d4bfce7c (ceph): mon: better debugging of caps messages/values
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:07 AM Revision 5bd93b3a (ceph): ceph: refactor help so it can be called after cluster connection
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:07 AM Revision 6cec9ccc (ceph): librados: fix unsigned vs. signed warning
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:06 AM Revision be1a5124 (ceph): cmdparse, mon: add cmd_vartype_stringify for _allowed_command
- cmd_vartype are not all strings, and need a type-variant function
to turn them into strings for authorization against... - 04:05 AM Revision f1021c9b (ceph): cmdparse: add handle_bad_get(), ceph:: qualifiers, cmdmap_t
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:53 AM Revision b8f1cb97 (ceph): mds: allow purging "dirty parent" stray inode
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 03:52 AM Revision 2d655bde (ceph): mds: initialize some member variables of MDCache
- I added some member variables to class MDCache, but forget to
initialize them.
Fixes: #5236
Signed-off-by: Yan, Zhen... - 01:26 AM Revision 17029b27 (ceph): test_librbd: use correct type for varargs snap test
- uint64_t is passed in, but int was extracted. This fails on 32-bit builds.
Fixes: #5220
Signed-off-by: Josh Durgin <... - 12:30 AM Revision df34cff7 (ceph): ceph: use conf_parse_argv to deal with nonspecial Ceph args
- This means parsing argv only once now, so pass arg lists to
new_style_command(). A little cleanup/commenting too.
S... - 12:30 AM Revision 456f96f9 (ceph): ceph: remove global declarations, declare verbose and cluster near top
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision b0469a14 (ceph): cephtool/test.sh: fix "expect failure"
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 8dd36183 (ceph): ceph: finish changing bestsigs to bestcmds
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 98093718 (ceph): ceph: move admin-daemon command before connect()
- Allow admin-daemon commands to work even if we can't connect()
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 12:30 AM Revision 74f5ea44 (ceph): mon/MonCap: allow osd, mds to write to cluster log
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:30 AM Revision dc73581a (ceph): mon: include cluster fsid/uuid in status output
- Implements: #5147
Signed-off-by: Sage Weil <sage@inktank.com> - 12:30 AM Revision 73a1b216 (ceph): ceph: make ceph -w output 'ceph status' first
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 12:30 AM Revision 065b29cd (ceph): librados, rados.py: add conf_parse_argv_remainder()
- New parsing function to extract any known arguments from a vector
and return any unknowns; useful for ceph CLI to all... - 12:24 AM Revision 22660bde (ceph): MDSMonitor, cmdparse: increase resiliency of bad cmd_getval()
- MDSMonitor: check for and handle bad maxmds get
cmdparse.h: Use gcc demangler to print bad boost::variant typenames,
...
06/03/2013
- 10:08 PM Cleanup #4809 (Resolved): MMonProbe extra fields
- 09:53 PM Feature #5147 (Resolved): Display unique cluster ID in ceph status
- don't think we need to backport this one.
- 09:53 PM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- could this simply be:
- start sync
- sync last_committed
- crash before reaching osdmap_$lastcommitted
- osd re... - 09:50 PM CephFS Bug #5236: mds assert when starting file scan
- commit:2d655bde8de9ad255d63718768558399cacd7068
thanks! - 05:53 PM CephFS Bug #5236: mds assert when starting file scan
- looks like I forget to initialize MDCache::rejoins_pending
- 02:17 PM CephFS Bug #5236: mds assert when starting file scan
- Yan, I got as far as identifying that the problem is that rejoin_gather_finish->identify_files_to_recovery is getting...
- 10:00 AM CephFS Bug #5236: mds assert when starting file scan
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-06-03_01:00:48-fs-master-testing-basic/30161
- 07:52 AM CephFS Bug #5236 (Resolved): mds assert when starting file scan
- ...
- 08:45 PM Revision 1cb7dbd9 (ceph): messages/MClientCapRelease: fix string output
- Use the vector size, not what is in the header, which is not yet filled in
for outgoing messages.
Signed-off-by: Sag... - 07:23 PM Revision 27f82ce3 (ceph): ceph: Add missing usage "ceph osd blacklist ls"
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:25 PM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
- ...
- 04:57 PM Revision bd7292b5 (ceph): ceph: debug valgrind error
- File "/var/lib/teuthworker/teuthology-master/teuthology/task/ceph.py", line 215, in valgrind_post
(file, kind) = ... - 04:44 PM RADOS Tasks #5243 (New): osd testing: create peering speed test
- Create teuthology task which generates a deterministic numbers of pg remaps and summarizes the peering "speed".
Th... - 04:23 PM rgw Feature #5170: RGW: Object restriping tool to fix large objects from argonaut.
- 04:09 PM devops Bug #5242: ceph-deploy: reports purgedata as invalid command when purge is not successful
- ubuntu@teuthology:/a/teuthology-2013-06-02_01:00:44-fs-master-testing-basic/29298
- 04:08 PM devops Bug #5242 (Resolved): ceph-deploy: reports purgedata as invalid command when purge is not successful
- ...
- 03:50 PM CephFS Fix #5241: MDS: not valgrind (leak) clean
- teuthology-2013-06-03_01:00:48-fs-master-testing-basic:
30170, 30172, 30174 - 03:43 PM CephFS Fix #5241 (New): MDS: not valgrind (leak) clean
- Valgrind info at /a/teuthology-2013-06-01_01:00:43-fs-next-testing-basic/28691/remote/ubuntu@plana85.front.sepia.ceph...
- 03:50 PM Bug #5240: run_seed_to_range failed, probably fdcache
- Looks like the tester will place objects with the same name into different collections, fixing test.
- 03:39 PM Bug #5240 (Resolved): run_seed_to_range failed, probably fdcache
- 2013-06-03T04:26:53.232 INFO:teuthology.orchestra.run.err:2013-06-03 04:27:34.948984 7fa652ef5780 0 filestore_diff d...
- 03:40 PM Bug #4976: osd powercycle triggers object corruption on xfs
- two writes to the object, at offset A~B and C~D, then read the whole thing. the original write appears intact, but a...
- 03:35 PM Bug #5156 (Duplicate): OSD: split followed by pg resurrection might leave an object in two collec...
- 02:55 PM Bug #5226: Some PG stay in "incomplete" state
- Well, if I look /var/lib/ceph/osd/ceph-19/current/4.5c_head or /var/lib/ceph/osd/ceph-19/current/4.0_head for example...
- 09:35 AM Bug #5226 (Need More Info): Some PG stay in "incomplete" state
- it sounds as though osd.19 was also missing hte data prior to osd.25 going away. can you look for the pg subdirector...
- 01:22 PM Revision 367e203f (ceph): fusetrace_ll.cc: handle return value of fuse_session_loop()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 01:07 PM Feature #4107: Usage quota for rados pools
- Duplicated by 4465 and 4466.
- 12:26 PM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- One way to do that would be to use lsblk /dev/<disk> and look for the word "part". I'm not sure lsblk is on every dis...
- 09:42 AM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- the python code that does this is pretty kludgey.. any suggestions for a more robust enumeration strategy should be p...
- 09:26 AM devops Bug #5211: ceph-disk prepare: list_partitions() shouldn't return disks
- More info:
A customer has its OS installed on /dev/sdak.
When running ceph-disk prepare /dev/sda, ceph-disk-pre... - 10:48 AM Revision 541320cf (ceph): mds/MDCache.cc: reduce scope of 'CDir *dir' in _create_system_file_fini...
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:19 AM rbd Bug #5220 (In Progress): test_ls_snaps segfaults on the arm test setup
- 09:55 AM Revision 7aa9b92d (ceph): mds/MDCache.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM Revision f7071b24 (ceph): osd/PG.cc: prefer prefix ++operator for iterator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM Revision 575652aa (ceph): key_value_store/kv_flat_btree_async.cc: fix some reassign before use va...
- Fix some cases of "(performance) Variable 'err' is reassigned a
value before the old one has been used." issues from ... - 09:55 AM Revision 8afbc280 (ceph): kv_flat_btree_async.cc: fix assigned but unused value issue
- Fix "Variable 'r' is assigned a value that is never used." issue from
cppcheck. Check return value and print warning ... - 09:55 AM Revision 1b70fcd4 (ceph): mds/Migrator.cc: reduce scope of 'in' in handle_export_prep()
- Reduce scope of 'CInode *in' since it's the way it's done already
in other paths of the function.
Signed-off-by: Dan... - 09:55 AM Revision 84dedf5b (ceph): mount/mount.ceph.c: reduce scope of 'value'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:55 AM rgw Feature #4310 (In Progress): rgw: multisite: radosgw changes: copy across regions
- 09:55 AM rgw Feature #4337 (In Progress): rgw: multisite: metadata sync agent: implement full sync
- 09:39 AM Bug #5176 (Resolved): leveldb: Compaction makes things time-out yielding spurious elections
- 08:42 AM Fix #5232: osd: slow peering due to pg log rewrites
- Should I post the config?
- 08:37 AM Bug #5239 (Can't reproduce): osd: Segmentation fault in ceph-osd / tcmalloc
- We're still experiencing segmentation faults in the ceph-osd daemons from the 0.61.2-1~bpo70+1 debian packages.
It a... - 08:28 AM Bug #5238 (Resolved): osd: slow recovery (uselessly dirtying pg logs during peering)
- seeing several failures due to slow recovery. it looks like the health checks stop, and teuthology continues on for ...
- 08:26 AM Bug #5237 (Duplicate): filestore idempotent tester failure
- ...
- 04:21 AM Revision 4fa5f99a (ceph): ceph-fuse: create finisher threads after fork()
- The ObjectCacher and MonClient classes both instantiate Finisher
threads. We need to make sure they are created *aft... - 03:59 AM Revision 1e99be15 (ceph): vstart.sh: make client logs unique
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:08 AM Revision eb6d5fcf (ceph): os/LevelDBStore: fix merge loop
- We were double-incrementing p, both in the for statement and in the
body. While we are here, drop the unnecessary el... - 12:27 AM Revision d017afb5 (ceph): msgr: add get_messenger() to Connection
- This was part of commit 27381c0c6259ac89f5f9c592b4bfb585937a1cfc.
Signed-off-by: Sage Weil <sage@inktank.com>
06/02/2013
- 11:34 PM Revision 38f8d850 (ceph): mon: discard messages from disconnected clients
- If the client is not connected, discard the message. They will
reconnect and resend anyway, so there is no point in ... - 11:34 PM Revision ffb87918 (ceph): mon: start lease timer from peon_init()
- In the scenario:
- leader wins, peons lose
- leader sees it is too far behind on paxos and bootstraps
- leader tr... - 11:34 PM Revision 61135964 (ceph): mon/Paxos: adjust trimming defaults up; rename options
- - trim more at a time (by an order of magnitude)
- rename fields to paxos_trim_{min,max}; only trim when there are mi... - 11:34 PM Revision 36d94898 (ceph): msgr: add Messenger reference to Connection
- This allows us to get the messenger associated with a connection.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherr... - 11:29 PM Revision 2dc40281 (ceph): common/Preforker: fix warnings
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a284c9ece85f11d020d492120be66a9f4c997416) - 10:52 PM Revision f7c19440 (ceph): Merge pull request #337 from dalgaaf/wip-da-CID-medium.v2
- Fix several medium impact CID issues V2
Reviewed-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision 44d15138 (ceph): Merge remote-tracking branch 'gh/next'
- 09:09 PM Revision 87dcba2d (ceph): os/LevelDBStore: do compact_prefix() work asynchronously
- We generally do not want to block while compacting a range of leveldb.
Push the blocking+waiting off to a separate th... - 09:09 PM Revision 6543da74 (ceph): os/LevelDBStore: allow compaction of key ranges
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e20c9a3f79ccfeb816ed634ca25de29fc5975ea8) - 09:09 PM Revision dcd9b793 (ceph): mon/MonitorDBStore: allow compaction of ranges
- Allow a transaction to describe the compaction of a range of keys. Do this
in a backward compatible say, such that o... - 09:09 PM Revision d14665e5 (ceph): mon: compact trimmed range, not entire prefix
- This will reduce the work that leveldb is asked to do by only triggering
compaction of the keys that were just trimme... - 09:09 PM Revision 83b1edac (ceph): os/LevelDBStore: merge adjacent ranges in compactionqueue
- If we get behind and multiple adjacent ranges end up in the queue, merge
them so that we fire off compaction on large... - 09:09 PM Revision 0109fa8a (ceph): mon: make compaction bounds overlap
- When we trim items N to M, compact over range (N-1) to M so that the
items in the queue will share bounds and get mer... - 09:09 PM Revision 85d629a5 (ceph): os/LevelDBStore: add perfcounters
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 7802292e0a49be607d7ba139b44d5ea1f98e07e6) - 09:09 PM Revision cc88cdfe (ceph): mon: return instead of exit(3) via preforker
- This lets us run all the locally-scoped dtors so that leak checking will
work.
Signed-off-by: Sage Weil <sage@inktan... - 09:09 PM Revision d284eaf9 (ceph): mon: fix leak of health_monitor and config_key_service
- Switch to using regular pointers here. The lifecycle of these services is
very simple such that refcounting is overk... - 09:09 PM Revision 3372235d (ceph): mon: destroy MonitorDBStore before g_ceph_context
- Put it on the heap so that we can destroy it before the g_ceph_context
cct that it references. This fixes a crash li... - 09:09 PM Revision 48ee9283 (ceph): fix test users of LevelDBStore
- Need to pass in cct.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 446e0770c77de5d72858dcf7... - 07:16 PM Fix #5232: osd: slow peering due to pg log rewrites
- No config changes except the minimum right now. Before I just had changed the osd op thread count.
4096 pgs 24 osd... - 02:40 PM Fix #5232: osd: slow peering due to pg log rewrites
- Stefan, are there any non-default options for in your ceph.conf that might affect pg log size? How many pgs do you h...
- 01:45 PM Fix #5232: osd: slow peering due to pg log rewrites
- even so, it seems like a lot of time is spent just in the removal phase.. perhaps there is something not quite right ...
- 01:43 PM Fix #5232: osd: slow peering due to pg log rewrites
- This looks to me like a lot of time is being spent in leveldb clearing and rewriting the pglog. This is probably jus...
- 11:33 AM Fix #5232: osd: slow peering due to pg log rewrites
- May be a hint or just luck i could reduce the effect and time to recover by lowering osd op threads to 2 (default) in...
- 11:32 AM Fix #5232: osd: slow peering due to pg log rewrites
- Attached you'll find a log with debugging enabled in betweek and two new gdb thread all traces.
- 09:39 AM Fix #5232: osd: slow peering due to pg log rewrites
- stefan: can you also do
ceph --admin-daemon /var/run/ceph/ceph-osd.NNN.asok config set debug_ms 1
ceph --admin-... - 09:38 AM Fix #5232: osd: slow peering due to pg log rewrites
- this thread?...
- 05:08 AM Fix #5232 (Resolved): osd: slow peering due to pg log rewrites
- I noticed that since cuttlefish the osd recovery process is extremely slow. Also client I/o gets stalled to the recov...
- 03:34 PM Bug #5163: filestore: ENOTEMPTY on object removal
- moved tamil's issue to #5233. and mike, i see the output now, but it doesn't make much sense. a more complete log w...
- 03:26 PM Bug #5163: filestore: ENOTEMPTY on object removal
- Tamil- I see, it's the python rados tests. Is this reproducible?
- 03:18 PM Bug #5163 (Need More Info): filestore: ENOTEMPTY on object removal
- Tamil- Yours looks like a different (and easier) bug. what was the workload? It appears to just be a bad trucnation...
- 03:29 PM Bug #5233 (Resolved): python rados tests induce bad filestore truncate on arm
- see #5163
filestore saw... - 10:50 AM Revision 6cdc4f8f (ceph): merge_old_entry arguments info and oe are changed to const because
- there is no side effect.
The PGLog::clear function is added to reset all data members to the
same state they have af... - 06:29 AM Bug #5226: Some PG stay in "incomplete" state
- After replacing OSD.25, near all incompletes PG are [19, 25] or [25, 19] :
> $ ceph health detail
> HEALTH_WARN 1...
06/01/2013
- 08:39 PM Revision bac5720b (ceph): qa: rsync test: exclude /usr/local
- Some plana have non-world-readable crap in /usr/local/samba. Avoid
/usr/local entirely for that and any similar land... - 08:33 PM Revision ed8e3c34 (ceph): rados: increase recovery timeout when powercycling
- Machine reboots take a while, and i've observed recovery making progress
but not finishing in time. - 01:36 PM Bug #4976 (In Progress): osd powercycle triggers object corruption on xfs
- ubuntu@teuthology:/a/teuthology-2013-05-31_20:00:08-rados-cuttlefish-master-basic/28270
trying to reproduce this w... - 04:17 AM Revision 9f1afe1a (ceph): mon: fix uninitialized fields in MMonHealth
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d7e2ab1451e284cd4273cca47... - 04:16 AM Revision d7e2ab14 (ceph): mon: fix uninitialized fields in MMonHealth
- Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision f1ccb2d8 (ceph): mon: start lease timer from peon_init()
- In the scenario:
- leader wins, peons lose
- leader sees it is too far behind on paxos and bootstraps
- leader tr... - 12:05 AM Revision fb3cd0c2 (ceph): mon: discard messages from disconnected clients
- If the client is not connected, discard the message. They will
reconnect and resend anyway, so there is no point in ... - 12:05 AM Revision 6b8e74f0 (ceph): mon/Paxos: adjust trimming defaults up; rename options
- - trim more at a time (by an order of magnitude)
- rename fields to paxos_trim_{min,max}; only trim when there are mi...
05/31/2013
- 11:22 PM Revision 957b0d00 (ceph): replaced tab with spaces
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 10:13 PM Revision a03ccf17 (ceph): OSD: *inodes_hard_limit must be less than the fd limit
- Also add a comment explaining that.
Fixes: #5224
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg... - 10:10 PM Revision e12a9c46 (ceph): OSD: tell them they died if they don't exist as well
- OSDMap::get_down_at() asserts that the osd exists.
Fixes: #5223
Signed-off-by: Samuel Just <sam.just@inktank.com>
Re... - 09:48 PM Revision b2e49041 (ceph): Merge branch 'wip-osd-leaks' into next
- Reviewed-by: David Zafman <david.zafman@inktank.com>
- 09:48 PM Revision 9865bb46 (ceph): osd: reset heartbeat peers during shutdown
- This fixes a leak of the Connection's and related structures.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision cec83798 (ceph): osd: fix msg leak on shutdown in ms_dispatch
- Reported-by: David Zafman <david.zafman@inktank.com>
Signed-off-by: Sage Weil <sage@inktank.com> - 09:48 PM Revision 222059ec (ceph): osd: fix leak of MOSDMarkMeDown
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:48 PM Revision 923683ff (ceph): mon/MonClient: fix leak of MMonGetVersionReply
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:35 PM Revision 08631e7a (ceph): rgw: some user metadata fixes
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:44 PM Revision d5b67d49 (ceph): PGLog: only add entry to caller_ops in add() if reqid_is_indexed()
- Fixes: #5216
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 08:36 PM Revision a5f6d896 (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 07:48 PM Revision 9aaff149 (ceph): upstart: handle upper case in cluster name and id
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
(cherry picked from commit 851619ab6645967e5d765... - 07:47 PM Revision 0f246a3a (ceph): Merge pull request #338 from alram/next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 07:33 PM Revision 851619ab (ceph): upstart: handle upper case in cluster name and id
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
- 07:30 PM Revision dfad09b0 (ceph): rgw_admin: modify mdlog functionality
- mdlog list, can handle cases where there is and there's no shard id
specified. mdlog trim requires shard if.
Signed-... - 07:30 PM Revision 2b9ab9f3 (ceph): rgw: set truncated as false if ENOENT when listing mdlog entries
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:28 PM rbd Bug #5040 (Resolved): krbd: record that an parent info refresh has failed
- The following has been committed to the ceph-client
"testing" branch:
93e85fb rbd: clean up a few things in the r... - 07:27 PM rbd Bug #3094 (Resolved): krbd: race between finding existing client and creating new one
- The following has been committed to the "testing" branch
of the ceph-client git repository.
601e01d rbd: protect ... - 07:22 PM Revision e46d7d68 (ceph): Merge branch 'wip-rgw-geo-enovance' into wip-rgw-geo-2
- Conflicts:
src/Makefile.am
src/rgw/rgw_admin.cc
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:23 PM rbd Bug #5222 (Fix Under Review): krbd: use per-rbd_dev mutex to protect header updates
- This patch has been posted for review:
0004-rbd-use-rwsem-to-protect-header-updates.patch
- 02:40 PM rbd Bug #5222 (Resolved): krbd: use per-rbd_dev mutex to protect header updates
- Currently updating header information for an rbd device
is protected by the control lock, which precludes
concurren... - 06:22 PM rbd Bug #3925 (Fix Under Review): krbd: sysfs write lockdep warnings
- I found that avoiding taking the ctl_lock when updating
getting or putting device references got rid of the
problem... - 10:58 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- That sequence reproduces the problem, even in the latest
version of the "testing" branch. (Not all of it may be
re... - 06:15 PM Revision 54d23052 (ceph): doc: Added Java example for setting protocol to HTTP.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:14 PM Revision 145c4808 (ceph): doc: Text of diagram for osd_throttles.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:14 PM rgw Bug #5228 (Duplicate): radosgw-admin bucket list no longer shows all buckets
- It can still list the buckets owned by a specific user when --uid is specified.
The bug was introduced by the foll... - 06:14 PM Revision 8d70c091 (ceph): doc: Omitted text diagram, and used literal include to text file.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:11 PM Bug #5227 (Can't reproduce): ARM set up: rados test failed
- rados_workunit_loadgen_mostlyread.yaml test failed in the ARM test setup [tala002, tala003, tala004]...
- 06:09 PM Revision e6ad9da0 (ceph): PGLog: only add entry to caller_ops in add() if reqid_is_indexed()
- Fixes: #5216
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:59 PM Revision f87a19d3 (ceph): OSDMonitor: skip new pools in update_pools_status() and get_pools_health()
- New pools won't be full. mon->pgmon()->pg_map.pg_pool_sum[poolid] will
implicitly create an entry for poolid causing... - 05:58 PM Revision ddb3a8d6 (ceph): unit tests for pg_missing_t
- All lines of code are tested. The conditions under which some methods
could corrupt the content of a pg_missing_t obj... - 05:39 PM Revision db85c52d (ceph): PG: don't write out pg map epoch every handle_activate_map
- We don't actually need to write out the pg map epoch on every
activate_map as long as:
a) the osd does not trim past ... - 05:35 PM Revision 8c6a912a (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:35 PM Revision f42e84ee (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 05:30 PM Revision 34733bdc (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:30 PM Revision 3d91301e (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 05:15 PM Revision 38ee69c2 (ceph): mds/MDCache.cc: fix dereference after null check
- Add assert for 'parent' before call assert on parent->is_auth().
CID 716922 (#1 of 1): Dereference after null check ... - 05:15 PM Revision 91f6b0f0 (ceph): mds/MDCache.cc: fix dereference null return value
- CID 716993 (#1 of 2): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might ... - 05:15 PM Revision c0e3d04b (ceph): mds/MDCache.cc: fix dereference null return value
- Add assert to fix:
CID 716994 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a... - 05:15 PM Revision 578e292b (ceph): mds/Migrator.cc: fix dereference after null check
- Add assert for 'le' to fix:
CID 716923 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Pas... - 05:15 PM Revision 0b78e2bc (ceph): mds/Migrator.cc: fix dereference after null check
- Add asserts to check for 'dir' to fix:
CID 716924 (#1-5 of 5): Dereference after null check (FORWARD_NULL)
var_der... - 05:15 PM Revision d9b00c43 (ceph): mds/Server.cc: fix dereference after null check
- Add assert to fix:
CID 716925 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null... - 05:15 PM Revision e5555582 (ceph): mds/Server.cc: fix dereference after null check
- CID 716926 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing "mdr" to function
"Ser... - 05:15 PM Revision cfdd87ca (ceph): mds/Server.cc: fix dereference after null check
- CID 716927 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "diri->snap... - 05:15 PM Revision 5aa0b129 (ceph): .gitignore: add directory from coverity tools
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:15 PM Revision 39a53e5c (ceph): mds/Server.cc: fix explicit null dereferenced
- CID 716928 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
var_deref_model: Passing null pointer "session" to ... - 05:15 PM Revision 2a024091 (ceph): mds/Locker.cc: fix explicit null dereferenced
- CID 716916 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to funct... - 05:15 PM Revision 679775ae (ceph): small_io_bench_fs.cc: check return value of FileStore::mkfs/mount()
- CID 743398 (#1 of 1): Unchecked return value (CHECKED_RETURN)
check_return: Calling function "FileStore::mount()" w... - 05:15 PM Revision a7a0425d (ceph): bench/dumb_backend.cc: check return value of posix_fadvise()
- CID 743396 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
check_return: Calling function "posix_fa... - 05:15 PM Revision db2fbb1d (ceph): bench/dumb_backend.cc: check return value of lseek()
- CID 743395 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
check_return: Calling function "lseek(fd... - 05:15 PM Revision bb8798e3 (ceph): mds/Locker.cc: fix dereference after null check
- CID 716917 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to fun... - 05:15 PM Revision 3969c695 (ceph): mds/Locker.cc: fix dereference after null check
- CID 716918 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to fun... - 05:15 PM Revision 59cffbab (ceph): mds/Locker.cc: fix dereference after null check
- CID 716919 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "cap" to fu... - 05:15 PM Revision 5d8440e3 (ceph): mds/MDCache.cc: fix dereference after null check
- CID 716921 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "dir" to fu... - 05:10 PM Revision c5fc52ae (ceph): rgw: only append prefetched data if reading from head
- Fixes: #5209
Backport: bobtail, cuttlefish
If the head object wrongfully contains data, but according to the
manifest... - 05:10 PM Revision b1312f94 (ceph): rgw: don't copy object idtag when copying object
- Fixes: #5204
When copying object we ended up also copying the original
object idtag which overrode the newly generate... - 04:39 PM Revision 8f3f0537 (ceph): rgw: Do not assum rest connection to be established
- Added a check to verify that rest connection is correctly initialized,
preventing a segmentation fault.
Signed-off-b... - 04:21 PM Bug #5226 (Won't Fix): Some PG stay in "incomplete" state
- Hi,
With bobtail I first loose the OSD.25 : the OSD process was crashing, and when its data are ballanced on other... - 03:55 PM Bug #4855: peek map assert
- root@ceph2:/var/log/ceph# ceph -v
ceph version 0.61.2 (fea782543a844bb277ae94d3391788b76c5bee60)
Hit this rep... - 03:35 PM Bug #5225 (Closed): arm: rbd fsx test failed on the arm set up
- rbd fsx test failed with core dump on the client.
logs are copied to ubuntu@burnupi24:/home/ubuntu/arm_testing_lo... - 03:19 PM Bug #5163: filestore: ENOTEMPTY on object removal
- The teuthology logs are copied to ubuntu@burnupi24.front.sepia.ceph.com:/home/ubuntu/bug5163/testing_logs_rados_python
- 03:16 PM Bug #5163: filestore: ENOTEMPTY on object removal
- This happened when running rados_python test on the arm test setup....
- 03:17 PM Bug #4579 (Resolved): kclient + ffsb workload makes osds mark themselves down
- e21f8df1eb0c459d12911785c69f7427d1ad5689
- 03:16 PM Bug #5216 (Resolved): restarted or failed osd resulted in a lot of caller_ops.size error messages...
- 11:25 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- The stalled I/O seems to come from the freshly started OSDs. They seem to tell ceph hey i can handle I/O but they're ...
- 11:24 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- this is the backport:
commit 2af3f1d40b9c64f58d1a05232c52b2a47426fef5
Author: Samuel Just <sam.just@inktank.com>
... - 11:12 AM Bug #5216 (Pending Backport): restarted or failed osd resulted in a lot of caller_ops.size error ...
- pushed fix to master, needs backport to cuttlefish
Note, this probably did not cause the IO hang. - 06:51 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- So i get the caller_ops.size 3002 > log size 3001 messages while the osd is offline and i get the slow request messag...
- 06:36 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- To me it seems that the osd sets itself online / available before it is really ready which then results in slow I/O.
... - 05:33 AM Bug #5216: restarted or failed osd resulted in a lot of caller_ops.size error messages and stalle...
- Then the whole ceph storage became instable until the osd is up and running again and had recovered.
- 05:32 AM Bug #5216 (Resolved): restarted or failed osd resulted in a lot of caller_ops.size error messages...
- I'm running upstream/cuttlefish 85ad65e294f2b3d4bd1cfef6ae613e31d1cea635
I've seen the following today while just ... - 03:16 PM Bug #5223 (Resolved): ./osd/OSDMap.h: 387: FAILED assert(exists(osd))
- 02:59 PM Bug #5223 (Resolved): ./osd/OSDMap.h: 387: FAILED assert(exists(osd))
- 13-05-31 03:07:57.486103 7fe8cc625700 0 -- 10.214.132.10:6801/30895 >> 10.214.131.23:6805/9730 pipe(0x211cc80 sd=70 ...
- 03:16 PM Bug #5224 (Resolved): too many open fds
- 03:11 PM Bug #5224 (Resolved): too many open fds
- 02:37 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- :/
0.61.2
[root@test-ceph-1001 ~]# yum list ceph
Loaded plugins: security
Installed Packages
ceph.x86_64 ... - 09:36 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- This fix landed in 0.61.1. Please try that (or a newer) version and see if you're still hitting it.
- 09:22 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- I hate to kick a dead horse, but did this make it into 0.63 or will it be available in a later release? Ran into this...
- 02:21 PM rbd Bug #5220: test_ls_snaps segfaults on the arm test setup
- recopying the yaml...
- 02:20 PM rbd Bug #5220 (Resolved): test_ls_snaps segfaults on the arm test setup
- Test setup: Tala002, Tala003, Tala004
this happens when trying to run rbd/workloads/c_api_tests.yaml on the arm te... - 01:17 PM rgw Bug #5197: Bucket shows up when listing buckets but does not exist anywhere else.
- And #5219 covers the "user check" not cleaning up.
- 01:09 PM rgw Bug #5197 (Resolved): Bucket shows up when listing buckets but does not exist anywhere else.
- Okay, so the bucket rm didn't work because the object's not on disk, so the initial stat fails, and the radosgw-admin...
- 01:17 PM rgw Feature #5219 (New): "radosgw-admin user check" should handle non-existent buckets in index
- Right now, if "radosgw-admin user check" encounters a bucket whose object doesn't exist it uses default values (becau...
- 01:04 PM rgw Feature #5218 (New): rgw: make bucket removal "atomic"
- Right now, bucket removal consists of two steps:
1) Remove the bucket object (making sure the bucket index doesn't l... - 12:04 PM devops Feature #5019 (In Progress): arm: gitbuilder for ARM
- The arm kernel gitbuilder is now building bootable kernels. No debug yet.
- 12:00 PM Fix #3188 (In Progress): osd: close read hole
- 11:33 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Some more details about my setup:
Hosts are CentOS 6.4 + elrepo kernel-ml. Ceph is cuttlefish (0.61.2) from official... - 10:54 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- I just want to add that I am definitely seeing this behavior on Cuttlefish. We run a number of VM's atop RBD. Any tim...
- 11:01 AM rgw Bug #5209 (Resolved): rgw: crash when head contains unexpected data (when getting range of bytes)
- Fix is reviewed and in the next branch, commit:c5fc52ae0fc851444226abd54a202af227d7cf17. Cherry-picked back to cuttle...
- 11:01 AM Bug #4813 (Resolved): pgs stuck creating
- 11:00 AM rgw Bug #5204 (Resolved): rgw: copy object leaks tail
- Fix is reviewed and in next branch, commit:b1312f94edc016e604f1d05ccfe2c788677f51d1. Cherry-picked to cuttlefish and ...
