Project

General

Profile

Activity

From 07/21/2013 to 08/19/2013

08/19/2013

11:42 PM Revision c0449515 (ceph): regression: remove
It's just an out-of-date symlink list at this point.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
10:54 PM Bug #6057 (Resolved): osd: log bound mismatch after bobtail -> dumpling -> next upgrade
yay, tested ok for me too. merged and backported Sage Weil
10:42 PM Bug #6057: osd: log bound mismatch after bobtail -> dumpling -> next upgrade
Ran the above yaml on wip-6057, seems to work. Samuel Just
05:59 PM Bug #6057: osd: log bound mismatch after bobtail -> dumpling -> next upgrade
wip-6057 Samuel Just
04:55 PM Bug #6057: osd: log bound mismatch after bobtail -> dumpling -> next upgrade
fatty:/home/sage/tmp/6057/ceph-osd.0.log for the full log Sage Weil
04:55 PM Bug #6057: osd: log bound mismatch after bobtail -> dumpling -> next upgrade
... Sage Weil
02:11 PM Bug #6057 (Resolved): osd: log bound mismatch after bobtail -> dumpling -> next upgrade
2013-08-19 06:24:27.814763 osd.2 0.0.0.0:6808/24619 1 : [ERR] 3.4 log bound mismatch, info (0''0,30''164] actual [21'... Sage Weil
10:47 PM Bug #5951: osd: next: EEXIST on mkcoll
no failures in previous run
~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-5951-5" -n 5...
Samuel Just
03:43 PM Bug #5951: osd: next: EEXIST on mkcoll
no failures in the last run
~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-5951-4" -n 5...
Samuel Just
11:08 AM Bug #5951: osd: next: EEXIST on mkcoll
~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-5951-3" -n 20 --owner samuelj@slider test... Samuel Just
08:58 AM Bug #5951: osd: next: EEXIST on mkcoll
ubuntu@teuthology:/a/teuthology-2013-08-19_01:00:13-rados-master-testing-basic-plana/969 Sage Weil
10:40 PM Bug #6040: Significant slowdown of osds since v0.67 Dumpling
merged wip-dumpling-pglog-undirty with the config set to false into next and dumpling. Samuel Just
12:08 AM Bug #6040: Significant slowdown of osds since v0.67 Dumpling
wip-dumpling-pglog-undirty may help with this. Samuel Just
10:39 PM Revision ceb1d7bb (ceph): readwrite: Specifying the domain root pool
This fixes a 404 error caused when the
reads from the newly created region cannot find
necessary data due to the doma...
Joe Buck
10:21 PM Revision 220f7d61 (ceph): osd/ReplicatedPG: remove broken AccessMode logic
The original intent here was to handle reads in two modes. For
workloads with read/modify/write ops, the RMW mode wo...
Sage Weil
10:14 PM Revision c64878b5 (ceph): Merge pull request #508 from ceph/wip-5905
examples: add a librados/hello_world program
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Loic Da...
Gregory Farnum
09:55 PM Revision 823435ce (ceph): examples: add a librados/hello_world program
This is a simple program with lots of explanatory comments people
can use as a model for using librados.
Signed-off-...
Greg Farnum
09:30 PM Revision 35313052 (ceph): upgrade/mixed-mons: run final dumpling test against all-dumpling mons
Sage Weil
09:30 PM Revision 3bcff449 (ceph): upgrade/mixed-mons: run cuttlefish tests against (2 cuttlefish, 1 dumpl...
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:18 PM Revision 5695de1f (ceph): upgrade: fix mixed workloads
We are running cuttlefish/dumpling mix. Client node still has cuttelfish.
Use cuttelfish workunits.
Sage Weil
09:10 PM Revision 0a8a1c98 (ceph): Merge pull request #41 from ceph/wip-3791
Various usability and documentation fixes Alfredo Deza
09:10 PM Revision d3b6d633 (ceph): Merge pull request #41 from ceph/wip-3791
Various usability and documentation fixes Alfredo Deza
07:49 PM Revision 96d719ee (ceph): ceph: parse CEPH_ARGS environment variable
Fixes: #6052
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked ...
Sage Weil
07:49 PM Revision d348cf5d (ceph): rados pybind: add conf_parse_env()
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit e...
Sage Weil
07:48 PM Revision eef7cacd (ceph): rados pybind: add conf_parse_env()
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil
07:48 PM Revision 67a95b98 (ceph): ceph: parse CEPH_ARGS environment variable
Fixes: #6052
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil
07:41 PM Revision 68c1c70e (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
07:41 PM Revision 9dda1cc0 (ceph): doc/release-notes: v0.61.8
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
07:32 PM Revision 233fed8c (ceph): Merge pull request #513 from dalgaaf/fix/wip-da-documentation
Fix documentation issues Sage Weil
06:56 PM Revision 090e4c4a (ceph): filestore-config-ref.rst: mark some filestore keys as deprecated
Marked the following keys as deprecated since v0.65:
- filestore flusher
- filestore flusher max fds
- filestore sync...
Danny Al-Gaaf
06:51 PM Revision 22abe029 (ceph): Whoops! Make 'MacOS X' a header again.
Zack Cerza
06:49 PM Revision 3f42335a (ceph): And, more formatting tweaks.
Zack Cerza
06:46 PM Revision adc3f62e (ceph): Mo' betta consistency.
Zack Cerza
06:35 PM Revision 59e01a41 (ceph): Don't necessarily need to manually link libvirt. Also, remove $'s.
Zack Cerza
06:16 PM Revision a396e027 (ceph): Merge pull request #512 from ceph/wip-5988
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
06:09 PM devops Bug #5599: ceph-disk: prepare should issue a partprobe on the journal device too
Actually this patch (attached) is probably more in keeping with the code style already used in ceph-disk, uses partpr... Mark Kirkwood
05:13 PM devops Bug #5599: ceph-disk: prepare should issue a partprobe on the journal device too
Fyi a tentative patch has been suggested, using partx rather than partprobe (no idea which might be best mind you):
...
Mark Kirkwood
06:02 PM Revision 0c5f842e (ceph): Merge branch 'wip-erasure-coded-doc'
Samuel Just
05:29 PM Revision 4e86be92 (ceph): librados: synchronous commands should return on commit instead of ack
This is unlikely to be noticed by anybody, but it is a big change. Document
in the PendingReleaseNotes and bump up th...
Greg Farnum
05:28 PM Revision efd1bce4 (ceph): Merge pull request #493 from dachary/wip-erasure-coding-doc
rearrange erasure code documents
Reviewed-by: Samuel Just <sam.just@inktank.com>
athanatos
05:21 PM Revision f5636be7 (ceph): mon: make MonMap error message about unspecified monitors less specific.
The error message helpfully references the -m and -c CLI options for
specifying monitors, but this code can be invoke...
Greg Farnum
05:06 PM rgw Bug #6056 (Fix Under Review): rgw: sync agent is not propagating bucket delete
We end up not removing the bucket entry point, although the bucket is unlinked from the user. Yehuda Sadeh
10:04 AM rgw Bug #6056: rgw: sync agent is not propagating bucket delete
I should have noted that I would expect that info for the bucket should not be found on either the source or the dest... Anonymous
10:02 AM rgw Bug #6056 (Resolved): rgw: sync agent is not propagating bucket delete
A new test that deletes an existing bucket on the source, then does a sync, then tries to get info for that bucket on... Anonymous
04:10 PM Bug #5902 (Resolved): s3tests failure during parallel upgrade test
backported Sage Weil
03:42 PM Bug #6003: journal Unable to read past sequence 406 ...
200 runs later and no luck reproducing this with logs.
/var/lib/teuthworker/archive/sage-bug-6003-a
200 passes
Sage Weil
09:38 AM Bug #6003: journal Unable to read past sequence 406 ...
Run this tasks repeatedly with logging Ian Colle
03:24 PM Fix #6059 (Resolved): osd: block reads while repgather is writing across replicas
Currently we use the ondisk_write/read locks to do mutual exclusion over the local filestore which avoids reading dat... Sage Weil
03:21 PM Feature #5905 (Resolved): hello world librados program (with explanatory comments!)
Merged into master, commit:823435ce650a2be0523eba0d91dc9feb28b795f7 Greg Farnum
03:01 PM Revision 6f9c759a (ceph): Remove false note about default value.
Zack Cerza
03:01 PM Revision 39879eca (ceph): Slightly tweak path.
Zack Cerza
02:59 PM Revision 5bd7f620 (ceph): Add comment about portability to get_testdir_base()
Zack Cerza
02:49 PM Revision 7a2cca1d (ceph): Update base_test_dir default to reflect reality
Zack Cerza
02:42 PM Bug #6058 (Duplicate): upgrading from bobtail to dumpling to next: log bound mismatch and wrong n...
Tamilarasi muthamizhan
02:39 PM Bug #6058 (Duplicate): upgrading from bobtail to dumpling to next: log bound mismatch and wrong n...
These failure are seen when running the rgw upgrade tests from bobtail to dumpling to next branch.
logs from the n...
Tamilarasi muthamizhan
02:03 PM Revision 657a070b (ceph): Merge pull request #37 from ceph/wip-fix5957-wusui
Display error message when locking a vpm fails due to downburst errors. Zack Cerza
01:37 PM CephFS Bug #5039 (Resolved): client: unlinking files leaves the cached entry behind
Sage Weil
01:04 PM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
getting somewhere. but it still can't find it.... Zoltan Arnold Nagy
12:31 PM Bug #6043 (In Progress): upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
is the ceph package still installed? some older versions didn't stop the jobs before they uninstalled, which might e... Sage Weil
11:54 AM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
well...... Zoltan Arnold Nagy
09:33 AM Bug #6043 (Rejected): upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
stop ceph-osd id=0
or
stop ceph-osd-all
Sage Weil
12:50 PM Bug #6052 (Resolved): ceph cli doesn't respect CEPH_ARGS
Sage Weil
09:42 AM Bug #6052 (Fix Under Review): ceph cli doesn't respect CEPH_ARGS
Sage Weil
09:01 AM Bug #6052 (Resolved): ceph cli doesn't respect CEPH_ARGS
... Sage Weil
12:29 PM Feature #6036 (Fix Under Review): cachepool: osd: add objecter
Sage Weil
11:20 AM Bug #5988 (Resolved): librados: synchronous IO generally returns on ack instead of commit
Merged into master, thanks Sage. Greg Farnum
11:16 AM Bug #5988 (Fix Under Review): librados: synchronous IO generally returns on ack instead of commit
wip-5988, commit:4e86be9232602ed595d885fcaeda5e47ad9a2a6a, pull request 512. Greg Farnum
11:19 AM Bug #5979 (Resolved): librados: imposes internal tooling expectations on users
Merged into master. Greg Farnum
11:15 AM Bug #5979 (Fix Under Review): librados: imposes internal tooling expectations on users
wip-5988, commit:f5636be742bffb19f16fdb832891fd1a43679ccf. Pull request 512. Greg Farnum
09:53 AM Fix #5844: osd: snaptrimmer should throttle itself
(09:57:41 AM) sjust: xdeller: right, the only way to fix that would be to increase OSDMap propogation speed
Regard...
Igor Lukyanov
09:42 AM rgw Bug #6051: rgw: 404 during readwrite test
Missed adding the traceback entry to an error dict in one codepath. I've pushed a one-line fix to the s3-tests branch... Anonymous
09:00 AM rgw Bug #6051 (Resolved): rgw: 404 during readwrite test
... Sage Weil
09:39 AM rgw Bug #6046 (Fix Under Review): rgw: empty pool created for control objects
Yehuda Sadeh
09:36 AM Bug #6041 (Resolved): Failing to add 3rd monitor
Please upgrade to 0.67(.1) dumpling; 0.64 is an interim development release that doesn't get backported fixes (as 0.6... Sage Weil
08:53 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
bernhard glomm wrote:
> Sage Weil wrote:
> > bernhard: i think the problem in your case is that you have old keyrin...
Sage Weil
12:40 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Sage Weil wrote:
> bernhard: i think the problem in your case is that you have old keyrings in /etc/ceph from prior ...
bernhard glomm
08:33 AM Revision a8462945 (ceph): auth-config-ref.rst: fix signature keys
Fix names of cephx signature keys.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf
07:34 AM Subtask #5862: FileStore must work with ghobjects rather than hobjects
Here is how I understand "stripe":https://www.usenix.org/legacy/events/fast09/tech/full_papers/plank/plank.pdf / shar... Loïc Dachary
07:11 AM devops Bug #6019 (In Progress): ceph-deploy needs to better detect yum/apt for bootstraping
Alfredo Deza
06:54 AM Revision d783e33b (ceph): v0.61.8
Gary Lowell
06:44 AM Subtask #5878: erasure plugin mechanism and abstract API
Wido den Hollander wrote:
> Will this be case sensitve? I would suggest not, since that will confuse users. I pers...
Loïc Dachary
06:32 AM Subtask #5878: erasure plugin mechanism and abstract API
I haven't looked at it in-depth, but one thing I noticed is that Reed-Solomon is always spelled with the first two le... Wido den Hollander
04:07 AM Revision 21a6e247 (ceph): RadosClient: shutdown monclient after dropping lock
Otherwise, the monclient shutdown may deadlock waiting
on a context trying to take the RadosClient lock.
Fixes: #589...
Samuel Just
02:44 AM Bug #6047: mon: Assert and monitor-crash when attemting to create pool-snapshots while rbd-snapsh...
This is pretty much the same as #5959, which was reported on cuttlefish and which we believed to have fixed on commit... Joao Eduardo Luis

08/18/2013

10:55 PM Bug #6022 (New): monitor crashed during ceph-deploy mon create on centos 6.4 and 6.3
verified that i can reproduce this. my first guess is a problem with the leveldb package on 6.4. 6.3 passes? Sage Weil
10:55 PM Bug #6022: monitor crashed during ceph-deploy mon create on centos 6.4 and 6.3
Sage Weil
10:32 PM Bug #6049 (Resolved): pgmap json output shows bytes_* values quadrupled
I was looking at the "ceph --format=json status" pgmap bytes_{used,avail,total} values with the goal of using them to... Faidon Liambotis
09:08 PM Bug #5897 (Resolved): ceph_test_rados_api_watch_notify hang on LibRadosWatchNotify.WatchNotifyTim...
fix preceded dumpling; backported to cuttlefish branch Sage Weil
09:06 PM rgw Bug #5949 (Resolved): radosgw: leaks
Sage Weil
06:45 PM Revision 290bcd8a (ceph): rgw: drain requests before exiting
Fixes: #5953
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry pick...
Yehuda Sadeh
06:45 PM Revision 863df08a (ceph): rgw: do not leak handler in get_handler() error path
If we fail to initialize, delete the handler.
Fixes (part of): #5949
Signed-off-by: Sage Weil <sage@inktank.com>
Rev...
Sage Weil
06:45 PM Revision 9ac003f7 (ceph): rgw: fix leak of RGWDataChangesLog::renew_thread
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 25948319c4d256c4aeb0137eb88947e54d14cc79)
Sage Weil
06:44 PM Revision 89cd9dc4 (ceph): rgw: free resolver on shutdown
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit a31356338b8ae55df59d829d9080ffad70b97d10)
Sage Weil
06:44 PM Revision 5b26ca7f (ceph): rgw: fix up signal handling
OMG libfcgi is annoying with shutdown and signals. You need to close
the fd *and* resend a signal to ensure that you...
Sage Weil
06:36 PM Revision 1670a73b (ceph): librados: fix async aio completion wakeup
For aio flush, we register a wait on the most recent write. The write
completion code, however, was *only* waking th...
Sage Weil
06:35 PM Revision 6cf05375 (ceph): librados: fix locking for AioCompletionImpl refcounting
Add an already-locked helper so that C_Aio{Safe,Complete} can
increment the reference count when their caller holds t...
Josh Durgin
11:42 AM devops Bug #4924 (Resolved): ceph-deploy: gatherkeys fails on raring (cuttlefish)
closing out this bug. i think i captured everything we learned in http://pad.ceph.com/p/quorum_pitfalls along with a... Sage Weil
11:36 AM rbd Bug #5919 (Resolved): qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to ke...
Sage Weil
11:08 AM Bug #6047 (Resolved): mon: Assert and monitor-crash when attemting to create pool-snapshots while...
While playing around on my test-cluster, I ran into a problem that I've seen before, but have never been able to repr... Oliver Daudey