- 09:58 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
As a work around, the xfsprogs rpm is available from the Centos 6 repository, however installing that may result in...- 09:35 AM devops Feature #5217 (Rejected): Add "Ceph" to all Ceph package descriptions
- A number of the Ceph packages such as librbd and librados do not have "Ceph" in the package title. This makes it har...
- 07:06 AM Bug #4357 (Can't reproduce): osd: FAILED assert("join on thread that was never started" == 0)
- I'm closing this one for now. It hasn't popped up anymore, when it does, I'll re-open.
- 05:39 AM Revision fbf5a242 (ceph): Merge branch 'wip-5046'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:19 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Then a component is missing on my test system (Debian 7 wheezy).
After rebooting the filesystem is not mounted whe... - 05:07 AM Revision 64eb6df9 (ceph): valgrind: add another leveldb suppression
- 04:43 AM Revision df2d06db (ceph): mon: destroy MonitorDBStore before g_ceph_context
- Put it on the heap so that we can destroy it before the g_ceph_context
cct that it references. This fixes a crash li... - 03:28 AM Revision f4eddd7b (ceph): doc: Updated to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 474bb164 (ceph): doc: Updated title and syntax to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:27 AM Revision 7365d0c3 (ceph): doc: Updated to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:26 AM Revision eb35d739 (ceph): doc: Updated title to reflect glossary usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:25 AM Revision 65294bf6 (ceph): doc: Updated conf with ServerAlias for S3 subdomains.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:24 AM Revision 442f082a (ceph): doc: Updated object storage quick start for S3-style subdomains.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:22 AM Revision 5e450baa (ceph): doc: Updated text with new glossary terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:21 AM Revision c4001b12 (ceph): doc: Removed FAQ from the index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:21 AM Revision d52b8055 (ceph): doc: Removed FAQ doc. It's now in the wiki.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:25 AM Revision 131dca7d (ceph): debian: sync up postinst and prerm with latest
- - do not use invoke-rc.d for upstart
- do not stop daemons on upgrade
- misc other cleanups
This corresponds to the ... - 12:23 AM Revision cf9aa7a0 (ceph): debian: guard upstart {start,stop} with -x check
- Sigh.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:17 AM Revision a4001053 (ceph): Merge branch 'wip-deb-removal' into next
- Tested by Tamil, Gary.
05/30/2013
- 11:38 PM Revision 6bac8ac0 (ceph): rbd/kernel.sh: quit looking for snapshot sysfs entries
- The sysfs entries for snapshots went away a while ago, and this
script used them to verify sizes matched what was exp... - 11:27 PM Revision 38ed3e43 (ceph): Merge pull request #334 from ceph/wip-mon
- Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:22 PM Revision 1d75b49c (ceph): debian: add radosgw.postinst
- Start radosgw-all job.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:22 PM Revision d126a205 (ceph): debian: invoke-rc.d does not work with upstart jobs
- Broken by 19c5ac37ef87aeb3d3c30aa35cd61b6f3a8414bf.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:54 PM CephFS Bug #4753 (Resolved): mds/Locker.cc: 4167: FAILED assert(0)
- fixed this in commit:482733e9603e47a3a427b17bfb9b9189dacd5109
- 10:53 PM Revision 446e0770 (ceph): fix test users of LevelDBStore
- Need to pass in cct.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:44 PM Revision ec7731f7 (ceph): move log, ondisklog, missing from PG to PGLog
- PG::log, PG::ondisklog, PG::missing are moved from PG to a new PGLog
class and are made protected data members. It is... - 10:42 PM Revision d1b3eebd (ceph): os/WBThrottle: remove asserts in clear()
- cur_ios, etc may not be zero due to an in progress
flush.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed... - 10:23 PM Bug #5171 (Resolved): After crash monitor trying to bind to address of other monitor
- Denis reports that #5203 fix should resolve this one as well. Thanks!
- 10:22 PM Bug #5203 (Resolved): mon: backup monmap for sync appears to drop correct monitor names?
- fix is merged, commit:626de387e617db457d6d431c16327c275b0e8a34, and backported to cuttlefish.
Denis, can you open ... - 10:20 PM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Good. Looks like solution for #5171 too (unsure about all cases, but I still too distubed to remember precise - happe...
- 10:24 AM Bug #5203 (Fix Under Review): mon: backup monmap for sync appears to drop correct monitor names?
- 10:23 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- 10:19 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- proposed fix in wip-5203
- 09:15 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Edit: crash log had nothing to do with this bug. It's an entirely different issue regarding pick_addresses().
- 08:43 AM Bug #5203: mon: backup monmap for sync appears to drop correct monitor names?
- Verified by forcing a monitor to sync and to assert out before actually synchronizing (using --mon-sync-requester-kil...
- 08:17 AM Bug #5203 (Resolved): mon: backup monmap for sync appears to drop correct monitor names?
- Came across this one while debugging one of saaby's mon crashes.
Apparently, saaby (@ #ceph) recreated a monitor u... - 10:18 PM Bug #5177 (Rejected): logrotate.conf: "which /etc/init.d/ceph reload"
- Ah, ok. THanks!
- 10:08 PM Bug #5177: logrotate.conf: "which /etc/init.d/ceph reload"
- Oh, sorry, there are not your bug. This is Gentoo ebuild "sed" result.
- 10:04 PM Revision 3cc0f3d8 (ceph): Merge pull request #335 from ceph/wip-5176
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 09:57 PM Revision 7802292e (ceph): os/LevelDBStore: add perfcounters
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:38 PM Bug #5215: mon: hang during sync with mon thrashing
- yeah, this one too:
ubuntu@teuthology:/a/teuthology-2013-05-30_18:12:14-rados-next-testing-basic/26830$ - 09:37 PM Bug #5215 (Resolved): mon: hang during sync with mon thrashing
- mon syncs for a while and then stops/get stuck. i think this job failed yesterday, too, so it is likely easy to repr...
- 09:36 PM Revision a47ca583 (ceph): mon: make compaction bounds overlap
- When we trim items N to M, compact over range (N-1) to M so that the
items in the queue will share bounds and get mer... - 09:28 PM rbd Bug #3925 (In Progress): krbd: sysfs write lockdep warnings
- Well shit.
I unmapped my image and I got a lockdep error.
I'll look some more tomorrow.... - 09:26 PM rbd Bug #3925 (Resolved): krbd: sysfs write lockdep warnings
- I have my answer. The problem does not show up
now that the snapshot sysfs files are gone.
I'm marking this bug ... - 08:48 PM rbd Bug #3925: krbd: sysfs write lockdep warnings
- Well that was fun. I reproduced the problem immediately with:...
- 07:14 PM rbd Bug #3925 (In Progress): krbd: sysfs write lockdep warnings
- Since I've been unable to reproduce this problem with
current code, I'm going to try reproducing it using
code that... - 04:42 PM rbd Bug #3925: krbd: sysfs write lockdep warnings
- I just committed the following change to the
rbd/kernel.sh workunit in the "master" branch
of the ceph git reposito... - 09:05 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- Oh, now I know what's happening. The "kernel.sh" script
was looking at the snapshot sysfs files, which are no
long... - 08:56 AM rbd Bug #3925: krbd: sysfs write lockdep warnings
- I have tried to reproduce this a bunch of times, both
manually (as I described, using the refresh sysfs file)
and u... - 09:26 PM Revision f628dd0e (ceph): os/LevelDBStore: merge adjacent ranges in compactionqueue
- If we get behind and multiple adjacent ranges end up in the queue, merge
them so that we fire off compaction on large... - 09:17 PM Revision e9c32b97 (ceph): doc: note openstack changes for Grizzly
- These are just for the cinder configuration, nothing else changed.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:29 PM Revision 743c5287 (ceph): doc: Hadoop clarifications
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:29 PM Revision 352b7b59 (ceph): doc: start Hadoop installation docs
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:20 PM Revision 5fa098f1 (ceph): Added -r option to usage
- Added the -r option, which starts the radosgw and apache2 to access it
to the usage message.
Signed-off-by: Christop... - 06:43 PM Revision 8b7ca687 (ceph): mon: Monitor: backup monmap using all ceph features instead of quorum's
- When a monitor is freshly created and for some reason its initial sync is
aborted, it will end up with an incorrect b... - 06:42 PM Revision 1ba14336 (ceph): Merge pull request #333 from ceph/wip-5203
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:30 PM Revision 61ed69b5 (ceph): use cuttlefish branch instead of master
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:25 PM Revision d029abfa (ceph): valgrind: update suppressions for leveldb, libc leaks from mon
- These result in clean valgrind leak checks on the mon (at least with my
limited vstart testing). - 06:23 PM Revision 02ef6e91 (ceph): osd: do not assume head obc object exists when getting snapdir
- For a list-snaps operation on the snapdir, do not assume that the obc for the
head means the object exists. This fix... - 06:17 PM Revision 3c570616 (ceph): mon: return instead of exit(3) via preforker
- This lets us run all the locally-scoped dtors so that leak checking will
work.
Signed-off-by: Sage Weil <sage@inktan... - 06:17 PM Revision c888d1d3 (ceph): mon: fix leak of health_monitor and config_key_service
- Switch to using regular pointers here. The lifecycle of these services is
very simple such that refcounting is overk... - 06:10 PM Bug #5198 (Duplicate): osd: powercycle testing triggers corrupt object data on xfs
- oh, this is a dup of #4976
- 05:40 PM Feature #3848 (Resolved): osd: gracefully handle cluster network heartbeat failure
- 05:27 PM devops Bug #5210 (Resolved): ceph_deploy: purge and purgedata fails on ceph master branch
- daemons weren't getting stopped. fixed as of commit:cf9aa7a0037e56eada8b3c1bb59d59d0bfe7bba5
- 12:53 PM devops Bug #5210 (Resolved): ceph_deploy: purge and purgedata fails on ceph master branch
- test set up: plana08...
- 05:26 PM Bug #5206 (Resolved): debian: daemons stopped on upgrade
- fixed as of commit:cf9aa7a0037e56eada8b3c1bb59d59d0bfe7bba5
- 09:30 AM Bug #5206 (Resolved): debian: daemons stopped on upgrade
- wip-deb-removal
- 05:21 PM Revision 626de387 (ceph): mon: Monitor: backup monmap using all ceph features instead of quorum's
- When a monitor is freshly created and for some reason its initial sync is
aborted, it will end up with an incorrect b... - 05:17 PM devops Feature #5214 (Resolved): Kernel gitbuilders for rpm distros
- Need kernel gitbuilders for centos 6.3 or 6.4, Fedora18, OpenSuse 12.2 or 12.3 and sles11sp2.
The centos and fedora ... - 04:27 PM Bug #5200 (Resolved): mon: valgrind leaks
- 11:24 AM Bug #5200 (Fix Under Review): mon: valgrind leaks
- 10:02 AM Bug #5200 (In Progress): mon: valgrind leaks
- 03:53 PM Revision 59916b8e (ceph): debian: stop radosgw daemons on package removal
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:53 PM Revision 9e658f03 (ceph): debian: stop sysvinit ceph-mds daemons
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:51 PM Revision 70a38320 (ceph): debian: only stop daemons on removea; not upgrade
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:29 PM Subtask #5213 (Resolved): unit tests for src/osd/PGLog.{cc,h}
- "work in progress":https://github.com/dachary/ceph/tree/wip-5213
Focus on the functions related to log merging ( m... - 03:10 PM Revision f4025687 (ceph): rbd/concurrent.sh: probe rbd module at start
- There's no guarantee the rbd module is loaded when this script is
run, so add a line that loads it if necessary.
Sig... - 03:06 PM rbd Documentation #5212 (Closed): doc: link to recommended kernel version from pages that describe us...
- Default kernels like 3.2 in ubuntu precise are missing a lot of bug fixes for rbd and cephfs.
The docs recommend k... - 03:05 PM Revision 2957d68c (ceph): rbd_concurrent: add new task to test concurrent.sh
- Add a new kernel task to run the rbd concurrent test.
Signed-off-by: Alex Elder <elder@inktank.com> - 03:04 PM Bug #5176 (Pending Backport): leveldb: Compaction makes things time-out yielding spurious elections
- merged ito next, commit:3cc0f3d803c376167175dd9082dc24f76ee1bd7a
- 11:29 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- sylvain reports:...
- 03:04 PM rgw Bug #5197 (In Progress): Bucket shows up when listing buckets but does not exist anywhere else.
- Looking at the cluster indicates that indeed, there's an orphaned omap entry on the <user>.buckets object, that doesn...
- 12:28 PM rgw Bug #5197: Bucket shows up when listing buckets but does not exist anywhere else.
- This was an empty bucket created under argonaut. It was deleted normally while an argonaut->bobtail upgrade was "in p...
- 02:39 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- Yes, but not trivially.
- 02:31 PM rgw Feature #4715: rgw: Add support for OPTIONS HTTP method
- Neil Levine wrote:
> Yehuda, can we close this?
Can this be backported to bobtail?
- 02:08 PM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- udev shoudl trigger ceph-disk active after the reboot to bring the osd back up; no fstab entry should be necessary (p...
- 12:53 AM devops Bug #5194: udev does not start osd after reboot on wheezy or el6 or fedora
- Something like...
- 01:55 PM devops Bug #5211 (Resolved): ceph-disk prepare: list_partitions() shouldn't return disks
- @# ceph-disk-prepare /dev/sda
ceph-disk: Error: Device is mounted: /dev/sdak1@
list_partitions('/dev/sda') will o... - 01:45 PM Bug #5157 (In Progress): install: unable to pull ceph rpm packages on fedora18
- The install is failing because the epel repository is not configured.
The work around is to configure the repo:
... - 01:41 PM Bug #5188 (Resolved): ceph-deploy nightlies failing
- tested this locally and it works fine.
- 01:14 PM Bug #5188: ceph-deploy nightlies failing
- related to bug#5210
- 01:14 PM Bug #5188: ceph-deploy nightlies failing
- modified the yaml for ceph-deploy to pick cuttlefish branch instead of master.
- 01:18 PM rgw Bug #5209 (In Progress): rgw: crash when head contains unexpected data (when getting range of bytes)
- 12:45 PM rgw Bug #5209 (Resolved): rgw: crash when head contains unexpected data (when getting range of bytes)
- We ended up with a multipart object that had head with data (some old argonaut issue?). A request to retrieve only pa...
- 11:38 AM devops Bug #5208 (Resolved): Debian Wheezy Needs the 'ca-certificates' package before you can wget the p...
- 'ceph-deploy install...' needs the ca-certificates or you get :
pushy.protocol.proxy.ExceptionProxy: Command 'wget -... - 11:23 AM Bug #5183 (Resolved): occasional failure of rbd DiffIterateStress test
- 11:09 AM rgw Feature #5207 (New): rgw: make listing non-standard bucket names through S3 api configurable
- Buckets that were created through the swift api and do not conform to the S3 naming requirements can be listed. Make ...
- 09:37 AM rgw Bug #5204 (In Progress): rgw: copy object leaks tail
- 09:03 AM rgw Bug #5204 (Resolved): rgw: copy object leaks tail
- Problem is that we end up overriding the copied object tag with the original tag.
- 09:24 AM Bug #5205 (Resolved): mon: FAILED assert(ret == 0) on config's set_val_or_die() from pick_address...
- This is the crash's log (from saaby @ #ceph):...
- 08:14 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The following has been committed to the ceph-qa-suite
"master" branch:
2957d68 rbd_concurrent: add new task t... - 08:11 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The following has been committed to the ceph "master" branch:
f402568 rbd/concurrent.sh: probe rbd module at s... - 07:40 AM rbd Bug #3978: krbd qa: concurrent.sh test leaves something read-only
- The cleanup routine run when concurrent.sh exits is
run after a call to "wait", so all background tasks
should be d... - 05:50 AM rbd Bug #3978 (In Progress): krbd qa: concurrent.sh test leaves something read-only
- I've been running this test this morning and am finding it
is *not* exhibiting the problem that I originally reporte... - 07:35 AM devops Documentation #5202 (Rejected): "ceph osd stop" not available
- The documentation at http://ceph.com/docs/master/rados/troubleshooting/troubleshooting-osd/#stopping-w-out-rebalancin...
- 05:45 AM Revision c410f032 (ceph): Merge pull request #331 from ceph/wip-osd-interfacecheck
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 05:44 AM Revision bd2ba0e3 (ceph): Merge branch 'next'
- 05:43 AM Revision 0c059551 (ceph): osd: wait for healthy pings from peers in waiting-for-healthy state
- If we are (wrongly) marked down, we need to go into the waiting-for-healthy
state and verify that our network interfa... - 05:43 AM Revision e1dc3fd3 (ceph): osd: augment osd heartbeat peers with neighbors and randoms, to up some...
- - always include our neighbors to ensure we have a fully-connected
graph
- include some random neighbors to get at ... - 05:43 AM Revision b586f4a9 (ceph): osd: factor out _remove_heartbeat_peer
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:43 AM Revision a4d3b47a (ceph): osd: only add pg peers if active
- We will soon be in this method for the waiting-for-healthy state. As
a consequence, we need to remove any down peers... - 05:43 AM Revision 28ea184d (ceph): osd: remove down hb peers
- If a (say, random) peer goes down, filter it out.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:43 AM Revision 04aa2b5e (ceph): osd: distinguish between definitely healthy and definitely not unhealthy
- is_unhealthy() will assume they are healthy for some period after we
send our first ping attempt. is_healthy() is no... - 05:21 AM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- There has been another iteration of this bug happening on PGMonitor (from user saaby on IRC):...
- 05:06 AM Feature #2283: The ceph command should time out
- I'm hitting this too ... I wanted to monitor the health more closely with the recent mon issues unfortunately it oft...
- 04:58 AM Revision d20e30a7 (ceph): flushed the formatter after closing the primary section in MDLOG, BILOG...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 12:04 AM devops Feature #5019: arm: gitbuilder for ARM
- Took some futzing but I got the builds working. Unfortunately it did build an armel image as it looks like the auto d...
05/29/2013
- 11:53 PM Revision d86b9a85 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 11:50 PM Revision 85ad65e2 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 11:50 PM Revision 50ac8917 (ceph): osd: initialize new_state field when we use it
- If we use operator[] on a new int field its value is undefined; avoid
reading it or using |= et al until we initializ... - 10:54 PM Bug #5201 (Resolved): osd: valgrind leaks
- 10:54 PM Bug #5200 (Resolved): mon: valgrind leaks
- 10:06 PM Revision e21f8df1 (ceph): Merge branch 'wip_osd_throttle'
- Fixes: #4782
Reviewed-by: Sage Weil - 10:05 PM Revision a55e03cd (ceph): WBThrottle: add some comments and some asserts
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:05 PM Revision 4b31c7e7 (ceph): WBThrottle: rename replica nocache
- We may want to influence the caching behavior for other
reasons.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:01 PM Bug #5157: install: unable to pull ceph rpm packages on fedora18
- [ubuntu@burnupi23 ~]$ su -c 'rpm -Uvh http://gitbuilder.ceph.com/ceph-rpm-fc18-x86_64-basic/ref/cuttlefish/RPMS/x86_6...
- 08:51 PM devops Bug #4641 (Resolved): ceph-deploy install fails on fedora 18
- tested and it works fine on ceph version 0.61.2
- 08:50 PM Revision 45873b57 (ceph): rgw: verify bucket location only if exists
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:50 PM devops Bug #5199 (Resolved): ceph-deploy: on fedora18, osd create command doesnt seem to mount the disks
- test setup: burnupi22
while osd create command succeeds with no error, the osd disks are not mounted and the osd p... - 08:48 PM Linux kernel client Bug #4646 (Need More Info): kcephfs: writeback pagevec pool size vs stripe unit limit
- I'd like someone (like Sage) to determine whether
we should just mark this "won't fix." - 05:55 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- I implemented a fix for this, and got all the way to
the end of describing it, when I realized the math
makes this ... - 03:56 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- I think an easy fix for now is just to allocate the pagevec_pool
to have objects sufficient to hold pages that would... - 02:35 PM Linux kernel client Bug #4646: kcephfs: writeback pagevec pool size vs stripe unit limit
- On the osd, it looks to me like CEPH_MDS_OP_SETLAYOUT uses
ceph_file_layout_is_valid() to verify the layout supplied... - 08:41 PM Revision aac828c2 (ceph): osd: tell peers that ping us if they are dead
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:41 PM Revision c093e5bf (ceph): osd: avoid duplicate mon requests for a new osdmap
- sub_want() returns true if this is a new sub; only renew then.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:41 PM Revision 80942eb0 (ceph): osd: move health checks into a single helper
- For now we still only look at the internal heartbeats.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:41 PM Revision ea2b2329 (ceph): osd: simplify is_healthy() check during boot
- This has a slight behavior change in that we ask the mon for the latest
osdmap if our internal heartbeat is failing. ... - 08:23 PM Linux kernel client Feature #4770: krbd: consider including write data with layered existence check
- Removing myself as assignee, I won't have time to complete this.
- 08:22 PM Linux kernel client Bug #4869: libceph: osd_client: get_reply() generalize for more ops
- Removing myself as assignee, I won't have time to complete this.
- 08:09 PM Revision 81a96086 (ceph): rgw: forward delete_bucket to master region
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:28 PM Revision 482733e9 (ceph): mds: stay in SCAN state in file_eval
- If we are in the SCAN state, stay there until the recovery finishes. Do
not jump to another state from file_eval().
... - 05:27 PM Revision 0071b8e7 (ceph): mds: stay in SCAN state in file_eval
- If we are in the SCAN state, stay there until the recovery finishes. Do
not jump to another state from file_eval().
... - 05:27 PM Revision f71e1b1f (ceph): Makefile: include new message header files
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:26 PM Revision 532dee52 (ceph): Merge remote-tracking branch 'yan/wip-mds'
- Reviewed-by: Sage Weil <sage@inktank.com>
Conflicts:
src/mds/MDCache.cc - 05:25 PM Bug #5198 (Duplicate): osd: powercycle testing triggers corrupt object data on xfs
- ...
- 04:53 PM Bug #4967 (Resolved): Misbehaving OSD sets over half of the cluster as down despite "osd min down...
- committed to next, backported to cuttlefish
- 04:15 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- 04:49 PM Revision 29e4e7e3 (ceph): osd: do not assume head obc object exists when getting snapdir
- For a list-snaps operation on the snapdir, do not assume that the obc for the
head means the object exists. This fix... - 04:40 PM rgw Bug #5197 (Resolved): Bucket shows up when listing buckets but does not exist anywhere else.
There is a bucket which shows up when buckets are listed through the api but exists nowhere else. We need to get th...- 04:37 PM Feature #5147: Display unique cluster ID in ceph status
- 03:40 PM Revision 6da4b20c (ceph): mon: compact trimmed range, not entire prefix
- This will reduce the work that leveldb is asked to do by only triggering
compaction of the keys that were just trimme... - 03:35 PM Revision ab09f1e5 (ceph): mon/MonitorDBStore: allow compaction of ranges
- Allow a transaction to describe the compaction of a range of keys. Do this
in a backward compatible say, such that o... - 03:34 PM Revision e20c9a3f (ceph): os/LevelDBStore: allow compaction of key ranges
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:32 PM Revision f03a6f21 (ceph): Fixed default region creation issue
- If the default region did not exist, it is created,
but the previously created RGWDefaultRegionInfo object is not upd... - 03:14 PM Revision 1d0aa2ad (ceph): Merge pull request #329 from javacruft/wip-fuse-deps
- Use new fuse package instead of fuse-utils
- 03:11 PM Revision 3e5cead0 (ceph): rgw: user master region's version of bucket
- When creating a bucket, retrieve the bucket object
version from the master region and use it.
Signed-off-by: Yehuda ... - 03:07 PM Feature #4782 (Resolved): osd: build writeback model to replace async flusher
- 02:47 PM Bug #5195 (Resolved): "ceph-deploy mon create" fails when adding additional monitors
- When trying to add another monitor to an existing cluster with "ceph-deploy mon create <hostname>" the operation fail...
- 02:35 PM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- Whoops, mean to update http://tracker.ceph.com/issues/4646.
- 02:33 PM Bug #4603: ceph: writeback pagevec pool is created incorrectly
- On the osd, it looks to me like CEPH_MDS_OP_SETLAYOUT uses
ceph_file_layout_is_valid() to verify the layout supplied... - 01:59 PM devops Bug #5194 (Resolved): udev does not start osd after reboot on wheezy or el6 or fedora
- ceph-deploy creates a partition with a filesystem (XFS by default) and mounts it to /var/lib/ceph/osd/<clustername>-<...
- 01:53 PM rbd Bug #5040 (Fix Under Review): krbd: record that an parent info refresh has failed
- The following has been posted for review:
[PATCH] rbd: clean up a few things in the refresh path - 01:51 PM rbd Bug #3094 (Fix Under Review): krbd: race between finding existing client and creating new one
- The following has been posted for review:
[PATCH] rbd: protect against duplicate client creation - 08:49 AM rbd Bug #3094 (In Progress): krbd: race between finding existing client and creating new one
- I've been able to reproduce this problem by simply running
five instances of an "rbd map" command for the same image... - 01:43 PM Feature #3848 (Fix Under Review): osd: gracefully handle cluster network heartbeat failure
- 01:39 PM Bug #4801 (Duplicate): osd class path broken on fedora 18?
- 01:35 PM devops Bug #4984 (New): ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- 01:35 PM devops Bug #4984: ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- yes, the problem still exists....
- 01:23 PM devops Bug #5193 (Resolved): RHEL6 does not ship with xfsprogs
- The following commit adds an rpm package dependency on xfsprogs,
https://github.com/ceph/ceph/commit/b2501e91bb8... - 12:42 PM rgw Bug #5192 (Won't Fix): RGW: radosgw-admin user rm --access-key not working on bobtail
- access-key should stil be able to lookup the uid, but the command is failing.
radosgw-admin user rm --access-key=$... - 12:11 PM devops Bug #5047 (Closed): ceph build needs libboost 1.50 for debian sid
- The boost library issue seems to have been resolved upstream.
- 11:48 AM devops Feature #5191 (Rejected): Create gitbuilder for Hadoop v2.x compatible Ceph plugin
- We need a gitbuilder to build the Hadoop / Ceph plugin that is compatible with the Hadoop 2.x line (this is distinct ...
- 11:47 AM rbd Feature #4834 (In Progress): Recompile/package qemu with new version of librbd to enable asynchro...
- QEMU packages built against bobtail (0.56.6) and cuttlefish (0.61.2) with and without the async flush patch are avail...
- 11:45 AM devops Feature #5190 (Rejected): Create Apache Hadoop 2.x gitbuilder
- We need another gitbuilder for the Apache Hadoop 2.x line so that we can develop and test against it.
Let's call it ... - 11:22 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Faidon, it shouldn't affect cuttlefish as much, though that is not clear. That patch would need to be installed on a...
- 11:17 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Igur, a main problem is that we are writing out the pg epoch to the filestore when we don't need to. The second prob...
- 10:40 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- We wrote a test that sequentially reads 1M blocks spreaded by 64Mb offsets (i.e. from different placement groups) an...
- 11:19 AM Bug #5183 (Pending Backport): occasional failure of rbd DiffIterateStress test
- 09:45 AM Bug #5183: occasional failure of rbd DiffIterateStress test
- Looks good.
- 11:18 AM rbd Feature #5005: cinder: switch rbd driver to use librbd instead of the cli tool
- 11:18 AM rbd Feature #5004: cinder: make rbd configuration easier to use
- 11:18 AM rbd Feature #5003: cinder/nova: don't require ceph.conf on a compute host / support multiple clusters
- 10:07 AM devops Feature #5019: arm: gitbuilder for ARM
- Need various flavors of kernel gitbuilders for ARM - both debug and performance
- 10:05 AM devops Bug #5189: ceph-deploy disk prepare fails silently
- When I add another disk to the test VM (/dev/sdc) and create a partition /dev/sdc1 ceph-deploy succeeds with:
ceph... - 09:10 AM devops Bug #5189: ceph-deploy disk prepare fails silently
- Ceph was installed from the cuttlefish Debian/Ubuntu repo (including ceph-deploy).
ceph-deploy was used to create ... - 09:09 AM devops Bug #5189 (Resolved): ceph-deploy disk prepare fails silently
- $ ceph-deploy disk list ceph01-test
/dev/sda :
/dev/sda1 other, ext2, mounted on /boot
/dev/sda2 other
/dev/sd... - 09:58 AM Bug #5176: leveldb: Compaction makes things time-out yielding spurious elections
- Sylvain, I have a wip-5176 branch that makes us compact in a background thread, and over smaller ranges. Can you giv...
- 09:57 AM Revision e634d9d6 (ceph): Use new fuse package instead of fuse-utils
- The fuse-utils package was deprecated a while ago.
Switch the primary dependency for fuse tools to use
the preferred... - 09:35 AM Bug #4179 (In Progress): osd: memory leak during deep scrub on bobtail
- 08:56 AM Bug #5188 (Resolved): ceph-deploy nightlies failing
- 08:47 AM rbd Feature #5187 (Resolved): rbd: allow unmap using mapped image name
- The umount(8) command has a very useful feature that allows
one to specify *either* the device *or* the directory th... - 08:44 AM rbd Bug #5186 (Won't Fix): krbd: mapping same image produces ambiguous /dev file
- Since it's possible to map the same image more than once,
the mechanism of putting an entry in /dev/rbd/rbd/<image>
... - 08:38 AM rbd Bug #5185 (Closed): rbd: nothing prevents concurrent write mappings
- While attempting to test http://tracker.ceph.com/issues/3094
I learned that nothing prevented me from mapping the sa... - 08:16 AM rbd Bug #5184 (Resolved): libceph: create_singlethread_workqueue() error handling
- In ceph_osdc_init() there are these lines of code:...
- 07:39 AM rbd Bug #5146 (Resolved): krbd: wait for safe callback for writes
- The following has been committed to the ceph-client
"testing" branch:
70c725f rbd: wait for safe callback for... - 07:39 AM rbd Bug #3859 (Resolved): osd_client: define ceph_osdc_clear_request_linger()
- The following has been committed to the ceph-client
"testing" branch:
ebd8324 libceph: add lingering request ... - 07:33 AM Bug #4999: monitor sync failure
- I've been unable to reproduce this while using the debugging info patch.
Finally, yesterday I tried the cuttlefish... - 07:32 AM rbd Bug #4777 (Resolved): krbd: verify a few things in the zeroing routines
- The following has been committed to the "testing" branch
of the ceph-client git respository:
81d7ac5 rbd: flu... - 05:13 AM Revision 1bb4e743 (ceph): mon: disable tdump by default
- Grr.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:10 AM Revision 6afc22a1 (ceph): Merge remote-tracking branch 'gh/last'
- 03:44 AM Revision b6be7857 (ceph): Merge branch 'wip-5172'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 03:40 AM Revision 4af917d4 (ceph): os/LevelDBStore: do compact_prefix() work asynchronously
- We generally do not want to block while compacting a range of leveldb.