08/17/2013

09:30 PM Revision 4677041d (ceph): objclass: move cls_log into class_api.cc
Not sure why but this seems to resolve a linking problem when loading
classes:
2013-08-17 13:28:19.015776 7fb2bcffa7...
Sage Weil
09:24 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Hi Sage, sorted it just before your reply. Was idly scrolling back through the thread when I spotted the word 'iptabl... Michael Potter
09:09 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Michael Potter wrote:
> Hi Sage, took everything out of the host for except for #ipaddr# #subdomain-identifier#.#res...
Sage Weil
07:45 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Hi Sage, took everything out of the host for except for #ipaddr# #subdomain-identifier#.#resolveable-domain#
Cleaned...
Michael Potter
06:14 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Ah, I think the problem is
{ "rank": 0,
"name": "#subdomain-identifier#",
...
Sage Weil
05:54 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Sage Weil wrote:
> Michael Potter wrote:
> > Getting the same thing on a fresh install of CentOS 6.4
> >
> > [.....
Michael Potter
07:34 PM Revision 70790ab6 (ceph): doc/dev/filestore-filesystem-compatibliity: remove outdated xattr notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:35 PM rgw Bug #6046 (Resolved): rgw: empty pool created for control objects
Yehuda Sadeh
06:00 PM Revision d7f1d166 (ceph): Merge pull request #494 from kri5/wip-s3-compliance-doc
doc: complete S3 features status from existing doc page Sage Weil
05:59 PM Revision 87affa2d (ceph): Merge pull request #491 from kri5/wip-clang-compilation
Fix compilation -Wmismatched-tags warnings
Reviewed-by: Loic Dachary <loic@dachary.org>
Sage Weil
05:35 PM Revision 2f221fe0 (ceph): doc: Updated upgrade doc to include dumpling and incorporate ceph-deploy.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
05:09 PM Revision ae7436ff (ceph): Merge pull request #479 from devoid/fix-5797
Document unstable nature of CephFS Sage Weil
04:40 PM Revision 060a4637 (ceph): Makefile: move objclass/*.cc to libosd.la
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:05 PM Revision 64bef4ae (ceph): mon/OSDMonitor: make 'osd pool mksnap ...' not expose uncommitted state
[This is a backport of d1501938f5d07c067d908501fc5cfe3c857d7281]
We were returning success without waiting if the pe...
Sage Weil
03:47 PM Revision 558237e5 (ceph): Detect multi-region test cases
Enable multi-region calls and tests only if
the configuration has specified a
radosgw-agent tastk.
Signed-off-by: Jo...
Joe Buck
03:38 PM Revision 8ac1af88 (ceph): doc/changelog: add missing file
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:30 PM Revision d0a6ff9d (ceph): os/FileStore: initialize blk_size on _detect_fs()
This was missed by a25d73effb38118602bc73da0aa258c639f69c2c.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
03:20 PM Revision ed4fe32f (ceph): doc/release-notes: v0.67.1
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:48 AM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
how about
ceph-deploy mon create-initial
which will
1. do mon create on each mon in the mon_initial_quorum ...
Sage Weil
10:07 AM Bug #6045 (Fix Under Review): mon/OSDMonitor.cc: 1609: FAILED assert(err == 0)
wip-6045
Sage Weil
09:57 AM Bug #6045 (In Progress): mon/OSDMonitor.cc: 1609: FAILED assert(err == 0)
we need to refresh any time we apply committed states to disk Sage Weil
09:47 AM Bug #6045 (Resolved): mon/OSDMonitor.cc: 1609: FAILED assert(err == 0)
... Sage Weil
10:01 AM CephFS Documentation #5797: Document unstable nature of CephFS
My PR is still open? Scott Devoid
09:10 AM Bug #5923 (Need More Info): osd: 6 up, 5 in; 91 active+clean, 1 remapped
Sage Weil
09:10 AM Bug #5902 (Pending Backport): s3tests failure during parallel upgrade test
Sage Weil
09:10 AM Bug #5901 (In Progress): stuck incomplete immediately after clean
Sage Weil
09:09 AM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
Sage Weil
09:07 AM Bug #5959 (Resolved): Quorum is crashing on 'osd pool mksnap'
backported by commit:64bef4ae4bab28b0b82a1481381b0c68a22fe1a4 Sage Weil
09:00 AM Bug #5986: mon: FAILED assert(snaps.count(s)) when removing pool snap on 0.61.7
backported in commit:411871f6bcc9a4b81140c2e98d13dc123860f6f7 Sage Weil
09:00 AM Bug #5986 (Resolved): mon: FAILED assert(snaps.count(s)) when removing pool snap on 0.61.7
Sage Weil
08:58 AM Bug #5985 (Pending Backport): very slow recovery for some objects
Sage Weil
06:41 AM Revision 81ddf1e8 (ceph): Merge pull request #505 from ceph/wip-post-file
ceph-post-file: single command to upload a file to cephdrop Sage Weil
05:34 AM Revision e625316d (ceph): kernel: fix sha1
6f8910eca47c3d00643c77fb8a166357637e55eb inadvertantly started
using the ceph sha1 for the kernel.
Signed-off-by: Sa...
Sage Weil
05:08 AM Revision 4fd34bef (ceph): mds: create only one ESubtreeMap during fs creation
Previously we would create an empty ESubtreeMap when we opened the log
segment and then immediately journal a second ...
Sage Weil
04:18 AM Revision 6bb7c625 (ceph): doc: quickstart: be more explicit that node == mon node
This appears to be one source of confusion for new users that leads to
a failure to form an initial mon quorum. See ...
Sage Weil
03:54 AM Bug #6043 (Won't Fix): upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
h3. Workaround
Using *restart* instead of *reload* restarts the daemons instead of sending them a signal that grac...
Zoltan Arnold Nagy
02:39 AM Revision e23b817a (ceph): v0.67.1
Gary Lowell
02:26 AM Revision bbf7c711 (ceph): radosgw-agent: adding debug logging
Signed-off-by: Joe Buck <jbbuck@gmail.com> Joe Buck
02:26 AM Revision 8a47230d (ceph): rename variables and log messages to be more clear
A few edits to make logging and variable names
more clear.
Signed-off-by: Joe Buck <jbbuck@gmail.com>
Joe Buck
02:26 AM Revision 7061e3c6 (ceph): rgw: fix domain root pool name assignment
Do not make the domain root pool the same
as the zone root pool. That causes sync issues.
Also, clarify a logging mes...
Joe Buck
02:26 AM Revision b883e338 (ceph): radosgw-admin: correct white space mistake
Signed-off-by: Joe Buck <jbbuck@gmail.com> Joe Buck
02:17 AM Revision c37faa8c (ceph): add multi-region tests
Signed-off-by: Joe Buck <jbbuck@gmail.com> Joe Buck
01:01 AM Revision 3cbf6a7b (ceph): rgw: drain requests before exiting
Fixes: #5953
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Yehuda Sadeh
12:59 AM Revision d08e05e4 (ceph): ceph-post-file: single command to upload a file to cephdrop
Use sftp to upload to a directory that only this user and ceph devs can
access.
Distribute an ssh key to connect to ...
Sage Weil
12:46 AM Revision c3e5090f (ceph): Add Rhel 6.4 and Centos 6.3 to ceph-deploy test suite.
Per issue #6014 and #6015.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
12:36 AM CephFS Bug #6004: osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(loff_t)length-opos)
the fix looks good Zheng Yan
12:31 AM Revision 50cc2efc (ceph): doc: Removed old mkcephfs references.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:28 AM Revision fa10c41d (ceph): doc: Removed mkcephfs references.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:27 AM Revision 31c1501a (ceph): doc: Updated script for dumpling.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:27 AM Revision 16f4bd51 (ceph): doc: Updated APT script for dumpling.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:26 AM Revision e97100db (ceph): doc: Removed mkcephfs references. Did a bit of clean-up work.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
12:10 AM Revision 7df9cf52 (ceph): Kernel value of - uses doesn't install kernel.
Using - as the kernel value (instead of what is usually 'testing'
will not add the kernel install tasks tot he yaml s...
Sandon Van Ness
12:05 AM Revision b007b330 (ceph): Merge pull request #509 from dmick/wip-rest-conf
config_opts: add two ceph-rest-api-only variables for convenience
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
12:00 AM Bug #6041 (Resolved): Failing to add 3rd monitor
After adding an additional (3rd) monitor, that new monitor will crash during first sync.
Ceph version: 0.64
201...
Bram Pieters

08/16/2013

11:42 PM Feature #5964 (Resolved): ceph-post-file (to replace/supplement cephdrop)
Sage Weil
11:40 PM Revision 211aadae (ceph): ReplicatedPG: add osd_recover_clone_overlap_limit to limit clones
We don't want to clone_range from clones too many times.
For now, just skip the cloning if there are too many holes.
...
Samuel Just
11:38 PM Revision 6f0a4982 (ceph): config_opts: add two ceph-rest-api-only variables for convenience
These aren't used by the C++ code at all, but in order for
rados_conf_get to find them, they need to be listed. They...
Dan Mick
11:35 PM Revision 967dc238 (ceph): Merge remote-tracking branch 'upstream/wip-zfs'
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
11:35 PM Feature #6036 (In Progress): cachepool: osd: add objecter
Sage Weil
03:17 PM Feature #6036 (Resolved): cachepool: osd: add objecter
Sage Weil
11:23 PM Revision a899b580 (ceph): Display error message when locking a vpm fails due to downburst errors.
When doing a lock-many, do not lock any of the vpms when downburst errors
occur. Made error messages more accurate,...
Warren Usui
10:48 PM Revision 6f8910ec (ceph): Merge pull request #42 from ceph/wip-arm5000-wusui
Fix ARM releases to be quantal armv7l releases. Zack Cerza
10:44 PM Revision 694cd670 (ceph): Fix ARM releases to be quantal armv7l releases.
Made grub execution conditional and not done when ARM.
Use ctx parameter to change machine type to tala.
Fix kernel a...
Warren Usui
10:08 PM CephFS Bug #4894 (Resolved): mds: standby shut itself down due to not having any data
Sage Weil
10:56 AM CephFS Bug #4894 (Fix Under Review): mds: standby shut itself down due to not having any data
wip-4894
saw this again in ubuntu@teuthology:/a/teuthology-2013-08-15_20:01:04-fs-cuttlefish-testing-basic-plana/1...
Sage Weil
10:03 PM rbd Bug #5955 (Need More Info): qemu deadlock when librbd caching enabled (writethru or writeback).
Sage Weil
10:01 PM Revision 47224f2d (ceph): Revert "Fix ARM releases to be quantal armv7l releases."
This reverts commit aabfabc34c101b5104d811eed0f57e262116ad4c. Warren Usui
09:47 PM Revision 666b2a48 (ceph): Merge pull request #40 from ceph/wip-teutharm-wusui
Wip teutharm wusui wusui
09:47 PM Revision 442a36c5 (ceph): Merge pull request #40 from ceph/wip-teutharm-wusui
Wip teutharm wusui wusui
09:39 PM Revision aabfabc3 (ceph): Fix ARM releases to be quantal armv7l releases.
Made grub execution conditional and not done when ARM.
Use ctx parameter to change machine type to tala.
Fix kernel a...
Warren Usui
09:09 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Diego Woitasen wrote:
> What do you think? https://github.com/ceph/ceph/pull/510
aha, i bet this is what is tripp...
Sage Weil
06:50 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
What do you think? https://github.com/ceph/ceph/pull/510 Diego Woitasen
05:55 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
I think the documentation is a little confusing. I had the same problems minutes ago I fixed it. In my escenario I ha... Diego Woitasen
05:43 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Michael Potter wrote:
> Getting the same thing on a fresh install of CentOS 6.4
>
> [...]
Can you post the out...
Sage Weil
03:42 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Getting the same thing on a fresh install of CentOS 6.4... Michael Potter
09:58 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
Hi,
I'm hitting the same bug on red hat 6.3 (Santiago), purging /var/lib/ceph and /etc/ceph doesn't help.
Bartlomiej Palmowski
09:26 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
bernhard: i think the problem in your case is that you have old keyrings in /etc/ceph from prior cluster instances. ... Sage Weil
06:59 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
... bernhard glomm
06:33 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
> runing ceph-create-keys manually gives:
>
> INFO:ceph-create-keys:ceph-mon is not in quorum: u'probing'
> repea...
bernhard glomm
09:03 PM Bug #6040: Significant slowdown of osds since v0.67 Dumpling
For completeness, the relevant part of "ceph.conf", the rest of which just defines a standard 3-node cluster, with mo... Oliver Daudey
06:20 PM Bug #6040: Significant slowdown of osds since v0.67 Dumpling
Kernel: SMP Debian 3.2.46-1~bpo60+1 x86_64 GNU/Linux on Debian Squeeze.
QEMU/KVM: 1:1.1.2+dfsg-2~bpo60+1, recompiled...
Oliver Daudey
06:10 PM Bug #6040 (Resolved): Significant slowdown of osds since v0.67 Dumpling
I'm running a Ceph-cluster with 3 nodes, each of which runs a mon, osd and mds. I'm using RBD on this cluster as sto... Oliver Daudey
08:51 PM Revision aee053c1 (ceph): mon: MonitorDBStore: output to derr instead of std::cout
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
06:43 PM Revision 6905b76a (ceph): Add yaml for rhel 6.4 in distros.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
06:07 PM Revision 37bf38f7 (ceph): Merge pull request #504 from ceph/wip-cls-hello
cls/hello: hello, world rados class
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Samuel Just <sam...
Sage Weil
06:02 PM rgw Bug #5953 (Pending Backport): rgw: drain requests when going down
Sage Weil
05:52 PM Revision 411871f6 (ceph): mon/OSDMonitor: make 'osd pool rmsnap ...' not racy/crashy
NOTE: This is a manual backport of d90683fdeda15b726dcf0a7cab7006c31e99f14.
Due to all kinds of collateral changes in...
Sage Weil
05:38 PM Revision a39e7f1b (ceph): Adding multi-region tests
Adding tests for ticket #5604 to test
user propagation via the radosgw-agent.
Signed-off-by: Joe Buck <jbbuck@gmail....
Joe Buck
05:23 PM rbd Bug #5220 (In Progress): test_ls_snaps segfaults on the arm test setup
hitting this again on dumpling but when tried with rbd old format. hence, reopening the bug... Tamilarasi muthamizhan
04:57 PM Revision 3eaa86ba (ceph): Merge pull request #38 from ceph/fix_nightlies
Use the json format for raw_cluster_status(). Sage Weil
04:24 PM Revision d74eefd9 (ceph): Use the json format for raw_cluster_status().
Zack Cerza
04:21 PM CephFS Bug #6004: osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(loff_t)length-opos)
Zheng Yan wrote:
> Sage Weil wrote:
> > looks like a read vs truncate race...
> > [...]
>
> looks like client r...
Sage Weil
04:09 PM Revision 2c9ac3e0 (ceph): Detect multi-region test cases
Enable multi-region calls and tests only if
the configuration has specified a
radosgw-agent tastk.
Signed-off-by: Jo...
Joe Buck
03:31 PM Feature #6000 (In Progress): EC: [link] erasure plugin mechanism and abstract API
Loïc Dachary
03:26 PM Feature #6038 (Resolved): cachepool: filestore/osd: infrastructure for large object COPY atomic r...
Sage Weil
03:24 PM Feature #6037 (Resolved): cachepool: osd: whiteout state
Sage Weil
03:17 PM Revision 6115d456 (ceph): Do more than just sleep and raise an exception.
Zack Cerza
03:13 PM devops Bug #6035 (Closed): ceph-deploy: ceph-create-keys stuck on fedora 18 VMs
logs: ubuntu@teuthology:/a/teuthology-2013-08-16_01:10:04-ceph-deploy-master-testing-basic-vps/109387... Tamilarasi muthamizhan
02:39 PM Subtask #5862: FileStore must work with ghobjects rather than hobjects

Use a "generation" number (gen_t?) instead of version_t.
Use a "shard" or "slice" number (shard_t or slice_t) i...
David Zafman
02:20 PM Feature #6033 (Resolved): cachepool: osd: basic io decision: read/write from/to cache pool or EAG...
Sage Weil
02:18 PM Feature #6032 (Resolved): cachepool: objecter: send requests to cache pool
Sage Weil
02:17 PM Feature #6029: cachepool: osd: separate object version from pg version
librados visible version seperate from PG version. There must also be an Objecter interface usable (in the future) f... Samuel Just
02:14 PM Feature #6029 (Resolved): cachepool: osd: separate object version from pg version
Sage Weil
02:17 PM Feature #6031 (Resolved): cachepool: osd: COPY from another pool; small objects only
Sage Weil
02:15 PM Feature #5703 (Duplicate): Allow ceph-deploy to work with non-root account
Duplicate of #3347 Neil Levine
02:15 PM Feature #6030 (Resolved): cachepool: osd: pg_pool_t cache_pool property
Sage Weil
02:08 PM Feature #5908 (Rejected): mon: formatted output sections should be consistent across services and...
Sage Weil
02:06 PM Feature #5904 (Resolved): hello world osd class (with explanatory documentation/comments!)
Sage Weil
02:04 PM Feature #6028 (Resolved): EC: [link] ensure that erasure coded pools don't work until the osds ca...
Samuel Just
02:02 PM Subtask #6027 (Resolved): ensure that erasure coded pools don't work until the osds can handle it
"work in progress":https://github.com/ceph/ceph/pull/941
Perhaps the OSDMap includes a lower bound set of feature ...
Samuel Just
01:37 PM devops Feature #5775: create qemu rbd package for rhel 6.5 - qemu-rbd
It's actually a symlink from /usr/lib64/qemu/librbd.so.1 to the librbd.so installed by the librbd package Josh Durgin
01:31 PM devops Feature #5775: create qemu rbd package for rhel 6.5 - qemu-rbd
depends on librbd
installs a symlink in /usr/lib/qemu to librbd.so installed by the librbd package
Sage Weil
01:26 PM devops Feature #5775: create qemu rbd package for rhel 6.5 - qemu-rbd
Sage Weil
01:28 PM rbd Cleanup #5757 (Resolved): remove any fiemap reference from rbd.cc
Sage Weil
01:25 PM rbd Feature #5774 (Resolved): test libvirt + qemu on rhel
Josh Durgin
01:22 PM rbd Feature #5774 (Need More Info): test libvirt + qemu on rhel
? Neil Levine
01:24 PM rgw Feature #2460 (Rejected): rgw: support multiple ceph backends
Sage Weil
01:23 PM rgw Cleanup #3154 (Rejected): rgw: configurable auid when creating pools
Sage Weil
01:20 PM devops Fix #5900: Create a Python package for ceph Python bindings
I've made all the bindings individual packages and updates `ceph-rest-api` script to use the right imports.
Instal...
Alfredo Deza
01:12 PM rgw Documentation #5669: Default site in Apache interferes with Gateway
This has been in the documentation for sometime.
http://ceph.com/docs/master/radosgw/config/#enable-the-configurati...
John Wilkins
01:09 PM Bug #6022: monitor crashed during ceph-deploy mon create on centos 6.4 and 6.3
... Tamilarasi muthamizhan
01:09 PM Bug #6022 (Resolved): monitor crashed during ceph-deploy mon create on centos 6.4 and 6.3
logs: ubuntu@teuthology:/a/teuthology-2013-08-16_01:10:04-ceph-deploy-master-testing-basic-vps/109409... Tamilarasi muthamizhan
01:07 PM rgw Feature #5605 (In Progress): rgw: teuthology tests to check bucket issues in multi region env
Ian Colle
11:59 AM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
Neil Levine
11:50 AM devops Feature #6017 (Resolved): ceph-deploy mon create: create on all mons in ceph.conf + then do gathe...
For mon status, use ... Sage Weil
11:59 AM devops Feature #6020: radosgw-apache opinionated package
Neil Levine
11:56 AM devops Feature #6020 (Rejected): radosgw-apache opinionated package
Sage Weil
11:54 AM devops Bug #6019 (Resolved): ceph-deploy needs to better detect yum/apt for bootstraping
ceph-deploy will fail horribly installing in CentOS because the EPEL repo does not exist.
It needs that because it...
Alfredo Deza
11:52 AM devops Feature #6018 (Resolved): Build ceph via jenkins
Set up a jenkins instance to build Ceph and push to repos.
- it should pull from a private repo, not github, so th...
Ian Colle
11:33 AM devops Feature #5845 (Rejected): Automate ceph-deploy push to ceph-extras.
Ian Colle
11:10 AM CephFS Documentation #5797 (Resolved): Document unstable nature of CephFS
Sage Weil
10:18 AM Fix #4635 (In Progress): mon: many ops expose uncommitted state
Sage Weil
10:10 AM Bug #6005 (Resolved): config stringification bug
Sage Weil
09:17 AM Bug #6005 (Resolved): config stringification bug
use of std::copy leaves separator at the end. fix in next, needs backport to dumpling Sage Weil
09:57 AM Bug #5981: osd: journal didn't preallocate
ext4, mounted with noatime,nodiratime,discard. Zoltan Arnold Nagy
09:39 AM Bug #5981 (Need More Info): osd: journal didn't preallocate
Sage Weil
09:39 AM Bug #5981: osd: journal didn't preallocate
strange, it is doing an fallocate on the jounral when it creates it, which should ensure there is sufficient disk spa... Sage Weil
03:59 AM Bug #5981: osd: journal didn't preallocate
Ok, the issue has been that the journal mountpoint has been filled, since it has been undersized.
Would it be poss...
Zoltan Arnold Nagy
09:40 AM Bug #5988: librados: synchronous IO generally returns on ack instead of commit
Sage Weil
09:37 AM Bug #5979: librados: imposes internal tooling expectations on users
on second thought, i think we should just drop the mention of the -m and just say 'no monitors specified' or somethin... Sage Weil
05:20 AM Revision b59f930a (ceph): osdc/ObjectCacher: match reads with their original rx buffers
Consider a sequence like:
1- start read on 100~200
100~200 state rx
2- truncate to 200
100~100 state...
Sage Weil
05:20 AM Revision 1c50c446 (ceph): osdc/ObjectCacher: do not merge rx buffers
We do not try to merge rx buffers currently. Make that explicit and
documented in the code that it is not supported....
Sage Weil
02:00 AM Revision 4a47eedc (ceph): Fixing assumed typo.
Assuming this has to be a typo but its breaking the ceph-deploy
task.
Signed-off-by: Sandon Van Ness <sandon@inktank...
Sandon Van Ness
01:32 AM Revision 067d5756 (ceph): Merge branch 'wip-5848-coll'
Reviewed-by: Sage Weil <sage@inktank.com> David Zafman
01:29 AM Revision 93d8be22 (ceph): osd: Add perf tracking for all states in RecoveryState
Fixes: #5848
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
12:49 AM devops Feature #5847 (Resolved): Build own versions of most recent leveldb for all supported platforms.
Latest leveldb has been added to ceph-extras repo. Anonymous
12:29 AM Bug #5492: scripts installing into /usr/usr/sbin (with --prefix=/usr)
Gary Lowell wrote:
> Thanks Danny. I tested $(exec_prefix)$(sbindir) on rpm and debian builds and it looks like do...
Yixun Lan
12:21 AM Revision f61698d5 (ceph): cls_rbd: remove old assign_bid method
This method is problematic because it both writes/mutates and returns data,
which means that an untimely client disco...
Sage Weil
12:21 AM Revision 359850b9 (ceph): osd: enforce RD, WR flags for class methods
Class methods are marked with RD and WR to help the OSD decide when we need
to flush objects or require certain permi...
Sage Weil
12:21 AM Revision 895d531c (ceph): cls/hello: hello, world rados class
Simple example of a rados class doing read, write, and read/modify/write
methods.
Signed-off-by: Sage Weil <sage@ink...
Sage Weil
12:21 AM Revision 681436ad (ceph): common/Preforker: shut up warning
common/Preforker.h: In member function 'void Preforker::daemonize()':
common/Preforker.h:97:40: warning: ignoring ret...
Sage Weil
12:21 AM Revision 610dc016 (ceph): osd: do not return data payload for successful writes
We were somewhat inadvertantly returning a data payload for write
operations. This was a side-effect of the OpContex...
Sage Weil
12:21 AM Revision 93ac92d8 (ceph): librbd: remove mostly-useless assign_bid helper
Do it inline.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
12:21 AM Revision 913a205c (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
12:14 AM Revision 1aa01910 (ceph): ceph.in: --admin-daemon was not returning EINVAL on bad command
Fix by restructuring code to hoist common code and have only one
place where admin_socket is actually called.
Signed...
Dan Mick
12:14 AM Revision 56e54cc4 (ceph): Merge pull request #506 from dmick/wip-admin-daemon
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
12:10 AM Revision 266460e9 (ceph): ceph.in: --admin-daemon was not returning EINVAL on bad command
Fix by restructuring code to hoist common code and have only one
place where admin_socket is actually called.
Signed...
Dan Mick