Push the blocking+waiting off to a separate th... - 03:39 AM Revision dd35c26e (ceph): osd: fix note_down_osd
- Fix bug introduced in 27381c0c6259ac89f5f9c592b4bfb585937a1cfc.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:39 AM Revision 45b84f39 (ceph): osd: fix hb con failure handler
- Fix a few bugs introduced by 27381c0c6259ac89f5f9c592b4bfb585937a1cfc:
- check against both front and back cons; eit... - 03:26 AM Feature #4929: Erasure encoded placement group
- maybe use erasure encoding from "rozofs":https://github.com/rozofs/rozofs
- 03:24 AM Subtask #5046: Factor out PG logs, PG missing
- Write "tests for pg_missing_t":https://github.com/dachary/ceph/tree/wip-pg_missing_t-tests
- 02:52 AM Revision ce6fc2ed (ceph): Merge pull request #319 from dalgaaf/wip-da-pylint-3
- Fix some smaller Python issues
- 12:51 AM Revision 260179b6 (ceph): Merge branch 'master' into merge
- 12:06 AM Revision 8f4de687 (ceph): Rhel support added
- Fixes: #4946
Signed-off-by: Warren Usui <warren.usui@inktank.com>
05/28/2013
- 10:48 PM Revision 648dcb92 (ceph): Merge pull request #326 from dalgaaf/wip-da-CID-727978
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 10:17 PM Feature #685 (Duplicate): libcephmon: interact with ceph monitors via a library
- 08:58 PM Revision 054e96cf (ceph): v0.63
- 08:48 PM Bug #5183 (Resolved): occasional failure of rbd DiffIterateStress test
- wip-osd-obc-snapdir
- 08:45 PM Bug #5172 (Resolved): wrongly marked down heartbeat issues
- commit:b6be785775442af1999b2543bd07a0d28391dbc5
- 08:39 PM Revision 64d1178f (ceph): rgw: mdlog, bilog RESTful api cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:00 PM Revision fabe7237 (ceph): ceph: first cut at --completion
- Factor out parsing JSON to sigdict; use from both main and completion
Currently invoking from bash completion with
... - 07:57 PM Revision 2dcc266f (ceph): ceph, MonCommands.h: code format/help format tweaks
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:57 PM Revision 65236a4a (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 07:56 PM Revision fca54bfb (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 07:47 PM Revision 5bca9c38 (ceph): HashIndex: sync top directory during start_split,merge,col_split
- Otherwise, the links might be ordered after the in progress
operation tag write. We need the in progress operation t... - 05:41 PM Revision 1c35556b (ceph): doc/dev/osd_internals: add wbthrottle.rst
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:41 PM Revision 4d53e9c9 (ceph): WBThrottle: add perfcounters
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:27 PM Revision e8f52840 (ceph): Merge pull request #325 from dalgaaf/wip-da-CID-727980
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 05:27 PM Revision 16e6b081 (ceph): Merge pull request #324 from dalgaaf/wip-da-CID-727979
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 04:39 PM devops Bug #5182 (Won't Fix): ceph-disk looks like it tries to mark preexisting OSD partitions with the ...
- ceph-disk prepare_dev says, near the end: if not is_partition(data), mark the partition as an OSD
type, udevadm set... - 04:38 PM Bug #5176 (Fix Under Review): leveldb: Compaction makes things time-out yielding spurious elections
- wip-5176
- 04:37 PM Documentation #5181 (Closed): need to explain what does and doesn't work with ceph-deploy and pre...
- ceph-deploy with preexisting partitions is weird; first, they may not be GPT, in which case
ceph-disk activate from ... - 04:17 PM Revision b528a915 (ceph): osd/OSDMap: fix Incremental dump
- The front hb addr entry may not be present.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:43 PM Revision 8e982071 (ceph): Merge pull request #322 from guilhem/patch-1
- Reviewed-by: Sage Weil <sage@inktank.com>
- 01:15 PM Bug #5180 (Resolved): start_split, start_col_split, start_merge must fsync after tagging the in p...
- 11:10 AM Bug #5180 (Resolved): start_split, start_col_split, start_merge must fsync after tagging the in p...
- 10:43 AM Revision 478b576a (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer needed.
CID 727978 (#1-2 of 2): Resource leak (RESOURCE... - 10:38 AM Revision e6efc39f (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer needed.
CID 727979 (#1-2 of 2): Resource leak (RESOURCE... - 10:27 AM Revision 6939b124 (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer
needed.
CID 727980 (#1-4 of 4): Resource leak (RESOURCE... - 09:55 AM rgw Feature #5169: Do not list swift containers when enumerating buckets using S3 API
- Can you provide some more logs for this issue, just to make sure that what we think happens actually happens?
- 09:49 AM Bug #5177 (Need More Info): logrotate.conf: "which /etc/init.d/ceph reload"
- I can't figure out which version has this problem... where do you see the borken reload line?
Thanks! - 09:08 AM Bug #5177 (Fix Under Review): logrotate.conf: "which /etc/init.d/ceph reload"
- 08:57 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- Okay, so you have a 15G monitor store? Is that it? If so, you might have been bit by #4895 and restarting the monito...
- 07:51 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- PPS
1) fix: 15G->30G->15G;
2) In theory, can be fixed by "--inject-monmap", but repair is slow or infinite... - 07:05 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- PS One more issue (I will not open new by same reason): in time of 2 of 3 monitors up and repair after (or in time) t...
- 06:43 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- OK, now I see: sync is tooo slow, but seems to be ready in future. Somebody can answer to this sync speed (fix or wan...
- 03:33 AM Bug #5171: After crash monitor trying to bind to address of other monitor
- No. First I trying to purge/recreate monitor. Now it infinite syncing and not going up. I just in panic (I have ticke...
- 08:51 AM rgw Documentation #5178 (Resolved): rgw: fix keystone openssl to nss conversion
- as specified in here:
[[http://thread.gmane.org/gmane.comp.file-systems.ceph.user/1637]] - 08:35 AM Revision 554b41b1 (ceph): Remove mon socket in post-stop
- If ceph-mon segfault, socket file isn't removed.
By adding a remove in post-stop, upstart clean run directory proper... - 06:08 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- See https://code.google.com/p/leveldb/issues/detail?id=158 and the discussion https://groups.google.com/forum/#!msg/...
- 04:28 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I just disabled compact-on-trim, and it doesn't look good :( It grew about 1GB in 2 hours.
On the plus side, there i... - 05:57 AM Revision 26effc0e (ceph): mds: warn on unconnected snap realms
- When there are more than one active MDS, restarting MDS triggers
assertion "reconnected_snaprealms.empty()" quite oft... - 05:57 AM Revision 03c0fe93 (ceph): mds: reorder EMetaBlob::add_primary_dentry's parameters
- prepare for adding new state parameter such as 'dirty_parent'
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 6c721116 (ceph): mds: journal backtrace update in EMetaBlob::fullbit
- Current way to journal backtrace update is set EMetaBlob::update_bt
to true. The problem is that an EMetaBlob can inc... - 05:57 AM Revision c9d2e256 (ceph): mds: rename last_renamed_version to backtrace_version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision b88c49b7 (ceph): mds: bring back old style backtrace handling
- To queue a backtrace update, current code allocates a BacktraceInfo
structure and adds it to log segment's update_bac... - 05:57 AM Revision 39b5e76c (ceph): mds: update backtraces when unlinking inodes
- unlink moves inodes to stray dir, it's a special form of rename.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 05a7588d (ceph): mds: remove old backtrace handling
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 617f70d2 (ceph): mds: move fetch_backtrace() to class MDCache
- We may want to fetch backtrace while corresponding inode isn't
instantiated. MDCache::fetch_backtrace() will be used ... - 05:57 AM Revision eeb68eb3 (ceph): mds: open inode by ino
- This patch adds "open-by-ino" helper. It utilizes backtrace to find
inode's path and open the inode. The algorithm lo... - 05:57 AM Revision ceaf51f7 (ceph): mds: bump the protocol version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 3120d969 (ceph): mds: open missing cap inodes
- When a recovering MDS enters reconnect stage, client sends reconnect
messages to it. The message lists open files, th... - 05:57 AM Revision 7e0e0963 (ceph): mds: use "open-by-ino" function to open remote link
- Also add a new config option "mds_open_remote_link_mode". The anchor
approach is used by default. If mode is non-zero... - 05:57 AM Revision d7b999be (ceph): mds: don't stop at export bounds when journaling dir context
- We only journal the finish of exporting subtree, so we shouldn't
consider export bounds as subtree root.
Signed-off-... - 05:57 AM Revision 5426c75d (ceph): mds: adjust subtree auth if import aborts in PREPPED state
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 0c1ca8ed (ceph): mds: fix uncommitted master wait
- We may add new waiter while the master is committing. so we should
take the waiters and wake up them when the master ... - 05:57 AM Revision 7a6ec353 (ceph): mds: fix slave commit tracking
- MDS may crash after journalling a slave commit, but before sending
commit ack to the master. Later when the MDS resta... - 05:57 AM Revision 0708d44f (ceph): mds: fix straydn race
- For unlink/rename request, the target dentry's linkage may change
before all locks are acquired. So we need check if ... - 05:57 AM Revision e8497f80 (ceph): mds: fix import cancel race
- Current code uses import state to detect obsolete import discover/prep
message. it does not work for the case: cancel... - 05:57 AM Revision 30c68218 (ceph): mds: fix typo in Server::do_rename_rollback
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision 8a1114ce (ceph): mds: remove buggy cache rejoin code
- I previously added code to handle a corner case of cache rejoin:
entire subtree, together with the inode subtree root... - 05:57 AM Revision 38fb2ec7 (ceph): mds: unfreeze inode after rename rollback finishes
- we should not wake up the unfreeze waiter while the inode is still
linked to a non-auth dirfrag.
Signed-off-by: Yan,... - 05:57 AM Revision 882be6b1 (ceph): mds: send slave request after target MDS is active
- when failure of peer is detected, MDCache::handle_mds_failure()
checks if there are requests waiting for slave replie... - 05:57 AM Revision e21f328f (ceph): mds: export CInode::STATE_NEEDSRECOVER
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 05:57 AM Revision fc94f47b (ceph): mds: export CInode:mds_caps_wanted
- CInode:mds_caps_wanted is used to keep track of caps wanted by non-auth
MDS. The auth MDS checks it when choosing loc... - 05:57 AM Revision 2b1b6cae (ceph): mds: notify auth MDS when cap_wanted changes
- So the auth MDS can choose locks' states base on our cap_wanted.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision a918e611 (ceph): mds: fix Locker::request_inode_file_caps()
- After sending cache rejoin message, replica need notify auth MDS when
cap_wanted changes. But it can send MInodeFileC... - 05:57 AM Revision 3962a751 (ceph): mds: defer releasing cap if necessary
- When inode is freezing or frozen, we defer processing MClientCaps
messages and cap release embedded in requests. The ... - 05:57 AM Revision c9707f63 (ceph): mds: Fix replica's allowed caps for filelock in SYNC_LOCK state
- For replica, filelock in LOCK_LOCK state doesn't allow Fc cap. So
filelock in LOCK_SYNC_LOCK/LOCK_EXCL_LOCK state sho... - 05:57 AM Revision 9424298f (ceph): mds: fix check for base inode discovery
- If a MDiscover message is for discovering base inode, want_base_dir
should be false, path should be empty.
Signed-of... - 05:57 AM Revision f3a9f474 (ceph): mds: slient MDCache::trim_non_auth()
- No need to output the function's debug message to console.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 8b4e9911 (ceph): mds: journal new subtrees created by rename
- this avoids creating bare dirfrags during journal replay.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:57 AM Revision 81d073fe (ceph): mds: fix underwater dentry cleanup
- If the underwater dentry is a remove link, we shouldn't mark the
inode clean
Signed-off-by: Yan, Zheng <zheng.z.yan@... - 04:17 AM Revision a6df7644 (ceph): PendingReleaseNotes: notes about enabling HASHPSPOOL
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:17 AM Revision aa0649c6 (ceph): osdmaptool: fix cli tests
- Now that the default pool flags have changed.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:31 AM Documentation #3808 (Resolved): Block device quick start page need update
- This was verified as working with cuttlefish and ceph-deploy.
- 01:29 AM rgw Documentation #2990 (Resolved): doc: expand/complete RGW S3 API reference
- This is complete now. Todo: A path between Quick Start and using the APIs. S3 subdomain configuration still needs to ...
- 12:28 AM Revision 07408117 (ceph): With mdlog lock and unlock functionality, listing and trimming base on ...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
05/27/2013
- 09:06 PM Revision 8cec56dd (ceph): valgrind: select notcmalloc ceph install flavor
- 08:55 PM Revision f0958c36 (ceph): Merge pull request #321 from dalgaaf/wip-da-CID-727981
- kv_flat_btree_async.cc: fix AioCompletion resource leak
- 08:55 PM Revision 35a8c616 (ceph): Merge pull request #320 from dalgaaf/wip-da-CID-727983
- kv_flat_btree_async.cc: fix resource leak
- 07:55 PM Bug #5172 (Fix Under Review): wrongly marked down heartbeat issues
- or wip-5172, don't see wip_5172 :)
- 07:44 PM Revision 0e127dc4 (ceph): mon: Paxos: get rid of the 'prepare_bootstrap()' mechanism
- We don't need it after all. If we are in the middle of some proposal,
then we guarantee that said proposal is likely... - 07:44 PM Revision f29206bd (ceph): mon: Paxos: finish queued proposals instead of clearing the list
- By finishing these Contexts, we make sure the Contexts they enclose (to be
called once the proposal goes through) wil... - 07:44 PM Revision b73d7c6b (ceph): mon: Paxos: finish_proposal() when we're finished recovering
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 2ff23fe784245f3b86bc98e0434b21a53... - 02:54 PM Fix #3188: osd: close read hole
- pushed wip-osd-readhole with some old incomplete work on this. here's a brain dump of where my thinking is/was on th...
- 01:44 PM Bug #5175: leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- i wonder if turning off the compaction will make this grow slowly enough to not be an issue. strangely, i still get ...
- 08:16 AM Bug #5175: leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- Work around for LOG is to use this config :...
- 07:29 AM Bug #5175 (Resolved): leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- leveldb has two files that seem to grow without bound and are only cleared on db open.
The first is the LOG file w... - 01:24 PM Bug #4895 (Resolved): leveldb: mon workload makes store.db grow without bound
- awesome. Sylvain, can you try setting 'mon compact on trim = false' and seeing if it continues to not grow? the ori...
- 01:22 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I've been testing this for the last 5 days and I haven't seen any uncontrolled/fast growth of the mon store like I us...
- 01:19 PM devops Bug #5174 (Resolved): df: ‘/media/osd.0/.’: No such file or directory
- fixed by commit:d81d0ea5c442699570bd93a90bea0d97a288a1e9, backported to cuttlefish branch, but not yet in a cuttlefis...
- 12:29 PM Bug #5171 (Need More Info): After crash monitor trying to bind to address of other monitor
- Do you have the full log for this monitor?
- 10:25 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- > As we can assume client ops are waiting for new OSD map that is issued only after peering finishes.
> It seems tha... - 08:28 AM Bug #5177 (Rejected): logrotate.conf: "which /etc/init.d/ceph reload"
- logrotate.conf: "which /etc/init.d/ceph reload". It always false (if no file "reload" in "."). New log always zero.
... - 07:56 AM Bug #5176 (Resolved): leveldb: Compaction makes things time-out yielding spurious elections
- It seems that compaction can take a few seconds (despite running on 10k SAS disks) and can cause peons to not renew t...
- 07:05 AM Tasks #4560 (Closed): unit tests for src/os/LFNIndex.cc
- There is still more work to be done but another ticket can be re-opened if someone wants to work on it.
- 04:51 AM CephFS Bug #5162: File is locked unexpected and not released anymore
- I tried restart all ceph services by issuing # /etc/init.d/ceph -a restart but didn't solve the problem. However I di...
- 12:44 AM CephFS Bug #5105: mds/CInode.cc: 1996: FAILED assert(auth_pins >= 0)
- I think uncomment MDS_AUTHPIN_SET in src/mds/mdstypes.h would help
05/26/2013
- 10:43 PM CephFS Bug #5162: File is locked unexpected and not released anymore
- >ceph: check_caps ffff880117288848 file_want pFscr used p dirty - flushing - issued pAsLsXsFcb revoking - retain pAsx...
- 08:09 PM CephFS Bug #5162: File is locked unexpected and not released anymore
- Hi Zheng,
Sorry for reply late. Here is the kernel msg.
[ 219.824078] ceph: mdsc delayed_work
[ 219.82... - 07:45 PM devops Bug #5174 (Resolved): df: ‘/media/osd.0/.’: No such file or directory
- In my cluster, there are two machine:
host1: mon/mds
host2: two osd/mon
When i exec" service ceph -a start' on h... - 08:14 AM Subtask #5046: Factor out PG logs, PG missing
- "Ceph placement groups backfilling":http://dachary.org/?p=2009
- 04:16 AM Bug #5173: ceph scrub found missing pg object
- Run ceph pg repair 2.df
Finally, I umounted all osds one by one and checked XFS and mounted back with barriers (we... - 03:27 AM Bug #5173: ceph scrub found missing pg object
- All files have equal md5 sums equal to:...
- 02:34 AM Bug #5173 (Can't reproduce): ceph scrub found missing pg object
- I'm using ceph version 0.56.4 (63b0f854d1cef490624de5d6cf9039735c7de5ca)
All data is 3-times replicated (pools Size ...
05/25/2013
- 11:17 PM Bug #4608 (Resolved): Incorrect RGW apache conf example
- http://ceph.com/docs/master/start/quick-rgw/#create-a-gateway-configuration-file
- 10:13 PM Revision 615b54c6 (ceph): doc: Updated rgw.conf example.
- fixes: #4608
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:11 PM Revision 6f935419 (ceph): doc: Updated RGW Quickstart.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:11 PM Revision e59897c8 (ceph): doc: Updated index for newer terms.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:27 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Update: seems to work fine if I turn writeback caching back on again (previously turned off before patching).
- 12:24 AM rbd Bug #3737: Higher ping-latency observed in qemu with rbd_cache=true during disk-write
- Using ceph 0.61.2 and qemu 1.4.2 or earlier versions with the patch:
The following hangs after a few iterations:
... - 03:36 AM Revision b4f63cee (ceph): ceph: --help-all
- Ask first extant daemon of each for its command descriptions and
daemon command descriptions. Suppress commands with... - 03:01 AM Revision ec0371c7 (ceph): ceph: print parameter name for CephString in concise_sig
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:01 AM Revision 99d7bcec (ceph): ceph: fix format strings for Py2.6 compatibility
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:01 AM Revision 1e0222a0 (ceph): ceph: Clean up/add missing docstrings
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 02:54 AM Revision 52b23b5e (ceph): rgw: propagate region on bucket creation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 02:12 AM Revision 3044fa8b (ceph): rgw: determine owner after effetctive user
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:57 AM Revision 4dafea43 (ceph): rgw: forward request params through upstream REST
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:21 AM Revision aee6665b (ceph): mon: Refactor
- Move some common code into JSON-command-description functions;
switch from char * to string & args
Signed-off-by: Da...
05/24/2013
- 11:21 PM Revision 6d1e14e0 (ceph): pg_pool_t: enable FLAG_HASHPSPOOL by default
- Fixes: #5160
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-b... - 09:27 PM Revision 51876499 (ceph): rgw: enable data sending via http client
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:57 PM Revision f9b58e00 (ceph): rados.py: don't access returned buffers if error/SIGINT
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:57 PM Revision ef4eb4c3 (ceph): PGMonitor: dead code removal
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 08:56 PM Revision 2c51b91d (ceph): MonCap: add pg r/w to osd capability profile
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 05:56 PM Bug #5172 (In Progress): wrongly marked down heartbeat issues
- wip_5172, going to test later
- 05:22 PM Bug #5172: wrongly marked down heartbeat issues
- 2013-05-23 10:35:22.200882 7fe1668a1700 1 -- 10.214.131.15:0/14951 <== osd.4 10.214.131.14:6803/14730 11 ==== osd_pi...
- 05:20 PM Bug #5172 (Resolved): wrongly marked down heartbeat issues
- ubuntu@teuthology:/a/samuelj-2013-05-23_10:20:47-rados-wip_osd_throttle-master-basic/20593/remote
Despite the bran... - 04:23 PM Bug #5160 (Resolved): Enable good pool behavior FLAG_HASHPSPOOL
- 04:02 PM Bug #5171: After crash monitor trying to bind to address of other monitor
- After it other 2 monitors working (answering) only after restart mon.3
- 03:58 PM Bug #5171 (Resolved): After crash monitor trying to bind to address of other monitor
- Rebooted cluster (3 nodes, 3 monitors). After it one of monitors sync, update database, then die (assertion) and then...
- 02:43 PM Cleanup #4828 (Rejected): dan: don't respond to e-mail via your phone in the bathroom
- I claim this is not a bug, and the behavior is expected. Closing as Rejected; submitter can appeal if he wants to co...
- 02:36 PM Feature #4457: api: add JSON schema/output protocol to rados.py
- 02:36 PM Feature #4547 (In Progress): api: implement self-description for --admin-daemon commands
- 02:36 PM Feature #4548: api: implement self-description for osd/mon tell commands
- 02:33 PM Feature #4455: api: move '--format' into just another command argument
- 02:32 PM Feature #4839: api: make new CLI send old version of commands to old monitors during upgrade
- 02:31 PM Feature #4315: api: create python CLI wrapper for ceph tool; read command descriptions and valida...
- 02:30 PM Feature #4314: api: modify ceph tool to describe own commands
- 02:29 PM rgw Feature #5170 (Resolved): RGW: Object restriping tool to fix large objects from argonaut.
- DHO needs a object restriping tool to read in the extremely large objects from argonaut and write them back into rado...
- 02:28 PM Feature #3849: Track slow PGs and times OSDs marked down
- 02:26 PM Bug #3143: Obsync object verification takes too long
- Apparently DH are maintaining the obsync code more than Inktank now . Perhaps check with them if they want to fix thi...
- 02:26 PM Feature #4982: OSD: namespaces pt 1 (librados/osd, not caps)
- The CRUSH bit of this is just for including the namespace when choosing the PG an object hashes into, right? (ie, the...
- 02:17 PM Feature #4982: OSD: namespaces pt 1 (librados/osd, not caps)
- crush needs to take into account the namespace argument in such a way that hobjects with an empty namespace hash the ...
- 02:03 PM rgw Feature #5169 (New): Do not list swift containers when enumerating buckets using S3 API
- If a user has created containers over swift protocol, they show up in bucket listing over S3, causing problems for an...
- 02:03 PM Feature #4782: osd: build writeback model to replace async flusher
- 12:50 PM Revision 0f547483 (ceph): kv_flat_btree_async.cc: fix AioCompletion resource leak
- Call AioCompletion::release() if the completion is no longer
needed to free the resources.
CID 727981 (#3 of 3): Res... - 12:43 PM Revision 7b438e13 (ceph): kv_flat_btree_async.cc: fix resource leak
- Call AioCompletion::release() if the completion is no longer
needed to free the resources.
CID 727983 : Resource lea... - 12:03 PM rbd Feature #4454: openstack: support volume migration in Cinder
- https://blueprints.launchpad.net/cinder/+spec/volume-migration
- 11:59 AM rbd Feature #4085: qemu-rbd: allow storing snapshot of ram associated with snapshot of disk
- 11:59 AM Linux kernel client Feature #4888: krbd: support boot from root file system on an rbd image
- 11:50 AM rbd Feature #5167: openstack: cinder: differential backups
- 11:26 AM rbd Feature #5167 (Resolved): openstack: cinder: differential backups
- Update the backup service in cinder to support a differential backup format, and the rbd driver to output differentials.
- 11:49 AM rbd Documentation #5009: doc: explain how to get qemu packages for each distro
- 11:49 AM rbd Documentation #5006: doc: openstack configuration changes for havana
- 11:48 AM rbd Feature #5168: openstack: cinder: rbd as a backup target
- 11:30 AM rbd Feature #5168 (Resolved): openstack: cinder: rbd as a backup target
- This would allow using a different pool as a backup instead of an object store.
- 11:17 AM rgw Documentation #5166 (Resolved): rgw: dr: async repl and DR documentation
- 11:17 AM rgw Documentation #5165 (Resolved): rgw: multisite: regions and global namespace documentation
- 11:12 AM rgw Feature #4335: rgw: dr: sync processing state: define datastructures
- This is so that agents which get restarted have durable information about what work they were doing before restart, a...
- 11:10 AM rgw Feature #5164 (Closed): rgw: multisite: metadata push notifications: design blueprint
- 10:49 AM rgw Feature #4334 (Fix Under Review): rgw: dr: bucket index log API: implement RESTful API
- 10:49 AM rgw Feature #4333 (Fix Under Review): rgw: multisite: metadata-changes log: implement RESTful API
- 10:49 AM rgw Feature #5008 (Fix Under Review): rgw: bucket metadata changes should be reflected in mdlog
- 10:46 AM Revision 9785478a (ceph): ceph-disk: remove unnecessary semicolons
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:41 AM Revision 16ecae15 (ceph): ceph-disk: cast output of _check_output()
- Cast output of _check_output() to str() to be able to use
str.split().
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 10:33 AM Revision 9429ff90 (ceph): ceph-disk: fix undefined variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:29 AM Revision c127745c (ceph): ceph-disk: add missing spaces around operator
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:53 AM devops Cleanup #5106 (In Progress): ceph_deploy: install/compile error on wheezy
- commit 61b610fbc841c6943e41f23569ed5f6835d8caed
Author: Gary Lowell <glowell@inktank.com>
Date: Thu May 23 09:23:... - 08:12 AM Linux kernel client Cleanup #2438 (Closed): ceph-client: use BUG_ON() for null auth_client->ops pointers
- Sage added this commit:
27859f9 libceph: wrap auth ops in wrapper functions
...which neatened up the auth calls... - 07:59 AM rbd Bug #3889 (Won't Fix): krbd: handle zero-length requests
- OK, after a little more discussion... We're going to
go the easy route and just close this issue. We'll
continue ... - 07:54 AM Bug #5163: filestore: ENOTEMPTY on object removal
- The object in question was part of an rbd image that a vm was doing a fstrim on when the crash happened.
- 07:46 AM Bug #5163 (Can't reproduce): filestore: ENOTEMPTY on object removal
- I had an osd crash during normal opperation, this could possibly be related to 4927. I was able to restart the osd a...
- 07:23 AM rbd Bug #5146: krbd: wait for safe callback for writes
- Josh has reviewed this patch and the two others I posted
with it. I was testing the three of them together yesterda... - 06:14 AM Revision 580a08c6 (ceph): rgw: multiple fixes and cleanups
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:13 AM Revision 2655c1e4 (ceph): utime: add asctime()
- dump time in a useful format
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:09 AM Revision 79eb61c4 (ceph): Merge branch 'wip_scrub_tphandle' into cuttlefish
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 03:08 AM Revision 8c1c2d98 (ceph): Merge branch 'wip_scrub_tphandle' into next
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 02:42 AM Revision b8a25e08 (ceph): OSD,PG: pass tphandle down to _scan_list
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:42 AM Revision d62716dd (ceph): PG: reset timeout in _scan_list for each object, read chunk
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:42 AM Revision 86822485 (ceph): PG: ping tphandle during omap loop as well
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:30 AM Revision ac6c7783 (ceph): Merge remote-tracking branch 'upstream/wip_scrub_tphandle_bobtail' into...
- Fixes: #5159
Reviewed-by: Sage Weil <sage@inktank.com> - 01:52 AM CephFS Bug #5162: File is locked unexpected and not released anymore
- looks like client's fault. try following command on client.5898 and upload debug.txt:
# echo module ceph +p >/sys/... - 12:41 AM Revision 0b50d073 (ceph): PG: ping tphandle during omap loop as well
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:02 AM Revision bb407bfd (ceph): doc: Updated Ceph FS Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:01 AM Revision 7c497d95 (ceph): doc: Added troubleshooting to Ceph FS index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:01 AM Revision 3dda794a (ceph): doc: Added separate troubleshooting for MDS and Ceph FS.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
05/23/2013
- 11:16 PM CephFS Bug #5162 (Can't reproduce): File is locked unexpected and not released anymore
- I deployed a ceph cluster and mount cephfs via kernel module. After using it few days later, when I ls a particular f...
- 10:24 PM Revision 5979a26d (ceph): PG: reset timeout in _scan_list for each object, read chunk
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:23 PM Revision bde6b58b (ceph): OSD,PG: pass tphandle down to _scan_list
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:13 PM Revision a460e53e (ceph): rgw: iterate usage entries from correct entry
- Fixes: #5152
When iterating through usage entries, and when user id was
provided, we started at the user's first entr... - 08:12 PM Revision 3984b988 (ceph): rgw: iterate usage entries from correct entry
- Fixes: #5152
When iterating through usage entries, and when user id was
provided, we started at the user's first entr... - 08:11 PM Bug #5159 (Resolved): OSD: reset heartbeat timer for each read chunk in deep scrub
- 03:26 PM Bug #5159 (Resolved): OSD: reset heartbeat timer for each read chunk in deep scrub
- 08:11 PM Revision 8b3a04de (ceph): rgw: iterate usage entries from correct entry
- Fixes: #5152
When iterating through usage entries, and when user id was
provided, we started at the user's first entr... - 08:09 PM Revision 0c805b6c (ceph): rgw: rest_client, forward requests
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:49 PM devops Bug #5161 (Resolved): daemons should create /var/run/ceph if it doesn't already exist
- I wanted to add a new mon into a cluster.But when i exce "ceph-mon -i majianpeng --mkfs --monmap map --keyring key", ...
- 07:29 PM Revision f2f73538 (ceph): rgw: some code cleanup
- move s3 signing code to a different common file.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:45 PM Revision 75600c6a (ceph): doc: Updates for ceph-deploy and cuttlefish.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:39 PM Revision c812bb51 (ceph): rgw: separate certain request info into different structure
- This is needed for later request forwarding.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:23 PM Revision 87cef3d5 (ceph): mon: drop unnecessary conditionals
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:21 PM Revision 6af64051 (ceph): Merge pull request #311 from ceph/wip-5102
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:17 PM Revision 8b2fbf21 (ceph): Merge pull request #312 from ceph/wip-osd-hb
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 03:49 PM Revision e8d0dc76 (ceph): Merge branch 'next'
- 03:48 PM Revision e09e9442 (ceph): modified: src/init-ceph.in
- fixed bug in init script, the "df" should be run on remote host by do_cmd,
and use $host instead of "hostname -s"
S... - 03:46 PM Revision f9ec5a79 (ceph): msgr: increase port range to 6900-7300 (from -7100)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:45 PM Revision 2802430a (ceph): Merge pull request #307 from xiaoxichen/master
- Reviewed-by: Sage Weil <sage@inktank.com>
- 03:31 PM Bug #5160 (Resolved): Enable good pool behavior FLAG_HASHPSPOOL
- 03:08 PM Feature #5158 (New): Objecter: support multi-read-from-replica
- Sam pointed out that we could turn our reads into essentially an Available (versus Consistent) model just by turning ...
- 01:18 PM rgw Bug #5152 (Resolved): rgw: usage iteration by user doesn't skip to correct epoch
- Landed to Next, Bobtail, and Cuttlefish.
- 10:24 AM rgw Bug #5152: rgw: usage iteration by user doesn't skip to correct epoch
- Reviewed-by.
- 09:33 AM rgw Bug #5152: rgw: usage iteration by user doesn't skip to correct epoch
- Please review - needs to go into Next, Cuttlefish, and Bobtail
- 08:57 AM rgw Bug #5152 (Fix Under Review): rgw: usage iteration by user doesn't skip to correct epoch
- 01:13 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- We repeat the same bug on both Bobtail and Cuttlefish deployments just by calling osd in/out/reweight.
Peering compl... - 12:33 PM rbd Feature #4236 (Duplicate): krbd: properly handle flush commands
- Marking this duplicate of: http://tracker.ceph.com/issues/3889
I looked into the zero-length request stuff more ge... - 11:39 AM Bug #5157 (Resolved): install: unable to pull ceph rpm packages on fedora18
- test set up: burnupi23...
- 10:59 AM Bug #5156 (Duplicate): OSD: split followed by pg resurrection might leave an object in two collec...
- remove a
split a -> a, c
create c
resurrect a
will leave objects in both a and c. - 10:35 AM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- I have attached the logs from two nodes of my MDS cluster.
I started mds.0 first. When I started mds.1, mds.0 crashed. - 05:54 AM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- Sage Weil wrote:
> Argh.. i don't have a log after all.
>
> Yan, dropping the assert avoids teh crash, but it see... - 10:29 AM rbd Bug #3889: krbd: handle zero-length requests
- We'll discuss details at our standup, but here is an update.
Unless I misunderstand him, Sage believes that reques... - 08:58 AM rbd Bug #3889 (In Progress): krbd: handle zero-length requests
- I just sent the following in an e-mail to Josh and Sage,
but thought I might as well document it here. If we want
... - 10:26 AM devops Bug #4641: ceph-deploy install fails on fedora 18
- [ubuntu@burnupi22 ceph-deploy]$ ./ceph-deploy install burnupi22
########################################
Error: Pac... - 10:22 AM Bug #5102 (Resolved): mon: assert(is_active()) on propose_pending()
- 10:14 AM rbd Bug #5040 (In Progress): krbd: record that an parent info refresh has failed
- I've implemented these fixes and will post them for review
after they've gone through a teuthology run this afternoon. - 07:58 AM rbd Bug #5040: krbd: record that an parent info refresh has failed
- ...
- 10:09 AM Bug #5069 (Need More Info): monitor crashed during mon thrash in nightlies
- Sage thought there were logs on teuthology, on the directory from the initial report from Tamil. That run must have ...
- 09:57 AM Bug #5069 (In Progress): monitor crashed during mon thrash in nightlies
- der, we have a complete log from the teuthology failure.
- 09:55 AM Bug #5069 (Need More Info): monitor crashed during mon thrash in nightlies
- i think the blind sync is still the way forward.. the more we make it aware of what is on top the harder it is to do ...
- 09:32 AM Bug #5069: monitor crashed during mon thrash in nightlies
- This is definitely something wrong in the store: 'version' contains the last committed version on the store, while md...
- 10:07 AM rbd Bug #5070: rbd map failed and stalled in "D"
- Quick summary: I don't think this is an rbd problem....
- 01:05 AM rbd Bug #5070: rbd map failed and stalled in "D"
- I added one more RBD device and mapped it, and it mapped ok, after I've tried to map again previous one and it is suc...
- 12:55 AM rbd Bug #5070: rbd map failed and stalled in "D"
- I use vanilla 3.7.2 and built it with debian make-kpkg env.
root@tsk-vps-node-04:/sys# grep blk_trace_attr_group /... - 09:40 AM Bug #5140 (Resolved): ceph init script failed to determine correct hostname for remote osd
- 09:35 AM devops Bug #4984: ceph_deploy: osd create succeeds with an error message (partprobe returns error)
- Please confirm if this is still happening or not.
- 09:32 AM devops Bug #5150 (Resolved): How many memory need if we compile ceph?
- we put ~4 gigs on our VMs for building... sometimes 6.
- 09:20 AM CephFS Bug #4832: mds: failed auth_unpin assert
- ubuntu@teuthology:/a/teuthology-2013-05-23_01:00:08-rados-next-testing-basic/20276
- 09:17 AM Bug #5154 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- ...
- 08:40 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- a variation of this i just fixed in commit:c2e262fc9493b4bb22c2b7b4990aa1ee7846940e. but note the
2013-05-22 09:0... - 02:23 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- No, since the upgrade to Cuttlefish I haven't seen the same one, BUT my cluster crashed yesterday with a different ba...
- 05:16 AM rbd Bug #4777 (Fix Under Review): krbd: verify a few things in the zeroing routines
- The following patch has been posted for review. It's one of three
new patches available in the "review/wip-rbd" bra... - 05:16 AM rbd Bug #3859 (Fix Under Review): osd_client: define ceph_osdc_clear_request_linger()
- The following patch has been posted for review. It's one of three
new patches available in the "review/wip-rbd" bra... - 05:15 AM rbd Bug #5146 (Fix Under Review): krbd: wait for safe callback for writes
- The following patch has been posted for review. It's one of three
new patches available in the "review/wip-rbd" bra... - 01:33 AM Revision 1dd99f0f (ceph): modified: src/init-ceph.in
- fixed bug in init script, the "df" should be run on remote host by do_cmd,
and use $host instead of "hostname -s"
S... - 12:38 AM rbd Bug #5099: io performance / ceph block device
- dd if=/dev/zero of=/dev/rbd1 bs=1M count=1000 oflag=direct
but I try to test the same command above on nfs file sy... - 12:36 AM devops Bug #5066: Problems with ceph-deploy debs
- Probably this is fixed by now (see http://article.gmane.org/gmane.comp.file-systems.ceph.user/1419) but I did not tes...
05/22/2013
- 11:35 PM rgw Feature #5153 (New): rgw: usage log trim is unbounded
- 11:13 PM Revision 0262301b (ceph): osd: send hb front addr to monitor at boot
- We still aren't binding it to anything yet, or putting it in the OSDMap.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:13 PM Revision 6ad10551 (ceph): osd: bind front heartbeat messenger to public_addr
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:13 PM Revision 28851424 (ceph): msgr: take an arbitrary set of ports to avoid binding to
- We used to only need to avoid 2 ports; now we need 3. Make it a set so we
don't have this problem later.
Signed-off... - 11:13 PM Revision 92a558bf (ceph): msgr: add Messenger reference to Connection
- This allows us to get the messenger associated with a connection.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:13 PM Revision 27381c0c (ceph): osd: ping both front and back interfaces
- Send ping requests to both the front and back hb addrs for peer osds. If
the front hb addr is not present, do not se... - 11:11 PM Revision da1940a2 (ceph): osd: create front and back hb messenger instances
- The hb_front messenger is not used yet.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:08 PM Revision 1fee4ccd (ceph): osd/OSDMap: encode front heartbeat addr
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:04 PM Revision 342eed36 (ceph): osd/OSDMap: hb_addr -> hb_back_addr
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:04 PM Revision cf977ce6 (ceph): osd/OSDMap: new_hb_up -> new_hb_back_up
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:03 PM Revision 6cfdb74e (ceph): osd/OSDMap: new_up_internal -> new_up_cluster
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:55 PM Revision 3fa65852 (ceph): osd: Add asserts for seg faults caused by corrupt OSDs
- fixes: #5139
Signed-off-by: David Zafman <david.zafman@inktank.com> - 10:17 PM Revision b355b987 (ceph): OSDMonitor: fix osd dump (need enclosing section)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:03 PM Revision c2e262fc (ceph): osd: skip mark-me-down message if osd is not up
- Fixes crash when the OSD has not successfully booted and gets a
SIGINT or SIGTERM.
Signed-off-by: Sage Weil <sage@in... - 09:56 PM Revision 32dc463a (ceph): osd, mds: shut down async signal handler on exit
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:50 PM Revision 4a8d9962 (ceph): rbd image_read.sh: ensure rbd is loaded
- Make sure rbd is loaded before proceeding with the script.
Signed-off-by: Alex Elder <elder@inktank.com> - 09:40 PM Revision 87eaaab6 (ceph): rgw: clean up s3 signing code
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:37 PM Revision 08c39b84 (ceph): ReplicatedPG::submit_push_complete don't remove the head object
- The object would have had to have been removed already. With
fd caching, this extra remove might check the wrong rep... - 09:29 PM Revision eb91f410 (ceph): messages/MOSDMarkMeDown: fix uninit field
- Fixes valgrind warning:
==14803== Use of uninitialised value of size 8
==14803== at 0x12E7614: sctp_crc32c_sb8_64_... - 09:11 PM Revision 70c9851a (ceph): mds: weaken reconnect assertion
- See #5031. This appears to be populated with another mds's mdsdir; just
not asserting avoids the problem for the tim... - 09:06 PM rgw Bug #5152 (Resolved): rgw: usage iteration by user doesn't skip to correct epoch
- Instead of starting to iterate from the correct timestamp, we iterate fro,m the beginning of time (if a user was spec...
- 08:55 PM Revision 48e1b11b (ceph): sysvinit: fix enumeration of local daemons when specifying type only
- - prepend $local to the $allconf list at the top
- remove $local special case for all case
- fix the type prefix chec... - 08:26 PM Revision 6e5f0db7 (ceph): sysvinit: fix osd weight calculation on remote hosts
- We need to do df on the remote host, not locally.
Simlarly, the ceph command uses the osd key, which exists remotely... - 08:26 PM Revision 674e75bc (ceph): sysvinit: use known hostname $host instead of (incorrectly) recalculating
- We would need to do hostname -s on the remote node, not the local one.
But we already have $host; use it!
Reported-b... - 08:25 PM Revision b0d64de4 (ceph): Merge pull request #316 from ceph/wip-sysvinit
- Reviewed-by: Dan Mick <dan.mick@inktank.com>
- 08:22 PM Revision 4e185879 (ceph): ceph: fix valgrind log check
- - logs are gzipped; use zgrep
- wait for the proc to exit before looking at stdout
Signed-off-by: Sage Weil <sage@in... - 08:08 PM Revision bec630fc (ceph): cephtool/test.sh: add test for --verbose and --concise
- 08:06 PM Revision 28a6761d (ceph): ceph: fix --concise (set verbose to False)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:45 PM Revision 3d7f8f84 (ceph): mon: be a bit more verbose about osd mark down events
- Put these in the cluster log; they are interesting.
This is a backport of 87767fb1fb9a52d11b11f0b641cebbd9998f089e.
... - 07:39 PM Revision d81d0ea5 (ceph): sysvinit: fix osd weight calculation on remote hosts
- We need to do df on the remote host, not locally.
Simlarly, the ceph command uses the osd key, which exists remotely... - 07:39 PM Revision caa15a34 (ceph): sysvinit: use known hostname $host instead of (incorrectly) recalculating
- We would need to do hostname -s on the remote node, not the local one.
But we already have $host; use it!
Reported-b... - 06:54 PM Bug #5140: ceph init script failed to determine correct hostname for remote osd
- A new commit has been submitted, thanks
https://github.com/ceph/ceph/pull/307 - 06:32 PM Revision f4cd61d3 (ceph): mon: be a bit more verbose about osd mark down events
- Put these in the cluster log; they are interesting.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from ... - 06:08 PM Revision 903d4a04 (ceph): rgw: add system users
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:35 PM rbd Bug #4777: krbd: verify a few things in the zeroing routines
- I'm going to ignore the whole IRC issue for now.
I'm almost certain it's not needed, and in fact
I'm pretty sure it... - 05:34 PM Revision e04b1894 (ceph): PG: subset_last_update must be at least log.tail
- Fixes: 5020
Backport: bobtail, cuttlefish
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman... - 05:34 PM Revision 3a02e00d (ceph): FileJournal: adjust write_pos prior to unlocking write_lock
- In committed_thru, we use write_pos to reset the header.start value in cases
where seq is past the end of our journal... - 05:34 PM Revision b35fafb6 (ceph): rgw: pre-generate bucket object version before creating it
- Use this version when creating the bucket instead of letting the
objclass auto-generate it, so that we could return i... - 05:33 PM Revision 85cd1d9f (ceph): Merge pull request #314 from ceph/wip-4228
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:27 PM devops Bug #4641: ceph-deploy install fails on fedora 18
- [ubuntu@burnupi22 ceph-deploy]$ ./ceph-deploy install burnupi22
ceph-deploy: Platform is not supported: Fedora Spher... - 05:23 PM Revision 0289c445 (ceph): OSDMonitor: skip new pools in update_pools_status() and get_pools_health()
- New pools won't be full. mon->pgmon()->pg_map.pg_pool_sum[poolid] will
implicitly create an entry for poolid causing... - 05:21 PM devops Bug #5150 (Resolved): How many memory need if we compile ceph?
- My machine hardware:
memory: 2G
Intel(R) Core(TM) i3-2120 CPU @ 3.30GHz
But when i compile ceph, it will cause O... - 05:18 PM Revision a43d3531 (ceph): ceph-mds: specify which types of addresses to pick
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:18 PM Revision 751b73af (ceph): ceph-syn: specify which types of addresses to pick
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 05:15 PM Revision 2c58b790 (ceph): Merge pull request #315 from ceph/wip-4507
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:07 PM rbd Bug #4870 (Resolved): rbd: watch request error handling bugs
- The first problem listed will be addressed by changes
done for http://tracker.ceph.com/issues/3859.
The second pr... - 05:05 PM Revision de499676 (ceph): mon: PaxosService: drop atomic_t on 'proposing'
- We don't need this to be atomic -- a simple boolean is enough.
Fixes: #4507
Signed-off-by: Joao Eduardo Luis <joao.... - 04:57 PM Revision 6d893230 (ceph): ceph-mon: only care about public addr during pick_addresses()
- Fixes: #4228
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:57 PM Revision c307d427 (ceph): ceph-osd: specify which types of addresses to pick
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 04:57 PM Revision 1ba9f84d (ceph): common: add mask argument to pick_addresses() to specify what we need
- Fixes: #4228
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:56 PM devops Bug #4864 (Resolved): ceph-deploy: mon create command seems to output info about the first node only
- 04:55 PM devops Bug #4864 (Closed): ceph-deploy: mon create command seems to output info about the first node only
- tested on centos machines and it works fine,
from ceph.log:
2013-05-22 16:54:58,117 ceph_deploy.mon DEBUG Deplo... - 04:50 PM rbd Bug #3859 (In Progress): osd_client: define ceph_osdc_clear_request_linger()
- 04:47 PM rbd Bug #3859: osd_client: define ceph_osdc_clear_request_linger()
- Once again, rather than doing what I thought might work,
I've decided on a better fix.
Right now the osd client t... - 04:12 PM rbd Bug #3859: osd_client: define ceph_osdc_clear_request_linger()
- As described initially, it's not really valid to
call ceph_osdc_unregister_linger_request() until
after the origina... - 04:06 PM rbd Bug #3859: osd_client: define ceph_osdc_clear_request_linger()
- I have implemented a change that waits for a WATCH
request (as well as "normal" data write requests)
to get an indi... - 04:44 PM Feature #5141: Some clone errors aren't repaired
- If I only deleted the head or clone data from one of the OSDs of a 3 replica pool, repair did work. So this is a VER...
- 04:39 PM Revision 78a1834d (ceph): ceph: remove cli test
- This is about to be removed by wip-ceph-cli anyway. And it broke in
commit 132d5bf7f9af7de9e2028e20c95ba91637da5875.... - 04:25 PM Revision 056a823b (ceph): schedule_suite.sh: resolve ceph sha1 using deb gitbuilder, not tarball
- The tarball one is old and largely obsolete.
- 04:24 PM Bug #5139 (Resolved): Seg fault if listsnaps request with missing clones
- To trigger this you have to delete all copies of a clone or the head. We aren't going to handle that gracefully, but...
- 10:22 AM Bug #5139 (Fix Under Review): Seg fault if listsnaps request with missing clones
- 04:12 PM Revision e15d2909 (ceph): mon: Paxos: get rid of the 'prepare_bootstrap()' mechanism
- We don't need it after all. If we are in the middle of some proposal,
then we guarantee that said proposal is likely... - 04:10 PM Revision 586e8c20 (ceph): mon: Paxos: finish queued proposals instead of clearing the list
- By finishing these Contexts, we make sure the Contexts they enclose (to be
called once the proposal goes through) wil... - 03:59 PM rbd Bug #5146: krbd: wait for safe callback for writes
- I have this implemented and will post a patch for
review after I've tested. It was easier than
expected.
Note,... - 12:57 PM rbd Bug #5146 (Resolved): krbd: wait for safe callback for writes
- Right now rbd only waits for the acknowledgement callback
for all osd requests. This means that an rbd client may
... - 03:54 PM Revision 308d7c46 (ceph): Merge pull request #297 from dalgaaf/wip-da-CID-727982
- Reviewed-by: Sage Weil <sage@inktank.com>
- 03:47 PM Feature #5148 (New): repair should handle snapset/clone discrepancies
- This should handle the following cases:
- head/snapdir are missing
- clone is missing - 03:37 PM Revision 0e733ba5 (ceph): Merge pull request #310 from dalgaaf/wip-da-CID-fixes-4
- Reviewed-by: Sage Weil <sage@inktank.com>
- 03:28 PM Revision 549e547b (ceph): mds/Migrator.cc: fix possible dereference NULL return value
- CID 716997 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might ... - 03:25 PM Revision 32b024c6 (ceph): mds/Migrator.cc: fix possible dereference NULL return value
- ID 716998 (#1 of 2): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might b... - 03:23 PM Revision ed53bf17 (ceph): mds/Migrator.cc: delete some empty lines at EOF
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 03:21 PM Revision 158e7409 (ceph): mds/Migrator.cc: fix possible dereference NULL return value
- CID 716999 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might ... - 03:20 PM Feature #5147 (Resolved): Display unique cluster ID in ceph status
- Some customers will be running more than one Ceph cluster.
In addition to associate the output of ceph status to a s... - 03:20 PM Revision cfebb835 (ceph): Merge pull request #309 from dalgaaf/wip-da-CID-fixes-3-v2
- Reviewed-by: Sage Weil <sage@inktank.com>
- 03:17 PM Revision 7ba34c13 (ceph): mds/Migrator.cc: fix dereference NULL return value
- CID 717000 (#1 of 2): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might ... - 03:06 PM Revision de1e3553 (ceph): mds/Migrator.cc: fix possible NULL pointer dereference
- Move dout() calls behind the related asserts to prevent possible NULL
pointer dereference.
CID 717001 (#1 of 1): Der... - 02:35 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- Something that's not clear to me: does this need to be in all peers to have an effect? Or in other words, to fix this...
- 02:20 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- This could be a result of writing out pg epochs on each map change. I have a branch which should greatly reduce the ...
- 02:12 PM CephFS Bug #5031 (Need More Info): mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- 02:12 PM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- Walter: can you produce a log? 'debug mds = 20', 'debug ms = 1', restart the mds and wait for it to crash.
I have... - 02:10 PM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- Argh.. i don't have a log after all.
Yan, dropping the assert avoids teh crash, but it seems like the real issue i... - 01:45 PM Revision c266d7c7 (ceph): mds/Server.cc: fix possible NULL pointer dereference
- Add asserts to solve these CID issues:
CID 717002 (#1 of 2): Dereference null return value (NULL_RETURNS)
derefere... - 01:45 PM Revision fd818a20 (ceph): src/rbd.cc: silence CID COPY_PASTE_ERROR warning
- CID 1021212 (#1 of 1): Copy-paste error (COPY_PASTE_ERROR)
copy_paste_error: "r" in "r = -*__errno_location()" look... - 01:42 PM Revision fa3149d2 (ceph): mds/MDS.cc: fix dereference null return value
- Fix for:
returned_null: Function "SessionMap::get_session(entity_name_t)" returns
null (checked 12 out of 14 times... - 01:38 PM Revision 71181087 (ceph): mds/MDCache.cc: fix possible NULL pointer dereference
- Assert if 'cur' is NULL.
CID 966616 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferen... - 01:21 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- pushed a patch to bobtail branch that logs on the only other osd down path in the mon.
- 11:35 AM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- No, I'm not. This is a standard Ubuntu/bobtail config.
- 11:16 AM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- I don't suppose you're using syslog? That will lose log messages quite easily.
- 10:37 AM Bug #4967 (Need More Info): Misbehaving OSD sets over half of the cluster as down despite "osd mi...
- 06:27 AM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- There was no shut down of those OSDs at the time:...
- 12:42 PM Bug #2891 (New): heap profiler hangs when trying to start it up on the mon
- Precise is still the latest LTS release. :/
Maybe we don't want to invest the effort to fixing it (if we can, since ... - 11:19 AM Bug #2891 (Closed): heap profiler hangs when trying to start it up on the mon
- This no longer seems to be an issue on Quantal, and haven't seen people complaining about it for a while.
So, I'm ... - 12:33 PM Revision 2ff23fe7 (ceph): mon: Paxos: finish_proposal() when we're finished recovering
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 12:20 PM rbd Bug #3858 (Resolved): osd_client: ceph_osdc_wait_request() seems wrong
- tl;dr: This is no longer a bug, so marking it resolved.
First of all, based on how it's used, if an
error occurs... - 10:08 AM rbd Bug #3858: osd_client: ceph_osdc_wait_request() seems wrong
- I honestly don't know when it happened, but I now find
that rbd is not susceptible to this problem. All rbd
reques... - 11:54 AM rbd Bug #5070: rbd map failed and stalled in "D"
- This is somewhat old code, and there are a few bugs
that have since been fixed that could be contributing
to this. ... - 11:13 AM Bug #4856: monitor: upgrades produce "client did not provide supported auth type" in log
- This comes from the AuthMonitor, and it *should* inhibit functionality to some extent, as the client should have rece...
- 11:13 AM Bug #4645 (Resolved): osd: Adding osd causes long stall without restart
- this should be fixed...
- 11:11 AM Bug #4357: osd: FAILED assert("join on thread that was never started" == 0)
- Wido, do you still hit this problem?
- 11:11 AM Bug #3440 (Resolved): Running OSDs on ZFS on Linux
- 11:10 AM Bug #3609 (Resolved): mon: track down the Monitor's memory consuption sources
- 11:07 AM Bug #4816 (Can't reproduce): Monitor crashed with signal Aborted in MMonSubscribe::~MMonSubscribe()
- 11:03 AM Bug #3552 (Resolved): After ceph-deploy installation a reboot breaks OSDs
- 11:02 AM Bug #5068 (Won't Fix): ceph_test_rados gets SIGFPE when run with no args
- 10:58 AM Bug #5082: OSD wrongly marked as down
- still need a log to track down the osd marked down issue, if you have it
- 10:57 AM Bug #5100 (Can't reproduce): teuthology kclient (?): fails to unmount after tiobench
- 10:54 AM Bug #5102 (Fix Under Review): mon: assert(is_active()) on propose_pending()
- 09:17 AM Bug #5102: mon: assert(is_active()) on propose_pending()
- new fix on wip-5102, comprised of simply ripping out the prepare_bootstrap() stuff.
- 10:53 AM Bug #5118 (Rejected): osd version reporting incorrectly when client libs installed
- 10:52 AM Bug #5114 (Rejected): os/FileStore.cc: 2225: FAILED assert(0 == "_close_replay_guard failed")
- 10:47 AM Bug #5054 (Resolved): deep scrub reports 1 inconsistent object
- 10:46 AM Bug #4910 (Duplicate): journal Unable to read past sequence 337 but header indicates the journal ...
- 10:46 AM Bug #4910 (Resolved): journal Unable to read past sequence 337 but header indicates the journal h...
- 10:45 AM Bug #4521 (Can't reproduce): mon: starting a new osd crashes all mon's
- 10:44 AM Bug #4855 (Can't reproduce): peek map assert
- 10:42 AM Bug #4602 (Can't reproduce): osd/ReplicatedPG.cc: 6487: FAILED assert(latest->is_update())
- 10:42 AM Bug #4801: osd class path broken on fedora 18?
- verify that ceph-osd --show-config | grep class shows the right class path that matches the rpm contents (/var/libsom...
- 10:41 AM Bug #4686 (Can't reproduce): corrupt or missing osdmap on load_pgs
- 10:40 AM Bug #3829: new osd added to the cluster is not receiving data
- 10:40 AM Bug #3829 (Can't reproduce): new osd added to the cluster is not receiving data
- 10:39 AM Cleanup #4507 (Resolved): mon: drop atomic_t
- merged into master; commit:2c58b790ff1dc7578325ae47c2ad0380c3310040
- 10:39 AM Bug #4937 (Can't reproduce): osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- This was caused by corruption of some kind. That corruption may have been a bug.
- 10:14 AM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- > Updated by Olivier Bonvalet 2 days ago
>
> I also have scrub errors with this message : "found clone without he... - 10:36 AM Bug #5020 (Resolved): osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones, 2908160...
- 10:34 AM Bug #4228 (Resolved): mon uses pick_addresses if invoked with mkfs or without mon addr; fails if ...
- 10:24 AM Bug #4813 (Pending Backport): pgs stuck creating
- 09:43 AM Bug #5145 (Resolved): make check fails on "ceph osd lost"
- just fixed it
- 09:42 AM Bug #5145: make check fails on "ceph osd lost"
- It is introduced by a "recent change in the usage":https://github.com/ceph/ceph/commit/132d5bf7f9af7de9e2028e20c95ba9...
- 09:39 AM Bug #5145 (Resolved): make check fails on "ceph osd lost"
- ...
- 09:08 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- wip-4895-cuttlefish has a backport of the proposed fix. anyone experiencing growth, please test!
- 05:26 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- Just a quick update for those following the bug and not on IRC:
joao found out that when there is an election whil... - 07:14 AM Revision f70d463c (ceph): wip: ceph: print help for osd.0, mon.a, mds.a daemon commands
- Issues:
1) ignore commands with no help text, as does daemon help?
2) come up with daemon names from running config s... - 07:10 AM Revision 34c42f65 (ceph): ceph: admin_socket() returns data rather than printing.
- Preparation for use in daemon command validation/help enumeration
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 07:08 AM Revision 06a156df (ceph): admin_socket and all users: command-descriptor support
- add cmddesc to all register_command calls, and add a class and
command to return all the command descriptors as is do... - 07:06 AM Revision 27b60d82 (ceph): Makefile.am: Move cmdparse to libcommon
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 07:04 AM rgw Tasks #5144 (New): rgw: incorporate greg's comment to the log objclass
- 06:59 AM Feature #5143 (New): objclass: maintain global namespaces
- Currently index data of different objclasses may overlap so it's a real problem using multiple classes on a single ob...
- 03:57 AM Revision ed315245 (ceph): rados.py, ceph: add timeout for run_in_thread and selected callers
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 03:33 AM Revision 70a96973 (ceph): packaging fixes around the new ceph cli:
- Remove ceph-legacy-cli
Include ceph in proper places to get it built/installed/packaged
Make ceph-common (deb) or cep...
05/21/2013
- 11:49 PM Bug #4895: leveldb: mon workload makes store.db grow without bound
- nm the comment about log rotate, I got confused between UTC and local time ...
- 11:16 PM Bug #4895: leveldb: mon workload makes store.db grow without bound
- @Sage: Looks like you're right.
My mon started again growing this morning (pretty much at 6am on the spot, the tim... - 12:18 PM Bug #4895: leveldb: mon workload makes store.db grow without bound
- mike: it looks like your store is growing not because of leveldb but because paxos isn't trimming. can you generate a...
- 11:38 PM Revision 9a085737 (ceph): ceph: add partial to validate()
- Allow validation of the front of a command, to precalculate the
target for a command (basically, whether it's a 'norm... - 11:38 PM Revision a502daa1 (ceph): ceph: figure out which daemon should get a command early
- Before even asking for a list of valid command signatures, do some fixed
parsing to figure out which daemon we should... - 11:38 PM Revision a568be83 (ceph): ceph: hack for tell so that we don't have to duplicate "tell <target>"
- in each command description
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:38 PM Revision 623d6302 (ceph): ceph: cleanup: remove dead code/imports, note apparently-unused objects
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:38 PM Revision c3f6e64c (ceph): mon, cmdparse: move dump_cmds_to_json to common/cmdparse
- Also include ARRAY_SIZE macro
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:38 PM Revision 5225028a (ceph): osd: handle new-style JSON commands directly (like mon)
- 'tell osd.n' and 'pg <pgid>' commands go directly to the OSD.
Both are enumerated in osd_commands[]; that could be cl... - 11:38 PM Revision de1b8557 (ceph): librados, rados.py: rados_*_command: pass inbuflen to handle zeroes
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:38 PM Revision a9b4f46f (ceph): mon: fix stdout vs. stderr throughout monitor
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:38 PM Revision d3027610 (ceph): objecter: allow osd-destined commands to fail if osd doesn't exist
- Return ENXIO instead of EINVAL, mostly because EINVAL is overused, but
also because we need to distinguish between th... - 11:38 PM Revision 948d396a (ceph): ceph: handle non-EINVAL failure on get_command_descriptions
- Treat as a fatal error, and report it.
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:38 PM Revision bf6220e1 (ceph): mon: Merge in (and add COMMAND() for) compact command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:38 PM Revision 7e6c4611 (ceph): ceph: handle our own help printing
- We want to see helptext from mon commands and osd commands (and,
eventually, daemon commands), and so we'll need to m... - 11:37 PM Revision 590cffe2 (ceph): mon/OSDMonitor: restructure command flow
- - boilerplate at the top
- reply and update labels
- default r == 0
- explicitly fall out invalid or unrecognized com... - 11:37 PM Revision 4dc6a166 (ceph): mon/PGMonitor: reflow command methods
- - simplify dump_stuck_pg_stats() method
- default r = 0
- explicit update, reply labels
- avoid deep nesting when man... - 11:37 PM Revision bcf064f8 (ceph): librados: rados_monitor_log's cb takes two ints rather than timespec
- Handling struct timespec as a callback arg in Python was just too
weird to little benefit.
Signed-off-by: Dan Mick <... - 11:37 PM Revision 48490841 (ceph): rados.py: implement rados_monitor_log
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 2ce5cb7d (ceph): rados.py: change all calls to librados to be on a child thread
- Handling SIGINT while blocked in librados() requires said blocking
to not block the main Python thread, so arrange fo... - 11:37 PM Revision 95e411dc (ceph): ceph: implement -w/--watch.
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 5f211ef2 (ceph): ceph: clean up line wraps, comments, add verbose command output
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 3ff7c364 (ceph): ceph: return error from json_command rather than raising exception
- Print outs along with error, and return errno to caller if it happens
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:37 PM Revision d7c68859 (ceph): ceph: send pgid in command strings of pg tell
- It's also passed as part of the message, but to avoid having to
rev MCommand, just pass it in cmd there as well
Sign... - 11:37 PM Revision fc629e6e (ceph): MonmapMonitor: mon tell: allow 'type.id' or 'id' as well as 'n'
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 0b9601d5 (ceph): MonmapMonitor: use parsed destination for mon tell
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 2a663a94 (ceph): rados.py: no exception on error, just return errno to caller
- also fix up a comment
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:37 PM Revision 26df7ace (ceph): ceph: allow CephName to validate when given only an 'id'
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision aa7f52fb (ceph): ceph: move parsing of a json funcsig into function for reusability
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:37 PM Revision 73d08b93 (ceph): mon: wire new command map to new caps
- We can drop the fullcmd nonsense entirely, yay!
Signed-off-by: Sage Weil <sage@inktank.com> - 11:37 PM Revision 05dda0f2 (ceph): mon: weaken security check on 'log' command
- The exec bit doesn't mean anything for the log; make it W.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:37 PM Revision db589d1f (ceph): vstart.sh: use new mon cap profiles
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:37 PM Revision d87e3712 (ceph): mon: fix 'osd dump'
- Need to set r == 0.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:37 PM Revision 839d5b36 (ceph): mon: transition from MonCaps -> MonCap
- Convert all monitor users to use the new MonCap class.
Simplify the semantics around auids by essentially dropping a... - 11:37 PM Revision 489cd5c4 (ceph): FileStore: integrate WBThrottle
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:37 PM Revision 6670e2a7 (ceph): os/: Add WBThrottle
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:23 PM Revision 93d8125d (ceph): rados.py: remove debug prints from *_command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision d4900419 (ceph): ceph: restructure so old-style commands and new-style can share code
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision a090abfc (ceph): librados: use memcpy rather than strncpy for possibly-NUL data
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision 63017ba3 (ceph): rados.py: use librados-allocating versions of *_command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision e830de58 (ceph): librados: unit tests for mon_command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:23 PM Revision 039b757d (ceph): librados: add rados_monitor_log()
- Add method to trail the cluster/monitor log for use by ceph -w. Add a
simple functional test.
Note that changing th... - 11:23 PM Revision dc4a5084 (ceph): ceph: remove ceph tool cli tests
- This is dynamic and based on a running cluster's command set. Drop it.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:23 PM Revision 2aefee21 (ceph): osd/OSDCap: fix allow_all() check
- Only return true for the global "allow all" if the match does not constrain
us at all. This matches the set_allow_al... - 11:23 PM Revision 27dc4fef (ceph): osd/OSDCap: avoid typedef for rwxa_t; rename to osd_rwxa_t
- Avoid implementing an operator<< on __u8, and make the naming less likely
to conflict with others.
We did a similar ... - 11:23 PM Revision 1123fc29 (ceph): mon/MonCap: add new MonCap implementation
- This is a new class with a new grammer. Implementation is modeled after
OSDCap, and the semantics are based on the o... - 11:23 PM Revision 5d7dd5ab (ceph): mon: bump wire protocol version
- We have changed MonCap encoding and command semantics (which affects
forwarding). Bump the wire protocol version.