08/15/2013

11:13 PM CephFS Bug #6004: osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(loff_t)length-opos)
Sage Weil wrote:
> looks like a read vs truncate race...
> [...]
looks like client releases Fr cap too early or ...
Zheng Yan
10:24 PM CephFS Bug #6004 (Fix Under Review): osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(lof...
Sage Weil
09:28 PM CephFS Bug #6004: osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(loff_t)length-opos)
looks like a read vs truncate race...... Sage Weil
09:20 PM CephFS Bug #6004 (Resolved): osdc/ObjectCacher.cc: 738: FAILED assert(bh->length() <= start+(loff_t)leng...
... Sage Weil
10:54 PM Revision 3f0afe16 (ceph): Merge pull request #507 from ceph/wip-4635.master
Bunch of tidying up on monitor services & fix #4635
Reviewed-by: Sage Weil <sage@inktank.com>
João Eduardo Luís
10:53 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
hit this again,... Sage Weil
10:52 PM Revision 249c7f27 (ceph): vstart.sh: s/osd crush set/osd crush add/ as it's supposed to be
'osd crush set' should only be used to update already existing items on
the map whereas 'osd crush add' should be abl...
Joao Eduardo Luis
10:52 PM Revision 12b012af (ceph): PendingReleaseNotes: reflect 'osd crush set' behavior change
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
10:52 PM Revision 995a3162 (ceph): mon: OSDMonitor: document 'prepare_command' wrt expected behavior of no...
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
10:52 PM Revision 9c624fb9 (ceph): mon: OSDMonitor: don't expose uncommitted state on 'osd crush add/set'
Fixes: #4635
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis
10:52 PM Revision 88464a6d (ceph): mon: OSDMonitor: don't expose uncommitted state on 'osd crush link'
Fixes: #4635
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil
10:52 PM Revision 97c3a9a5 (ceph): mon: clarify 'osd crush add' vs 'osd crush set'
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil
10:52 PM Revision ed6233e5 (ceph): mon/MonCap: remove useless 'osd crush add' perm from profile bootstrap-osd
Bootstrap doesn't use or need this; the crush update happens when the osd
starts up (see init-ceph or upstart/ceph-os...
Sage Weil
10:32 PM Revision cf189cf9 (ceph): mon: AuthMonitor: remove dead code
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
10:32 PM Revision 737fe1fc (ceph): mon: AuthMonitor: fix whitespaces
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
10:32 PM Revision 0380475b (ceph): mon: AuthMonitor: fix some >80 columns debug strings
Give AuthMonitor a new look. She sure deserves it.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis
09:38 PM Revision d290a915 (ceph): mon: use str_join instead of std::copy
The std::copy method leaves a trailing separator.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick ...
Sage Weil
09:38 PM Revision b9992174 (ceph): config: fix stringification of config values
The std::copy construct leaves a trailing separator character, which breaks
parsing for booleans (among other things)...
Sage Weil
09:38 PM Revision d212bba6 (ceph): common: add str_join helper
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit c...
Sage Weil
09:37 PM Revision 35565ee6 (ceph): mon: use str_join instead of std::copy
The std::copy method leaves a trailing separator.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick ...
Sage Weil
09:36 PM Revision fc23cfe3 (ceph): config: fix stringification of config values
The std::copy construct leaves a trailing separator character, which breaks
parsing for booleans (among other things)...
Sage Weil
09:36 PM Revision ce3a0944 (ceph): common: add str_join helper
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil
09:18 PM CephFS Bug #5927: kcephfs: ENOTEMPTY on rm -r
Sage Weil
09:14 PM Bug #6003 (Resolved): journal Unable to read past sequence 406 ...
* fix : commit:bae1f3eaa09c4747b8bfc6fb5dc673aa6989b695... Sage Weil
09:11 PM Revision e7836e6e (ceph): mon/PGMap: fix typo
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision 3ba4dc31 (ceph): Revert "config: fix stringification of config values"
This reverts commit fefe0c602f78e66d35fd5806da4c2e4e154a267c.
I have a cleaner cleanup.
Sage Weil
08:45 PM Revision ba8f1698 (ceph): Merge pull request #501 from liewegas/wip-5906
gussy up ceph -s
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
08:42 PM Revision fefe0c60 (ceph): config: fix stringification of config values
The std::copy construct leaves a trailing separator character, which breaks
parsing for booleans (among other things)...
Sage Weil
08:39 PM Revision 5b2828dc (ceph): Merge pull request #502 from ceph/wip-mon-log-level
mon: mon_cluster_log_file_level
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
07:25 PM Feature #6002 (Resolved): EC: [link] erasure coding library plugin API documentation, including a...
Samuel Just
07:24 PM Feature #6001 (Resolved): EC: [link] jerasure plugin
Samuel Just
07:23 PM Feature #6000 (Resolved): EC: [link] erasure plugin mechanism and abstract API
Samuel Just
07:22 PM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
Samuel Just
07:21 PM Feature #5998 (Resolved): EC: [link] FileStore must work with ghobjects rather than hobjects
Samuel Just
07:20 PM Feature #5997 (Resolved): EC: [link] Refactor scrub to use PGBackend methods
Samuel Just
07:19 PM Feature #5996 (Resolved): EC: [link] PG::calc_acting and friends should always choose the shortes...
Samuel Just
07:18 PM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
Samuel Just
07:17 PM Feature #5994 (Resolved): EC: [link] Backfill should be able to handle multiple backfill peers
Samuel Just
07:13 PM Feature #5993 (Resolved): EC: [link] Refactor recovery to use PGBackend methods
Samuel Just
07:12 PM Feature #5992 (Resolved): EC: [link] Refactor Backfill to use PGBackend methods
Samuel Just
07:12 PM Feature #5991 (Resolved): EC: [link] Backfill peers should not be included in the acting set
Samuel Just
07:11 PM Feature #5990 (Resolved): EC: [link] Factor out the ReplciatedPG object replication and client wr...
Samuel Just
07:09 PM Subtask #5433: Factor out the ReplicatedPG object replication and client IO logic as a PGBackend ...
Samuel Just
07:09 PM Subtask #5046 (Resolved): Factor out PG logs, PG missing
Samuel Just
07:01 PM Revision 9f1ad4db (ceph): Document unstable nature of CephFS
- Add note to docs indicating that CephFS is not recommended for
production datasets.
- Add note to docs indicating...
Scott Devoid
06:35 PM Tasks #5848 (Resolved): add perf counter for each RecoveryMachine state
David Zafman
01:57 PM Tasks #5848 (Fix Under Review): add perf counter for each RecoveryMachine state
David Zafman
10:45 AM Tasks #5848 (In Progress): add perf counter for each RecoveryMachine state
David Zafman
06:29 PM Revision 50698d18 (ceph): librados: fix async aio completion wakeup
For aio flush, we register a wait on the most recent write. The write
completion code, however, was *only* waking th...
Sage Weil
06:29 PM Revision ef731dfc (ceph): librados: fix locking for AioCompletionImpl refcounting
Add an already-locked helper so that C_Aio{Safe,Complete} can
increment the reference count when their caller holds t...
Josh Durgin
06:01 PM Revision ea79bb29 (ceph): Merge pull request #496 from ceph/wip-monstore-copy
tools: ceph-monstore-tool: copy a store's contents to another store Sage Weil
05:52 PM Revision 893331be (ceph): Merge pull request #490 from dachary/master
ant is missing from the list of packages to install Sage Weil
05:50 PM Revision 4a437b84 (ceph): Merge pull request #396 from hutkev/wip-wireshark-alt
Adding alternative Wireshark dissector.
Signed-off-by: Kevin Jones <k.j.jonez@gmail.com>
Sage Weil
05:46 PM Revision ab60b5da (ceph): Merge pull request #499 from dachary/wip-test_osd_types
remove racy test assertions Sage Weil
05:45 PM Feature #5964 (Fix Under Review): ceph-post-file (to replace/supplement cephdrop)
Sage Weil
01:45 PM Feature #5964 (In Progress): ceph-post-file (to replace/supplement cephdrop)
Sage Weil
05:44 PM Feature #5904 (Fix Under Review): hello world osd class (with explanatory documentation/comments!)
Sage Weil
05:42 PM Revision 17667301 (ceph): Don't raise an exception if apt-key list fails
Zack Cerza
05:27 PM Bug #5973 (Resolved): ceph --admin-daemon return code broken
Sage Weil
05:24 PM Revision 83dd1c8b (ceph): Passwordless sudo, not passphraseless sudo.
Zack Cerza
04:51 PM Feature #5905 (Fix Under Review): hello world librados program (with explanatory comments!)
wip-5905 and pull request https://github.com/ceph/ceph/pull/508 Greg Farnum
01:46 PM Feature #5905 (In Progress): hello world librados program (with explanatory comments!)
Sage Weil
04:48 PM Revision a25d73ef (ceph): store: Abstract the underlying filesystem functionality
This patch defines class FileStoreBackend, and use it to abstracts
filesystem's functionalities.
Fiemap() and syncfs...
Yan, Zheng
04:48 PM Revision 5a153698 (ceph): store: Add (experimental) ZFS parallel journal support
This patch adds ZFS parallel journal support. It uses libzfs provided by
zfsonlinux to access ZFS' functionalities. T...
Yan, Zheng
04:48 PM Revision 3d7a9495 (ceph): Renamed filestore_backend test
Renamed filestore_backend to testfilestore_backend in
order to resolve compilation time issue.
Signed-off-by: Joe Bu...
Joe Buck
04:36 PM Fix #5989 (Resolved): librados: document that bufferlist usage model is inconsistent
I discussed this on irc and it's not clear if we want to provide any guarantees or not, but it's certainly unpleasant... Greg Farnum
04:33 PM Bug #5988 (Resolved): librados: synchronous IO generally returns on ack instead of commit
This is not defaulting to data safety, and the synchronous functions don't provide any interface for doing something ... Greg Farnum
04:32 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
This has just happened to me, so log with 'debug mon = 20' and 'debug ms = 1' and 'debug monc = 20' is attached.
...
Rob Taylor
12:32 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
So after reinstalling the server, this went away. Next time I run into this, I'll update. Zoltan Arnold Nagy
04:13 PM Feature #5909 (In Progress): mon: keep track of monitor store size estimate vs 'du $mon_data'
Joao Eduardo Luis
04:10 PM Fix #4635: mon: many ops expose uncommitted state
We've fixed a couple of cases on the OSDMonitor and merged them into master. I'll keep this open for a while longer ... Joao Eduardo Luis
04:05 PM Bug #5959 (Pending Backport): Quorum is crashing on 'osd pool mksnap'
I'm pretty sure this is fixed by d1501938f5d07c067d908501fc5cfe3c857d7281 on next. Joao Eduardo Luis
03:21 PM Bug #5959 (In Progress): Quorum is crashing on 'osd pool mksnap'
I haven't been able to reproduce this either on 0.61.7 or -earlier- *latest* versions.
I was however able to trigg...
Joao Eduardo Luis
04:03 PM Bug #5986 (Pending Backport): mon: FAILED assert(snaps.count(s)) when removing pool snap on 0.61.7
Well, duh.
This was fixed by Sage (and reviewed by me) on d90683fdeda15b726dcf0a7cab7006c31e99f146
Joao Eduardo Luis
03:37 PM Bug #5986: mon: FAILED assert(snaps.count(s)) when removing pool snap on 0.61.7
I can now confirm this is also really easy to trigger on cuttlefish HEAD. Joao Eduardo Luis
03:20 PM Bug #5986 (Resolved): mon: FAILED assert(snaps.count(s)) when removing pool snap on 0.61.7
While attempting to reproduce #5959, I managed to trigger this crash. It doesn't trigger on next, but I'm able to tr... Joao Eduardo Luis
03:58 PM Revision c17a18ef (ceph): Don't assume the ubuntu user when getting the test dir.
Zack Cerza
03:53 PM Documentation #5987 (Resolved): document requirement for monitor host time sync
We used to say words about keeping monitor hosts in timesync with NTP or the like, but I can no longer find any menti... Dan Mick
03:17 PM Revision 3afc7d9b (ceph): If get_testdir_base() exists, might as well use it...
Zack Cerza
03:14 PM Bug #5985 (Resolved): very slow recovery for some objects
The snap cloning recovery logic can cause a push transaction to generate dozens of tiny writes followed by dozens of ... Samuel Just
03:11 PM Bug #5951: osd: next: EEXIST on mkcoll
2 failures in previous set, 1 mon clock, 1 stuck wait_backfill. Didn't have logging. D'oh. Rerunning.
~/teuthol...
Samuel Just
03:10 PM Revision 93afb59b (ceph): Merge pull request #36 from ceph/wip-3791
Continue to make teuthology easier to use for the first time Alfredo Deza
02:57 PM Revision f41436ab (ceph): Tweak regex to work for non-FQDN hostnames
Zack Cerza
02:34 PM Revision 54ed1d16 (ceph): Note that target hostnames must be resolvable.
Zack Cerza
02:32 PM rgw Feature #5611: rgw: swift GET request for object with custom metadata should show custom metadata
Neil Levine
01:53 PM Revision 7e37c5f6 (ceph): Merge pull request #35 from ceph/logging
Default log level to INFO; Fix some instances where print is being used instead of log Alfredo Deza
01:49 PM Revision 5746efbb (ceph): Fix some instances where print is being used instead of log
Zack Cerza
01:49 PM Revision 09b01b27 (ceph): Fix some instances where print is being used instead of log
Zack Cerza
01:45 PM Feature #5906 (Resolved): mon: better ceph -s output
Sage Weil
01:29 PM Feature #5984 (Resolved): mon: probe monitors to check on their status regardless of quorum
This could be used to figure out if a monitor is up, and if it is what's its excuse for not being in the quorum.
W...
Joao Eduardo Luis
01:29 PM Revision ab2d2fad (ceph): Default to log level INFO.
Zack Cerza
01:09 PM Bug #5982 (Rejected): injectargs seems to be broken for bools
Sage Weil
01:08 PM Bug #5982: injectargs seems to be broken for bools
Stefan Priebe wrote:
> at least to me this doesn't change anything:
> ceph osd tell \* injectargs -- "--osd_recover...
Sage Weil
12:51 PM Bug #5982: injectargs seems to be broken for bools
at least to me this doesn't change anything:
ceph osd tell \* injectargs -- "--osd_recover_clone_overlap false"
ok
...
Stefan Priebe
12:49 PM Bug #5982: injectargs seems to be broken for bools
you need a -- to make the cli stop parsing the option. or a space in there.
ceph tell osd.0 injectargs -- --some-...
Sage Weil
12:33 PM Bug #5982: injectargs seems to be broken for bools
also for admin socket Samuel Just
12:30 PM Bug #5982 (Rejected): injectargs seems to be broken for bools
ceph2/src [wip-5910] » ./ceph tell osd.\* injectargs '--osd_recover_clone_overlap=false'
*** DEVELOPER MODE: setting...
Samuel Just
12:22 PM Bug #5981: osd: journal didn't preallocate
Oh, I forgot. This is on Ubuntu 13.04, with the following packages:
zoltan@signina:~$ dpkg -l | grep 0.61.
ii ce...
Zoltan Arnold Nagy
12:16 PM Bug #5981 (Resolved): osd: journal didn't preallocate
I had a node deployed using ceph-deploy. 7 disks in total, the journals are
on files on an SSD.
After rebooting t...
Zoltan Arnold Nagy
11:33 AM rgw Bug #5192: RGW: radosgw-admin user rm --access-key not working on bobtail
Further updates on this issue have come in from the customer, details can be found here: https://inktank.zendesk.com/... JuanJose Galvez
10:42 AM Bug #5979 (Resolved): librados: imposes internal tooling expectations on users
... Greg Farnum
10:18 AM Feature #5978 (Rejected): ceph.conf: create hierarchy
Currently we have semi-flat hierarchy. We have global section, section per entity type and section per entity. The va... Yehuda Sadeh
10:10 AM rbd Bug #5977 (Resolved): librbd: python bindings need docstrings to show up in online docs
Some methods don't have docstrings, which means they don't show up in http://ceph.com/docs/master/rbd/librbdpy/ at al... Josh Durgin
09:36 AM Bug #5972: Permissions on /var/run/ceph changed causing permission error messages
this is teuthology? it does the 777 on /var/run/ceph so that we can use the asok for non-root processes. normal ins... Sage Weil
08:00 AM devops Bug #5895 (Resolved): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish bran...
Alfredo Deza
07:48 AM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
Opened #5975; merged https://github.com/ceph/ceph-deploy/pull/44 Zack Cerza
07:41 AM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
I'll merge this pull request but I really want a ticket to stay open reminding us that this needs to be *fixed* and n... Zack Cerza
07:38 AM devops Bug #5895 (Fix Under Review): ceph-deploy: mon create command hung on ceph-create-keys in cuttlef...
I have opened a new pull request with some tested changes that fix this problem: https://github.com/ceph/ceph-deploy/... Alfredo Deza
05:34 AM devops Bug #5895 (In Progress): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish b...
Alfredo Deza
07:46 AM devops Bug #5975 (Resolved): Find a real fix for the pushy issue of hanging/deadlocking during long-runn...
Issue #5895 caused us to have to implement a really disappointing workaround to deal with a pushy problem: https://gi... Zack Cerza
05:50 AM Revision 24ec3201 (ceph): Ceph-qa: change the fsx.sh to support hole punching test
This patch change the fsx.sh to pull better fsx.c from xfstests site
to support hole punching test.
Signed-off-by: Y...
Li Wang
05:34 AM devops Bug #5971 (Duplicate): ceph-deploy: ceph-create-keys hung during mon create in dumpling release o...
Alfredo Deza
04:37 AM Revision a8965a6a (ceph): rados/monthash: fix 5925 yaml
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:16 AM devops Bug #5947 (Resolved): ceph-deploy RPM release is pointing to the wrong repo
ceph-deploy-release packages have been rebuilt to point to http://ceph.com/packages/ceph-extras/rpm/${dist}/noarch
T...
Anonymous
12:05 AM Revision 5ac68dc1 (ceph): added upgrade-dumpling suite to test point releases for dumpling
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan

08/14/2013

11:53 PM Revision 086abe44 (ceph): doc: Fixed typo.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
11:11 PM Revision dd0df583 (ceph): rados.py: fix Rados() backwards compatibility
Previously it had no name parameter, so the default will be used by
old clients. However, if an old client set rados_...
Josh Durgin
11:11 PM Revision a99fef91 (ceph): rados.py: fix Rados() unicode checking
Check new parameters and check that rados_id is not None again to
catch the empty string.
Signed-off-by: Josh Durgin...
Josh Durgin
11:07 PM Revision 4422f21a (ceph): rados.py: fix Rados() unicode checking
Check new parameters and check that rados_id is not None again to
catch the empty string.
Signed-off-by: Josh Durgin...
Josh Durgin
11:07 PM Revision 34da9cbc (ceph): rados.py: fix Rados() backwards compatibility
Previously it had no name parameter, so the default will be used by
old clients. However, if an old client set rados_...
Josh Durgin
10:53 PM Revision 3e2a269e (ceph): added workunit: branch:dumpling wherever applicable
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
10:50 PM Revision 2cfcb77c (ceph): mon/PGMap: degraded what?
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:50 PM Revision 49ddecda (ceph): mon: status: client io, recovery io prefixes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:47 PM Revision 48a3393e (ceph): upgrade from cuttlefish to next and dumpling to next
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
10:34 PM Linux kernel client Bug #5429: libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
hit this again, ubuntu@teuthology:/a/teuthology-2013-08-14_01:01:26-kcephfs-next-testing-basic-plana/106215
it was...
Sage Weil
10:34 PM Revision df17d021 (ceph): Merge pull request #500 from ceph/wip-5910
Resolves #5910.
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
10:31 PM Revision 94c3f29a (ceph): OSDMonitor: add 'osd perf' command to dump recent osd perf information
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:19 PM Bug #5973 (Resolved): ceph --admin-daemon return code broken
'ceph daemon path bad' returns error
'ceph --admin-daemon path bad' does not
see wip
Sage Weil
10:07 PM Revision bf525445 (ceph): upgrade cuttlefish to dumpling, instead of next in upgrade-fs suite
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
09:22 PM Revision ebde89d5 (ceph): ObjectStore: add ObjectStore::get_cur_stats and impl in FileStore
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:42 PM Revision 2813c33b (ceph): renamed the folders and files appropriately
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
08:32 PM Revision 058fab0d (ceph): replace cuttlefish with dumpling in upgrade suites
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
08:15 PM Revision 6c699cbc (ceph): modified upgrade tasks to run from cuttlefish to dumpling, dumpling to ...
and bobtail to dumpling
Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
Tamilarasi muthamizhan
08:15 PM Revision e1dca285 (ceph): Merge pull request #34 from ceph/wip-3791
Don't bail if ~/.teuthology.yaml doesn't exist. Alfredo Deza
07:48 PM Revision 63b64e29 (ceph): Don't bail if ~/.teuthology.yaml doesn't exist.
Zack Cerza
07:48 PM Bug #5922: osd: unfound objects on next
in this case acting set was [5,3], marking 0 down caused it to finish recovery. Samuel Just
07:47 PM Bug #5922: osd: unfound objects on next
"last_epoch_started": 145},
"recovery_state": [
{ "name": "Started\/Primary\/Active",
"e...
Samuel Just
06:23 PM Bug #5922: osd: unfound objects on next
ubuntu@plana31:~$ sudo ceph pg dump | grep recovering
dumped all in format plain
0.22 187 37 82 37...
Samuel Just
07:46 PM Revision ebf476d3 (ceph): Obligatory automatic vim whitespace cleanup commit
Zack Cerza
07:08 PM Bug #5972 (Won't Fix): Permissions on /var/run/ceph changed causing permission error messages
ubuntu@mira044:~$ cat /etc/issue
Ubuntu 12.04.2 LTS \n \l
ubuntu@mira044:~$ ls -ld /var/run/ceph
drwxrwxrwx 2 ro...
David Zafman
06:19 PM Bug #5951: osd: next: EEXIST on mkcoll
failed due to github:
~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-5951-1" -n 50 --ow...
Samuel Just
05:31 PM Revision 2c887578 (ceph): Revert "Display error message when locking a vpm fails due to downburst...
This reverts commit 4681b35016619ece44730a368070220e6c2e56a3. Warren Usui
05:30 PM Bug #5958: os/DBObjectMap.cc: 393: FAILED assert(!valid || cur_iter->valid())
Uploaded osd7_omap_bug5958.tar.bz2 to cephdrop as reuqested, it's a tar of the current/omap directory of osd.7 that k... Eric Renfro
05:21 PM devops Bug #5895 (Duplicate): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish bra...
Tamilarasi muthamizhan
03:01 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
The only way I see around this (other than pushy fixing this problem) is to avoid capturing the stdout/stderr of the ... Alfredo Deza
01:41 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
I opened a bug in Pushy: https://github.com/axw/pushy/issues/45
Still investigating and trying all kinds of things...
Alfredo Deza
12:56 PM devops Bug #5895 (In Progress): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish b...
hitting this issue now on centos 6.4 - burnupi05, burnupi21.
Alfredo is already on it.
Tamilarasi muthamizhan
05:19 PM devops Bug #5971 (Duplicate): ceph-deploy: ceph-create-keys hung during mon create in dumpling release o...
An user from the community [ishkabob] have been reporting this problem on IRC and i tried reproducing this locally, i... Tamilarasi muthamizhan
05:16 PM Revision 6230623c (ceph): Merge pull request #32 from ceph/wip-fix5957-wusui
Display error message when locking a vpm fails due to downburst errors. wusui
04:54 PM Revision b9d1bf51 (ceph): librados: fix async aio completion wakeup
For aio flush, we register a wait on the most recent write. The write
completion code, however, was *only* waking th...
Sage Weil
04:54 PM Revision 29ae033b (ceph): librados: fix locking for AioCompletionImpl refcounting
Add an already-locked helper so that C_Aio{Safe,Complete} can
increment the reference count when their caller holds t...
Josh Durgin
04:51 PM Revision 16ed0b9a (ceph): librados: fix async aio completion wakeup
For aio flush, we register a wait on the most recent write. The write
completion code, however, was *only* waking th...
Sage Weil
04:50 PM Revision 7a52e2ff (ceph): librados: fix locking for AioCompletionImpl refcounting
Add an already-locked helper so that C_Aio{Safe,Complete} can
increment the reference count when their caller holds t...
Josh Durgin
04:40 PM Revision 4681b350 (ceph): Display error message when locking a vpm fails due to downburst errors.
When doing a lock-many, do not lock any of the vpms when downburst errors
occur. Do not display message on unlock w...
Warren Usui
04:36 PM Revision 9b947e27 (ceph): Merge pull request #31 from ceph/wip-5941
Instructions for installing teuthology on non-debian-based OSs Zack Cerza
04:36 PM Revision 6bc8fcd0 (ceph): add link to homebrew
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
04:27 PM Bug #5970 (Resolved): librados: python bindings Rados() backwards compatiblity issue with 0.67.0
commit:34da9cbc33205623cf64aee1989f53dfb2c5bddd in next and commit:dd0df583e2661444287a36acc240a8ac0ec381e8 in dumpling Josh Durgin
03:53 PM Bug #5970 (Resolved): librados: python bindings Rados() backwards compatiblity issue with 0.67.0
As described on ceph-users:... Josh Durgin
04:07 PM Revision aa464e29 (ceph): add generic instructions for installation
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
04:01 PM Revision 3e9cf895 (ceph): create instructions to install on OSX
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
04:01 PM Revision 8c5b5efc (ceph): sort the requirements
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
04:00 PM Revision 18ea0239 (ceph): remove install_requires from setup.py
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
03:48 PM devops Feature #5523 (Resolved): libcurl 7.28+ packages
Anonymous
03:47 PM devops Bug #5947 (In Progress): ceph-deploy RPM release is pointing to the wrong repo
Anonymous
03:46 PM devops Bug #5960 (Resolved): Missing deb packages for ceph-deploy 1.2
First push only picked up the sources for some reason. I reran reprepro and confirmed that debs where included this ... Anonymous
05:58 AM devops Bug #5960 (Resolved): Missing deb packages for ceph-deploy 1.2
There are currently no ceph-deploy 1.2 deb packages in the repo http://ceph.com/packages/ceph-extras/debian/pool/main... Alfredo Deza
03:40 PM Feature #5907: permanently log all administrative actions
I choose to interpret this as follows:
1) effectful mon commands should end up in the central log
2) the osd should...
Samuel Just
03:38 PM Revision d95a6c17 (ceph): Merge pull request #29 from ceph/wip-4264
update to reflect required install task Alfredo Deza
03:35 PM Feature #5910 (Resolved): osd: report filestore op latency (apply and commit) to monitor
df17d021a6b517588d04cda7430ac11b2a83ef9a Samuel Just
02:59 PM Revision 4f31756c (ceph): doc: Added dumpling to RPM installation.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
02:58 PM Revision d38a041f (ceph): doc: Minor tweaks to debian install.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
02:58 PM Revision 456a394c (ceph): doc: Added dumpling installation for Debian/Ubuntu.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
02:37 PM rbd Feature #4550 (Resolved): Create Qemu+RBD rpm package for RHEL+CentOS 6.3 on ceph.com
Ian Colle
02:36 PM rbd Feature #4013: rbd: openstack: extend nova boot api to support going from image to volume
Ian Colle
02:36 PM rbd Feature #4017: rbd: openstack: simplify volume booting with new api
Ian Colle
02:04 PM devops Documentation #5968 (Resolved): typo in monmap
In the following page http://ceph.com/docs/master/man/8/monmaptool/, there is a typo for monmap, it is instead mentio... Tamilarasi muthamizhan
01:40 PM devops Bug #5962 (Resolved): ceph-deploy: install should default to dumpling and not cuttlefish
Merged to ceph-deploy master with hash: c9fa0912dfc75660bc3e207f9918d3f95464d71c Alfredo Deza
11:52 AM devops Bug #5962 (Fix Under Review): ceph-deploy: install should default to dumpling and not cuttlefish
Opened pull request: https://github.com/ceph/ceph-deploy/pull/43 Alfredo Deza
11:02 AM devops Bug #5962 (Resolved): ceph-deploy: install should default to dumpling and not cuttlefish
ceph-deploy install should now default to picking dumpling, instead of cuttlefish.
I tested this on ubuntu and it ...
Tamilarasi muthamizhan
01:22 PM Bug #5967 (Resolved): monitor caps parser should accept '.' as a legal unquoted character
caps mention 'entities' (type.id) a lot, and to have to quote that is annoying and unnecessary; if the parser accepte... Dan Mick
01:13 PM Revision dfd58548 (ceph): remove racy test assertions
Do not assert before the loop waiting for the thread to complete the
expected side effect. The whole point of the loo...
Loïc Dachary
11:08 AM Feature #5964 (Resolved): ceph-post-file (to replace/supplement cephdrop)
Sage Weil
11:04 AM Bug #5963 (Won't Fix): ceph pg dump {,sum,pgs,pgs_brief} is all the same for format=plain
20:56 < paravoid> "ceph pg dump pgs_brief" seems to be the same as "ceph pg dump" to me
20:57 < paravoid> same as "c...
Faidon Liambotis
11:03 AM Feature #5905: hello world librados program (with explanatory comments!)
Sam's asked that this include omap and xattr ops, so it needs to demonstrate some semi-advanced uses of librados, not... Greg Farnum
10:23 AM Bug #5226: Some PG stay in "incomplete" state
For the record : today I replaced all OSD by new models, and it fix the problem : it seems that incomplete data were ... Olivier Bonvalet
09:49 AM rbd Bug #5919 (Pending Backport): qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O lea...
Oliver Francke wrote:
> Hi Josh, Sage,
>
> it looks very good right now, could not get it to break, even with 4 m...
Sage Weil
04:19 AM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
Hi Josh, Sage,
it looks very good right now, could not get it to break, even with 4 more VM's producing I/O, deep-...
Oliver Francke
09:39 AM Feature #5904 (In Progress): hello world osd class (with explanatory documentation/comments!)
Sage Weil
09:30 AM Bug #5920: mon daemon crashes
Dmitry Panov wrote:
> Hi Sage!
>
> I've cleaned up everything and have re-created the cluster. This time I replac...
Sage Weil
01:27 AM Bug #5920: mon daemon crashes
Hi Sage!
I've cleaned up everything and have re-created the cluster. This time I replaced node sn2 by node sn4.
...
Dmitry Panov
07:09 AM Subtask #5878 (In Progress): erasure plugin mechanism and abstract API
Loïc Dachary
07:09 AM Subtask #5877 (In Progress): Plugable erasure code library
Loïc Dachary
06:18 AM Bug #5959: Quorum is crashing on 'osd pool mksnap'
s/entire pool/entire quorum/g in prev comment Andrey Korolyov
06:17 AM Bug #5959: Quorum is crashing on 'osd pool mksnap'
There is some update:
- if pool contains volumes with their own snapshots, it`s more likely for entire pool to die...
Andrey Korolyov
04:09 AM Bug #5959 (Resolved): Quorum is crashing on 'osd pool mksnap'
Full backtrace is attached. Crashed mons running 0.61.7,
ceph osd pool mksnap --keyfile admin dev-rack0 snap2
201...
Andrey Korolyov
05:59 AM Subtask #5527 (Resolved): unit tests for common/sharedptr_registry.hpp
Loïc Dachary
04:28 AM Revision 90ccd267 (ceph): qa/workunits/fs/multiclient_sync_read_eof.py
Simple test to verify clients behave at EOF.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:59 AM Revision 8ff69011 (ceph): Merge branch 'next'
Gary Lowell
12:37 AM Revision 95f3353a (ceph): osd_types: add osd_perf_stat_t type
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:28 AM Revision d1a81654 (ceph): client: add enclosing object for asok dumps
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:17 AM Revision 0c236337 (ceph): pybind/ceph_argparse: GPL -> LGPL2
Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Dan Mick <dan.mick@inktank.com>
both consented to this change via email.
Si...
Sage Weil
12:16 AM Revision 2206f557 (ceph): rbd.cc: relicense as LGPL2
All past authors for rbd.cc have consented to relicensing from GPL to
LGPL2 via email:
---
Date: Sat, 27 Jul 2013 0...
Sage Weil
12:15 AM Revision 0e9a9379 (ceph): monthrash workloads: Add task to reproduce 5925 with extra logging
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman

08/13/2013

11:52 PM Revision a9033eb6 (ceph): mon: move recovery rate to a separate line
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:52 PM Revision 6d8d7263 (ceph): mon: status: only include mdsmap if epoch > 1
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:52 PM Revision fbc65ea8 (ceph): mon/PGMap: make pg state indentation cleaner
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:51 PM Revision ef9c9916 (ceph): mon: make pg info in 'status' more informative and visually parseable
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:51 PM Revision eeed33aa (ceph): mon/PGMap: make si modifiers look prettier
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:51 PM Revision c926d083 (ceph): mon: move mdsmap up
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:51 PM Revision 9b94f90e (ceph): types: pretty_si_t
Similar to si_t, but leaves a space between the numbers and the units. In
the degenerate case (no M, K, etc. modifie...
Sage Weil
11:51 PM Revision 054fd886 (ceph): mon: expand osd summary (flags on separate line)
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:51 PM Revision 1860ed97 (ceph): mon/PGMap: break out print_oneline_summary
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:40 PM Revision f417b101 (ceph): osdmap: move oneliner summary to separate function
We're about to make print_summary() do something much nicer.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
10:05 PM Revision 32631685 (ceph): mon/Paxos: bootstrap peon too if monmap updates
If we get a monmap update, the leader bootstraps. Peons should do the
same.
Signed-off-by: Sage Weil <sage@inktank....
Sage Weil
08:31 PM Revision 1ea6b561 (ceph): osd: fix race when queuing recovery ops
Previously we would sample how many ops to start under the lock, drop it,
and start that many. This is racy because ...
Sage Weil
08:31 PM Revision 4433f9ad (ceph): osd: tolerate racing threads starting recovery ops
We sample the (max - active) recovery ops to know how many to start, but
do not hold the lock over the full duration,...
Sage Weil
08:21 PM Revision 810c52de (ceph): rgw: do not leak handler in get_handler() error path
If we fail to initialize, delete the handler.
Fixes (part of): #5949
Signed-off-by: Sage Weil <sage@inktank.com>
Rev...
Sage Weil
08:21 PM Revision 6f5d8036 (ceph): librados: fix MWatchNotify leak
Do not leak the message if the watcher is not registered. Also, simplify
this block.
Fixes (part of): #5949
Backpor...
Sage Weil
08:12 PM Bug #5958: os/DBObjectMap.cc: 393: FAILED assert(!valid || cur_iter->valid())
From irc, looks like disk/leveldb issue. Hoping to get current/omap subdir of osd in question (osd 7). Seems somewh... Samuel Just
08:07 PM Bug #5958 (Can't reproduce): os/DBObjectMap.cc: 393: FAILED assert(!valid || cur_iter->valid())

0> 2013-08-13 22:48:26.503696 7fab63ec4700 -1 os/DBObjectMap.cc: In function 'virtual bool DBObjectMap::...
Samuel Just
06:45 PM Revision 94698555 (ceph): Merge pull request #30 from ceph/wip-5952
Fix a case where _get_config_value_for_remote could return None mistakenly Sage Weil
06:30 PM Revision f1c9125f (ceph): Fix a case where _get_config_value_for_remote could return None mistakenly
Zack Cerza
06:03 PM Revision 0f3d9edd (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
06:02 PM Revision 000efc65 (ceph): samba: wait longer for smbd to start
sleep(1) is occasionally not long enough, it seems! Sage Weil
05:46 PM Revision 2797d8d8 (ceph): Merge pull request #27 from dachary/wip-5946
do not check the jobid if check-locks is False Zack Cerza
05:45 PM Revision e3b7bc5b (ceph): v0.67
Gary Lowell
05:32 PM Revision 9d4104f4 (ceph): do not check the jobid if check-locks is False
Because it relies on the lock server which is presumably not available
since check-locks was set to False. It matters...
Loïc Dachary
05:11 PM Revision e9d4f9b0 (ceph): Merge pull request #497 from ksperis/rbdmap.init-3
Rbdmap.init 3
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:49 PM Revision 977b7f58 (ceph): doc/release-notes: fix rst
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:40 PM Revision f501ec77 (ceph): doc/release-notes: upgrade sequence
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:27 PM Revision de7bbdbc (ceph): doc/release-notes: roll-up of upgrade/compat notes from cuttlefish to d...
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:10 PM Revision 13edfe6b (ceph): Merge pull request #28 from alfredodeza/5887
Allow a user to define a ceph-deploy branch to use (instead of master) Zack Cerza
04:07 PM Revision 6df75da3 (ceph): init-rbdmap: minor fix no rbd exist
Avoid error if stop when no rbd device exist
Signed-off-by: Laurent Barbe <laurent@ksperis.com>
Laurent Barbe
04:06 PM Revision d9cb2ead (ceph): init-rbdmap: fix for recursive umount
Umount is not always done in the correct order.
For exemple in that case :
/dev/rbd1 on /myrbd
/dev/rbd2 on /myrbd/.s...
Laurent Barbe
03:57 PM Revision ac78bc90 (ceph): Merge pull request #24 from ceph/wip-5937
Don't hit an AttributeError if ctx.config['overrides'] is set to None Alfredo Deza
03:56 PM Revision 643da65e (ceph): remove fallback of the fallback. so silly
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
03:45 PM Revision 3aa995a6 (ceph): Remove three characters just for Alfredo
Zack Cerza
03:42 PM Revision 70cd884f (ceph): safer fallback. Updates docstring
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
03:31 PM Bug #5792 (Resolved): ceph-deploy mon create hangs on fedora18 vm's
Sage Weil
07:03 AM Bug #5792: ceph-deploy mon create hangs on fedora18 vm's
Sandon, it seems that this issue is gone, are you able to reproduce this?
#5895 was very similar (if not the same)...
Alfredo Deza
03:10 PM Revision f4de5151 (ceph): Add notes about install task precedence
Zack Cerza
02:53 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Looks good to me. Will see if I can accept pull request. Mark Kirkwood
06:20 AM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
I created a branch and applied your patch with one (minor) change which was to use `distro.init` for the RuntimeError... Alfredo Deza
02:32 PM rbd Bug #5955: qemu deadlock when librbd caching enabled (writethru or writeback).
normally completions follow this pattern... Sage Weil
01:32 PM rbd Bug #5955 (Resolved): qemu deadlock when librbd caching enabled (writethru or writeback).
From Mike Dawson on ML:
Logs are uploaded to cephdrop with the file name mikedawson-rbd-qemu-deadlock.
- At abo...
Sage Weil
02:27 PM rgw Feature #418: rgw: object versioning
There's no one working on it right now AFAIK. I'd be more than happy to discuss this feature with you. Yehuda Sadeh
02:05 PM rgw Feature #418: rgw: object versioning
Versioning is quite a common feature nowadays, both in the S3 API as well as the Google Storage API. I really like to... Roald van Loon
02:06 PM Bug #5951: osd: next: EEXIST on mkcoll
./virtualenv/bin/teuthology-schedule --name "samuelj-5951-0" -n 50 --owner samuelj@slider testruns/5951.yaml | tee 59... Samuel Just
09:57 AM Bug #5951 (Resolved): osd: next: EEXIST on mkcoll
... Sage Weil
01:53 PM devops Bug #5895 (Resolved): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish bran...
Merged into ceph-deploy master branch: 40c8088e011670d881432a94d8f159355d57d1e5
The problem here is that, by not r...
Alfredo Deza
12:48 PM devops Bug #5895 (Fix Under Review): ceph-deploy: mon create command hung on ceph-create-keys in cuttlef...
With Sage's suggestion to execute directly on those nodes, I was able to replicate the problem and find a fix.
A p...
Alfredo Deza
11:34 AM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
Ugh, I keep failing to replicate :(
The error on the second one is the famous ulimit configuration but that is not...
Alfredo Deza
09:39 AM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
Alfredo, I mentioned that the issue is not reproducible on a single node but the problem still exists with 2 nodes. Tamilarasi muthamizhan
01:43 PM devops Bug #5887 (Resolved): create a `-b` flag to use a ceph-deploy branch
Merged into teuthology's master branch
Hash: 13edfe6bdf48abb22a20598c6da09207529f8cc4
Alfredo Deza
08:46 AM devops Bug #5887 (Fix Under Review): create a `-b` flag to use a ceph-deploy branch
Pull request opened: https://github.com/ceph/teuthology/pull/28 Alfredo Deza
08:21 AM devops Bug #5887 (In Progress): create a `-b` flag to use a ceph-deploy branch
Alfredo Deza
01:42 PM devops Bug #5934 (Resolved): include a CHANGELOG and a --version flag
Merged into the master branch.
Hash: caf43ffd3e8c4b5fa35932b5b6784e725f5d998b
Alfredo Deza
01:40 PM devops Feature #5956 (Rejected): Implement a radosgw command in ceph-deploy
As a proof of concept, to see if ansible could work for ceph-deploy remote commands, implement a radosgw deployment w... Alfredo Deza
01:16 PM rgw Bug #5953 (Fix Under Review): rgw: drain requests when going down
Yehuda Sadeh
01:11 PM rgw Bug #5953 (Resolved): rgw: drain requests when going down
If receiving either SIGUSR1 or SIGTERM, wait (for a period of time) for requests to complete. This changes the SIGTER... Yehuda Sadeh
01:15 PM rgw Bug #5949 (Pending Backport): radosgw: leaks
Sage Weil
11:17 AM rgw Bug #5949 (Fix Under Review): radosgw: leaks
Sage Weil
08:40 AM rgw Bug #5949 (Resolved): radosgw: leaks
ubuntu@teuthology:/a/teuthology-2013-08-13_01:02:14-rgw-next-testing-basic-plana/104857... Sage Weil
01:02 PM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
Hi Oliver,
Okay, I think we spotted the (other) bug. I pushed another patch to the same branch; can you try again...
Sage Weil
02:01 AM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
Hi Josh,
update/upgrade our cluster with ceph version 0.56.6-28-gf07447f (f07447f28c6e468c1dc76149f51d7958b10482c2...
Oliver Francke
11:58 AM Revision c927f89a (ceph): rgw: rgw-admin throw an error when invalid flag is passed
fix #5820 http://tracker.ceph.com/issues/5820
Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Christophe Courtaut
11:49 AM rgw Bug #5893 (Resolved): failures in s3 tests but teuthology task still passes
Anonymous
10:27 AM rgw Bug #5893: failures in s3 tests but teuthology task still passes
Commit 9799858e90d9055f387f7c991cfcbf50f48cf42d in ceph/s3-tests allows s3tests to propagate exceptions up to the cal... Anonymous
11:14 AM Bug #5920: mon daemon crashes
>Hi Dmitry,
Hi Sage, please see my replies embedded.
>This looks like fallout from a rare paxos bug (#5750), fixe...
Dmitry Panov
10:38 AM Bug #5920 (Duplicate): mon daemon crashes
Hi Dmitry,
This looks like fallout from a rare paxos bug (#5750), fixed in commit:17aa2d6d16c77028bae1d2a77903cdfd...
Sage Weil
11:12 AM Bug #5922: osd: unfound objects on next
2013-08-13 11:08:20.438338 osd.3 [WRN] slow request 25666.244730 seconds old, received at 2013-08-13 04:00:34.193533:... Samuel Just
09:56 AM Bug #5922: osd: unfound objects on next
/var/lib/teuthworker/archive/teuthology-2013-08-13_01:00:13-rados-next-testing-basic-plana/104754 Sage Weil
11:11 AM Bug #5804: mon: binds to 0.0.0.0:6800something port
Just noticed that the port is set as 6801 -- that's used by the osds iirc -- and we've seen reports of the messenger ... Joao Eduardo Luis
10:41 AM Feature #5906 (In Progress): mon: better ceph -s output
Sage Weil
10:01 AM rgw Feature #5506 (Fix Under Review): rgw: use Keystone to authenticate S3 requests
Yehuda Sadeh
09:59 AM devops Bug #5930 (Resolved): ceph-deploy: osds disappear after reboot
this was commit:10cf3088ceeb70970a1ffb8b34e5a4871115face. backported to cuttlefish too. Sage Weil
09:16 AM CephFS Bug #5950 (Rejected): kcephfs: cephfs set_layout -p 4 gets EINVAL
from ML Georg H?llrigl <georg.hoellrigl@xidras.com>:
> By the way setting the layout seems to have a bug:
>
> #...
Sage Weil
08:31 AM Fix #5844: osd: snaptrimmer should throttle itself
We've scrutinized influence of snapshotting on disk IO and got some curious results. From our point of view, snapshot... Igor Lukyanov
06:29 AM Revision b9a5664b (ceph): Makefile.am: fix libglobal.la races
Several targets had libglobal.la in the _LDFLAGS macro definition
when it should have been in the _LDADD macro. Rem...
Gary Lowell
06:25 AM Revision d4c2576c (ceph): radosgw-agent.py: refactor, enable overrides
Refactored the radosgw-agent.py code so that it
is structured more like existing teuthology
tasks.
Additionally, adde...
Joe Buck
06:25 AM Revision 1d90d7bc (ceph): rgw.py: fix example config
In the example config, the region root and
zone root where pointing to the same pool,
which is not a best practice. U...
Joe Buck
06:25 AM Revision 9ee64524 (ceph): rgw.py: add a better error message
When pulling region info from the config
structure, if the region info isn't there,
log a more helpful message.
Sign...
Joe Buck
06:25 AM Revision e517cd4c (ceph): s3readwrite.py: make user creation optional
Extend the s3readwrite.py task to enable the
creation and deletion of users for the s3readwrite
tests to be independe...
Joe Buck
06:25 AM Revision e3b9add3 (ceph): rgw.py: refactor configure
Extend the rados pool configuration options to
specify all pools (if desired).
Also, reordered zone and region config...
Joe Buck
06:25 AM Revision 18e80147 (ceph): rgy.py: make log_(data|metadata) configurable
The log_data and log_metadata are made configurable
via the YAML file and default to false
(meaning neither data nor ...
Joe Buck
06:24 AM Revision 3fb53189 (ceph): agent name should also contain port number
otherwise multiple agents per machines will have the same id
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
06:24 AM Revision 4adc1da5 (ceph): radosgw-admin: various multiregion related fixes and changes
Go to the master zone in the master region for radosgw-admin
operations. Trigger metadata sync. Other fixes.
Signed-...
Yehuda Sadeh
05:44 AM devops Bug #5947 (Resolved): ceph-deploy RPM release is pointing to the wrong repo
The new release of ceph-deploy (1.2.1) has a problem with dependencies and it is not possible to install.
From IRC...
Alfredo Deza
05:38 AM Revision 0964d53e (ceph): ceph-disk: fix mount options passed to move_mount
Commit 6cbe0f021f62b3ebd5f68fcc01a12fde6f08cff5 added a mount_options but
in certain cases it may be blank. Fill in ...
Sage Weil
04:55 AM rgw Bug #5931: radosgw crashes when deleting object
I just wanted to confirm that the issue is gone. Thanks for a quick fix! Artem Salpagarov
03:47 AM Bug #5946 (Resolved): lockstatus.get_status called although check-locks: false
"work in progress":https://github.com/dachary/teuthology/tree/wip-5946
lockstatus.get_status "is called":https://git...
Loïc Dachary

08/12/2013

11:10 PM Revision 92138621 (ceph): Merge pull request #25 from dmick/master
tasks/ceph-deploy: allow configurations with no mds Zack Cerza
11:04 PM Revision c81edf1e (ceph): tools: ceph-monstore-tool: allow copying store contents to a new location
Usage:
ceph-monstore-tool --mon-store-path <in-path> --out <out-path> \
--command store-copy
Sig...
Joao Eduardo Luis
10:43 PM Revision fa733e43 (ceph): Change "Exception" to "RuntimeError" as advised by zackc
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
09:55 PM Revision 28e42197 (ceph): tasks/ceph-deploy: allow configurations with no mds
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
09:38 PM Revision 5be53270 (ceph): Default to master and not next.
Zack Cerza
09:31 PM Revision 6a37a62b (ceph): rgw: fix multi delete
Fixes: #5931
Backport: bobtail, cuttlefish
Fix a bad check, where we compare the wrong field. Instead of
comparing t...
Yehuda Sadeh
09:30 PM Revision d6be5ed2 (ceph): rgw: fix multi delete
Fixes: #5931
Backport: bobtail, cuttlefish
Fix a bad check, where we compare the wrong field. Instead of
comparing t...
Yehuda Sadeh
09:29 PM Revision 2632846e (ceph): rgw: fix multi delete
Fixes: #5931
Backport: bobtail, cuttlefish
Fix a bad check, where we compare the wrong field. Instead of
comparing t...
Yehuda Sadeh
09:21 PM Revision ef1c9669 (ceph): Add install task to examples
Zack Cerza
09:18 PM Revision 93b532f0 (ceph): Don't hit an AttributeError if ctx.config['overrides'] is set to None
Zack Cerza
07:35 PM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
I found one bug - there's a fix on top of the current bobtail branch in wip-librados-aio-flush. Could you see if that... Josh Durgin
06:15 PM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
Thanks Oliver, that's good to hear. If you use cache=writethrough instead of no cache, it will have the same write pr... Josh Durgin
05:38 AM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
Hi Josh,
even under high ceph-load I was not able to break things down with rbd_cache=true after 2 hours, whereas ...
Oliver Francke
06:35 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Ok here's my revised patch that hopefully incorporates what you were suggesting. Obviously feel free to editorialize ... Mark Kirkwood
03:36 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Lol - I think opening a new ticket is fine. You can mention that you have discussed the proposed change with me.
...
Mark Kirkwood
08:34 AM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Mark, you are spot on.
I will create a new ticket so I can fix this and apply your branch, unless you want to subm...
Alfredo Deza
05:40 PM Revision a714c011 (ceph): Merge pull request #23 from ceph/pep8
Make this module pep8-clean. Alfredo Deza
05:14 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
Tamil, you mentioned on IRC that you could not reproduce this anymore, can you confirm that is the case to resolve th... Alfredo Deza
03:47 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
this issue seems to be on ubuntu systems as well.
we need this issue to be resolved so we can test the upgrades fr...
Tamilarasi muthamizhan
04:40 PM Revision cabb4142 (ceph): Make this module pep8-clean.
Zack Cerza
04:21 PM rgw Bug #5931 (Resolved): radosgw crashes when deleting object
Yehuda Sadeh
02:34 PM rgw Bug #5931: radosgw crashes when deleting object
Yehuda Sadeh wrote:
> Do you have log for the entire request? Looks like an issue with multi-delete.
I hope that'...
Artem Salpagarov
09:48 AM rgw Bug #5931 (In Progress): radosgw crashes when deleting object
Ian Colle
03:05 PM devops Bug #5944 (Closed): ceph-deploy osd needs to be moved to use the new remote helpers
Debugging remote issues with ceph-deploy is very complicated if we are not logging the remote end.
`ceph-deploy os...
Alfredo Deza
01:40 PM rbd Feature #5938 (Rejected): openstack: nova: allow live-migration without detach/reattach for rbd
Currently nova requires shared local storage for live-migration. Even when it is shared, volumes are detached and re-... Josh Durgin
12:00 PM Bug #5901: stuck incomplete immediately after clean
The bug is that the primary can report that the pg is clean before the replica sees the OP_BACKFILL_FINISH message. ... Samuel Just
09:28 AM rgw Bug #5820: radosgw-admin should fail on non-valid flags
The dashed options are what I meant. I'd prefer Yehuda to review this; I'll try and ping him on it today. Anonymous
04:58 AM rgw Bug #5820: radosgw-admin should fail on non-valid flags
What do you mean by "flag"?
are the "--dashed-option" flags?
If so, here comes a pull request to fix this issue : h...
Christophe Courtaut
09:22 AM devops Bug #5489 (Resolved): ceph-deploy: mon destroy throws inappropriate message
With the addition of more logging and better output from the remote node this should no longer be an issue.
Tamil,...
Alfredo Deza
09:20 AM devops Bug #5813 (Closed): Normalize ceph-deploy Exceptions for better error reporting
With the combination of the new decorator to catch exceptions I noticed most of the exceptions are inherited from exc... Alfredo Deza
09:18 AM devops Bug #5887: create a `-b` flag to use a ceph-deploy branch
Actually, better than a flag is a `YAML` key.
There is some work being done with this, but the naming will be odd ...
Alfredo Deza
09:15 AM devops Bug #5928 (Closed): Catch KeyboardInterrupt and RuntimeError for nicer reporting
Merged into master with hash: a8dcfbbf7268cc0bfb15ac986650e37962e4d9d6 Alfredo Deza
09:13 AM devops Bug #5934 (Fix Under Review): include a CHANGELOG and a --version flag
Opened pull request: https://github.com/ceph/ceph-deploy/pull/39 Alfredo Deza
08:42 AM devops Bug #5934 (In Progress): include a CHANGELOG and a --version flag
Alfredo Deza
06:53 AM devops Bug #5934 (Resolved): include a CHANGELOG and a --version flag
ceph-deploy doesn't have a changelog where a list of changes can be seen for each release. Since the release cycle fo... Alfredo Deza
08:58 AM Revision c566c034 (ceph): doc: complete S3 features status from existing doc page
Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com> Christophe Courtaut
08:13 AM rgw Feature #5935 (New): rgw: implement IP-based ACL capabilities
radosgw could possibly implement access control based on source IP or header, the latter being beneficial for those b... Brian Andrus