S... - 11:23 PM Revision 917341ea (ceph): ceph-object-corpus: note MForward encoding change
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:23 PM Revision e3f13e83 (ceph): vstart.sh: set python path(s); echo something for user to paste
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:23 PM Revision e748d9bb (ceph): ceph: add support for --admin-socket <path>
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:23 PM Revision 2e526492 (ceph): ceph: 'ceph daemon <name|path> <command ...>'
- This is *much* easier than 'ceph --admin-daemon <path> <command ...>'.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:23 PM Revision 3b7062b7 (ceph): RadosClient: handle command replies
- 11:23 PM Revision 808f518e (ceph): ceph: fix exception msg
- 11:23 PM Revision 7dbe4ef1 (ceph): ceph: pop off 'target' before sending command
- 11:23 PM Revision d5497fa3 (ceph): rados.py: errnos must have errno. qualifier
- 11:23 PM Revision 2919bdec (ceph): Set conffile to passed -c, not conf
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision d5075cab (ceph): Return correct error to main; always write outs to stderr
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision 9e8397a2 (ceph): Check for and handle old-monitor
- If it doesn't support get_command_descriptions, just send the
entire command.
Signed-off-by: Dan Mick <dan.mick@inkt... - 11:23 PM Revision 4698d99c (ceph): Enhance cephtool tests for coverage of CLI rewrite
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 11:23 PM Revision 1af5f74a (ceph): wip: osd tell commands, CephFileparse, etc.
- 11:23 PM Revision aeeabcd6 (ceph): librados: add *_command() variants that allocate the result w/ malloc
- These are helpful for commands that may have large results and are
expensive to process and/or transfer because retry... - 11:23 PM Revision f26bd55e (ceph): mon, ceph: transition to separate CLI parsing
- ceph is a new Python CLI that:
1) queries the underlying cephbin to get command descriptors,
2) parses user input and... - 10:54 PM Revision d9ff7d4a (ceph): mon: add JSON command parsing framework
- Use json_spirit to read/parse JSON command input into a "cmdmap",
which is a boost::variant typechecked discriminant ... - 10:54 PM Revision 2e172225 (ceph): osdc/Objecter: implement osd and pg commands
- This is reimplementing the 'tell osd' and 'pg ...' commands in the ceph
tool in the Objecter infrastruture. As a res... - 10:54 PM Revision a9ce3117 (ceph): str_list: cleanup/enhancement
- - move #includes to str_list.h
- remove redundant std::, add using for vector, set, list
- add get_str_vec and get_st... - 10:54 PM Revision 3bc0d3ff (ceph): Add C and C++ interfaces to mon_command, osd_command, pg_command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:54 PM Revision 4227490f (ceph): rados.py: functions for new librados functions {mon,osd,pg}_command
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:54 PM Revision 850a4cc4 (ceph): Rename "ceph" tool to "ceph-legacy-cli"
- Conflicts:
src/Makefile.am
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 10:54 PM Revision 31484826 (ceph): Formatter: add new_formatter(type)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:54 PM Revision ed2266a0 (ceph): Formatter: fix XML parsing assert
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:54 PM Revision 5e21b301 (ceph): mon: set tid on MMonCommandAck
- Set the tid on the reply to match the request. This will allow a client
to have multiple commands in flight.
Signed... - 10:54 PM Revision 0c6a31c8 (ceph): mon/MonClient: add mon command handling
- Reimplement the ceph tool functionality to set a command to the monitor
and collect a response.
Signed-off-by: Sage ... - 10:54 PM Revision 9f55333c (ceph): mon/MonClient: assume tid 0 is the first command
- If we get an ack with no tid, we have to assume it is the first (hopefully
only) command we have in flight. Old code... - 10:53 PM Revision 17cf8dfa (ceph): Revert "mon: fix validatation of mds ids in mon commands"
- This reverts commit 5c305d63043762027323052b4bb3ae3063665c6f.
This will avoid a conflict with the mon command refact... - 10:15 PM Revision 8a030eb0 (ceph): mon: implement --extract-monmap <filename>
- This will make for a simpler process for
http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-moni... - 10:14 PM Revision e9d20ffe (ceph): mon: implement --extract-monmap <filename>
- This will make for a simpler process for
http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-moni... - 10:14 PM Revision 5110497e (ceph): doc: update mon cluster rescue process for cuttlefish+
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:58 PM Bug #5139: Seg fault if listsnaps request with missing clones
- A similar issue caused by push_to_replica() not checking the return from get_snapset_context().
Program received s... - 05:04 PM Bug #5139 (Resolved): Seg fault if listsnaps request with missing clones
After doing this to cloned object called obj2:
$ find dev -name obj2_* -ls
660758 8 -rw-r--r-- 1 dzafman ...- 09:47 PM Feature #5141 (New): Some clone errors aren't repaired
0 log [ERR] : repair 3.7 6cf8deff/obj1/64//3 found clone without head
0 log [ERR] : 3.7 repair 1 errors, 0 fixed
...- 09:43 PM Revision 132d5bf7 (ceph): Fix usage for "ceph osd lost"
- Will be superceded, but use this commit to backport
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-... - 09:36 PM Revision c0268e27 (ceph): mon: implement --extract-monmap <filename>
- This will make for a simpler process for
http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-moni... - 09:26 PM Revision 0822b360 (ceph): Merge pull request #306 from Elbandi/wip-fuse-ioctl
- ceph-fuse: add ioctl support
Reviewed-by: Sage Weil <sage@inktank.com> - 09:17 PM Revision 9c7faf95 (ceph): cls_rbd: make sure stripe_unit is not larger than object size
- Test a few other cases too.
backport: cuttlefish, bobtail
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cher... - 09:17 PM Revision 684444f8 (ceph): rbd.py: fix stripe_unit() and stripe_count()
- These matched older versions of the functions, but would segfault
using the current versions.
backport: cuttlefish, ... - 09:17 PM Revision 4ad13c94 (ceph): librbd: make image creation defaults configurable
- Programs using older versions of the image creation functions can't
set newer parameters like image format and fancie... - 09:07 PM Revision 669e45ea (ceph): rgw: forward bucket creation to master region
- plus many fixes.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:27 PM Revision 5671fa9f (ceph): ceph-monstore-tool: implement getmonmap
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:26 PM Revision 945328d4 (ceph): rbd_image_read: add new task to test image_read.sh
- Add a new kernel task to test image reads. More could be
done to test various parameters by setting environment
vari... - 08:07 PM Revision f21a7f7b (ceph): rgw: protect ops log socket formatter
- Fixes: #4905
Ops log (through the unix domain socket) uses a formatter, which wasn't
protected.
Signed-off-by: Yehud... - 08:07 PM Revision 4071d7a7 (ceph): rgw: protect ops log socket formatter
- Fixes: #4905
Ops log (through the unix domain socket) uses a formatter, which wasn't
protected.
Signed-off-by: Yehud... - 08:05 PM Revision d48f1edb (ceph): rgw: protect ops log socket formatter
- Fixes: #4905
Ops log (through the unix domain socket) uses a formatter, which wasn't
protected.
Signed-off-by: Yehud... - 07:59 PM Revision 08665176 (ceph): FileStore: add fd cache
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:53 PM Revision 14d8cc67 (ceph): ceph-fuse: add ioctl support
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:52 PM Revision bcc8bfdb (ceph): ceph-disk: fix stat errors with new suppress code
- Broken by 225fefe5e7c997b365f481b6c4f66312ea28ed61.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:51 PM Revision 12eff5d9 (ceph): common/shared_cache.hpp: add clear()
- Clear clears a key/value from the cache.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 07:51 PM Revision 17a6e7fa (ceph): doc/dev/osd_internals: add some info about throttles
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:51 PM Revision ca28d87e (ceph): common/shared_cache.hpp: fix set_size()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:44 PM Revision bfb08ee4 (ceph): rbd image_read.sh: test different clone object orders
- An rbd clone image can be created with an object order that differs
from that of its parent. This patch adds testing... - 07:44 PM Revision 7ad5ceba (ceph): rbd image_read.sh: add clone-of-clone testing
- Add testing to verify that a snapshot of a clone and a clone of
that snapshot both produce the correct results when r... - 07:44 PM Revision a6b4847e (ceph): rbd image_read.sh: allocate local file at create time
- Move the dd command that touches the last byte in a local file
into create_image() where it belongs (out of fill_orig... - 07:44 PM Revision 512e9077 (ceph): rbd image_read.sh: a few cleanups
- The function boolean_toggle() in qa/workunits/rbd/image_read.sh is
defined but never used. My intentions were good t... - 07:37 PM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- I also have encountered this. Under Bobtail, I had it running with 2 active nodes and a passive node. Now, I can only...
- 07:16 PM Revision 9cc787a9 (ceph): ceph-monstore-tool: dump-keys command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:16 PM Revision a6569c5f (ceph): ceph-monstore-tool: compact command
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:16 PM Revision ebc09136 (ceph): ceph-monstore-tool: be more verbose when replaying a trace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:16 PM Revision cbff720f (ceph): rbd: prevent import of a dir
- Fixes: #2865
Signed-off-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision bb64adb7 (ceph): Merge pull request #303 from ceph/wip-librbd-config-create
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 06:01 PM Bug #5140: ceph init script failed to determine correct hostname for remote osd
- Fixed committed via pull request:
https://github.com/ceph/ceph/pull/307
Please help me to review it , thanks - 05:58 PM Bug #5140 (Resolved): ceph init script failed to determine correct hostname for remote osd
- When using /etc/init.d/ceph -a start, and if you have osds spread across multi hosts. The init script failed to run c...
- 05:56 PM Revision 7be705e0 (ceph): rgw: infrastructure to send requests to different region
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:55 PM Feature #3848 (In Progress): osd: gracefully handle cluster network heartbeat failure
- 03:28 PM Bug #4813: pgs stuck creating
- 2013-05-21 03:01:38.686052 7f53bdb97700 10 mon.b@0(leader).pg v133 check_osd_map applying osdmap e102 to pg_map
2013... - 01:34 PM Bug #4813: pgs stuck creating
- 2013-05-21 02:59:29.070891 mon.0 10.214.131.24:6789/0 44 : [INF] osdmap e8: 6 osds: 6 up, 6 in
2013-05-21 02:59:28.0... - 01:23 PM Bug #4813: pgs stuck creating
- ubuntu@plana15:~$ ceph pg dump | grep creating
34.5 0 0 0 0 0 0 0 creat... - 12:57 PM Bug #4813: pgs stuck creating
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-05-21_01:00:05-rados-next-testing-basic/18454
- 03:26 PM Revision bbcbab44 (ceph): Merge branch 'next'
- Conflicts:
debian/ceph.prerm - 03:25 PM Revision 150e1706 (ceph): Merge pull request #304 from javacruft/wip-invoke-rc.d
- Use invoke-rc.d in maintainer scripts
- 03:16 PM Revision 1c7b9c35 (ceph): os/LevelDBStore: fix compression selection
- We were always disabling compression.
Fixes: #5131
Reported-by: Sylvain Munaut <s.munaut@whatever-company.com>
Signe... - 02:58 PM rbd Feature #4834: Recompile/package qemu with new version of librbd to enable asynchronous flushing ...
- Need deb and RPM
- 02:57 PM rbd Feature #4550: Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
- Ensure that aync flush from 4834 is included when building these packages for RHEL
- 02:40 PM Feature #5125 (Resolved): Need tool(s) for manually manipulating monmaps
- commit:5671fa9fe54be9e7764546c6856563dd07a45dad
- 02:38 PM Feature #5125 (Fix Under Review): Need tool(s) for manually manipulating monmaps
- see commit:c0268e27497a4d8228ef54da9d4ca12f3ac1f1bf... backport to cuttlefish so we can update docs?
- 01:38 PM Feature #5125: Need tool(s) for manually manipulating monmaps
- Not sure I'd call this a feature; it's functionality we rely on, and lost with the change
to leveldb - 02:36 PM rbd Feature #5138 (Closed): LIO Support
- Modify the LIO scsi system to support RBD natively.
- 02:33 PM rbd Feature #4231 (In Progress): librbd: Java bindings
- 02:33 PM rbd Feature #4231: librbd: Java bindings
- 02:25 PM rbd Feature #5005 (In Progress): cinder: switch rbd driver to use librbd instead of the cli tool
- 02:25 PM rbd Feature #5004 (In Progress): cinder: make rbd configuration easier to use
- 02:25 PM rbd Feature #5003 (In Progress): cinder/nova: don't require ceph.conf on a compute host / support mul...
- 02:16 PM Feature #3527 (In Progress): osd: blacklist should cancel outstanding watches from blacklisted cl...
- 02:03 PM devops Feature #5071 (Duplicate): ceph-deploy osd list
- 02:03 PM devops Feature #3350 (Rejected): ceph-deploy: add "ceph-deploy refresh" that just pushed out changes to ...
- 02:00 PM devops Feature #3122 (Resolved): chef: Use "argonaut"/"bobtail" in apt sources.list, not "stable"
- 01:57 PM devops Feature #5014 (Resolved): arm: Build ARM packages
- 01:57 PM devops Feature #3310 (Resolved): ceph-deploy: handle stderr from commands better
- 01:56 PM devops Bug #4820 (Resolved): ceph-deploy : intermittent errors during install
- 01:54 PM devops Bug #5130 (Resolved): ceph-deploy osd create ubuntu:sdb
- 08:22 AM devops Bug #5130 (Need More Info): ceph-deploy osd create ubuntu:sdb
- the disk is probably in use or already partitioned... do 'ceph-deploy disk list ubuntu' to see, and/or pass --zap-dis...
- 12:03 AM devops Bug #5130 (Resolved): ceph-deploy osd create ubuntu:sdb
- root@majianpeng:/tmp/my-cluster# ceph-deploy osd create ubuntu:sdb
INFO:ceph-disk:Will colocate journal with data on... - 01:52 PM devops Bug #4864: ceph-deploy: mon create command seems to output info about the first node only
- 01:50 PM devops Bug #4651 (Can't reproduce): ceph-deploy: unfriendly error message
- 01:49 PM devops Bug #4651: ceph-deploy: unfriendly error message
- john do you remember what os this was?
- 01:47 PM devops Bug #4655 (Resolved): error handling in ceph-deploy could be better for negative tests
- 01:46 PM devops Bug #4588 (Resolved): pushy local transport steps on command
- 01:44 PM devops Bug #5107 (Duplicate): ceph-deploy: on centos 6.3, osd create command should be cleaned up
- dup of #4984
- 01:36 PM devops Bug #4862 (Resolved): ceph-deploy: install occassionally throws exceptions though installation is...
- 01:20 PM rgw Bug #4754 (Resolved): GET/HEAD on account is extremely slow, times out
- see #5136 for larger architectural overhaul
- 01:19 PM rgw Bug #5132 (Duplicate): nightlies: rgw crashed in bobtail
- dup of #4905. backported and merged fix.
- 09:54 AM rgw Bug #5132 (Duplicate): nightlies: rgw crashed in bobtail
- logs: ubuntu@teuthology:/a/teuthology-2013-05-21_01:30:03-upgrade-master-testing-basic/18675...
- 01:18 PM rgw Bug #4902 (Resolved): Issuess handling very large files
- 01:17 PM Feature #5137 (Resolved): osd: magically fall back to leveldb for xattrs
- see the grief for example in #4902
add some librados api tests for large xattrs, many xattrs. - 01:15 PM rgw Bug #2366 (Resolved): rgw: bucket index update rely on pg state
- 01:14 PM rgw Bug #3450: WRITE permission only doesn't allow proper multi-part upload
- We're going to revise the whole subuser scheme as part of a bigger multi-tenancy project.
- 01:10 PM rgw Bug #3450 (Won't Fix): WRITE permission only doesn't allow proper multi-part upload
- 01:13 PM rgw Bug #4755 (Resolved): rgw: assumption of signed char
- 01:11 PM rgw Bug #4409 (Resolved): rgw: better logging on fastcgi socket error
- 01:10 PM rgw Bug #3706 (Resolved): rgw functional test testSlashInName failed in nightly
- 01:07 PM rgw Feature #5136 (Closed): rgw: revise user stats
- 01:07 PM rgw Bug #4497 (Resolved): rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- 01:07 PM rgw Bug #4905 (Resolved): rgw: log formatter for ops socket not protected
- commit:d48f1edb07a4d8727ac956f70e663c1b4e33e1dd
- 12:57 PM CephFS Bug #4832: mds: failed auth_unpin assert
- 12:57 PM CephFS Bug #4832: mds: failed auth_unpin assert
- ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-05-21_01:00:40-fs-next-testing-basic/18590
- 12:17 PM rbd Bug #2865 (Resolved): rbd import fails for directory but creates rbd image
- commit:cbff720ff54ac6948f455cf82c4c2eee31d703f4
- 11:39 AM rbd Bug #2667 (Won't Fix): librbd: create_snap on a closed image segfaults
- 11:39 AM rbd Bug #3964 (Won't Fix): krbd: 32-bit, kernel 3.2.0 system can't do O_DIRECT writes to mapped rbd i...
- 11:26 AM rbd Bug #4897 (Duplicate): qemu rbd driver should allow manipulation of format 2, striped images
- 11:25 AM rbd Bug #5099 (Resolved): io performance / ceph block device
- this is becuase dd is single a single sync io. doing 2 dd procs means you have 2 ios in flight, so 2x as fast. the ...
- 11:21 AM rbd Bug #4522 (Can't reproduce): RBD utility "showmapped" bug
- 11:20 AM rbd Feature #5135 (Duplicate): librbd should create format 2 images by default
- 11:11 AM rbd Feature #5135 (Duplicate): librbd should create format 2 images by default
- The current way of creating RBD format 2 images is calling either rbd_create2 or rbd_create3.
Older binaries like ... - 11:19 AM rbd Feature #5067 (Resolved): librbd: configuration options to override default image creation parame...
- 10:35 AM rgw Feature #5133: rgw: RESTful api to lock/unlock mdlog
- * Get datalog info
(we'll modify the list metadata log):
GET /admin/log?type=metadata
result:
return a js... - 10:31 AM rgw Feature #5133 (Resolved): rgw: RESTful api to lock/unlock mdlog
- 10:34 AM rgw Feature #5134 (Resolved): rgw: RESTful api for datalog
- 08:25 AM devops Bug #5113 (Resolved): ceph-deploy: purgedata on debian-wheezy returns error
- the daemons were still running; debs are now fixed to stop daemons.
- 08:24 AM Documentation #5116: Clarify that "DISK" means "disk, partition, or directory" in ceph-deploy
- PATH?
- 08:23 AM Bug #5118: osd version reporting incorrectly when client libs installed
- i'm skeptical, but we should test to verify.
- 08:22 AM Revision 19c5ac37 (ceph): Use invoke-rc.d in maintainer scripts
- Upstart configurations and sysv init scripts should be started and stopped
using invoke-rc.d in maintainer scripts.
... - 08:18 AM Bug #5131 (Resolved): leveldb: Compression config option is just ignored
- ha, thanks! commit:1c7b9c35053d26b556a247297da127ff0d6aa07d
- 08:11 AM Bug #5131: leveldb: Compression config option is just ignored
- Damnit, I've just noticed it was created in the wrong sub project and I can't move it ...
- 08:11 AM Bug #5131 (Resolved): leveldb: Compression config option is just ignored
- In the code there is :...
- 05:11 AM Revision 047d32a8 (ceph): Added send_response implementation for MDLOG and BILOG list APIs so tha...
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
05/20/2013
- 10:48 PM Revision 183280c8 (ceph): PG: kill some dead IndexedLog methods
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:32 PM Revision 4cf00b9d (ceph): OSD: kill old split code, it's been dead for a while
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com> - 10:09 PM Revision 57a6a54d (ceph): Makefle: force char to be signed
- On an armv7l build, we see errors like
warning: rgw/rgw_common.cc:626:16: comparison is always false due to limited... - 09:40 PM Revision d9c92e77 (ceph): Merge pull request #260 from ceph/wip-suppress
- Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
- 09:39 PM Revision 85fb422a (ceph): debian: stop sysvinit on ceph.prerm
- Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 2f193fb931ed09d921e6fa5a985ab87aa4874589) - 09:39 PM Revision 2f193fb9 (ceph): debian: stop sysvinit on ceph.prerm
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:34 PM Revision d2a42538 (ceph): mds: better error check on sessionmap load
- Would have helped with #5104.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:41 PM Revision 87767fb1 (ceph): mon: be a bit more verbose about osd mark down events
- Put these in the cluster log; they are interesting.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:35 PM Revision 03b93260 (ceph): Makefile: add -Wformat-security
- Clean up the formatting a bit here too.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:26 PM Revision 6c9292c8 (ceph): thrashosds: sync before doing powercycle testing
- Hopefully fixes #5112
- 07:22 PM Revision d37a7bcc (ceph): Merge remote-tracking branch 'gh/next'
- 07:13 PM Revision a7096f8f (ceph): rgw: add access key to zone info
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 06:44 PM Revision 29521f96 (ceph): rbd: add read flags test with each cache mode
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:39 PM Revision 18e975eb (ceph): ceph-qa-suite: updating Hadoop tests
- Changes to the teuthology YAML parsing
necessitates a small tweak to the Hadoop
and libceph-fs YAML files.
Signed-of... - 06:28 PM rgw Cleanup #5129 (New): rgw: document RGWRegionMap::update()
- 06:27 PM rgw Cleanup #5128 (Closed): rgw: rename RGWRegionMap::get_params()
- By popular demand. Maybe call it get_storage_object_location(), and potentially make it static.
- 06:24 PM rgw Feature #5127 (New): rgw: region map versioning
- 06:23 PM Revision f9941077 (ceph): schedule_suite.sh: 8hr -> 10hr suite timeout
- Still missing some slow rbd tests.
- 06:11 PM rgw Feature #5126 (New): rgw: identify master region divergence
- Identify the cases where the region map holds conflicting info about the master region and handle it appropriately.
- 06:01 PM Feature #5125 (Resolved): Need tool(s) for manually manipulating monmaps
- http://ceph.com/docs/master/rados/operations/add-or-rm-mons/#removing-monitors-from-an-unhealthy-cluster, for instanc...
- 05:58 PM rgw Cleanup #5124 (Resolved): rgw: use region instead of regions in radosgw-admin
- and keep it consistent
- 05:57 PM Tasks #5123 (New): document src/objclass/objclass.h
- 05:45 PM rgw Tasks #5121 (Closed): bump up librados version
- Need to bump up librados version (due to librados related changes for dr/geo)
- 05:37 PM rgw Documentation #5119 (Resolved): rgw: document which pools allowed to collide
- within a zone configuration we may reuse the same pool for different purposes (e.g., rgw_zone_root_pool, rgw_region_r...
- 04:10 PM Revision 80973a00 (ceph): Merge pull request #301 from javacruft/wip-upstart-tasks
- Reviewed-by: Sage Weil <sage@inktank.com>
- 04:07 PM Revision ea6a262b (ceph): Merge pull request #300 from javacruft/wip-format-security
- Fix -Werror=format-security errors
- 04:06 PM Revision eac3cd2d (ceph): ceph df: fix si units for 'global' stats
- si_t expects bytes, but it was being given kilobytes.
Signed-off-by: Mike Kelly <pioto@pioto.org>
(cherry picked fro... - 04:06 PM Revision d05a4e55 (ceph): ceph df: fix si units for 'global' stats
- si_t expects bytes, but it was being given kilobytes.
Signed-off-by: Mike Kelly <pioto@pioto.org>
(cherry picked fro... - 04:05 PM Revision 90740d88 (ceph): Merge pull request #302 from pioto/ceph-df-unit-fix
- Reviewed-by: Sage Weil <sage@inktank.com>
- 02:53 PM devops Feature #3255 (Resolved): ceph-disk: allow prepare without activate (for spares)
- 01:49 PM CephFS Bug #5104 (Can't reproduce): MDS crashed in Objecter::handle_osd_op_reply
- if there is a decode error, find the parent frame with the bl and p bl._len to see how big it is. usually it is fall...
- 01:44 PM CephFS Bug #5104: MDS crashed in Objecter::handle_osd_op_reply
- Sadly, no logs on this guy any more, sorry.
If it happens again, I'll collect that frame 15 info.
Do you have a... - 01:23 PM CephFS Bug #5104 (Need More Info): MDS crashed in Objecter::handle_osd_op_reply
- any logs? would love to see value of 'r' and bl._len in frame 15..
- 01:34 PM Bug #5118 (Rejected): osd version reporting incorrectly when client libs installed
- Client reported that during upgrade his OSDs were not showing the upgrade in some cases. It appears that when client...
- 01:17 PM Documentation #5116 (Closed): Clarify that "DISK" means "disk, partition, or directory" in ceph-d...
- People continue to be confused about this; we have to come up with some way to make
it more clear.
- 12:48 PM Revision 0c2b738d (ceph): ceph df: fix si units for 'global' stats
- si_t expects bytes, but it was being given kilobytes.
Signed-off-by: Mike Kelly <pioto@pioto.org> - 12:43 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- Faidon Liambotis wrote:
> Moments ago I've had a failed disk and seven more OSDs were marked as down. They were all ... - 12:32 PM Bug #4967 (In Progress): Misbehaving OSD sets over half of the cluster as down despite "osd min d...
- 12:28 PM Bug #5112 (Resolved): cannot find config file after ceph-osd restart
- pushed change to teuthology master, next, cuttlefish...
- 12:25 PM Bug #5112: cannot find config file after ceph-osd restart
- i've seen this before, too. i wonder if the thrasher task needs to just run 'sync' when it starts before starting to...
- 11:09 AM Bug #5112 (Resolved): cannot find config file after ceph-osd restart
- 17561: (1391s) collection:osd-powercycle clusters:3osd-1per-target.yaml fs:xfs.yaml powercycle:default.yaml tasks:cfu...
- 12:22 PM Bug #5111 (Rejected): HEALTH_WARN stuck reporting recovery though all pgs are active+clean
- commit:65072f2e432c212f88dc5d5b9e8034decb019103 was in next, but not merged into master yet.
- 11:06 AM Bug #5111 (Rejected): HEALTH_WARN stuck reporting recovery though all pgs are active+clean
- ubuntu@plana25:/var/log/ceph$ ceph -w
health HEALTH_WARN recovery recovering 0 o/s, 60B/s
monmap e1: 3 mons ... - 12:08 PM rbd Bug #4559 (Resolved): krbd: kernel BUG when mapping unexisting rbd device
- Maciej is correct, message signatures are not yet supported
in the kernel client. This issue has been created to ge... - 06:47 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- ...
- 11:37 AM Bug #5114 (Rejected): os/FileStore.cc: 2225: FAILED assert(0 == "_close_replay_guard failed")
- ...
- 11:26 AM devops Bug #5113 (Resolved): ceph-deploy: purgedata on debian-wheezy returns error
- purgedata on burnupi26 returns error. ceph-deploy is installed on the same node....
- 09:54 AM Linux kernel client Feature #5109 (Resolved): libceph: implement message signatures
- userland has done this since bobtail, and someday we might want to require it.
- 09:52 AM devops Bug #4865 (Resolved): ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid ...
- you were on 0.61.2... the udev fix was 2 patchs after that. tested after doing install --dev=cuttlefish and it worke...
- 09:45 AM Bug #5081 (Can't reproduce): Data migration and recover slow after changed OSD weight
- If you want help debugging your system performance, you should probably be engaging inktank professional services...
- 09:40 AM Bug #5100: teuthology kclient (?): fails to unmount after tiobench
- This test is part of the kernel suite that runs nightly, and AFAICS never fails there... :/
- 09:38 AM CephFS Bug #5105: mds/CInode.cc: 1996: FAILED assert(auth_pins >= 0)
- probably a dup of #4832?
- 09:37 AM devops Cleanup #5106: ceph_deploy: install/compile error on wheezy
- let's just disable these tests.. dan and i don't even know how to run them.
- 09:35 AM Bug #5108 (Rejected): ceph recovery: unmotivated stuck
- 'stuck' just means it has been in this state for more than a few minutes.. in this case, recovery is just taking a wh...
- 09:26 AM Revision 17f6fcca (ceph): Remove stop on from upstart tasks
- Upstart tasks don't have to concept of 'stop on' as they
are not long running. - 09:21 AM Revision 6340ba8a (ceph): Fix -Werror=format-security errors
- Fixup a couple of errors when compilng with -Werror=format-security.
- 08:04 AM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- I also have scrub errors with this message : "found clone without head"
Should not a "ceph pg repair" fix that kind ... - 06:54 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- Sage,
This weekend my monitor leveldb store.db's started growing again. Although I don't know when it started for ...
05/19/2013
- 11:36 AM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- Moments ago I've had a failed disk and seven more OSDs were marked as down. They were all neighbouring (67 failed, 60...
- 06:03 AM Bug #5082: OSD wrongly marked as down
- I added options
osd recovery max active = 1
osd osd maxbackfills = 1
to config and injected them in co... - 04:02 AM Bug #5108 (Rejected): ceph recovery: unmotivated stuck
- Sorry if there are "feature", not a "bug", but from users point of view there are annoying bug.
I have 3 node, HEA...
05/18/2013
- 05:02 AM Revision 947e1331 (ceph): MDLOG and BILOG REST Apis implemented along with some bug fixes
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 01:53 AM Revision d7ec0892 (ceph): install: make overrides grouped by project
- This lets us set different overrides for e.g. ceph vs samba, and makes it
so the schedule_teuthology.sh overrides don... - 12:06 AM Revision 8bba266b (ceph): libcephfs: add ceph_get_pool_name()
- Convert an int pool id to a pool name. Useful for making sense of the
output from ceph_get_*_layout()'s poolid outpu...
05/17/2013
- 11:59 PM Revision 863d6d78 (ceph): Merge pull request #253 from Elbandi/wip-getlayout
- Reviewed-by: Sage Weil <sage@inktank.com>
- 10:59 PM Revision feec1b46 (ceph): doc: Added more glossary-compliant terms and indexing.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:58 PM Revision 5c4b4f0f (ceph): doc: Added another instance term to the glossary.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:56 PM Revision decf342c (ceph): doc: Minor improvements to Ceph FS landing page.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:07 PM Revision 0f4c67f1 (ceph): rgw: store region in bucket info
- only handle requests that come to buckets stored in correct
region.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:50 PM Revision 3255f115 (ceph): libcephfs: get the pool name of a file path
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:45 PM Revision 3562c8c5 (ceph): libcephfs: get replication factor of a file handle/path
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:43 PM Revision 877fcf0b (ceph): libcephfs: get file handle/path layout info
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:39 PM Revision 42c74fde (ceph): libcephfs: get stripe_unit/stripe_count/object_size/pool_id by file han...
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:10 PM Revision ee3d50e6 (ceph): Client: get describe_layout by file handle/path
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:10 PM Revision 10496a84 (ceph): libcephfs: fix typos
- Signed-off-by: Andras Elso <elso.andras@gmail.com>
- 07:08 PM Revision 5a274c8e (ceph): client config will be done only after the cluster is operational.
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 05:47 PM devops Bug #4865 (In Progress): ceph-disk: activate fails on debian wheezy due to missing udev by-partuu...
- tested with cuttlefish branch on burnupi26, still seeing the same issue
- 05:23 PM devops Bug #5086 (Resolved): ceph-deploy: osd create command fails sometimes on centos 6.3
- commit:bae521159deb0ca58c05ec14fa8362c4cc334fc2
- 05:06 PM devops Bug #5107: ceph-deploy: on centos 6.3, osd create command should be cleaned up
- ...
- 04:57 PM devops Bug #5107 (Duplicate): ceph-deploy: on centos 6.3, osd create command should be cleaned up
- on centos 6.3, [burnupi05, burnupi21]
while osd create command when used with zapdisk option, does create osds suc... - 04:44 PM devops Bug #4925 (Resolved): Incorrect yum conf for Cuttlefish and el6
- The ceph-release rpms in the rpm-bobtail repo have been respun to reference ceph.com/rpm-bobtail instead of ceph.com/...
- 04:26 PM Revision d0a5d3a7 (ceph): Merge pull request #295 from ceph/wip-5077
- Reviewed-by: Joao Luis <joao.luis@inktank.com>
- 04:17 PM Revision 69e2cbef (ceph): mon: add 'compact' command
- As in, 'ceph mon tell \* compact'
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Luis <joao.luis@inkt... - 03:35 PM Revision b238f356 (ceph): Merge pull request #296 from dalgaaf/wip-da-CID-1021213
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 03:26 PM devops Cleanup #5106 (Resolved): ceph_deploy: install/compile error on wheezy
- Incompatible syntax with python 2.6 compiler:
administrator@ceph-admin:~$ sudo aptitude install ceph-deploy
The f... - 03:10 PM CephFS Bug #5105 (Duplicate): mds/CInode.cc: 1996: FAILED assert(auth_pins >= 0)
- While trying to reproduce #4999, I collected this in an MDS.
I was running next branch (commit c80c6a032c) merged ... - 02:34 PM Subtask #5046: Factor out PG logs, PG missing
- Move code to PGLog.cc PGLog.h so that missing, log and ondisklog are protected. Fix what breaks.
- 02:22 PM CephFS Bug #5104 (Can't reproduce): MDS crashed in Objecter::handle_osd_op_reply
- While trying to reproduce #4999, I collected this in an MDS.
I was running next branch (commit c80c6a032c) merged ... - 02:14 PM CephFS Bug #5103 (Rejected): mds: hung getattrs after restart
- this was an osd issue.
- 11:06 AM CephFS Bug #5103 (Rejected): mds: hung getattrs after restart
- logs on cephdrop ceph-mds.1.log
hung requests are... - 01:21 PM Documentation #2271: FAQ: BTRFS vs XFS
- Correction: btrfs is not a journaled fs. The xfs is better than ext4 for subtle desSigns reasons that are probably n...
- 12:49 PM Documentation #2271 (Resolved): FAQ: BTRFS vs XFS
- This is covered here: http://ceph.com/docs/master/rados/configuration/filesystem-recommendations/ and has a link from...
- 12:30 PM rbd Bug #4661: xfstest 139 hung
- Note that both the original crash and this latest one
involve (probably) some corruption found in a path
involving ... - 12:28 PM rbd Bug #4661: xfstest 139 hung
- Finally getting back to this.
Here is the end of the log:... - 11:58 AM Revision a130cd50 (ceph): kv_flat_btree_async.cc: release AioCompletion before leave the loop
- CID 727982 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "aioc" going out of scope leaks the st... - 11:54 AM Revision 4ba70f8f (ceph): librbd/internal.cc: fix resource leak
- Call release() on librados::AioCompletion to free storage before
leave the loop or call new again.
CID 1021213 (#1 o... - 11:52 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- One interesting observation is that when I tried restarting an OSD a few minutes after it has been restarted and clus...
- 10:29 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Here's the same with osd.6, but with --debug-ms 1 as requested. Besides peering being slow, the recovery_wait phase s...
- 11:43 AM Linux kernel client Bug #5043 (Resolved): Oops in remove_osd
- The following has been committed to the "testing" branch
of the ceph-client git repository:
14d2f38 libceph: must... - 11:42 AM rbd Bug #4559 (Need More Info): krbd: kernel BUG when mapping unexisting rbd device
- I have committed the following to the "testing" branch of
the ceph-client git respository:
7262cfc rbd: don't des... - 04:20 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I am going to test the patch. I will let you know about results probably next week.
- 10:59 AM Bug #5102: mon: assert(is_active()) on propose_pending()
- wip-5102 has a proposed fix.
- 10:56 AM Bug #5102 (Resolved): mon: assert(is_active()) on propose_pending()
- This bug popped up while Jim Schutt was trying to reproduce #4999
This was my reply to the assert:
The issue ... - 10:14 AM Documentation #3388 (Resolved): doc: create documentation for juju installation
- Patrick McGarry completed this on the wiki. Since it's third party, it should be in the wiki rather than the mainline...
- 09:26 AM Bug #5077 (Resolved): nightlies: single node cluster hung waiting for ceph_health to be OK
- 08:55 AM rgw Feature #5101 (New): teuthology: make rgw.py test multiple instances
- even running 2 instances is a start, but ideally we also make an haproxy task that balances between them?
- 08:47 AM devops Feature #5091: google-perftools for arm
- - Enable google-perftools on armhf: TODO
+ Enable google-perftools on armhf: DONE
i guess this means its in the u... - 06:39 AM Bug #5100 (Can't reproduce): teuthology kclient (?): fails to unmount after tiobench
- If I run the "suites/tiobench.sh" suite with kclient I sometimes
(or maybe always) get a failure, *after* the suite ... - 06:10 AM Revision 7494e4eb (ceph): doc: Omitted literal syntax from toc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:10 AM Revision 381ad24d (ceph): doc: Added fuse syntax to the fstab doc.
- fixes: #3672
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 03:39 AM Revision 231a2aa8 (ceph): Merge branch 'next'
- 03:39 AM Revision c80c6a03 (ceph): sysvinit: fix enumeration of local daemons when specifying type only
- - prepend $local to the $allconf list at the top
- remove $local special case for all case
- fix the type prefix chec... - 03:26 AM Bug #4999: monitor sync failure
- Yeah, the assert guarantees an invariable is always met (we must be active to propose a new value through Paxos).
... - 02:22 AM rbd Bug #5099 (Resolved): io performance / ceph block device
- ceph version 0.61.2,
ceph -s
health HEALTH_OK
monmap e1: 2 mons at {a=ip1:6789/0,b=ip2:6789/0}, election epoch... - 01:40 AM Revision 7bc7c9d4 (ceph): udev: install disk/by-partuuid rules
- Wheezy's udev (175-7.2) has broken rules for the /dev/disk/by-partuuid/
symlinks that ceph-disk relies on. Install p... - 01:40 AM Revision d8d7113c (ceph): udev: install disk/by-partuuid rules
- Wheezy's udev (175-7.2) has broken rules for the /dev/disk/by-partuuid/
symlinks that ceph-disk relies on. Install p... - 12:58 AM Revision 65072f2e (ceph): mon: clear pg delta after some period
- If we have not pg_map updates, the delta doesn't update, and can get stuck
with the velocity right before activity st...
05/16/2013
- 11:46 PM CephFS Documentation #3672 (Resolved): doc: how to mount ceph-fuse from fstab
- 11:14 PM Documentation #4933 (Resolved): ceph-deploy. Partition usage should be disk usage.
- 11:12 PM Revision acf6b8f9 (ceph): os/FileStore: fix replay guard error msgs (again)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:47 PM Documentation #3394 (Resolved): doc: create documentation for ceph-deploy
- We have full docs for ceph-deploy now.
- 10:46 PM Documentation #3321 (Resolved): doc: Explain monitor HA better
- Added quite a bit of content on high availability, and index entries for it too.
- 10:46 PM Revision 9b9d322c (ceph): test_filestore_idempotent_sequence: unmount prior to deleting store
- FileStoreDiff umounts the stores in its destructor.
Also, DeterministicOpSequence handles deletes its passed
object ... - 10:45 PM Documentation #3247 (Resolved): doc: Move content out of wiki, kill it with fire
- New wiki has been up for awhile, and the old wiki is de-linked from the main site.
- 10:45 PM Revision 5a27e85c (ceph): Revert "test_filejournal.cc: cleanup memory in destructor"
- The finish() method for Contexts calls delete this.
This reverts commit 36028916c4630ea66007760efed8fc6c441e7af5.
F... - 10:37 PM Revision 49c04c62 (ceph): librbd: make image creation defaults configurable
- Programs using older versions of the image creation functions can't
set newer parameters like image format and fancie... - 10:37 PM Revision 4d7058fe (ceph): rbd.py: fix stripe_unit() and stripe_count()
- These matched older versions of the functions, but would segfault
using the current versions.
backport: cuttlefish, ... - 10:36 PM Revision 82a16c32 (ceph): cls_rbd: make sure stripe_unit is not larger than object size
- Test a few other cases too.
backport: cuttlefish, bobtail
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
(cher... - 10:28 PM Revision aacc9adc (ceph): librbd: make image creation defaults configurable
- Programs using older versions of the image creation functions can't
set newer parameters like image format and fancie... - 10:28 PM Revision c49ba750 (ceph): os/FileStore: print error code to log on replay guard failure
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:21 PM Revision 53ee6f96 (ceph): rbd.py: fix stripe_unit() and stripe_count()
- These matched older versions of the functions, but would segfault
using the current versions.
backport: cuttlefish, ... - 10:19 PM Revision 810306a2 (ceph): cls_rbd: make sure stripe_unit is not larger than object size
- Test a few other cases too.
backport: cuttlefish, bobtail
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:59 PM Revision 8fa3039e (ceph): doc: Added index reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:59 PM Revision 74a73f2f (ceph): doc: Added glossary references and index references.
- fixes: #3321
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 08:57 PM Revision 5737d032 (ceph): doc: Added cluster map and CRUSH definitions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:57 PM Revision 58a880bd (ceph): doc: Fixing index references.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:56 PM Bug #5082: OSD wrongly marked as down
- Since I use XFS on OSD and It does massive RAM caching, and linux VFS in general, don't you think it could be the rea...
- 07:58 PM Bug #5082: OSD wrongly marked as down
- -loses a moves-
moves - 07:57 PM Bug #5082: OSD wrongly marked as down
- I wonder if next scenario could be realized in my case. I have a lot of data on OSD and change weight such as OSD los...
- 11:15 AM Bug #5082: OSD wrongly marked as down
- As I see It could be that During the process a lot of IO placed on backing device and OSD just waits in 'D' state and...
- 10:54 AM Bug #5082: OSD wrongly marked as down
- BTW, I got a lot of
2013-05-17 00:52:47.278462 osd.23 [WRN] slow request 30.313363 seconds old, received at 2013-... - 09:36 AM Bug #5082 (Need More Info): OSD wrongly marked as down
- hmm, ok, this is going to need more in the way of logs to diagnose. can you capture 'debug mon = 10', 'debug ms = 1'...
- 08:56 PM Revision 46f5f585 (ceph): doc: Added latency comment.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:18 PM Revision c2acecbd (ceph): debian: make radosgw require matching version of librados2
- ...indirectly via ceph-common. We get bad behavior when they diverge, I
think because of libcommon.la being linked b... - 08:17 PM Revision 604c83ff (ceph): debian: make radosgw require matching version of librados2
- ...indirectly via ceph-common. We get bad behavior when they diverge, I
think because of libcommon.la being linked b... - 08:14 PM Revision bc9f502c (ceph): set permission for config file
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 08:10 PM Revision 2df6e376 (ceph): Merge pull request #291 from dalgaaf/wip-da-CID-1019548
- client/Client.cc: fix/silence "logically dead code" CID-Error
Even money that this satisfies the coverity gods...
R... - 06:41 PM devops Bug #4865 (Resolved): ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid ...
- commit:d8d7113c35b59902902d487738888567e3a6b933
- 01:08 PM devops Bug #4865: ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid rules
- http://bugs.debian.org/cgi-bin/bugreport.cgi?bug=681809
- 01:08 PM devops Bug #4865: ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid rules
- wip-4865
paravoid says it's specific to wheezy.. the udev rules are different than upstream.
moving the by-part... - 06:30 PM Revision 1df344fe (ceph): schedule_suite.sh: put sha1 in install: overrides, not ceph:
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:14 PM Revision eaf3abf3 (ceph): FileJournal: adjust write_pos prior to unlocking write_lock
- In committed_thru, we use write_pos to reset the header.start value in cases
where seq is past the end of our journal... - 05:49 PM Revision 541396fa (ceph): client/Client.cc: fix/silence "logically dead code" CID-Error
- Fix handling of 'safe' and the conditions after calling file_flush().
CID 1019548 (#1 of 1): Logically dead code (DE... - 05:48 PM Bug #5077 (Fix Under Review): nightlies: single node cluster hung waiting for ceph_health to be OK
- wip-5077
- 05:19 PM devops Bug #4925 (In Progress): Incorrect yum conf for Cuttlefish and el6
- The rpm symbolic link was moved from pointing at bobtail to point at cuttlefish. The solution is rebuild the ceph-re...
- 09:50 AM devops Bug #4925 (New): Incorrect yum conf for Cuttlefish and el6
- This was fix last week, but it is happening again.
From http://ceph.com/rpm-cuttlefish/el6/x86_64/ceph-release-1-0... - 04:49 PM Revision 7cb59d3b (ceph): added UserKnownHostsfile to ssh config
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 04:42 PM Revision 64871e09 (ceph): mds: avoid assert after suicide()
- Fixes: #5079
Signed-off-by: Sage Weil <sage@inktank.com> - 04:40 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- 04:39 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- 500 passes of the job on commit:1f65594c23309b527d74afe648c888c69a3c2acd wip-5021
- 04:24 PM devops Bug #5086: ceph-deploy: osd create command fails sometimes on centos 6.3
- Grr. Yes, this is a pre-Python-2.7 thing. "{}" in format strings was added in 2.7.
Yargh; I hate using field numbe... - 04:05 PM devops Bug #5086: ceph-deploy: osd create command fails sometimes on centos 6.3
- this seems to work fine, when tried manually.
- 12:51 PM devops Bug #5086 (Resolved): ceph-deploy: osd create command fails sometimes on centos 6.3
- test set up: burnupi05, burnupi20.
while running ceph-deploy tests from teuthology, found that "osd create" comman... - 04:14 PM Revision 707ad738 (ceph): Merge pull request #290 from dalgaaf/wip-da-SCA-cppcheck-v2
- Reviewed-by: Sage Weil <sage@inktank.com>
rgw bits Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 04:07 PM rbd Feature #5067 (Fix Under Review): librbd: configuration options to override default image creatio...
- wip-librbd-config-create
- 03:46 PM Bug #5075 (Resolved): filejournal tests failing in nightlies
- 03:46 PM Bug #5076 (Resolved): nightlies:segfault in ceph_test_filestore_idempotent_sequence
- 03:17 PM Bug #4999: monitor sync failure
- Hmmm, this bit seems odd:...
- 11:18 AM Bug #4999: monitor sync failure
- Hmm, got the following during mon startup:...
- 09:56 AM Bug #4999: monitor sync failure
- OK, I'll take it for a spin. next branch is fine, except we might run into other issues that confound debugging this...
- 09:52 AM Bug #4999: monitor sync failure
- Jim, pushed wip-4999 with a patch to output what I believe to be the relevant information on 'debug mon = 9' (some me...
- 09:16 AM Bug #4999: monitor sync failure
- Yeah. Will push something shortly and let you know.
- 08:15 AM Bug #4999: monitor sync failure
- Joao, maybe it would be best if you pushed a branch with the debugging you'd like to see, since you know the code muc...
- 08:03 AM Bug #4999: monitor sync failure
- I'm afraid the debug ms = 1 is responsible for whatever is keeping me from reproducing, so I was
leaning towards the... - 07:35 AM Bug #4999: monitor sync failure
- huh, although debug ms = 1 would still be useful to see what's triggering what. That could also be surgically debugge...
- 07:31 AM Bug #4999: monitor sync failure
- That's pretty much what I was going to suggest if you were unable to trigger this.
Trying to output only the relev... - 07:15 AM Bug #4999: monitor sync failure
- Well, unfortunately it didn't reproduce overnight, either.
I was reproducing this every day at lower debug levels,... - 02:55 PM devops Feature #5092: libatomic-ops for arm; or use gcc atomics instead
- i wonder if it would actually be less effort to make our include/atomic.h use the gcc atomic types if they are availa...
- 02:27 PM devops Feature #5092 (Closed): libatomic-ops for arm; or use gcc atomics instead
- Customer reported an issue with ceph and libatomic-ops on quantal. We are currently building with version "7.2~alpha...
- 02:54 PM devops Feature #5091: google-perftools for arm
- Blueprint changed by James Page:
Work items changed:
Work items for ubuntu-13.06:
+ Enable google-perftools on... - 02:23 PM devops Feature #5091 (Resolved): google-perftools for arm
- Need google-perftools package for arm
- 02:30 PM rbd Bug #4559 (Fix Under Review): krbd: kernel BUG when mapping unexisting rbd device
- The following has been posted for review:
[PATCH] rbd: don't destroy ceph_opts in rbd_add()
- 01:26 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I don't have enough information nor do I have a Xen setup so
it isn't easy for me to try to reproduce the problem re... - 01:12 PM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I believe I have found the problem.
In rbd_add(), if rbd_client_create() failed the error path
would call ceph_de... - 09:23 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I asked Maciej to report more specifically the platform he
was using (VM, and kernel/user space rbd). Answer:
Op... - 02:20 PM devops Feature #5015 (In Progress): ceph-deploy: push packages to all ceph repos
- Currently pushing ceph-deploy to debian and to centos6. The others are in progress.
- 02:10 PM devops Feature #5014 (In Progress): arm: Build ARM packages
Packages available at:
http://gitbuilder.ceph.com/ceph-deb-quantal-armv7l-basic/ref/master/
- 01:56 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- Did all that, attached the logs & peering.txt. Peering took two minutes, with recovery_wait taking another two, so I ...
- 01:03 PM Bug #5084: osd: slow peering after osd restart (bobtail)
- two theories:
- deep scrub is slowing things down. can you try 'ceph osd set nodeepscrub' and/or 'ceph osd set no... - 11:26 AM Bug #5084: osd: slow peering after osd restart (bobtail)
- Thanks for opening this. Attached are osd dump, osd tree and the ceph.log right after I did "restart ceph-osd id=0". ...
- 11:12 AM Bug #5084 (Resolved): osd: slow peering after osd restart (bobtail)
- 01:47 PM devops Feature #5090: ceph-build: Need to support arm in the repos.
- commit 8dcf3f991bfffef5ea19453e39c65366b2e496fe
Author: Gary Lowell <glowell@inktank.com>
Date: Thu May 16 13:42:... - 01:35 PM devops Feature #5090 (Resolved): ceph-build: Need to support arm in the repos.
- This may be as simple as adding armhf to the repo config.
- 01:32 PM devops Feature #5089 (Resolved): ceph-deploy install fails on arm
- Need to update the install function ot work with arm packages.
- 01:30 PM devops Feature #5088 (Resolved): ceph-deploy packages need to install on arm
- Need to add arm into the package indexes. Currently get the following error message:
Unable to find expected entr... - 01:20 PM rgw Bug #4997 (Resolved): Seg Fault on rgw 0.61.1 with cluster in 0.61
- commit:604c83ff18f9a40c4f44bc8483ef22ff41efc8ad
- 01:05 PM CephFS Bug #4965 (Resolved): libcephfs-java test failure
- 12:20 PM Revision 56f8c364 (ceph): test/system/st_rados_create_pool.cc_ reduce scope of 'ret' in run()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 6147df48 (ceph): test/system/st_rados_list_objects.cc: reduce scope of 'ret' in run()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision a634a13d (ceph): test/system/systest_runnable.cc: reduce scope of 'ret' in join()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 297b573d (ceph): tools/ceph-filestore-dump.cc: reduce scope of 'r' in export_files()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 49033b69 (ceph): objclass/class_debug.cc: reduce scope of 'n' in cls_log()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision b9fe22b3 (ceph): rbd_fuse/rbd-fuse.c: reduce scope of some variables in open_rbd_image()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision a3eeb9f8 (ceph): rgw/rgw_acl_s3.cc: remove local variable 'ret' from create_from_headers()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 9d6e0866 (ceph): rgw/rgw_admin.cc: reduce scope of 'ret'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 682f1076 (ceph): rgw/rgw_bucket.cc: reduce scope of 'max' in rgw_remove_bucket()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 492553b3 (ceph): rgw/rgw_common.cc: reduce scope of 'end' in two cases
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 95bf066b (ceph): rgw/rgw_tools.cc: reduce scope of 'ret' in rgw_get_obj()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision 8f486f0b (ceph): test/librbd/test_librbd.cc: reduce scope of several variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:20 PM Revision d226d9c3 (ceph): test/system/rados_list_parallel.cc: reduce scope of 'ret'
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 393de325 (ceph): osdc/Objecter.cc: reduce scope of skipped_map
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 84ce4e9b (ceph): os/chain_xattr.cc: reduce scope of local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 829fdd41 (ceph): src/os/LFNIndex.cc: reduce scope of suffix_len
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 8254072b (ceph): os/HashIndex.cc: reduce scope of a local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision ea7d8a4d (ceph): os/FileStore.cc: reduce scope of a local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 2c60bc1e (ceph): src/os/FlatIndex.cc: reduce scope of suffix_len
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:16 PM Revision 44275282 (ceph): src/os/DBObjectMap.cc: reduce scope of some variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM Revision 14871d05 (ceph): mount/mount.ceph.c: reduce scope of 'skip' in parse_options()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM Revision eb808cff (ceph): src/mds/flock.cc: reduce scope of old_lock_to_end in two cases
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM Revision ce84a226 (ceph): mds/Locker.cc: reduce scope of forced_change_max
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:15 PM Revision e7d47827 (ceph): src/crush/mapper.c: reduce scope of some local variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:11 PM Revision e0f10845 (ceph): auth/Crypto.cc: reduce scope of local variable in_buf
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 12:11 PM Revision aa11c68f (ceph): rgw/rgw_rados.cc: remove not needed code
- Fix for cppcheck warning:
[src/rgw/rgw_rados.cc:2390]: (warning) Assignment of function
parameter has no effect out... - 12:10 PM Revision cd48f570 (ceph): rgw/rgw_gc.cc: fix possible NULL pointer dereference
- Fix/silence cppcheck warning:
[src/rgw/rgw_gc.cc:185] -> [src/rgw/rgw_gc.cc:181]: (error) Possible
null pointer der... - 12:04 PM Revision 403bfa43 (ceph): osd/OSD.cc: remove unused variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:34 AM devops Feature #4947 (Resolved): Chef: Support for custom repositories
- 11:17 AM Bug #5020: osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones, 2908160/2723840 bytes
- eaf3abf3f9a7b13b81736aa558c9084a8f07fdbe and
72bf5f4813c273210b5ced7f7793bc1bf813690c are both required. - 11:16 AM Bug #5057 (Duplicate): assertion in DeleteOp::_begin
- 11:14 AM Subtask #5085 (Rejected): PG::merge_log should not have side effects other than on the log & miss...
- The modifications on info around
* https://github.com/ceph/ceph/blob/master/src/osd/PG.cc#L678
* https://github.com... - 10:47 AM Subtask #5046: Factor out PG logs, PG missing
- pg_info_t ( including pg_stat_t ) is modified during the log merging phase but it should not be the case. When factor...
- 10:45 AM Subtask #5046: Factor out PG logs, PG missing
- read PG::merge_log PG::merge_old_entry PG::rewind_divergent_log PG::proc_replica_log
pg_log_t + pg_missing_t
Read ... - 10:40 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- If anybody who sees this can generate a leveldb trace file (procedure is described above) i think that will help.
... - 04:56 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- When this state occurs, leveldb compacts on trim as expected, but the store either too large or growing fast enough t...
- 04:06 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- On IRC, Florian Wiessner have been mentioning some strange behaviors that may be related to leveldb growth/compaction...
- 12:51 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I'm on 0.61.2 as well and I can report that I struck this issue too. tnt suggested the MON restart and that fixed it....
- 12:06 AM Bug #4895: leveldb: mon workload makes store.db grow without bound
- I'd like to report that I also have this happenning ...
All the mons have grown to > 9G this night (from 200 M usu... - 10:26 AM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- Done. Reinstalling ceph and repaired from backups - I have troubles with monitor reinit as I do before. Wiped new mon...
- 09:43 AM CephFS Bug #5079 (Resolved): assert in MDCache::_recovered()
- thanks, this one was easy to fix.
commit:64871e093159ad06d84fb2a84c7808a81800dfc4 - 09:38 AM Bug #5081: Data migration and recover slow after changed OSD weight
- btw, simpler to do 'ceph osd crush reweight osd.8 .25'
it is normal to have a bit of a long tail. also note that ... - 08:17 AM rbd Subtask #5028 (Resolved): rbd: treat clones with zero parent overlap as non-layered
- The following was committed to the ceph-client "testing" branch.
70cf49cf rbd: ignore zero-overlap parent
- 08:16 AM Bug #5027 (Resolved): rbd: support reading parent page data for writes
- The following was committed to the ceph-client "testing" branch:
b91f09f1 rbd: support reading parent page data fo... - 08:15 AM Bug #5038 (Resolved): krbd: fix parent request size assumption
- The following was committed to the ceph-client "testing" branch:
ebda6408 rbd: fix parent request size assumption
- 08:14 AM Bug #5026 (Resolved): libceph: allow osd requests to be reused
- The following was committed to the ceph-client "testing" branch:
c10ebbf5 libceph: init sent and completed when st... - 06:02 AM Revision 17d8ee9d (ceph): Fix some little/big endian issues
- Ceph uses little endian, this patch fixes some endian issues
while Ceph running on big endian machine.
Signed-off-by... - 06:02 AM Revision 769a16d6 (ceph): Makefle: force char to be signed
- On an armv7l build, we see errors like
warning: rgw/rgw_common.cc:626:16: comparison is always false due to limited... - 04:58 AM Linux kernel client Bug #5043 (Fix Under Review): Oops in remove_osd
- The following patch has been posted for review.
[PATCH] libceph: must hold mutex for reset_changed_osds() - 03:25 AM Bug #5069: monitor crashed during mon thrash in nightlies
- I have some more logs - unfortunatelly, the mon is unable to start up and rejoin the cluster after this assert.
- 12:18 AM Revision 1d6ed811 (ceph): Merge branch 'wip-4783'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 12:18 AM Revision c0378b60 (ceph): OSD: Repair with 0 fixed doesn't complete properly
- Queue DoRecovery() event on any repair
Signed-off-by: David Zafman <david.zafman@inktank.com> - 12:18 AM Revision 3759daa9 (ceph): OSD: After repairs finish a new deep-scrub should be avoided
- When errors fixed, clear them so pg not inconsistent and no deep-scrub needed
In the rare case of incomplete repair, ...
05/15/2013
- 11:26 PM Bug #5059: PGs can get stuck degraded if OSD removed before being out
- CORRECTION: A lost OSD can be marked out and crush will recalculate replica locations. But administrator accidentall...
- 11:23 PM Bug #5082: OSD wrongly marked as down
- reweighted OSD.9 -> OSD.9, OSD.21 down ...
- 11:11 PM Bug #5082: OSD wrongly marked as down
- When it reports them down, they're down in tree also, after some seconds they're up again.
ceph osd crush reweight... - 11:00 PM Bug #5082: OSD wrongly marked as down
- can you attach 'ceph osd tree' output before and after the command? it's not clear to me what is going on.. you shou...
- 10:32 PM Bug #5082: OSD wrongly marked as down
- Could it be because I'm using the command above instead of
ceph osd crush reweight? - 10:25 PM Bug #5082: OSD wrongly marked as down
- ceph version 0.56.4 (63b0f854d1cef490624de5d6cf9039735c7de5ca)
- 10:24 PM Bug #5082 (Can't reproduce): OSD wrongly marked as down
- During ceph crush manipulation
ceph osd crush set 17 osd.17 0.8 pool=default host=ceph-osd-2-1
I see messages ... - 10:32 PM Bug #4783 (Resolved): After repairs finish a new deep-scrub should be avoided
- commit:3759daa9c41f274f2834ed57f8c58f9ab6a725d7
- 09:06 PM Bug #5081 (Can't reproduce): Data migration and recover slow after changed OSD weight
- I'm using ceph version 0.56.4 (63b0f854d1cef490624de5d6cf9039735c7de5ca)
Now, I'm trying to make some osds with sm... - 06:08 PM devops Bug #4865 (In Progress): ceph-disk: activate fails on debian wheezy due to missing udev by-partuu...
- 05:57 PM devops Bug #4865: ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid rules
(01:59:54 PM) sagelap [~sage@2607:f298:a:607:598c:d480:4af:b6ce] entered the room.
(02:00:44 PM) paravoid: http://...- 01:53 PM devops Bug #4865: ceph-disk: activate fails on debian wheezy due to missing udev by-partuuid rules
- http://git.kernel.org/cgit/linux/hotplug/udev.git/commit/?id=693b6344e193f5aeca21df5f1c98fd32148006ac
paravoid sug... - 03:46 PM Revision e34a56f8 (ceph): doc: fix mkcephfs production use, deprecated note
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:55 PM rbd Bug #4559 (In Progress): krbd: kernel BUG when mapping unexisting rbd device
- Finally starting to look at this again. I'm going to
start by trying to reproduce it in the newly-reported
context.
- 02:15 PM Linux kernel client Bug #5043: Oops in remove_osd
- I think I may have just found something.
It appears as though access to the osd client's osd red-black
tree is su... - 01:16 PM Linux kernel client Bug #5043: Oops in remove_osd
- The ceph_osd_client in question is osdc @ 0xffff8802244a4950
The ceph_osd is osd @ 0xffff88020a285000
(struct rb_... - 02:14 PM Bug #4999: monitor sync failure
- Hmmm, I've been running all day, but I haven't reproduced yet.
I'm seeing a mon repeatedly drop out of and then re... - 07:10 AM Bug #4999: monitor sync failure
- I'll be attempting to reproduce this morning with the debug mon = 10, debug ms = 1.
- 06:43 AM Bug #4999: monitor sync failure
- Yeah, I'd say so.
Anyway, this ticket has two (independent, I hope) bugs: the sync bug and the leveldb bug. I've ... - 01:52 PM Bug #5077: nightlies: single node cluster hung waiting for ceph_health to be OK
- looks like one of the monitors on the single node cluster went down
- 10:37 AM Bug #5077: nightlies: single node cluster hung waiting for ceph_health to be OK
- also,
ubuntu@teuthology:/a/teuthology-2013-05-15_01:00:04-rados-master-testing-basic/13515$ cat orig.config.yaml ... - 10:36 AM Bug #5077: nightlies: single node cluster hung waiting for ceph_health to be OK
- ...
- 10:35 AM Bug #5077 (Resolved): nightlies: single node cluster hung waiting for ceph_health to be OK
- logs: ubuntu@teuthology:/a/teuthology-2013-05-15_01:00:04-rados-master-testing-basic/13506...
- 11:37 AM CephFS Bug #5079 (Resolved): assert in MDCache::_recovered()
- While trying to reproduce 4999 with the requested logging, I got this MDS assert.
I'm running cuttlefish branch @ ... - 11:30 AM devops Bug #5065 (Duplicate): ceph-deploy: osd prepared but not activated on debian-wheezy
- #4865
- 10:59 AM Bug #5078 (Won't Fix): Debian missing sudo results in unclear error
- Due to the missing 'sudo' command in debian the install.py fails while resolving the hostnames.
Perhaps a 'you need ... - 10:54 AM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- ...
- 10:32 AM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- ...
- 10:28 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- The test still generates a too short bucket name. The swift tree on github has that fixed but the test pulls from cep...
- 09:32 AM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- ubuntu@teuthology:/a/teuthology-2013-05-15_01:30:03-upgrade-master-testing-basic/13769
- 10:25 AM Bug #5076: nightlies:segfault in ceph_test_filestore_idempotent_sequence
- ubuntu@teuthology:/a/teuthology-2013-05-15_01:00:04-rados-master-testing-basic/13530
- 10:24 AM Bug #5076 (Resolved): nightlies:segfault in ceph_test_filestore_idempotent_sequence
- logs:...
- 10:00 AM Bug #5075 (Resolved): filejournal tests failing in nightlies
- logs: ubuntu@teuthology:/a/teuthology-2013-05-15_01:00:04-rados-master-testing-basic/13528
2013-05-15T01:20:47.123... - 09:55 AM Bug #5074 (Can't reproduce): nightlies: timed out waiting for admin socket of restarted osd
- logs:ubuntu@teuthology:/a/teuthology-2013-05-15_01:00:04-rados-master-testing-basic/13494
2013-05-15T05:05:50.579 ... - 09:08 AM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- By finishing a sync before the current proposal is fully committed (and now that I think of it, we might still have t...
- 08:56 AM Bug #5062: mon: 0.61.2 asserts on AuthMonitor during monitor start
- Any idea how sync could have missed a version?