08/11/2013

11:12 PM Bug #5920: mon daemon crashes
Hi Sage,
Sure. You can download it here: [[https://dl.dropboxusercontent.com/u/22489421/mon.tgz]]
Dmitry Panov
09:43 PM Bug #5923: osd: 6 up, 5 in; 91 active+clean, 1 remapped
ubuntu@teuthology:/a/samuelj-5901-1/101594 may be an example. (others in the same suite) Samuel Just
09:42 PM Bug #5922: osd: unfound objects on next
ubuntu@teuthology:/a/samuelj-5901-1/101594 may be an example. (others in the same suite) Samuel Just
08:53 PM rgw Bug #5931: radosgw crashes when deleting object
Yehuda Sadeh
05:27 PM rgw Bug #5931: radosgw crashes when deleting object
Do you have log for the entire request? Looks like an issue with multi-delete. Yehuda Sadeh
03:23 AM rgw Bug #5931 (Resolved): radosgw crashes when deleting object
I use 3hub mac app (S3 client) for managing files in rados. Rados is installed on two physical Ubuntu presice machine... Artem Salpagarov
12:31 PM Bug #5932 (Won't Fix): osdmaptool --create-from-conf ignore "osd pool default pg[p] num"
osdmaptool --create-from-conf ignore "osd pool default pg num" & "osd pool default pgp num" values from config, I fix... Denis kaganovich

08/10/2013

06:35 PM Revision 5aee4a8b (ceph): Merge pull request #22 from ceph/rpm-upgrades
Fix rpm upgrades for nested branch configs Sage Weil
05:48 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
With your commit 1d2d9881f93df6383d99720c84d6e7397a04bba0 the problem is solved. Absolutely. I was merely thinking th... Mark Kirkwood
05:14 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Mark,
Are you sure you are able to replicate this with the latest release of ceph-deploy?
This commit fixed t...
Alfredo Deza
05:45 PM Revision 7c377cb7 (ceph): Make _get_baseurlinfo_and_dist() provide the correct uri
Zack Cerza
04:57 AM Revision ef91c699 (ceph): mon: mon_cluster_log_file_level
By popular demand, control the min level of logging that goes to
/var/lib/ceph/ceph.log.
Signed-off-by: Sage Weil <s...
Sage Weil
04:24 AM Revision cb50b5a7 (ceph): ceph-disk: fix mount options passed to move_mount
Commit 6cbe0f021f62b3ebd5f68fcc01a12fde6f08cff5 added a mount_options but
in certain cases it may be blank. Fill in ...
Sage Weil
02:19 AM Revision b66a3d60 (ceph): config_opts.h: reduce osd_recovery_max_active and osd_recovery_max_sing...
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just

08/09/2013

11:42 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Sorry - was a bit keen with the 'submit' button! That mon create patch does is not really doing what it should, espec... Mark Kirkwood
11:12 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
I notice I should have used "from ceph_deploy import lsb" in the above. Having said that - there is another place whe... Mark Kirkwood
09:15 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
In fact like this seems to work:... Mark Kirkwood
03:56 PM devops Bug #5911: ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Well that was a fast turnaround!
A minor niggle - I note the osd code does:...
Mark Kirkwood
03:32 PM devops Bug #5911 (Resolved): ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Sage Weil
03:27 PM devops Bug #5911 (Fix Under Review): ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart...
Opened pull request: https://github.com/ceph/ceph-deploy/pull/36 Alfredo Deza
11:39 PM Revision 5433ca2a (ceph): upgrade-parallel: test on multiple target distros
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:26 PM Revision 251cbf7f (ceph): Merge pull request #21 from ceph/rpm-upgrades
Make install.upgrade work on RPM-based systems. Zack Cerza
11:19 PM Revision ecaa46a1 (ceph): ceph.spec.in: obsolete ceph-libs only on the affected distro
The ceph-libs package existed only on Redhat based distro,
there was e.g. never such a package on SUSE. Therefore: ma...
Danny Al-Gaaf
11:19 PM Revision 81aa68c3 (ceph): ceph.spec.in: Obsolete ceph-libs
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Gary Lowell
11:15 PM Revision b221a42e (ceph): doc/release-notes: adjust whitespace
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:14 PM Revision bec6f09c (ceph): doc/release-notes: v0.67 release notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:03 PM Revision d3d56ee5 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
10:47 PM Revision ebd94a9a (ceph): upgrade: do not wait for full quorum on mixed-version mon cluster
It won't happen Sage Weil
10:38 PM Revision 44b093c8 (ceph): ceph: retry new-style mon command if we get EINVAL from the old-style c...
We can race with a mon upgrade:
- get command descriptions, get EINVAL
- mons upgrade, new quorum
- send old-style c...
Sage Weil
10:30 PM Revision 2a34df68 (ceph): common: pick_addresses: fix bug with observer class that triggered #5205
The Observer class we defined to observe conf changes and thus avoid
triggering #5205 (as fixed by eb86eebe1ba42f04b4...
Joao Eduardo Luis
10:01 PM Revision b78a6c77 (ceph): Make install.upgrade work with CentOS/RHEL/Fedora.
Zack Cerza
09:48 PM Revision 7ed6de9d (ceph): common: pick_addresses: fix bug with observer class that triggered #5205
The Observer class we defined to observe conf changes and thus avoid
triggering #5205 (as fixed by eb86eebe1ba42f04b4...
Joao Eduardo Luis
09:26 PM Revision 8bf3971b (ceph): rearrange the documentation to be inserted and maintained in master
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:57 PM Revision 9baaf862 (ceph): Merge pull request #486 from kri5/wip-s3-compliance-doc
Wip s3 compliance doc
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
07:49 PM Revision 068baae7 (ceph): rgw: return 423 Locked response when failing to lock object
Fixes: #5882
Translate the EBUSY we get when trying to lock a shard / object
to 423 Locked response. Beforehand it wa...
Yehuda Sadeh
07:33 PM Revision 9029555f (ceph): rgw: make RGWHTTPClient callback methods pure virtual
This will make it easier to catch interface changes, like the
ones that triggered #5921.
Reviewed-by: Sage Weil <sag...
Yehuda Sadeh
07:33 PM Revision 71177fe3 (ceph): rgw: rename read_header() to receive_header() where needed
The same as with #5921, fixing a missed interface change.
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Y...
Yehuda Sadeh
07:33 PM Revision 1563613d (ceph): rgw: rename data receive callbacks in swift token revocation
Fixes: #5921
As part of the work that was made for dumpling, the http
client in-data callback was renamed in order to...
Yehuda Sadeh
06:42 PM Bug #5925: hung ceph_test_rados_delete_pools_parallel
The pool create process died after getting a write error:
@
2013-08-09T02:08:27.288 INFO:teuthology.task.workunit...
David Zafman
02:18 PM Bug #5925: hung ceph_test_rados_delete_pools_parallel
This looks like a test case race.
2 processes hung while mon thrasher keeps running:
ubuntu 7800 1 0 02:0...
David Zafman
10:28 AM Bug #5925 (Can't reproduce): hung ceph_test_rados_delete_pools_parallel
... Sage Weil
06:36 PM rbd Bug #5919: qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to kernel_hung_t...
The log shows one aio_flush (that started at 2013-08-08 14:19:36.425555) never completing. This log is without cachin... Josh Durgin
02:07 AM rbd Bug #5919 (Resolved): qemu-1.4.0 and onwards, linux kernel 3.2.x, ceph-RBD, heavy I/O leads to ke...
Hi,
we had a number of tickets raising, where users reported problems with latest debian-7.[01] and kernel 3.2.x/ ...
Oliver Francke
06:28 PM Revision 2a7a61cd (ceph): Add Remote.system_type property. Also, clean up whitespace.
Zack Cerza
06:00 PM CephFS Bug #5927: kcephfs: ENOTEMPTY on rm -r
my patch "ceph: rework trim caps code" can explain this issue Zheng Yan
02:24 PM CephFS Bug #5927 (Resolved): kcephfs: ENOTEMPTY on rm -r
... Sage Weil
05:40 PM devops Bug #5930 (Resolved): ceph-deploy: osds disappear after reboot
while using ceph-deploy to deploy cluster, when the test system is reboot, the osds and mount point disappears.
th...
Tamilarasi muthamizhan
04:41 PM Revision d5aa3a90 (ceph): Merge remote-tracking branch 'gh/wip-5648-c'
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
04:14 PM devops Fix #5900: Create a Python package for ceph Python bindings
Josh also pointed out about the licensing.

I am not sure how to proceed here but the Python files say GPLv2
...
Alfredo Deza
04:11 PM devops Fix #5900: Create a Python package for ceph Python bindings
There are some references to the python files that will need to be updated for the new paths. The first one is for bu... Josh Durgin
04:07 PM Revision eade36df (ceph): PendingReleaseNotes: note 'ceph daemon ...' argument behavior change
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:04 PM Revision a0e74a96 (ceph): admin_socket: split command into multiple arguments
We were passing the command as a single string, but that does not work the
same way it used to.
Signed-off-by: Sage ...
Sage Weil
03:54 PM Bug #5901: stuck incomplete immediately after clean
./virtualenv/bin/teuthology-schedule --name "samuelj-5901-1" -n 50 --owner samuelj@slider testruns/5799.yaml | tee 59... Samuel Just
02:49 PM Bug #5901: stuck incomplete immediately after clean
~/teuthology [mine?] » ./virtualenv/bin/teuthology-schedule --name "samuelj-5901-0" -n 10 --owner samuelj@slider test... Samuel Just
03:48 PM Feature #5910 (In Progress): osd: report filestore op latency (apply and commit) to monitor
Samuel Just
03:48 PM devops Bug #5928 (Fix Under Review): Catch KeyboardInterrupt and RuntimeError for nicer reporting
Pull request opened: https://github.com/ceph/ceph-deploy/pull/37 Alfredo Deza
03:29 PM devops Bug #5928 (Closed): Catch KeyboardInterrupt and RuntimeError for nicer reporting
ceph-deploy should show tracebacks when keyboardinterrupt or RuntimeERror are raised, just displaying the actual erro... Alfredo Deza
03:43 PM devops Bug #5929 (Resolved): debian: python-ceph should depend on libcephfs1
There are libcephfs python bindings in it as well. This dependency is already in the spec file. Josh Durgin
03:40 PM Bug #5788: ceph: try new, fallback to old can race with daemon upgrade
fixed the main path where this happens. dan still wants to clean this up and fix other similar cases. Sage Weil
02:31 PM Tasks #5585 (Resolved): test large scale exapnsion and contraction
Done using Mark's burnupi nodes. Resulted in the TPHandle patches. Samuel Just
02:26 PM Bug #5902: s3tests failure during parallel upgrade test
another example: ubuntu@teuthology:/a/teuthology-2013-08-09_01:30:23-upgrade-parallel-next-testing-basic-plana Sage Weil
12:58 PM rgw Bug #5921 (Resolved): rgw: failure in token revocation
Fixed by commits 1563613d83aa6937529fda8e09a0f59ff939712d and 71177fe3c7a164ad4b0c7d507949b2f07a792f9a. Added commit ... Yehuda Sadeh
09:47 AM rgw Bug #5921 (Fix Under Review): rgw: failure in token revocation
Ian Colle
07:44 AM rgw Bug #5921: rgw: failure in token revocation
can't read message (callback was renamed, need to update). Yehuda Sadeh
07:44 AM rgw Bug #5921 (Resolved): rgw: failure in token revocation
Yehuda Sadeh
12:56 PM rgw Bug #5882 (Resolved): rgw: failure to lock shard should result in another error
Done, merged at commit:068baae719b6a06487110e30b3cdcafddda0e579. Yehuda Sadeh
11:56 AM rgw Bug #5882 (Fix Under Review): rgw: failure to lock shard should result in another error
pushed change to wip-5882. Yehuda Sadeh
12:42 PM Documentation #5926 (Resolved): 5 minute quick start should deploy cluster using ceph-deploy and ...
5 minute quick start still uses mkcephfs to deploy ceph cluster and this should not be the case anymore. It should us... Tamilarasi muthamizhan
11:37 AM devops Feature #5847 (In Progress): Build own versions of most recent leveldb for all supported platforms.
Anonymous
10:46 AM Bug #5922: osd: unfound objects on next
I attached gdb to the process for too long and osd.1 got briefly marked down. This was enough to cause it to to clea... Samuel Just
08:40 AM Bug #5922 (Duplicate): osd: unfound objects on next
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2013-08-09_01:00:22-rados-next-testing-basic-plana/100980
...
Sage Weil
10:40 AM devops Bug #5917 (Resolved): ceph-deploy: f18 install broken
Sage Weil
10:19 AM devops Bug #5917 (Fix Under Review): ceph-deploy: f18 install broken
There is an open pull request ready to be reviewed: https://github.com/ceph/ceph-deploy/pull/35
Alfredo Deza
09:39 AM devops Bug #5917 (In Progress): ceph-deploy: f18 install broken
Alfredo Deza
10:25 AM Bug #5785 (Resolved): librados: deadlock during shutdown
Sage Weil
09:58 AM Revision e1666d04 (ceph): Fix compilation -Wmismatched-tags warnings
Keep consistency in the code to not generate warnings of this type.
Signed-off-by: Christophe Courtaut <christophe.c...
Christophe Courtaut
09:57 AM Fix #5844: osd: snaptrimmer should throttle itself
(09:50:05 AM) sjust: xdeller: you mean snapshot trimming?
(09:50:58 AM) xdeller: if i may call it so, it`s about #58...
Samuel Just
09:42 AM Feature #5648: mon should use 'module'/'perm' string in MonCommands.h for caps checking
merged post-dumpling; we can backport later if we feel like it. Sage Weil
09:42 AM Feature #5648 (Resolved): mon should use 'module'/'perm' string in MonCommands.h for caps checking
Sage Weil
09:11 AM Bug #5923 (Duplicate): osd: 6 up, 5 in; 91 active+clean, 1 remapped
I suspect the same root cause as #5922.... Sage Weil
08:44 AM Bug #5920 (Need More Info): mon daemon crashes
Hi Dmitry,
Can you create a tar.gz of your mon data directory (/var/lib/ceph/mon/*) and post it somewhere? (Or co...
Sage Weil
05:47 AM Bug #5920: mon daemon crashes
OS - Ubuntu 12.04.2 x64.
Ceph packages were download from Ceph repository.
Dmitry Panov
05:43 AM Bug #5920 (Duplicate): mon daemon crashes
Hello!
I'd like to report about the problem. May be it will help you to improve Ceph.
I've created Ceph cluster...
Dmitry Panov
08:26 AM Revision 5082fec1 (ceph): doc: Add a page about rgw S3 API compliance
Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com> Christophe Courtaut
08:17 AM Revision fd062610 (ceph): ant is missing from the list of packages to install
to build the documentation.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:42 AM Revision 980a0738 (ceph): document the write / read path for erasure encoding
Explains how objects are stored and used in erasure coded pools. It is
the result of discussions that occured on the ...
Loïc Dachary
05:48 AM Revision 1243c974 (ceph): make sure we are using the mount options
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 34831d0989d4bcec4920068b6ee09ab6b3234c91)
Alfredo Deza
05:40 AM Revision 0aacd10e (ceph): RadosClient: shutdown monclient after dropping lock
Otherwise, the monclient shutdown may deadlock waiting
on a context trying to take the RadosClient lock.
Fixes: #589...
Samuel Just
05:29 AM Revision ca3987ff (ceph): mds: notify clients about deleted inode
To make sure clients trim the deleted inode from the their cache
ASAP. After all clients release the inode, we can re...
Yan, Zheng
05:19 AM Revision 151e6d24 (ceph): Merge remote-tracking branch 'yan/wip-mds'
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
05:18 AM Revision 7e285149 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
01:38 AM Revision b2515b9e (ceph): buffer: change #include order
huangjun <hjwsm1989@gmail.com> reports that this fixes the compilation on
CentOS5.
Signed-off-by: Sage Weil <sage@in...
Sage Weil
01:38 AM Revision 6cbe0f02 (ceph): make sure we are using the mount options
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
(cherry picked from commit 34831d0989d4bcec4920068b6ee09ab6b3234c91)
Alfredo Deza
01:34 AM Revision 469d30b8 (ceph): Merge pull request #480 from dachary/master
Add the definition of PG temp to the glossary
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:31 AM Revision b8e80462 (ceph): Merge pull request #482 from dachary/wip-erasure-coding-doc
Links to newly created tracker items, typo, M+K convention Sage Weil
01:29 AM Revision f4aa05a4 (ceph): Merge pull request #487 from ceph/wip-5746
ceph.in: Re-enable ceph interactive mode (missing its output).
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:06 AM Revision 5bdbe9d6 (ceph): Merge pull request #489 from ceph/wip-5903
make sure we are using the mount options
Backport: dumpling, cuttlefish
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil

08/08/2013

11:09 PM Revision 34831d09 (ceph): make sure we are using the mount options
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
10:53 PM Feature #5918 (Rejected): osd: friendly error message about missing xattr support
nevermind, it was the use omap option that was missing. Sage Weil
10:39 PM Feature #5918 (Rejected): osd: friendly error message about missing xattr support
a user in irc hit this:... Sage Weil
10:51 PM devops Bug #5208 (Resolved): Debian Wheezy Needs the 'ca-certificates' package before you can wget the p...
Sage Weil
10:51 PM Bug #5897 (Pending Backport): ceph_test_rados_api_watch_notify hang on LibRadosWatchNotify.WatchN...
Sage Weil
10:48 PM devops Bug #5903 (Resolved): ceph-deploy ignores defined xfs mount options
Sage Weil
06:06 PM devops Bug #5903 (Pending Backport): ceph-deploy ignores defined xfs mount options
Sage Weil
04:13 PM devops Bug #5903 (Fix Under Review): ceph-deploy ignores defined xfs mount options
There is a pull request that needs some reviewing that addresses the problem: https://github.com/ceph/ceph/pull/489 Alfredo Deza
01:27 PM devops Bug #5903 (Resolved): ceph-deploy ignores defined xfs mount options
When specifying specific XFS mount options within ceph.conf, ceph-deploy ignores defined mount options and mounts wit... Brian Andrus
10:10 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
It looks to me like the last command that mon create ran is finished, but pushy still has its connection open. that ... Sage Weil
09:48 PM devops Bug #5917 (Resolved): ceph-deploy: f18 install broken
2013-08-08T01:21:46.541 INFO:teuthology.orchestra.run.err:[10.214.138.154]: [ESC[1mvpm099ESC[0m][ESC[1;37mINFOESC[0m ... Sage Weil
09:30 PM Messengers Feature #5916 (Resolved): msgr: allow connect to multi-addr peer
add a multi-addr get_connection() method that lets you specify an ordered list of peer addrs. try them in succession... Sage Weil
09:27 PM Messengers Feature #5915 (Resolved): msgr: allow binding to multiple addresses, address types
Currently we either bind to ipv4 or ipv6. With the rsockets code, we may also bind to an rsockets v4 or v6 addr. Al... Sage Weil
09:25 PM Messengers Feature #5914 (Rejected): msgr: use either socket or rsocket calls
Use either the normal socket api or the rsockets one, depending on the peer entity_addr_t type. This will affect Pip... Sage Weil
09:24 PM Messengers Feature #5913 (Rejected): msgr: add wrappers for remaining socket calls in Pipe, Accepter
Almost all socket calls are confined to Accepter.cc (which is small) and Pipe.cc (which is not). Most actual socket ... Sage Weil
09:23 PM Messengers Feature #5912 (Rejected): msgr: create rsockets entity_addr_t type
use the (currently unused) entity_addr_t::type to have an 'rsockets' flavor of IP addresses so that we can disambigua... Sage Weil
08:14 PM Revision a9a370be (ceph): PG: set !flushed in Reset()
Otherwise, we might serve a pull before we start_flush in the
ReplicaActive constructor.
Fixes: #5799
Signed-off-by:...
Samuel Just
07:33 PM Revision a71fc46b (ceph): Merge pull request #488 from dmick/wip-dmick-daemon-einval
Wip dmick daemon einval
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
07:23 PM Bug #5823: cpu load on cluster node is very high, client can't get data on pg from primary node ...
ceph-osd process is causing the high load, ...
When i used the htop to monitor cpu load, I saw that %cpu spend fo...
Khanh Nguyen Dang Quoc
01:22 PM Bug #5823: cpu load on cluster node is very high, client can't get data on pg from primary node ...
Which process is causing the load? Samuel Just
06:30 PM Bug #5746 (Resolved): ceph cli interactive mode completely broken
Sage Weil
06:20 PM Bug #5872 (Resolved): ceph daemon <name> badcommand does not return error
Sage Weil
08:32 AM Bug #5872: ceph daemon <name> badcommand does not return error
Sage Weil
06:11 PM devops Bug #5911 (Resolved): ceph-deploy to Ubuntu targets touches sysvinit for mons and upstart for osds
Testing ceph-deploy from git master (checked out 6 Aug ad1f3f3689e8b060a13f715e7ac3735f91e9c546) for Ubuntu 12.04 tar... Mark Kirkwood
05:23 PM Revision fd192358 (ceph): ceph.in: return EINVAL on daemon command error
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
04:38 PM Revision 0be14757 (ceph): ceph.in: Re-enable ceph interactive mode (missing its output).
Also, loop on error. There's no reason to exit the interpreter loop on
an error, and it's probably less annoying if ...
Dan Mick
04:03 PM Feature #5910 (Resolved): osd: report filestore op latency (apply and commit) to monitor
ceph osd dump perf_info (maybe?)
Could also dump other potentially useful perf information.
Samuel Just
04:01 PM Feature #5909 (Resolved): mon: keep track of monitor store size estimate vs 'du $mon_data'
Allows us to figure out whether the monitor is starting to suffer from leveldb's compaction shenanigans Joao Eduardo Luis
03:37 PM Feature #5908 (Rejected): mon: formatted output sections should be consistent across services and...
With the rest api, almost *everything* in the monitor now outputs to a formatter. However, someone parsing this outp... Joao Eduardo Luis
03:33 PM Feature #5907 (Resolved): permanently log all administrative actions
Samuel Just
03:30 PM Revision 2e280874 (ceph): mon: fix 'osd crush rule rm ...' dup arg
This was broken way back in 0d66c9ebbf626117c641c975a8682a0aaba588c4, but
we were ignoring the dup until recently.
t
...
Sage Weil
03:28 PM Feature #5906 (Resolved): mon: better ceph -s output
The current output is hard to scan.
Each status on a different line.
active/non-active
recovering/backfilling/re...
Samuel Just
03:22 PM Feature #5905: hello world librados program (with explanatory comments!)
This should probably in a seperate repo? Samuel Just
03:19 PM Feature #5905 (Resolved): hello world librados program (with explanatory comments!)
Samuel Just
03:18 PM Feature #5904 (Resolved): hello world osd class (with explanatory documentation/comments!)
Samuel Just
01:20 PM Bug #5749 (Duplicate): osd: unfound objects on cuttlefish
This is a dup of #5799, backported the fix. Samuel Just
11:22 AM Bug #5822 (Resolved): ceph_argparse.py: parsing of required arguments broken
Dan Mick
09:17 AM Bug #5902 (Resolved): s3tests failure during parallel upgrade test
... Sage Weil
08:31 AM rgw Bug #5874 (Resolved): rgw: cuttlefish cls_rgw tests fails against next
backported the preload osd class patches to cuttlefish and enabled in teuthology so we can avoid this problem in test... Sage Weil
01:38 AM Documentation #5899 (Closed): transcript of Emperor CDS discussion about erasure coding
Published "in the wiki":http://wiki.ceph.com/01Planning/CDS/Emperor/Transcript_:_Erasure_coded_storage_backend_%28ste... Loïc Dachary
01:34 AM Subtask #5510: ObjectContext : replace ref with shared_ptr
rebased against master Loïc Dachary

08/07/2013

09:01 PM Revision a7392066 (ceph): ceph.conf: open osd classes on start
This is the default for master, but needs to be explicitly enabled for
cuttlefish.
Sage Weil
08:53 PM Revision 65bfa494 (ceph): osd: make open classes on start optional
This is cuttlefish; default to the old behavior!
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from com...
Sage Weil
08:52 PM Revision e8253ae5 (ceph): osd: load all classes on startup
This avoid creating a wide window between when ceph-osd is started and
when a request arrives needing a class and it ...
Sage Weil
04:03 PM Revision 77b63f04 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
03:35 PM Revision 0c1fd629 (ceph): qa/workunits/cephtool/test.sh: test set/unset of all osd flags
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:32 PM Revision 298e7d87 (ceph): mon/MonCommands: fix typo nobackfile -> nobackfill
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:29 PM Revision afa21e80 (ceph): Add back the mistakenly removed "ceph osd set noscrub/nodeep-scrub"
Fixes: #5868
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
02:15 PM devops Fix #5900 (Fix Under Review): Create a Python package for ceph Python bindings
Branch `wip-5900` was pushed and it needs a few things addressed:
* Versioning -> (it currently is defaulting to 0...
Alfredo Deza
12:20 PM devops Fix #5900 (In Progress): Create a Python package for ceph Python bindings
The `src/pybind` directory needs to be converted to a proper Python package structure so we can create and publish Py... Alfredo Deza
12:40 PM Bug #5901 (Duplicate): stuck incomplete immediately after clean
2013-08-06T19:19:00.289 INFO:teuthology.orchestra.run.err:[10.214.133.31]: dumped all in format json
2013-08-06T19:1...
Samuel Just
09:37 AM Feature #4929: Erasure encoded placement group
Archive of the erasure code session "PAD":http://pad.ceph.com/p/osd-erasure-coding of the Emperor session summit.
...
Loïc Dachary
08:45 AM Bug #5898 (Resolved): ceph cli lost "osd set/unset noscrub/nodeep-scrub"
Sage Weil
02:31 AM Documentation #5899 (Closed): transcript of Emperor CDS discussion about erasure coding
as found at http://youtu.be/-K8bSHx7zJ0?t=30m26s Loïc Dachary
01:05 AM Revision fb06bf60 (ceph): Merge branch 'wip-recovery-op-warn' into next
Reviewed-by: Sage Weil <sage@inktank.com> Samuel Just

08/06/2013

10:20 PM Revision 6acee41c (ceph): add a key for ceph-deploy-branch detection
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
10:15 PM rgw Bug #5893: failures in s3 tests but teuthology task still passes
So the error I'm seeing is when the s3readwrite test goes to read an object and doesn't find it (due to a YAML issue ... Anonymous
02:20 PM rgw Bug #5893 (Resolved): failures in s3 tests but teuthology task still passes
In a dev branch, I had the read tests for s3 fail but the overall teuthology task passed. This seems like a pretty bi... Anonymous
10:04 PM Revision 68203903 (ceph): OSD: suspend timeout on process_peering_events pg lock
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:25 PM Revision f71ec8e6 (ceph): Merge pull request #476 from dalgaaf/wip-CID-1058791
Fix CID 1058791
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
09:01 PM Revision 258135b9 (ceph): qa: workunits: mon: workunit to stress the monitor's caps
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
09:01 PM Revision da69756c (ceph): test: mon: moncap: add 'allow command foo with arg="bar.baz"' tests
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
08:59 PM Revision 2071af2f (ceph): mon: Monitor: purge old permission checking format on handle_command()
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
08:59 PM Revision 612444a8 (ceph): mon: services: no longer needed to enforce caps on a per-service basis
We now perform all perm checks for commands on Monitor::handle_command().
Services no longer need to check them.
Sig...
Joao Eduardo Luis
08:59 PM Revision 94002c43 (ceph): mon: drop old _allowed_command()
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:59 PM Revision 5c6dc1c8 (ceph): mon: AuthMonitor: change 'auth add' behaviour
If an entity already existed, 'auth add' would smash its key and caps
with whatever was on the supplied keyring file;...
Joao Eduardo Luis
08:59 PM Revision f087d84b (ceph): mon: Monitor: check caps considering command's requirements
Fixes: #5648
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis
08:51 PM Revision 321f57de (ceph): OpRequest: don't warn as quickly for slow recovery ops
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:51 PM Revision 95b3604b (ceph): OSD: also suspend timeout while grabbing recovery_tp lock
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:51 PM Revision d0cbdde2 (ceph): ReplicatedPG: ping TPHandle during scan_range
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:51 PM Revision 8b53a140 (ceph): ReplicatedPG: ping tphandle between pushes
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:51 PM Revision 944f3b73 (ceph): OSD: only start osd_recovery_max_single_start at once
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:21 PM Revision 7a14a93d (ceph): Add a useful error message in case of an invalid hostname
Zack Cerza
08:13 PM Revision 00170107 (ceph): mon, osd: Clean up "flush(stringstream)" continued
Missing files in last commit; sorry!
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
07:15 PM Revision 70f4eeb9 (ceph): s3readwrite.py: enable overrides
Enable s3readwrite task to have the branch to
download specified and for overrides to be
incorporated into the config...
Joe Buck
06:39 PM rgw Bug #5874: rgw: cuttlefish cls_rgw tests fails against next
So basically this is #5752. We can try working around it by running the objclass unitest before the upgrade (which wi... Yehuda Sadeh
04:21 PM rgw Bug #5874: rgw: cuttlefish cls_rgw tests fails against next
The osd hasn't been restarted at this point. Yehuda Sadeh
04:20 PM rgw Bug #5874: rgw: cuttlefish cls_rgw tests fails against next
We get this, which looks like #5752:... Yehuda Sadeh
01:56 PM rgw Bug #5874: rgw: cuttlefish cls_rgw tests fails against next
It looks like some osd crashed here:... Yehuda Sadeh
06:32 PM Bug #5898 (Fix Under Review): ceph cli lost "osd set/unset noscrub/nodeep-scrub"
Dan Mick
06:27 PM Bug #5898 (Resolved): ceph cli lost "osd set/unset noscrub/nodeep-scrub"
These flags were added at a time while the Ceph CLI restructuring was in progress, and
got lost in the transition. ...
Dan Mick
06:15 PM Bug #5897 (Resolved): ceph_test_rados_api_watch_notify hang on LibRadosWatchNotify.WatchNotifyTim...
2013-08-06T04:50:26.730 INFO:teuthology.task.thrashosds.thrasher:Added osd 1
2013-08-06T04:50:27.345 INFO:teuthology...
Samuel Just
06:00 PM Bug #5896 (Resolved): mon: MonmapMonitor: 'ceph mon add' always returns 'mon already exists'
on next (ceph version 0.67-rc3-100-ge8d72ef (e8d72ef0402a42c8aa8ea624497d13db81d5e361))... Joao Eduardo Luis
06:00 PM devops Bug #5895: ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish branch on RHEL 6.3
oops, it is not centos 6.3, it is RHEL 6.3 Tamilarasi muthamizhan
06:00 PM devops Bug #5895 (Resolved): ceph-deploy: mon create command hung on ceph-create-keys in cuttlefish bran...
on centos 6.3, when trying to deploy ceph using --stable=cuttlefish branch, the mon create command hung on ceph-creat... Tamilarasi muthamizhan
05:03 PM Bug #5894 (Can't reproduce): test_daemon teuthology failure
Dan Mick
05:02 PM Bug #5894: test_daemon teuthology failure
Yeah, this was fixed with 9466a0b152beeab894be66c6528495ca01a1974a I believe. If it happens again with a version >= ... Dan Mick
04:54 PM Bug #5894: test_daemon teuthology failure
ubuntu@teuthology:/a/teuthology-2013-08-05_01:00:16-rados-next-testing-basic-plana/96941 Samuel Just
04:31 PM Bug #5894 (Can't reproduce): test_daemon teuthology failure
2013-08-06T02:37:04.714 INFO:teuthology.task.workunit.client.0.out:[10.214.132.22]: crush_ruleset: 2
2013-08-06T02:3...
Samuel Just
04:58 PM Bug #5503 (Resolved): osd: ceph --admin-daemon interface doesn't handle spaces in names
Dan Mick
04:17 PM Bug #5746 (Fix Under Review): ceph cli interactive mode completely broken
Dan Mick
02:14 PM Bug #5749: osd: unfound objects on cuttlefish
ubuntu@teuthology:/a/teuthology-2013-08-04_01:30:24-upgrade-parallel-next-testing-basic-plana/96526
Another instance?
Samuel Just
01:50 PM rgw Bug #5885: Valgrind issue found while running s3 and swift tests
And now it shows up again with my wip-56040-ysw-5602-buck teuthology branch. I wonder if we're introducing some kind ... Anonymous
12:14 PM rgw Bug #5885: Valgrind issue found while running s3 and swift tests
This test is now passing against next. Uploading the archive from the run. Guessing we can close this and attribute i... Anonymous
01:28 PM Revision e9040188 (ceph): mon, osd: Clean up "flush(stringstream); bl.append(stringstream.str())
Also: One redundant flush in AuthMonitor, two in PGMonitor, and
a ds << that should have been conditional in Monitor....
Dan Mick
10:18 AM rgw Feature #4342: rgw: dr: data sync agent: update sync processing state
    - mark bucket index log progress on local (target) zone
Sage Weil
10:18 AM rgw Feature #4341: rgw: dr: data sync agent: implement delta changes sync
    - watch (sharded) data log: which buckets were modified
      - lock/mark each shard
      - processes it
    ...
Sage Weil
10:17 AM rgw Feature #4340: rgw: dr: data sync agent: implement full sync
- use special admin user
- use admin metadata api to enumerate all buckets
- use normal api to enumerat...
Sage Weil
07:39 AM devops Bug #5499: ceph-deploy --cluster clustername osd prepare fails
Amit Vijairania wrote:
> Hello! I'm running into similar issue..
>
> ***
> root@svl-swift-1:/home/ceph# /usr/lo...
Amit Vijairania
07:33 AM devops Bug #5499: ceph-deploy --cluster clustername osd prepare fails
Hello! I'm running into similar issue..... Amit Vijairania
05:22 AM Bug #5891 (Won't Fix): rados bench displaying wrong unit
When using rados bench via a gigabit Ethernet [1] I can reach up to 111.7 MB/s [2]. With a different tool I can reach... Niklas Goerke
04:01 AM rbd Bug #5890: can't remove rbd image from pool
ceph version 0.61.7 (8f010aff684e820ecc837c25ac77c7a05d7191ff) Khanh Nguyen Dang Quoc
04:01 AM rbd Bug #5890 (Closed): can't remove rbd image from pool
do rbd -p newpool ls, i see 2 images (bk_cache, bk_cache1) in there.
Then i performs delete the image bk_cache ,bu...
Khanh Nguyen Dang Quoc