- 07:06 AM Bug #5062 (Need More Info): mon: 0.61.2 asserts on AuthMonitor during monitor start
- Waiting on Florian to provide me a copy of a healthy monitor's data dir to assess whether the "corrupted" state is pa...
- 08:57 AM rgw Feature #5073: rgw: create tenant namespace
- How would this interact with stuff like bucket URLs?
- 07:06 AM rgw Feature #5073 (New): rgw: create tenant namespace
- Currently rgw has a single global namespace. It is possible to provide different namespaces for different tenants as ...
- 07:40 AM Bug #5069: monitor crashed during mon thrash in nightlies
- Logs are gone. I'll try to reproduce. In the future, it would be nice to grab the logs and data dirs before nuking/a...
- 07:01 AM rgw Feature #4098 (In Progress): rgw: multi-site: Global Bucket Namespace
- 06:39 AM Bug #5072 (Can't reproduce): mon: segfault on leveldb::Table::Open() during monitor start
- Jim Schutt is hitting this after triggering #4999...
- 05:05 AM Revision 3ac7fb8a (ceph): rgw: parse location constraint on bucket creation
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:04 AM Revision a7e80e2b (ceph): rgw: a function to read all request input
- Factor out this useful function. Also make sure that
we never read more than a specified (large enough) max.
Signed-... - 04:35 AM Revision 84c17b68 (ceph): rgw: update json encode/decode for new bucket info
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:52 AM Revision b6464076 (ceph): Modified PutMetadata::get_data() to handle chunked transfers
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 01:52 AM Revision c8ac2879 (ceph): rgw: add region to bucket info
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 01:52 AM Revision 648c3bc2 (ceph): With admin metadata rest API implementation and unit test cases for it
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 01:52 AM Revision bf612f04 (ceph): rgw: modify metadata RESTful implementation
- REST handler should derive from RGWHandler_Auth_S3,
other changes.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:52 AM Revision efaa33f3 (ceph): Fixed certain bugs on rest admin APIs
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 01:52 AM Revision 02197744 (ceph): Removed the check for parameter validation in op_get()
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 01:52 AM Revision 3c8ef2b9 (ceph): ceph_json: don't try to parse NULL buffer
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:06 AM Revision 2a441aa2 (ceph): Merge pull request #279 from ceph/wip-libcephfs-env
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 12:06 AM Revision 8f3fb972 (ceph): Added OSD to glossary, removed parenthetical.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:05 AM Revision f36ec02f (ceph): doc: Updated architecture document.
- fixes: #2968
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
05/14/2013
- 11:38 PM Revision 624c8cc3 (ceph): Merge branch 'wip-5049'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 11:28 PM Revision 48e89b51 (ceph): OSD: scrub interval checking
- Do arithmetic so large intervals don't wrap
Fix log messages to reflect the change and improve output
Add message whe... - 11:28 PM Revision 1f4e7a5a (ceph): OSD: Don't scrub newly created PGs until min interval
- Set initial values for last_scrub_stamp, last_deep_scrub_stamp
fixes: #5050, #5051
Signed-off-by: David Zafman <dav... - 11:24 PM Revision e582e15c (ceph): Fix scrub_test.py permission error
- Add description of yaml file including log-whitelist
Add sudo to dd that corrupts data
Signed-off-by: David Zafman <... - 11:02 PM Revision 7b93d287 (ceph): doc/release-notes: v0.62
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:38 PM Revision 2ba167be (ceph): Merge branch 'next'
- 10:28 PM Revision 5ff703d6 (ceph): Merge pull request #283 from dachary/wip-5058
- internal documentation proofreading
Reviewed-by: Sam Just <sam.just@inktank.com> - 10:05 PM CephFS Bug #5021 (In Progress): ceph-fuse: crash on traceless reply
- 09:51 PM Bug #5060 (Can't reproduce): osd: decode failure in load_pgs on 0.56.4
- If you see this again, please capture the stacktrace of the original before recovering, and if you can, generate a co...
- 05:14 PM Bug #5060: osd: decode failure in load_pgs on 0.56.4
- Yes, it was in 0.56.4 and before.
I can not reproduce because already formatted. - 09:41 AM Bug #5060 (Need More Info): osd: decode failure in load_pgs on 0.56.4
- Was the ceph-osd process that originally crashed under load also 0.56.4? Or an earlier version? (Do you have the lo...
- 05:20 AM Bug #5060 (Can't reproduce): osd: decode failure in load_pgs on 0.56.4
- On of my osd hosts crashed on high load and after rebooted it is unable to start some osds.
Error log for osd.3 is ... - 09:02 PM Revision 52b0438c (ceph): doc/rados/configuration: fix [mon] osd min down report* config docs
- Fix other osd -> mon section name, and note the old config value name prior
to v0.62.
Fixes: #5044.
Signed-off-by: S... - 08:46 PM Revision 1c53991e (ceph): fix typos and add hyperlink to peering
- s/;/:/
s/up_acting_affected/acting_up_affected/
Add relative link to ../../peering
http://tracker.ceph.com/issues/50... - 08:46 PM Revision 2a4425af (ceph): reflect recent changes in the pg deletion logic
- No need to wait on DeletingStateRef for flush https://github.com/ceph/ceph/commit/d3dd99b725afaa026fe6f700ddc14a7f657...
- 08:46 PM Revision b7d4012c (ceph): typo s/come/some/
- http://tracker.ceph.com/issues/5058 refs #5058
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:44 PM Revision dbddffef (ceph): update op added to a waiting queue or discarded
- The decision to discard an op happens either in OSD or in PG.
The operation queue goes to a single OpWQ object if wai... - 07:58 PM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- 1) Just one mo symptom: "assert(soid.snap == *curclone);" (IMHO there are too similar to others, include "clone witho...
- 07:44 PM Revision e9935f2c (ceph): ceph_json: fix bool decoding
- "false" means false.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 07:26 PM Bug #4783 (Fix Under Review): After repairs finish a new deep-scrub should be avoided
- 07:25 PM Revision 67ecd75c (ceph): rgw: json_encode json a bit differently
- Encode map as a list, it's a more friendly representation.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:05 PM devops Feature #5071 (Duplicate): ceph-deploy osd list
- There is a disk list that shows all disks (and, if they map to osds, some info about them).
ceph-deploy osd list s... - 06:04 PM devops Bug #4919: ceph-deploy: disk list doesn't properly display all the disks on a VM
- I got as far as verifying that the VM didn't list all devices in /dev/disk/by-path.. no idea why. it seemed to list ...
- 05:31 PM Revision afeb8f2d (ceph): md/Sever.cc: fix straydn assert
- From fb222a0a1c98a4141b6d0e79eac7a41c208f7147, we only know straydn is
non-null if oldin is non-null.
Signed-off-by:... - 05:30 PM Revision 29d8ec4e (ceph): Merge pull request #285 from dalgaaf/wip-da-CID-fixes-2-v3
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:20 PM rbd Bug #5070: rbd map failed and stalled in "D"
- probably connected with #4522
- 05:15 PM rbd Bug #5070 (Can't reproduce): rbd map failed and stalled in "D"
- It happened with one device while others are mapped well.
[6765922.875713] ------------[ cut here ]------------
[... - 05:20 PM Revision e69257ea (ceph): rgw/rgw_user.cc: fix possible NULL pointer dereference
- CID 1019559 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "usr" to f... - 05:15 PM Revision d6929021 (ceph): mds/Server.cc: fix possible NULL pointer dereference
- Assert if straydn is NULL.
CID 1019554 (#2 of 2): Dereference after null check (FORWARD_NULL)
var_deref_model: Pas... - 05:15 PM CephFS Bug #4832 (Need More Info): mds: failed auth_unpin assert
- cranked up mds logs in qa.. should get useful info next time we hit this.
- 05:07 PM CephFS Bug #4832: mds: failed auth_unpin assert
- recent logs: ubuntu@teuthology:/a/teuthology-2013-05-14_01:00:46-kernel-next-testing-basic/13128
- 05:10 PM rgw Bug #4497: rgw: FAIL: testSlashInName (test.functional.tests.TestContainer)
- recent logs: ubuntu@teuthology:/a/teuthology-2013-05-14_01:00:34-rgw-next-testing-basic/13055
- 05:10 PM Documentation #2968 (Resolved): doc: complete architecture section
- This architecture document has enough information that we can close this bug. We'll, of course, continue to update it.
- 05:07 PM Revision fb222a0a (ceph): mds/Server.cc: fix possible NULL pointer dereference
- Assert of straydn is NULL here.
CID 1019558 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model... - 05:05 PM rbd Bug #5032: xfstest 269 failure
- logs: ubuntu@teuthology:/a/teuthology-2013-05-14_01:00:46-kernel-next-testing-basic/13125
- 05:02 PM Revision c87788b6 (ceph): mds/Server.cc: fix possible NULL pointer dereference
- Assert if destdn == NULL.
CID 1019557 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Pass... - 04:59 PM Bug #5069 (Resolved): monitor crashed during mon thrash in nightlies
- logs: ubuntu@teuthology:/a/teuthology-2013-05-14_01:00:05-rados-next-testing-basic/12938...
- 04:57 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- Nodes were not rebooted and those OSDs that were marked as down weren't restarted (ps shows them as started on Apr 3r...
- 02:06 PM Bug #4967 (Can't reproduce): Misbehaving OSD sets over half of the cluster as down despite "osd m...
- We are not sure about why logging didn't show OSDs getting marked down. It is possible that OSDs were restarted, or ...
- 04:52 PM Fix #4567: mon: refactor mon caps; allow restriction of key/value storage by prefix
- 04:50 PM Revision 088455f8 (ceph): librados/AioCompletionImpl.h: add missing Lock
- Add missing Lock around code changing AioCompletionImpl::rval/ack and safe
in C_AioCompleteAndSafe::finish().
CID 10... - 04:44 PM Revision 8a52350d (ceph): src/dupstore.cc: check return value of list_collections()
- CID 1019545 (#1 of 1): Unchecked return value (CHECKED_RETURN)
check_return: Calling function "ObjectStore::list_co... - 04:43 PM Revision 70a4a971 (ceph): mds/Server.cc: fix possible NULL pointer dereference
- CID 1019555 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "in" to fu... - 04:42 PM Bug #5049 (Resolved): scrub interval checking
- commit:48e89b5171b912eba3521d918c437978107fc298
- 04:41 PM Bug #5050 (Resolved): initial scrub timestamp is 0.000000
- commit:1f4e7a5aafdace9fb82d311ec4ff0a1a6c7c9a31
- 10:23 AM Bug #5050 (In Progress): initial scrub timestamp is 0.000000
- 04:41 PM Bug #5051 (Resolved): initial deep scrub timestamp is 0.0000000
- commit:1f4e7a5aafdace9fb82d311ec4ff0a1a6c7c9a31
- 10:19 AM Bug #5051 (In Progress): initial deep scrub timestamp is 0.0000000
- 04:39 PM Revision 21489acf (ceph): src/rbd.cc: use 64-bits to shift 'order'
- CID 1019568 (#1 of 1): Unintentional integer overflow (OVERFLOW_BEFORE_WIDEN)
overflow_before_widen: Potentially ov... - 04:39 PM Revision 043ea2ce (ceph): tools/ceph.cc: close file descriptor in error case
- CID 717121 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_handle: Handle variable "fd" going out of scope leaks th... - 04:39 PM Revision c3c140b3 (ceph): tools/ceph.cc: close file descriptor in error case
- CID 717122 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_handle: Handle variable "fd" going out of scope leaks
... - 04:39 PM Revision eac545e1 (ceph): tools/ceph.cc: cleanup memory allocated for 'buf'
- CID 717123 (#1-2 of 2): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "buf" going out of scope leaks the s... - 04:39 PM Revision 8df55e0a (ceph): test/test_cors.cc: initialize key_type in constructor
- CID 1019635 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
uninit_member: Non-static class member "kt" is not... - 04:39 PM Revision 98836309 (ceph): mon/QuorumService.h: remove unused QuorumService::flags
- CID 1019626 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "flags" is n... - 04:39 PM Revision 528ec353 (ceph): mon/Monitor.h: init 'crc' in constructor with '0'
- CID 1019624 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "crc" is not... - 04:39 PM Revision 3e446825 (ceph): mon/Monitor.cc: init 'timecheck_acks' with '0' in constructor
- CID 1019623 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "timecheck_a... - 04:39 PM Revision df4c099a (ceph): ceph-filestore-dump.cc: cleanup resource in error case
- CID 1019590 (#1 of 1): Resource leak (RESOURCE_LEAK):
leaked_storage: Variable "rmt" going out of scope leaks the
s... - 04:39 PM Revision 349cfb41 (ceph): ceph-filestore-dump.cc: cleanup on error case
- CID 1019589 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "t" going out of scope leaks the
st... - 04:39 PM Revision d8cb7dfc (ceph): filestore/test_idempotent_sequence.cc: fix FileStore leaks
- CID 717107 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "store" going out of scope leaks the
... - 04:39 PM Revision cab8e9bf (ceph): test/kv_store_bench.cc: fix resource leak
- CID 727984 (#5 of 5): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "cb_args" going out of scope leaks the... - 04:39 PM Revision 3c285c44 (ceph): scratchtool.c: cleanup rados_t on error
- Make sure rados_shutdown() get called also in error case.
CID 717106 (#1 of 1): Resource leak (RESOURCE_LEAK)
leak... - 04:39 PM Revision 7ea44ee0 (ceph): librbd/test_librbd.cc: free memory in test_list_children()
- CID 719581 (#7 of 7): Resource leak (RESOURCE_LEAK)
CID 719581 (#6 of 7): Resource leak (RESOURCE_LEAK)
leaked_stor... - 04:39 PM Revision 36028916 (ceph): test_filejournal.cc: cleanup memory in destructor
- CID 716885 (#1 of 1): Resource leak in object (CTOR_DTOR_LEAK)
alloc_new: Allocating memory by calling "new C_SafeC... - 04:19 PM Revision e0de0089 (ceph): mon: fix validatation of mds ids in mon commands
- Fixes: #4996
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5c305d63043762027323052b4bb3ae306... - 04:14 PM Revision 4c0d3eb7 (ceph): mon: fix validatation of mds ids in mon commands
- Fixes: #4996
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5c305d63043762027323052b4bb3ae306... - 04:13 PM Revision 9382379c (ceph): v0.62
- 02:50 PM Bug #5068 (Won't Fix): ceph_test_rados gets SIGFPE when run with no args
- Probably dividing by zero; didn't look closely:...
- 02:08 PM rbd Feature #5067 (Resolved): librbd: configuration options to override default image creation parame...
- From http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/15064:
For example, there could be just:
rbd... - 02:03 PM Cleanup #5044 (Resolved): osd_min_down_reporters/osd_min_down_reports are incorrectly documented
- commit:52b0438c66b23c5eec4eed62a489143f995f6c94
- 01:58 PM Documentation #5058: docs/master/dev/osd_internals updates
- Sam Just says : Some of the details of the PG op queueing have changed again in next. See "fd90105":https://github.co...
- 11:56 AM devops Bug #5066 (Resolved): Problems with ceph-deploy debs
- * Used Distribution:
Ubuntu 12.04.2 (amd64)
* Installed packages from external sources:
- kernel 3.8.11 ... - 11:27 AM devops Bug #5065 (Duplicate): ceph-deploy: osd prepared but not activated on debian-wheezy
- tried this on two different debian machines [burnupi24 and burnupi26].
on burnupi24:
hit ioerror and osd was no... - 11:14 AM Bug #5064 (Won't Fix): mon/monclient: subscribe protocol does not allow cancellation
- This only really comes up with the librados rados_monitor_log(); no other users (might potentially) need this.
- 11:13 AM Bug #4999: monitor sync failure
- This failure is the first type, in sync_start_reply_timeout().
It looks just like the previous one, and I don't have... - 10:39 AM Bug #4999: monitor sync failure
- I've got a monitor that has just failed, so I'll see what gdb has to say
about that one.
Am I correct in assuming... - 10:27 AM Bug #4999: monitor sync failure
- After talking with Sage, this bug is being postponed until we get a log with higher debug levels to catch intermediat...
- 10:23 AM Bug #4999 (Need More Info): monitor sync failure
- 10:19 AM Bug #4999 (In Progress): monitor sync failure
- Jim, still unable to restart the monitor? If so, could you by any chance run the monitor with gdb and check out what...
- 11:05 AM Linux kernel client Bug #5043 (In Progress): Oops in remove_osd
- I'm taking this for the time being.
This is in rb_erase().
Which means that maybe the osd client's red-black tr... - 10:51 AM Bug #5055 (Rejected): osd: crash in FileJournal::wrap_read_bl
- wrap_read_bl returned EIO.
- 10:27 AM Bug #5062 (In Progress): mon: 0.61.2 asserts on AuthMonitor during monitor start
- 09:01 AM Bug #5062 (Can't reproduce): mon: 0.61.2 asserts on AuthMonitor during monitor start
- Florian from Smart Weblications bumped into this crash on one of his monitors *roughly two hours after* upgrading fro...
- 10:15 AM Bug #5054: deep scrub reports 1 inconsistent object
- i think this is a dup of the bug sam is still worknig on
- 10:03 AM Feature #4839 (In Progress): api: make new CLI send old version of commands to old monitors durin...
- 09:47 AM Bug #5056 (Won't Fix): rados_mon_workunits failed in the nightlies
- this is a known problem with idempotency of the mon commands.. see fix #4635. we aren't going to fix it for bobtail/...
- 09:44 AM Bug #5059: PGs can get stuck degraded if OSD removed before being out
- what does 'ceph osd tree' say? usually stuck degraded happens bc there aren't enough up/in osds
- 09:29 AM Bug #4698: osd suicide timed out after 150
- ubuntu@teuthology:/a/teuthology-2013-05-14_01:30:05-upgrade-master-testing-basic/13144
- 09:20 AM Bug #4996 (Resolved): mon: bogus mds tell can crash monitors
- 09:11 AM devops Bug #5063 (Rejected): Unexpected build warning
- This issue is really just a reminder to myself to check this out:
glowell@pudgy:~/build/ceph-0.62/ceph$ dch -v 0.6... - 08:34 AM Bug #5061 (Duplicate): Monitor crash with 0.61.2
- Only now did I notice this is a duplicate of #4999
Marking it as such.
Thanks again Matthew! - 06:43 AM Bug #5061 (Duplicate): Monitor crash with 0.61.2
- https://pastee.org/sznze is the log at time of failure. I haven't been able to reproduce it yet.
- 03:48 AM Revision c5deb5db (ceph): doc/release-notes: v0.61.2
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:01 AM rbd Bug #4897: qemu rbd driver should allow manipulation of format 2, striped images
- I'm running into this as well.
Wouldn't it be a start to at least start creating image with rbd_create2|3 instead ... - 01:45 AM CephFS Bug #5037: Ceph-MDS asserts after upgrade 0.56.2 -> 0.56.6
- Our ceph is productive, yeah. We are only using rbd, not CephFS or RadosGW, though. SJust and Sage are familiar with ...
- 01:11 AM CephFS Bug #5036: `ls` hangs on random folder
- By turning on the debug mode of MDS:...
- 12:17 AM Revision 45e19510 (ceph): Merge remote-tracking branch 'gh/next'
05/13/2013
- 11:58 PM Revision 97a73091 (ceph): rgw: tie bucket/user removal to mdlog differently
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:52 PM Bug #5059 (Won't Fix): PGs can get stuck degraded if OSD removed before being out
If an OSD goes down and the user marks it lost and/or removes before it is marked out, then PGs are left degraded a...- 11:45 PM Documentation #5058 (Resolved): docs/master/dev/osd_internals updates
- "work in progress":https://github.com/dachary/ceph/tree/wip-5058
* See OSD::handle_pg_(notify|info|log|query) rela... - 11:07 PM Revision 393140e7 (ceph): Merge pull request #281 from ceph/wip-rbd-rm-enoent
- Reviewed-by: Sage Weil <sage@inktank.com>
- 11:06 PM Revision 4bb40633 (ceph): ceph_test_libcephfs: parse environment
- Lets you use CEPH_ARGS to get output from the tester.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:56 PM Revision f24b8fb9 (ceph): PG: fix some brace styling
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com> - 10:55 PM Revision 72bf5f48 (ceph): PG: subset_last_update must be at least log.tail
- Fixes: 5020
Backport: bobtail, cuttlefish
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman... - 09:49 PM Revision 395a775a (ceph): SimpleThrottle: fix -ENOENT checking
- The condition was reversed. Rewrite it so it's clear that we're
ignoring -ENOENT only when m_ignore_enoent is set.
S... - 09:26 PM Revision d06d0c3b (ceph): rgw: slightly simplify metadata abstraction
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:19 PM Revision 58836d9d (ceph): qemu: load the kvm module before trying to use it
- It should be loaded before this, but in some cases it is not for some reason.
Signed-off-by: Josh Durgin <josh.durgi... - 08:29 PM Revision bb6d1f07 (ceph): rgw: read bucket metadata before writing it
- In order to keep track of version.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 08:24 PM Revision 88af2b0f (ceph): Replace mis-named mon config variables using mon_osd_min_down_reports/m...
- Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 07:35 PM Revision 225fefe5 (ceph): ceph-disk: add '[un]suppress-activate <dev>' command
- It is often useful to prepare but not activate a device, for example when
preparing a bunch of spare disks. This mar... - 07:31 PM Revision de4678fa (ceph): Merge pull request #280 from ceph/wip-4996
- Reviewed-by: Joao Luis <joao.luis@inktank.com>
- 06:58 PM Cleanup #5044: osd_min_down_reporters/osd_min_down_reports are incorrectly documented
- 88af2b0f7b951367e670869db76e57f0d970aa38
Update to master branch for the next release renaming these these values to... - 01:01 PM Cleanup #5044: osd_min_down_reporters/osd_min_down_reports are incorrectly documented
I pushed the change to rename these configuration variables to wip-5044.- 11:52 AM Cleanup #5044: osd_min_down_reporters/osd_min_down_reports are incorrectly documented
- we should rename these config fields in master branch and add an item to /PendingReleaseNotes documenting the change....
- 11:49 AM Cleanup #5044 (Resolved): osd_min_down_reporters/osd_min_down_reports are incorrectly documented
These 2 configuration variables do NOT follow standard convention that a mon variable begin mon_. Everywhere I've ...- 06:58 PM Revision fea78254 (ceph): v0.61.2
- 06:49 PM Revision 5c305d63 (ceph): mon: fix validatation of mds ids in mon commands
- Fixes: #4996
Signed-off-by: Sage Weil <sage@inktank.com> - 06:40 PM Revision 8464c064 (ceph): mon: Monitor: tolerate GV duplicates during conversion
- Fixes: #4974
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit ba05b16ee2b6e25141f... - 06:39 PM Revision 11041163 (ceph): Merge pull request #278 from ceph/wip-4974
- Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 06:37 PM Revision ba05b16e (ceph): mon: Monitor: tolerate GV duplicates during conversion
- Fixes: #4974
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:16 PM Revision 6db072d4 (ceph): libcephfs: add ceph_conf_parse_env()
- This exists in the librados API.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:16 PM Revision 9ec77ebb (ceph): ceph_test_libcephfs: fix xattr test
- This broke in 0c70e44630734760fd36e0c770a33fb0e74b42a4.
Fixes: #5030
Signed-off-by: Sage Weil <sage@inktank.com> - 05:15 PM Bug #5057 (Duplicate): assertion in DeleteOp::_begin
- log: ubuntu@teuthology:/a/teuthology-2013-05-13_01:00:04-rados-master-testing-basic/12278...
- 05:11 PM Bug #5056 (Won't Fix): rados_mon_workunits failed in the nightlies
- log: ubuntu@teuthology:/a/teuthology-2013-05-13_01:00:04-rados-master-testing-basic/12200...
- 04:58 PM Bug #5055 (Rejected): osd: crash in FileJournal::wrap_read_bl
- logs: ubuntu@teuthology:/a/teuthology-2013-05-12_01:00:05-rados-master-testing-basic/11664...
- 04:54 PM Bug #5054 (Resolved): deep scrub reports 1 inconsistent object
- logs: ubuntu@teuthology:/a/teuthology-2013-05-12_01:00:05-rados-master-testing-basic/11672...
- 04:52 PM Revision 9bb58b2a (ceph): OSD: We need to wait on CLEARING_DIR, not DELETED_DIR
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 04:42 PM Revision c24ffc16 (ceph): Merge pull request #274 from dalgaaf/wip-da-fix-osd_h
- osd/OSD.h: fix try_stop_deletion
Reviewed-by: Sam Just <sam.just@inktank.com> - 04:38 PM rbd Bug #5053 (Duplicate): qemu xfs test failed in the nightlies
- 04:35 PM rbd Bug #5053 (Duplicate): qemu xfs test failed in the nightlies
- ...
- 04:30 PM Bug #5052 (Duplicate): kclient_workunit_misc test failed in the nightlies
- the test failed, as rsync was unable to copy a few files due to permission denied errors,
logs: ubuntu@teuthology:... - 04:18 PM Bug #5020 (Pending Backport): osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones,...
- 02:24 PM Bug #5020: osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones, 2908160/2723840 bytes
- I think I found the issue. wip_5020. Testing.
- 01:18 PM Bug #5020: osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones, 2908160/2723840 bytes
- Got it reproduced with logs.
- 03:33 PM Bug #4873 (Can't reproduce): osd: scrub found missing object on primary
- 02:54 PM Bug #5051 (Resolved): initial deep scrub timestamp is 0.0000000
- The initial deep scrub timestamp is 0.000000 and it should be the current time. This causes the OSD to do a deep scr...
- 02:52 PM Bug #5050 (Resolved): initial scrub timestamp is 0.000000
- When PGs are created, the initial scrub timestamp is 0.000000 where it should be the current time. With the current ...
- 02:39 PM Bug #5049 (In Progress): scrub interval checking
- 02:38 PM Bug #5049 (Resolved): scrub interval checking
- In OSD.cc right now we set:
utime_t max = ceph_clock_now(g_ceph_context);
utime_t min = max;
min -= g_conf->osd_... - 02:39 PM Bug #4698: osd suicide timed out after 150
- ...
- 02:37 PM Bug #4698: osd suicide timed out after 150
- logs: ubuntu@teuthology:/a/teuthology-2013-05-13_01:30:03-upgrade-master-testing-basic/12483...
- 02:33 PM Bug #4967 (In Progress): Misbehaving OSD sets over half of the cluster as down despite "osd min d...
- 01:54 PM rbd Bug #4959: xfstest 17 failure
- The same test failed again in the same way. This time rbd caching was enabled, while the first time it was disabled.
... - 01:09 PM rbd Fix #5048 (Resolved): krbd: limit of ~230 mapped images at once
- this is just because we are using our major/minor device ids in a stupid way, iirc.
- 12:55 PM Bug #4996 (Pending Backport): mon: bogus mds tell can crash monitors
- 12:50 PM Bug #4996: mon: bogus mds tell can crash monitors
- Is this already backported to where it needs to be?
- 12:36 PM Bug #4996 (Resolved): mon: bogus mds tell can crash monitors
- 12:40 PM Bug #5024 (Resolved): mon_debug_dump_transactions should default to False
- 08:59 AM Bug #5024 (Fix Under Review): mon_debug_dump_transactions should default to False
- 12:40 PM Bug #4974 (Resolved): nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- 11:28 AM Bug #4974 (In Progress): nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- Comments on github.
- 07:38 AM Bug #4974 (Fix Under Review): nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- 07:38 AM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- Pushed wip-4974 to gh. It fixes Via's store, but haven't dumped the transactions yet to make sure the correct orderi...
- 04:21 AM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- Cause:
We had a bug on bobtail that would create duplicate GV versions, so there's a fair chance that at some poin... - 04:07 AM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- plana's status is now gone, no logs on teuthology, but I'll update the ticket next with a description on what's happe...
- 12:37 PM rbd Feature #3763 (Resolved): krbd: handle flattening of mapped image
- 12:37 PM CephFS Feature #4326 (Resolved): qa: add samba + (kclient|ceph-fuse) to suite
- 12:16 PM devops Bug #5047 (Closed): ceph build needs libboost 1.50 for debian sid
- The build on sid needs a boost library newer than the default due to a conflict in header files. This is clamied to ...
- 12:09 PM Bug #5038 (Fix Under Review): krbd: fix parent request size assumption
- The following has been posted for review:
[PATCH] rbd: fix parent request size assumption - 07:53 AM Bug #5038 (Resolved): krbd: fix parent request size assumption
- When Josh was reviewing a recent kernel rbd patch he pointed
out that a variable named "obj_size" was misleading bec... - 12:02 PM Subtask #5046 (Resolved): Factor out PG logs, PG missing
- PG logs, PG missing: The logic for merging an authoritative PG log with another PG log while filling in the missing s...
- 12:00 PM Subtask #4928 (Rejected): PG/ReplicatedPG API
- ...
- 11:28 AM Linux kernel client Bug #5043 (Resolved): Oops in remove_osd
- Stack output:
Stack traceback for pid 29892
0xffff88022140bf20 29892 2 1 6 R 0xffff88022140c3a8 ... - 11:07 AM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- Never mind that comment, I was just looking at the job it happened on, not the actual failure...
- 10:20 AM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- Will come back for another pass and verify, but I assume this is the disconnected inode error.
- 10:54 AM CephFS Bug #5033: oops in ceph_put_wrbuffer_cap_refs
- plana47 died with:
[0]kdb> bt
Stack traceback for pid 25102
0xffff88001c499f90 25102 23405 1 0 R 0x... - 10:39 AM Feature #5042 (New): Backport option to disable deep scrub to bobtail
- 10:32 AM Feature #5041 (New): Deep scrub CPU limit behavior
- Determine if deep scrub is properly using the CPU utilization limits (rather than just scrub). If not, should it? M...
- 10:17 AM CephFS Bug #5030 (Resolved): libcephfs xattr test failure
- 10:12 AM devops Feature #4954 (In Progress): ceph-deploy: help and document need to be updated for osd create
- 10:11 AM CephFS Bug #5037: Ceph-MDS asserts after upgrade 0.56.2 -> 0.56.6
- It couldn't find the actual table object in RADOS. We've seen this pop up a few times, but I believe it's always been...
- 01:43 AM CephFS Bug #5037 (Can't reproduce): Ceph-MDS asserts after upgrade 0.56.2 -> 0.56.6
- After upgrading our Ceph setup to 0.56.6 from 0.56.2, the MDS processes assert() on start and will not work.
This i... - 09:24 AM rbd Bug #5040 (Resolved): krbd: record that an parent info refresh has failed
- In order to manage resized clone images (including the flattening
of a clone image) the kernel rbd client needs to g... - 09:01 AM CephFS Bug #5039 (Resolved): client: unlinking files leaves the cached entry behind
- http://comments.gmane.org/gmane.comp.file-systems.ceph.user/1277
When unlinking a file, the client should make an ... - 08:10 AM rgw Bug #4997: Seg Fault on rgw 0.61.1 with cluster in 0.61
- gary, do you see a problem with matching up the versions like this? i think in radosgw's case it may be more importa...
- 07:34 AM rgw Bug #4997: Seg Fault on rgw 0.61.1 with cluster in 0.61
- This is the issue I reported on the ML and is tracked in http://tracker.ceph.com/issues/4944
- 02:59 AM rgw Bug #4997: Seg Fault on rgw 0.61.1 with cluster in 0.61
- , it was a problem with ceph-common and librados2 packages who wasn't up-to-date.
It's not the first time that thi... - 06:28 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- Do you suggest any workaround? I dont think that it is possible to downgrade to bobtail.
- 05:59 AM rbd Bug #4559: krbd: kernel BUG when mapping unexisting rbd device
- I am affected by the same bug but only with ceph 0.61.1. Every time I try to map any volume (with proper keyring, id ...
- 06:01 AM Revision db29f49f (ceph): Merge pull request #275 from ceph/wip-rbd-read-from-replica
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
- 04:11 AM CephFS Bug #5036: `ls` hangs on random folder
- As you can see, the @ls@ process is stuck in D state:
*@/proc/10297/status@*... - 12:16 AM CephFS Bug #5036 (Resolved): `ls` hangs on random folder
- strace hangs at "getdents(3,": https://clbin.com/LktUw
The informations when dumping via SysRq:... - 02:31 AM Revision d5193460 (ceph): Objecter, librados: use only ObjectOperation form of sparse_read intern...
- This will be used when exposing an ObjectOperation version of sparse_read()
to the librados user, and there's no reas... - 02:31 AM Revision 442f0588 (ceph): librados: add sparse_read() to the C++ bindings for an ObjectOperation
- This will allow it to be used with general aio_operate() so we don't have
to add new versions of each operation when ... - 02:31 AM Revision 4ddaea70 (ceph): librados: add per-ObjectOperation flags for balanced and localized reads
- These need to apply to the entire ObjectOperation, not just a subop,
so use a new enum and a new aio_operate() call t... - 02:31 AM Revision 0c7414b1 (ceph): ReplicatedPG: send -EAGAIN for both balanced and localized reads
- This logic for localized reads applies to balanced reads too.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 02:31 AM Revision 13ae13a9 (ceph): librbd: add options to enable balanced or localized reads for snapshots
- Since snapshots never change, it's safe to read from replicas for them.
A common use for this would be reading from a... - 02:26 AM Revision ed76824c (ceph): Objecter: fix error handling for decoding stat
- r is just a local variable, changing it has no effect.
Set the per-operation return value if provided when a decoding... - 01:31 AM CephFS Bug #4850: ceph-fuse: disconnected inode on shutdown with fsstress + mds thrashing
- FYI: I have code that finds the missing inode by using backtrace. The code is under test, will send out soon.
- 01:11 AM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- The items left in reconnected_snaprealms should be other MDS's mdsdir. I comment out that line when running test
05/12/2013
- 11:09 PM rbd Feature #3064 (Resolved): librbd: A way to read from nearby replicas
- Flags to do this for reads of snapshots are added by commit:13ae13a9068afcd4eb4b3574c46875cad8c91ab6.
Making the i... - 11:08 PM Feature #5035 (Resolved): rados: smarter localized reads
- Currently localized reads just match based on client and osd ip matching, which was originally implemented for hadoop...
- 12:36 AM Revision 82211f21 (ceph): qa: rsync test: exclude /usr/local
- Some plana have non-world-readable crap in /usr/local/samba. Avoid
/usr/local entirely for that and any similar land... - 12:07 AM Revision 62eb49f6 (ceph): schedule_suite.sh: bump suite timeout from 6->8 hours
- This captures the current slow rbd tasks.
Signed-off-by: Sage Weil <sage@inktank.com>
05/11/2013
- 06:15 PM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- we hit it again! leaving the machines locked and task hung.
ubuntu@teuthology:/a/teuthology-2013-05-11_01:30:03-u... - 05:58 PM Revision 459c7311 (ceph): osd/OSD.h: fix try_stop_deletion
- Fix try_stop_deletion(): The comment above the while loop says "If we are
in DELETING_DIR or DELETED_DIR", but the wh... - 05:41 PM CephFS Bug #5033 (Can't reproduce): oops in ceph_put_wrbuffer_cap_refs
- ...
- 05:38 PM rbd Bug #5032 (Closed): xfstest 269 failure
- ...
- 05:27 PM CephFS Bug #5031: mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- logs copied to logs/ subdir
- 05:27 PM CephFS Bug #5031 (Resolved): mds/MDCache.cc: 5221: FAILED assert(reconnected_snaprealms.empty())
- ...
- 05:25 PM Bug #4579: kclient + ffsb workload makes osds mark themselves down
- ubuntu@teuthology:/a/teuthology-2013-05-11_01:00:38-fs-next-testing-basic/11289
- 05:22 PM CephFS Bug #5030 (Resolved): libcephfs xattr test failure
- 2013-05-11T02:29:39.882 INFO:teuthology.task.workunit.client.0.out:[ RUN ] LibCephFS.Xattrs
2013-05-11T02:29:39... - 05:04 PM Bug #4813: pgs stuck creating
- ...
- 05:02 PM Bug #4976: osd powercycle triggers object corruption on xfs
- ...
- 10:58 AM rbd Feature #3763: krbd: handle flattening of mapped image
- The following patches have been posted for review. They
are available in the "review/wip-flatten" branch of the
ce... - 10:57 AM rbd Feature #3763 (Fix Under Review): krbd: handle flattening of mapped image
- The following patches have been posted for review. They
are available in the "review/wip-flatten" branch of the
ce... - 10:21 AM rbd Feature #3763: krbd: handle flattening of mapped image
- I've got over 2800 iterations on UML and over 5300 iterations
on "normal" Linux running flattens while writing 16 co... - 10:56 AM rbd Subtask #5028 (Fix Under Review): rbd: treat clones with zero parent overlap as non-layered
- The following patch has been posted for review. It is
available in the "review/wip-flatten" branch of the
ceph-cli... - 10:31 AM rbd Subtask #5028 (Resolved): rbd: treat clones with zero parent overlap as non-layered
- When the overlap of a clone with its parent is 0, there
is no need to consult the parent for any image data any
mor... - 10:56 AM Bug #5027 (Fix Under Review): rbd: support reading parent page data for writes
- The following patch has been posted for review. It is
available in the "review/wip-flatten" branch of the
ceph-cli... - 10:28 AM Bug #5027 (Resolved): rbd: support reading parent page data for writes
- Currently, rbd_img_obj_parent_read_full() assumes the incoming
object request contains bio data. But if a layered i... - 10:55 AM Bug #5026 (Fix Under Review): libceph: allow osd requests to be reused
- The following patch has been posted for review. It is
available in the "review/wip-flatten" branch of the
ceph-cli... - 10:27 AM Bug #5026 (Resolved): libceph: allow osd requests to be reused
- Because certain fields in an osd request structure are never
cleared, any attempt to reuse a request leads to a fail... - 06:14 AM Revision f330d038 (ceph): fs/samba: disable smbtorture lock test
- Until we fix #5025.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:02 AM Revision 89257384 (ceph): fs/samba: fix noceph mount point
- We need to clean this dir up at the end of the test or else teuthology
will be unhappy with the dirty testdir. Use t... - 06:01 AM Revision 63203c6e (ceph): localdir: create/cleanup mnt.foo dir on local fs
- This creates and cleans up a local mnt dir that can be consumed
by other tasks (like workunit, samba, etc), just like... - 05:02 AM Revision a0d238c3 (ceph): rgw: cache obj version
- Also keep bucket objv_tracker on the request state.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:55 AM Revision 391f3abb (ceph): fs/samba: smbtorture: disable base.bench-hold* tests
- These seem to hang, even when run on samba + local fs (no ceph).
- 04:44 AM Revision 857279b8 (ceph): fs/samba: add noceph.yaml baseline
- Run samba against the a local directory to isolate issues not specific to
the ceph backend. - 04:44 AM Revision 464e5e3c (ceph): fs/samba: disable kernel build
- bus error, bad file handle errors... maybe an issue with cifs.ko?
2013-05-10T19:58:02.736 INFO:teuthology.task.worku... - 03:57 AM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
- Docs say "You can change the minimum number of osd down reports by adding an osd min down reports setting under the [...
- 03:10 AM Revision 703bc2fd (ceph): config_opts: default mon_debug_dump_transactions to 'false'
- otherwise, it chews mon log space at an alarming rate.
Fixes: #5024
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 02:00 AM Revision a095075f (ceph): ceph-qa: update Hadoop tests overrides
- Changes to the install teuthology task have caused the
Hadoop tasks to fail. This patch fixes the test specification
... - 01:03 AM Revision 6205c3da (ceph): rados/osd-powrcycle: turn up mds logging
- To catch #4832
Signed-off-by: Sage Weil <sage@inktank.com> - 01:03 AM Revision d0e9a19e (ceph): fs/samba: restructure and expand test collection
- All workloads on samba, samba+fuse, samba+kernel. Workloads include
torture and cifs + {various workunits} - 12:33 AM Revision a12464f7 (ceph): Do not scan for vm locks when listing all machines.
- Fixes: #4830
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 12:13 AM Revision b5e9b56f (ceph): Merge pull request #272 from ceph/wip-rbd-parallel
- Reviewed-by: Sage Weil <sage@inktank.com>
05/10/2013
- 11:45 PM Revision ea0e0c7e (ceph): Merge branch 'wip-4273'
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 11:32 PM Revision 996f1edc (ceph): task modified to include a '-' before the test script
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:17 PM Revision 93f27942 (ceph): Throttle: move start_op() to C_SimpleThrottle constructor
- This is done by all callers right before constructing this.
Since C_SimpleThrottle is already responsible for calling... - 11:17 PM Revision bfa10669 (ceph): librbd: only send non-zero copyup data
- If the parent image is logically zero for the range of a child object,
it's equivalent to the object not existing. Sa... - 11:17 PM Revision a6d0a254 (ceph): librbd: parallelize and simplify flatten
- Flattening reads the logical child object from the parent image, and
then does a copyup operation if the data is non-... - 11:17 PM Revision fb299d38 (ceph): librbd: move completion release into rbd_ctx_cb()
- All the users of rbd_ctx_cb() do this separately right now, but
there's no reason to keep the completion around after... - 11:17 PM Revision 613d7471 (ceph): librbd: run copy in parallel
- Instead of using read_iterate(), loop over each period of objects in
the source, read from them asynchronously, and t... - 11:17 PM Revision cfece23d (ceph): librbd: parallelize rollback
- Use a SimpleThrottle like trim_image() to limit the number of
requests in flight.
Signed-off-by: Josh Durgin <josh.d... - 11:13 PM CephFS Bug #5025 (Resolved): samba smbtorture lock test fails on kclient
- ...
- 11:12 PM Revision 922df6c5 (ceph): rgw: op->PutACLs uses the correct set_attr for buckets
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:55 PM Revision 1f0b947d (ceph): rgw: rados->set_attr() just calls rados->set_attrs()
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:19 PM CephFS Bug #5022 (Resolved): samba: smbtorture failures
- 05:27 PM CephFS Bug #5022 (Resolved): samba: smbtorture failures
- logs: ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:36-fs-master-testing-basic/10437...
- 10:14 PM Bug #4996 (Fix Under Review): mon: bogus mds tell can crash monitors
- wip-4996
this will be soon obsoleted by the new cli work, but this fix should go to bobtail and cuttlefish. - 02:42 AM Bug #4996 (Resolved): mon: bogus mds tell can crash monitors
- I was trying to run this command at the time:...
- 10:08 PM Revision 7b408537 (ceph): Merge pull request #273 from dalgaaf/wip-da-CID-fixes-v2
- Reviewed-by: Sage Weil <sage@inktank.com>
- 10:02 PM Revision 4b3a7dcb (ceph): client/SyntheticClient.cc: fix another memory leak
- Fix memory leak in read_random: call delete[] on buf before
call new[] again in the for-loop.
CID 717071 Resource le... - 10:02 PM Revision 5af2cbfe (ceph): rados.cc: fix leaking of Formatter*
- Make sure Formatter* is deleted in error case.
717096 Resource leak (CWE-404) (25 of 25 cases)
Signed-off-by: Danny... - 10:02 PM Revision cb91f0fd (ceph): client/Client.cc: fix possible NULL pointer dereference
- CID 751332 Dereference null return value (CWE-476)
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 10:02 PM Revision f6635cb3 (ceph): client/SyntheticClient.cc: check return value of describe_layout()
- Fix SyntheticClient::chunk_file(): check return value of
describe_layout() and handle the error.
CID 966615 Unchecke... - 10:02 PM Revision d1e0fc64 (ceph): kv_flat_btree_async.cc: fix resource leak
- Call AioCompletion::release() if the completion is no longer
needed to free the resources.
CID 727976 Resource leak ... - 10:02 PM Revision c006151c (ceph): ceph-monstore-tool.cc: check if open() was successful
- Should fix: "fd" is passed to a parameter that cannot be negative.
CID 1019566 Improper use of negative value (NEGAT... - 10:02 PM Revision 437d69ef (ceph): mds/CDir.cc: fix possible dereference after NULL check
- CID 1019553 Dereference after null check (FORWARD_NULL, CWE-476)
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 10:02 PM Revision 4908079c (ceph): rados_sync.cc: remove dead and not needed code
- The first if handles all chars < 32, the last 2 if's check for
'\n' (10) and '\r' (13). This code will never be reach... - 10:02 PM Revision 5babc816 (ceph): rbd.cc: fix error handling
- Fix undead code. Get error code from write_fd() before check
the result against < 0.
CID 1019550 Logically dead code... - 10:02 PM Revision b097f656 (ceph): rgw/rgw_rest.cc: remove dead and unneeded code
- Since origin and meth are already checked to be true there is
no need to check again in s->cio->print() after the ini... - 10:02 PM Revision f56cb984 (ceph): osd/OSD.h: add missing unlock of osd_lock
- CID 1019560 Missing unlock (CWE-667)
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 10:02 PM Revision 5392e970 (ceph): mds/Server.cc: remove dead default in switch
- The default switch can't get executed since the switch value
can only have the two values already checked.
CID 71689... - 10:02 PM Revision d258df4d (ceph): mds/MDCache.cc: add NULL pointer check
- Check for result of get_inode() for NULL before use the pointer.
716990 Dereference null return value (CWE-476)
Sig... - 10:02 PM Revision 447f3186 (ceph): mds/MDCache.cc: fix dereference NULL pointer
- Fix possible NULL pointer dereference. Change return value of
CInode::get_dirfrag() to return NULL instead of 0 since... - 10:02 PM Revision b9fbc821 (ceph): client/SyntheticClient.cc: fix memory leak
- Fix memory leak in read_random: call delete[] on buf before
call new[] again in the for-loop.
CID 717070 Resource le... - 10:02 PM Revision 6e241b97 (ceph): ObjectStore.cc: add missing break in switch
- Fix switch handling for case OP_SPLIT_COLLECTION2, add break after
the case to prevent fall through into default case... - 10:02 PM Revision d9c5b5b7 (ceph): client/SyntheticClient.cc: add missing break in switch
- Fix switch handling for case SYNCLIENT_MODE_OVERLOAD_OSD_0, add break
after the case to prevent fall through into nex... - 10:02 PM Revision 8d614665 (ceph): rgw/rgw_user.cc: add missing break in switch
- Fix switch handling for case KEY_TYPE_SWIFT, add break after the
case to prevent fall through into KEY_TYPE_S3 case.
... - 10:02 PM Revision 0c70e446 (ceph): libcephfs/test.cc: add assert for result of ceph_getxattr()
- Check result of ceph_getxattr() before pass it as parameter to
strncmp(). Make sure it's not negative.
CID 739411 Ar... - 10:02 PM Revision 077cdb04 (ceph): test/omap_bench.cc: remove dead code
- CID 716900 Logically dead code (CWE-561)
CID 716901 Logically dead code (CWE-561)
CID 727968 Logically dead code (CWE... - 09:42 PM Revision 92db7a01 (ceph): rgw: metadata handler for bucket set_attr operations
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:39 PM Revision 27fb38bb (ceph): doc: Fixed typos. Somehow got a merge error.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:30 PM Revision 65768a68 (ceph): mds: be more explicit about path_traverse completion
- Coverity turned up
CID 717085 (#1 of 1): Resource leak (RESOURCE_LEAK)
10. leaked_storage: Variable "c" going out of... - 08:53 PM Revision 8eaa15f2 (ceph): doc: fix broken link to ceph-deploy in release notes
- Signed-off-by: Ross Turk <ross@inktank.com>
- 08:43 PM Bug #4967: Misbehaving OSD sets over half of the cluster as down despite "osd min down reporters ...
You need "osd min down reporters = 14" in the [mon] section not the [osd] section of ceph.conf.
- 08:23 PM Bug #5024: mon_debug_dump_transactions should default to False
- I pushed a fix to the cuttlefish branch to get the gitbuilders chewing on it.
- 08:07 PM Bug #5024 (Resolved): mon_debug_dump_transactions should default to False
- 797089ef082b99910eebfd9454c03d1f027c93bb added mon_debug_dump_transactions to dump to a
separate log file (mon_debu... - 08:21 PM CephFS Bug #4965: libcephfs-java test failure
- Commit a095075fe4dcdac817895dac316100e733ab4698 has a patch that I believe fixes this issue. If it resolves things in...
- 07:00 PM Revision 537386d9 (ceph): Throttle: add a simpler throttle that just blocks above a threshold
- This is convenient to use to turn synchronous calls into asynchronous
calls with a limited number of operations in fl... - 07:00 PM Revision 40956410 (ceph): librbd: delete more than one object at once
- Speed up deletions when resizing down or removing an image by keeping
up 10 operations in flight by default.
Refs: #... - 07:00 PM Revision 3b2c5fb8 (ceph): librados: add selfmanaged_snap_rollback as an ObjectOperation
- This allows it to be done asynchronously, or in conjunction with
other operations.
Signed-off-by: Josh Durgin <josh.... - 06:30 PM Revision 261aaba1 (ceph): doc: Added entry for the RGW Admin Ops API.
- fixes: #5002
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 06:06 PM rgw Bug #4975 (Resolved): nightlies: swift test failed after upgrading from bobtail to next
- 09:46 AM rgw Bug #4975: nightlies: swift test failed after upgrading from bobtail to next
- I want to start moving us towards zero-tolerance for nightly failures.
If this is a bug in the test suite, we shou... - 06:06 PM rgw Bug #4957 (Resolved): 400 Bad Request after bucket rm ... on radosgw-admin test
- commit:1b0f241dcb7f4a03c3c5095464e740e5dd75831a in teuthology.git reverts the bad test.
- 09:51 AM rgw Bug #4957: 400 Bad Request after bucket rm ... on radosgw-admin test
- Made this urgent because I want to start driving us towards zero-tolerance for nightly failures. If the problem is i...
- 05:31 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- ...
- 05:31 PM CephFS Bug #4565: MDS/client: issue decoding MClientReconnect on MDS
- log: ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:36-fs-master-testing-basic/10442...
- 05:26 PM Revision 49d22aa6 (ceph): Merge pull request #271 from dalgaaf/wip-da-sca-cppcheck-v2.1
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:23 PM CephFS Bug #5021 (Resolved): ceph-fuse: crash on traceless reply
- logs: ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:36-fs-master-testing-basic/10448...
- 05:21 PM rbd Bug #4959: xfstest 17 failure
- Whoops, meant to update this this morning. There's only one set of tests running, so no concurrency.
- 11:29 AM rbd Bug #4959: xfstest 17 failure
- That's a really weird output.
The "*** test 3" (and 3 and 4) are shown at the top of a
loop that:
- runs fsstres... - 05:19 PM Revision ad2990c4 (ceph): include/addr_parsing.c: reduce scope of port_str in safe_cat()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision cd0f461f (ceph): include/ceph_hash.cc: reduce scope of a var in ceph_str_hash_rjenkins()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision 54e7a6ff (ceph): libcephfs_jni.cc: reduce scope of ret variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision 45ffb36b (ceph): ceph-filestore-dump.cc: use empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision cdfc4a7e (ceph): rgw/rgw_op.cc: use empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision e7d11140 (ceph): cls/rbd/cls_rbd.cc: reduce scope of variable rc
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision b66b8ddf (ceph): common/admin_socket.cc: remove scope of ret variable in do_accept()
- Reduce scope of ret variable and remove usage in one case.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 05:19 PM Revision 6256d3ed (ceph): common/ceph_argparse.cc: remove scope of some variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision 8c97e77e (ceph): common/obj_bencher.cc: reduce scope of avg_bandwidth
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision e064e67c (ceph): common/safe_io.c: reduce scope of some ssize_t variables
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision 73a10ac9 (ceph): crush/builder.c: reduce scope of oldsize in crush_add_bucket()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:19 PM Revision cc3376cf (ceph): global/global_init.cc: reduce scope of ret in global_init_daemonize()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:18 PM Revision 1b0f241d (ceph): Revert "radosgw-admin: Test bucket list for bucket starting with unders...
- This reverts commit fa70eb8f67371568f47ae237606be63024164214.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:14 PM Feature #4273 (Resolved): osd: prioritize recovery for degraded pgs
- commit:ea0e0c7e34f6b99ecb123d0ee761f653e7e6bc04
- 05:13 PM rbd Feature #2256: rbd: parallelize deletions
- commit:b5e9b56fc93dd4896c802aff1096430b523ad84c
- 05:13 PM rbd Feature #2256 (Resolved): rbd: parallelize deletions
- 04:58 PM CephFS Bug #4832: mds: failed auth_unpin assert
- ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:06-rados-master-testing-basic/10278...
- 04:53 PM CephFS Feature #3243 (Resolved): qa: test samba reexport via libcephfs vfs plugin in teuthology
- 04:52 PM Bug #4976: osd powercycle triggers object corruption on xfs
- ...
- 04:51 PM Bug #4976: osd powercycle triggers object corruption on xfs
- ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:06-rados-master-testing-basic/10288
- 04:52 PM Fix #4840: mon: transition from old-style allow command to new command descriptions
- the underlying bits are all now in place in wip-mon-cap.
i think all that's needed is a translate of old strings t... - 04:50 PM Fix #4567 (Fix Under Review): mon: refactor mon caps; allow restriction of key/value storage by p...
- 04:48 PM Bug #5020 (Resolved): osd: 2.5 deep-scrub stat mismatch, got 710/665 objects, 0/0 clones, 2908160...
- ubuntu@teuthology:/a/teuthology-2013-05-10_01:00:06-rados-master-testing-basic/10305...
- 04:37 PM Revision 723062bb (ceph): doc: Updated usage syntax. Added links to hardware and manual OSD remove.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:04 PM devops Feature #5019 (Resolved): arm: gitbuilder for ARM
- 03:03 PM devops Feature #5018 (Resolved): arm: ceph-deploy: push packages to ARM
- 03:00 PM devops Feature #5016: ceph-deploy: gitbuilders for release packages
- 02:57 PM devops Feature #5016 (Resolved): ceph-deploy: gitbuilders for release packages
- 03:00 PM devops Feature #5015: ceph-deploy: push packages to all ceph repos
- 02:57 PM devops Feature #5015 (Resolved): ceph-deploy: push packages to all ceph repos
- 02:56 PM devops Feature #5014 (Resolved): arm: Build ARM packages
- 02:55 PM devops Feature #5013 (Rejected): build internal openstack + ceph cluster out of some burnupi
- 02:45 PM Bug #5010 (Resolved): doc: Trasitioning to ceph-deploy doc missing
- Sorry for the delay. Someone caused a merge conflict. The link syntax was wrong, and there was a reference in two pla...
- 01:49 PM Bug #5010 (Resolved): doc: Trasitioning to ceph-deploy doc missing
- http://ceph.com/docs/master/release-notes/#v0-61-cuttlefish has a link called "Transitioning to ceph-deploy" that res...
- 01:36 PM rgw Feature #3366: rgw: dr: define management api
- Extend mgt API to implement new zone commands
- 01:32 PM rgw Feature #3366: rgw: dr: define management api
- Extend the management API to allow it execute commands related to establishing multi-site or DR
- 01:31 PM rgw Feature #3366: rgw: dr: define management api
- 01:31 PM rgw Feature #3366 (In Progress): rgw: dr: define management api
- 01:31 PM rgw Feature #3366: rgw: dr: define management api
- 01:30 PM rgw Feature #4309: rgw: multisite: metadata objects versioning
- 01:30 PM rgw Feature #4312: rgw: multisite: log metadata changes
- 01:28 PM rgw Feature #4331: rgw: multisite: metadata-changes log: create internal API
- 01:28 PM rgw Feature #4311: rgw: dr: radosgw changes: internal bucket changes tracker
- 01:28 PM rgw Feature #4347: rgw: dr: bucket index objclass: fetch changes log
- 01:28 PM rgw Feature #4346: rgw: dr: bucket index objclass: changes
- 01:28 PM rgw Feature #4332: rgw: multisite: metadata-changes log: tie into metadata update operations
- 01:25 PM rbd Documentation #5009 (Resolved): doc: explain how to get qemu packages for each distro
- Once #4550 and #4834 are done, we'll have qemu packages with async flush for several distros. This is pretty importan...
- 01:20 PM rbd Feature #5003: cinder/nova: don't require ceph.conf on a compute host / support multiple clusters
- The nova blueprint is: https://blueprints.launchpad.net/nova/+spec/better-libvirt-network-volume-support
- 12:04 PM rbd Feature #5003 (Rejected): cinder/nova: don't require ceph.conf on a compute host / support multip...
- https://bugs.launchpad.net/cinder/+bug/1077817
- 01:13 PM rgw Documentation #3217 (Closed): rgw: document RESTful usage api
- Landed via da271f7f78fee9e349860695b1913210a44018cc
- 01:11 PM rgw Feature #5008 (In Progress): rgw: bucket metadata changes should be reflected in mdlog
- 01:11 PM rgw Feature #5008 (Resolved): rgw: bucket metadata changes should be reflected in mdlog
- 01:11 PM RADOS Feature #5007 (New): librados: expose snap_set_diff interfaces?
- Just looking at source organization, I see snap_set_diff.cc in librados, but it's only
linked into librbd; perhaps i... - 01:09 PM rgw Feature #4334 (In Progress): rgw: dr: bucket index log API: implement RESTful API
- 01:09 PM rgw Feature #4333 (In Progress): rgw: multisite: metadata-changes log: implement RESTful API
- 01:09 PM rgw Feature #4329 (In Progress): rgw: dr: updated buckets log: RESTful API
- 01:08 PM rgw Feature #4330 (Fix Under Review): rgw: dr: updated buckets log: radosgw-admin changes
- Please review wip-rgw-geo
- 01:07 PM rgw Feature #4328 (Fix Under Review): rgw: dr: updated buckets log: tie into internal bucket changes ...
- Please review wip-rgw-geo
- 01:07 PM rgw Feature #4327 (Fix Under Review): rgw: dr: updated buckets log: create internal API
- Please review wip-rgw-geo
- 01:05 PM rgw Feature #4745: rgw: radosgw-admin command to stat object
- wip-rgw-geo
- 01:05 PM rgw Feature #4745: rgw: radosgw-admin command to stat object
- Greg, can you please review this?
- 12:29 PM rbd Documentation #5006 (Resolved): doc: openstack configuration changes for havana
- In Havana, the cinder and nova configuration should be a bit simpler (see #5003, #5004, and #5005). Update (or add a ...
- 12:28 PM Bug #4813: pgs stuck creating
- this happened again on latest master: ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-05-10_01:00:06-r...
- 12:14 PM rbd Feature #5004: cinder: make rbd configuration easier to use
- Moved the librbd part to #5005.
- 12:08 PM rbd Feature #5004 (Resolved): cinder: make rbd configuration easier to use
- Get the user out of a config option instead of an environment variable, and switch to librbd from cli rbd so
the opt... - 12:14 PM rbd Feature #5005 (Resolved): cinder: switch rbd driver to use librbd instead of the cli tool
- This will give us better error handling and easier backwards compatibility. It will also make it easer to match the c...
- 11:35 AM Bug #5002 (Resolved): doc: API Page missing link to RGW User Admin API
- Added link: http://ceph.com/docs/master/api/
- 11:10 AM Bug #5002 (Resolved): doc: API Page missing link to RGW User Admin API
- http://ceph.com/docs/master/api/ should have an entry for the new RGW User Admin API located at http://ceph.com/docs/...
- 11:32 AM rbd Feature #3064 (In Progress): librbd: A way to read from nearby replicas
- 10:53 AM rbd Feature #3763: krbd: handle flattening of mapped image
- I found that in the case that an existence check callback
(for a write) if the image had been flattened, I was
resu... - 06:27 AM rbd Feature #3763: krbd: handle flattening of mapped image
- I have evidence that handling a flatten of an image
works correctly when a read parent is underway, as
well as when... - 10:35 AM rbd Feature #4804: tgt: switch to aio
- 10:35 AM rbd Feature #4917: iSCSI: Package tgt
- 10:19 AM rgw Bug #4958: rgw test failing when trying to delete a bucket
- I reverted the relevant teuthology test.
- 10:07 AM Bug #4999: monitor sync failure
- OK, here's what happens when I try to restart:...
- 09:37 AM Bug #4999: monitor sync failure
- Or, I guess, maybe my browser was getting in the way of a big cut-n-paste?
Anyway, it all seems to be there now.
- 09:33 AM Bug #4999: monitor sync failure
- Evidently it's Redmine's issue. Here's the rest, really!...
- 09:31 AM Bug #4999: monitor sync failure
- Oops, sorry; too-small cut-n-paste buffer clipped off the trace.
I'll try the restart here in a bit -- I had to sh... - 09:21 AM Bug #4999: monitor sync failure
- Hi Jim!
Can you generate a 'debug ms = 1' 'debug mon = 20' 'debug paxos = 20' log for the restart after the crash?... - 09:16 AM Bug #4999 (Can't reproduce): monitor sync failure
I've been testing v0.61 and v0.61.1 with 262,144 PGs in
a single pool, 576 OSDs, 3 mon, 3 MDS (1 active + 2 standb...- 09:25 AM devops Bug #4916 (In Progress): ceph-deploy: mon create fails on bobtail branch in centos 6.3
- 08:53 AM devops Feature #4998 (Resolved): ceph-deploy should allow user specified installation sources
- ceph-deploy currently uses the package repos at ceph.com or gitbuilder.ceph.com for installation sources, and additio...
- 08:43 AM Bug #4974 (In Progress): nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- Forgot to update status
- 08:43 AM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- Matthew provided a store for me to play with.
Doing some analysis, it looks like the issue is confined to the mdsm... - 05:17 AM Bug #4974: nightlies: failed assert at Monitor::StoreConverter::_convert_machines
- We lost the logs for these runs after being nuked. I left a teuthology job running overnight to reproduce it, but fo...
- 08:19 AM rgw Bug #4997 (Resolved): Seg Fault on rgw 0.61.1 with cluster in 0.61
- Hi,
I've tried to update the rgw to 0.61.1 and I had a segfault while connecting to the 0.61 cluster.
I have anot... - 07:16 AM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- PS This can differ in details from natural failure: I copy another copy of problem files, so CAN (or not), for exampl...
- 06:59 AM Bug #4937: osd/ReplicatedPG.cc: 1379: FAILED assert(0)
- OK.
I have xfs on OSDs and reiserfs on system & monitors. Now I have more this objects. I understand next: IMHO ther... - 05:37 AM Revision fd901056 (ceph): Merge branch 'wip_4955' into next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:24 AM Revision b353da6f (ceph): Merge branch 'wip_pg_res'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:23 AM Revision 01a07c1e (ceph): OSD: rename clear_temp to recursive_remove_collection()
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:23 AM Revision f5a60ca2 (ceph): osd: remove_dir use collection_list_partial
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:08 AM Revision 8b3cd6e7 (ceph): rgw: don't handle ECANCELLED anymore
- Simplify, remove obsolete logic.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:21 AM Revision d7fe5c0a (ceph): nuke: don't require noipmi in ctx
- This is called from run.py too, which won't have ctx.noipmi.
The default of using impmi is fine for now for run.py.
... - 12:30 AM Revision 7a8d6fd4 (ceph): PG,OSD: delay ops for map prior to queueing in the OpWQ
- Previously, we simply queued ops in the OpWQ without checking. The PG
would then check in do_request whether the mes... - 12:28 AM Revision b274c8a0 (ceph): common/sharedptr_registry.hpp: add remove
- remove() can be used to clear an entry before all of its
references are removed.
Signed-off-by: Samuel Just <sam.jus... - 12:28 AM Revision 90f50c48 (ceph): OSD: add pg deletion cancelation
- DeletingState now allows _create_lock_pg() to attempt to cancel
pg deletion.
PG::init() must mark the PG as backfill... - 12:28 AM Revision 0ef9b1e0 (ceph): osd_internals/pg_removal.rst: update for pg resurrection
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:28 AM Revision d3dd99b7 (ceph): PG: no need to wait on DeletingStateRef for flush
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Also available in: Atom