08/05/2013

09:48 PM Revision 2e9c25f5 (ceph): doc: fixing reported bug in CRUSH map example.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
09:13 PM Revision cafccfaf (ceph): doc: Added many new fields to config reference.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:49 PM Revision a5d86057 (ceph): doc: Added trouble shooting entry. Fixed formatting.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:45 PM Revision e3d59a2c (ceph): doc: Nomenclature update.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:44 PM Revision 1db0f254 (ceph): doc: Nomenclature update.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:44 PM Revision a38ab07a (ceph): doc: Nomenclature update.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:44 PM Revision 0f56e3eb (ceph): doc: Nomenclature update.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:43 PM Revision ea80532d (ceph): doc: Nomenclature update. Added topic for monitor key caps. Added defau...
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
08:06 PM Revision 42582f02 (ceph): mon/PGMonitor: add 'pg dump pgs_brief' subcommand
It is useful to map OSDs to PGs and vice-versa; pg dump gives that
information, but gives a lot of other stuff. This...
Dan Mick
08:06 PM Revision db27c3f5 (ceph): qa/workunits/cephtool/test.sh: add tests for 'pg dump ...'
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:03 PM Revision 5a495b1e (ceph): Merge branch 'wip-python-cleanup' into next
Reviewed-by: Sage Weil <sage@inktank.com> Dan Mick
07:52 PM Revision a0929955 (ceph): mds: fix locking, use-after-free/race in handle_accept
We need to hold mds_lock here.
Normally the con also holds a reference, but an ill-timed connection reset
could drop...
Sage Weil
07:30 PM Revision b165d33a (ceph): rgw_admin: flush replicalog entries
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Yehuda Sadeh
07:30 PM Revision 9e88b1b4 (ceph): rgw: only log (as in ops logging) certain operations
Fixes: #5875
ops logging should (at this point) should only include object
store related operations.
Signed-off-by: ...
Yehuda Sadeh
06:21 PM Revision 28d58eba (ceph): ceph.in, ceph_rest_api.py: import only used syms from ceph_argparse.py
This makes pyflakes/pylint happier and is better practice in general
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
06:21 PM Revision 6dd4ff83 (ceph): cephtool/test.sh, rest/test.py: add tell command tests
Also add HTTP method to test.py output
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
06:20 PM Revision 55095d56 (ceph): cephtool/test.sh: add a few tests for invalid command args
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
06:20 PM Revision 71ff794e (ceph): ceph_argparse.py: add stderr note if nonrequired param is invalid
If we run across a user-supplied parameter that doesn't validate against
a non-required descriptor, it may be that it...
Dan Mick
06:20 PM Revision 9466a0b1 (ceph): Fix "too few args validate"
Check that number of validated arguments matches the number of required
arguments in the signature. Also, sort all p...
Dan Mick
05:31 PM Revision e8d72ef0 (ceph): Merge pull request #483 from ceph/wip-5881
fix invalid cluster naming in example John Wilkins
05:16 PM Revision 1cd6e2e3 (ceph): fix invalid cluster naming in example
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
03:43 PM devops Feature #5730 (Resolved): Show what command is being executed
There was not a specific pull request for this since it was included as part of a bigger refactoring.
The new modu...
Alfredo Deza
02:45 PM devops Bug #5887 (Resolved): create a `-b` flag to use a ceph-deploy branch
Teuthology does not currently allow to pass in a flag to be able to point to a `ceph-deploy` branch and it will
use...
Alfredo Deza
01:36 PM Revision 0304dfbc (ceph): Add links to OSD internals related tracker items.
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:32 PM Revision 0d1040d7 (ceph): Add links to scrub related tracker items.
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:28 PM Revision 349e7900 (ceph): Add links to peering related tracker items.
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:27 PM Revision 42361477 (ceph): Add links to recovery related tracker items.
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:13 PM devops Bug #5208 (In Progress): Debian Wheezy Needs the 'ca-certificates' package before you can wget th...
Alfredo Deza
01:09 PM Revision 12862882 (ceph): Add links to backfill related tracker items.
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:09 PM Revision 160fa710 (ceph): fix typo
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
01:09 PM CephFS Bug #5883: mds: broken locking, ref count in handle_accept

warning: Can't read pathname for load map: Input/output error.
[Thread debugging using libthread_db enabled]
Usin...
Sage Weil
12:52 PM CephFS Bug #5883 (Resolved): mds: broken locking, ref count in handle_accept
Sage Weil
01:08 PM Revision ac6f3b72 (ceph): M+K means M data + K parity and implies M chunks necessary to recover
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
12:56 PM rgw Bug #5885 (Resolved): Valgrind issue found while running s3 and swift tests
While validating some teuthology changes, a test run found a Valgrind issue with RGW. I'm attaching the archive outpu... Anonymous
12:52 PM Bug #5884 (Resolved): negative num_objects_degraded in pool stats
On `mira103` I'm seeing a negative value for `num_objects_degraded` for `pool 5`. I run `ceph pg dump pools` and see ... Noah Watkins
12:30 PM rgw Bug #5875 (Resolved): rgw: usage logging should only account object store operations
Fixed and merged, commit:9e88b1b48c1f990ae202085d0a809f8ce6b18743. Yehuda Sadeh
12:06 PM Bug #5872: ceph daemon <name> badcommand does not return error
commit:9afdea21aa072f9262155c178d6ee0da9a7b1815
Dan Mick
12:05 PM Bug #5872 (Resolved): ceph daemon <name> badcommand does not return error
Dan Mick
11:34 AM Bug #5873 (Duplicate): osd: unfound object from thrashing when all osds are up
This was probably caused by the same bug as 5799. We'll see if it comes up again with that patch in next. Samuel Just
11:33 AM devops Bug #5849 (Resolved): ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ubuntu)
Confirmed the lack of writing to the configuration file when `mon create` was being called.
Fixed and merged to ce...
Alfredo Deza
11:28 AM devops Documentation #5881 (Closed): [ceph-deploy] Naming cluster example command shows wrong example
Just merged into ceph's master branch.
Hash: e8d72ef0402a42c8aa8ea624497d13db81d5e361
Alfredo Deza
08:00 AM devops Documentation #5881 (Closed): [ceph-deploy] Naming cluster example command shows wrong example
In the ceph-deploy documentation, in the Naming Cluster section (http://ceph.com/docs/next/rados/deployment/ceph-depl... Daniele Stroppa
11:02 AM rgw Bug #5882 (Resolved): rgw: failure to lock shard should result in another error
currently returning 500, should find some appropriate 4xx error code. Yehuda Sadeh
09:25 AM Bug #4254: osd: failure to recover before timeout on rados bench and thrashing; negative stats
I think I'm seeing the negative stats again on mira103
`sudo ceph -f json-pretty pg dump pools | grep "\-"`
Noah Watkins
07:16 AM RADOS Documentation #5880 (New): erasure-code: library plugin API documentation, including a simple exa...
Loïc Dachary
07:12 AM Subtask #5879 (Resolved): jerasure plugin
"work in progress":https://github.com/ceph/ceph/pull/538
Create a standalone jerasure plugin, outside of the Ceph ...
Loïc Dachary
07:10 AM Subtask #5878 (Resolved): erasure plugin mechanism and abstract API
"work in progress":https://github.com/ceph/ceph/pull/518
The "abstract API":https://github.com/dachary/ceph/blob/w...
Loïc Dachary
07:08 AM Subtask #5877 (Resolved): Plugable erasure code library
The "plugable erasure code library":https://github.com/dachary/ceph/blob/wip-4929/doc/dev/osd_internals/erasure-code.... Loïc Dachary
03:17 AM rbd Bug #5876 (Resolved): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_reque...
Hi,
with CuttleFish with RBD kernel client (from Linux 3.9.11), I have this kernel BUG :...
Olivier Bonvalet
03:09 AM Revision 75558197 (ceph): mds: fix cap revoke confirmation
There are several issues in the Capability::confirm_receipt()
1. when receiving a client caps message with 'seq == l...
Yan, Zheng
03:09 AM Revision 3c3b2ceb (ceph): mds: revoke GSHARED cap when finishing xlock
If lock state is LOCK_XLOCKDONE, the xlocker can have GSHARED cap.
So when finishing xlock, we may need to revoke the...
Yan, Zheng
03:09 AM Revision 63a21b41 (ceph): mds: remove "type != CEPH_LOCK_DN" check in Locker::cancel_locking()
For acquiring/cancelling xlock, the lock state transitions for
dentry lock and other types of locks are the same. So ...
Yan, Zheng
03:09 AM Revision f86828d1 (ceph): mds: handle "state == LOCK_LOCK_XLOCK" when cancelling xlock
If we find lock state is LOCK_LOCK_XLOCK when cancelling xlock,
set lock state to LOCK_XLOCK_DONE and call Locker::ev...
Yan, Zheng
03:09 AM Revision 8f67adfb (ceph): mds: change LOCK_SCAN to unstable state
commit 0071b8e75b (mds: stay in SCAN state in file_eval) makes
Locker::file_eval() ignore lock in LOCK_SCAN state. If...
Yan, Zheng
03:09 AM Revision 0c22dade (ceph): mds: don't issue caps while session is stale
Locker::issue_caps() does not issue new caps to stale client,
CInode::encode_inodestat() should have the same logical...
Yan, Zheng

08/04/2013

10:41 PM Revision a0ac4875 (ceph): upgrade-parallel/rgw: use different client for final run
rgw task doesn't like to be stopped, then started as the same client.
That is probably fixable (it's just the archive...
Sage Weil
10:25 PM Bug #5869 (Fix Under Review): osd/OSD.h: 447: FAILED assert(ret) in get_map
wip-5869 Sage Weil
03:05 PM Bug #5869: osd/OSD.h: 447: FAILED assert(ret) in get_map
it's osd.2 on this run:... Sage Weil
10:24 PM Revision e5d9ac64 (ceph): qa/workunits/cephtool/test_daemon.sh: we should error on bad command
See #5872.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:54 PM Revision 18580c1d (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
09:54 PM Revision 89347539 (ceph): samba: wait for smbd process to exit
I saw
2013-08-03T12:56:26.641 DEBUG:teuthology.orchestra.run:Running [10.214.131.28]: 'sudo killall -9 smbd'
2013-08...
Sage Weil
09:14 PM rgw Bug #5875 (Resolved): rgw: usage logging should only account object store operations
Don't aggregate admin stuff, etc. The problem is that it currently does that, and moreover it sets a 'bucket' name wh... Yehuda Sadeh
09:13 PM CephFS Bug #4685: BUG: unable to handle kernel NULL pointer dereference at
proposed fix in testing branch, 'ceph: fix null pointer dereference' Sage Weil
08:59 PM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
another user hit this: http://marc.info/?l=ceph-devel&m=137566541229652&w=2 Sage Weil
03:55 PM rgw Bug #5874 (Resolved): rgw: cuttlefish cls_rgw tests fails against next
... Sage Weil
03:18 PM Bug #5873: osd: unfound object from thrashing when all osds are up
also ubuntu@teuthology:/a/teuthology-2013-08-02_01:00:11-rados-next-testing-basic-plana/93547. sitll running too Sage Weil
03:17 PM Bug #5873 (Duplicate): osd: unfound object from thrashing when all osds are up
... Sage Weil
03:16 PM Bug #5872 (Resolved): ceph daemon <name> badcommand does not return error
... Sage Weil
03:15 PM rgw Feature #5602: rgw: teuthology task to test default region as master region
I have code out for review. Branches are:
s3-tests: wip-buck-next-2
teuthology: wip-buck-5602
This work is predi...
Anonymous
03:02 PM Fix #4635: mon: many ops expose uncommitted state
teuthology-2013-08-02_01:00:11-rados-next-testing-basic-plana/93344 for a recent occurance Sage Weil
02:48 PM CephFS Bug #5871 (Resolved): client.4145 released lease on dn 1000000061b/f108 which dne
failure_reason: '"2013-08-03 12:43:47.073985 mds.0 10.214.133.35:6801/3070 2 : [WRN]
client.4145 released lease on...
Sage Weil
10:42 AM devops Bug #5849: ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ubuntu)
install should installt he deb/rpm which will mkdir /etc/ceph. mon create and osd create will put ceph.conf there. ... Sage Weil
08:34 AM devops Bug #5849 (Need More Info): ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ub...
Who's responsibility is to create `/etc/ceph.conf` ? ceph-deploy?
Because I can't find a place where `ceph-deploy...
Alfredo Deza
12:16 AM Revision 4bd5b591 (ceph): rgw.py: add None object check when parsing info
The rgw task was failing to check for a None object
when parsing user info in the case where there were
config option...
Joe Buck

08/03/2013

11:28 AM Bug #5869 (Resolved): osd/OSD.h: 447: FAILED assert(ret) in get_map
note this was from yesterday... maybe fixed now?... Sage Weil
03:59 AM Revision 9e7d6d54 (ceph): PG: set !flushed in Reset()
Otherwise, we might serve a pull before we start_flush in the
ReplicaActive constructor.
Fixes: #5799
Signed-off-by:...
Samuel Just

08/02/2013

11:05 PM Revision 826478cf (ceph): dev/osd_internals,src/osd: add erasure_coding.rst and PGBackend.h
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:34 PM Bug #5822 (Fix Under Review): ceph_argparse.py: parsing of required arguments broken
wip-5822 Dan Mick
09:03 PM Bug #5799 (Resolved): SIGABRT in build_push_op -> object_info_t::decode
Samuel Just
02:10 PM Bug #5799 (Fix Under Review): SIGABRT in build_push_op -> object_info_t::decode
Sage Weil
01:36 PM Bug #5799: SIGABRT in build_push_op -> object_info_t::decode
Sage Weil
12:03 PM Bug #5799: SIGABRT in build_push_op -> object_info_t::decode
Just kidding, ext4 just happens to be slow enough to trigger it. wip-5799. ubuntu@teuthology:/a/samuelj-5799-1/92938 Samuel Just
08:01 PM CephFS Bug #5864: cfuse_workunit_suites_ffsb suite on Centos hangs with *** Got Signal Interrupt ***
I believe that this is indicative of a problem with ceph-fuse as opposed to a teuthology issue (I could also be wrong). Anonymous
08:00 PM CephFS Bug #5864 (Closed): cfuse_workunit_suites_ffsb suite on Centos hangs with *** Got Signal Interrup...
The cfuse_workunit_suites_ffsb suite seems to get stuck with the message *** Got Signal Interrupt *** After several ... Anonymous
07:15 PM Subtask #5863 (Rejected): OSD internals must work in terms of cpg_t
A cpg_t type should be created (basically pair<pg_t, chunk_id_t>). All osd internal maps and PG<->PG messages should... Samuel Just
07:13 PM Subtask #5862 (Resolved): FileStore must work with ghobjects rather than hobjects
"pull request":https://github.com/ceph/ceph/pull/546
vhobjects should be basically tuple<hobject_t, version_t, chu...
Samuel Just
07:00 PM Revision 98f35a5e (ceph): rgw: do not ignore leaks
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:58 PM Subtask #5861 (Resolved): Refactor scrub to use PGBackend methods
ScrubMap should be adapted to allow for PGBackend specific metadata Samuel Just
06:54 PM Revision 97979866 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
06:54 PM Revision ea1243a1 (ceph): Merge remote-tracking branch 'gh/wip-rgw-leaks'
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> Sage Weil
06:48 PM Subtask #5860 (Rejected): PG::calc_acting and friends should use PGBackend to select the acting s...
Samuel Just
06:46 PM Subtask #5859 (Rejected): GetInfo should use PGBackend methods to determine when peering can cont...
Samuel Just
06:46 PM Subtask #5858 (Resolved): Backfill should be able to handle multiple backfill peers
Samuel Just
06:45 PM Subtask #5857 (Resolved): Refactor recovery to use PGBackend methods
"work in progress":https://github.com/athanatos/ceph/tree/wip-5857
"work in progress (2)":https://github.com/athanat...
Samuel Just
06:45 PM Subtask #5856 (Resolved): Refactor Backfill to use PGBackend methods
Samuel Just
06:44 PM Subtask #5855 (Resolved): Backfill peers should not be included in the acting set
Backfill peers should be included in the IO path as they currently are, but should not be included in the acting set.... Samuel Just
05:06 PM Documentation #5854 (Closed): ceph-deploy new needs to be clearer that "the names here are mon na...
Many people assume they should name all machines in the cluster in ceph-deploy new. We
need to make the documentati...
Dan Mick
05:05 PM devops Bug #5849: ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ubuntu)
and this was on ceph branch: next Tamilarasi muthamizhan
04:12 PM devops Bug #5849: ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ubuntu)
This problem also appears on Ubuntu... Anonymous
02:57 PM devops Bug #5849 (Resolved): ceph-deploy install does not create ceph.conf in /etc/ (CentOS and Ubuntu)
For some reason, `ceph-deploy install {node}` is failing to create the config files in `/etc/ceph/`
Alfredo Deza
05:02 PM Documentation #5853 (Resolved): quickstart is freaking people out about mons and osds on same mac...
http://ceph.com/docs/master/start/quick-ceph-deploy/#add-a-monitor says
Tip
In production environments, we rec...
Dan Mick
03:48 PM Feature #5648: mon should use 'module'/'perm' string in MonCommands.h for caps checking
pushed wip-5648-b with some changes! Sage Weil
02:27 PM Feature #2009 (Resolved): osd: report performance to monitor
we did this! Sage Weil
02:26 PM Tasks #5848 (Resolved): add perf counter for each RecoveryMachine state
Samuel Just
02:23 PM Tasks #5585: test large scale exapnsion and contraction
Use plana nodes to expand Ian Colle
02:13 PM devops Feature #5847: Build own versions of most recent leveldb for all supported platforms.
Related to http://tracker.ceph.com/issues/5818 Ian Colle
02:11 PM devops Feature #5847 (Resolved): Build own versions of most recent leveldb for all supported platforms.
Ian Colle
02:11 PM Bug #5754: mon: occasional osd full map not trimmed
Sage Weil
02:10 PM rbd Bug #5812: qemu-kvm guest hangs on disk write with rbd storage
The cluster is healthy and i could not find slow requests in osd logs:
ceph -s
health HEALTH_OK
monmap e1:...
Kevin Fibich
01:53 PM rbd Bug #5812: qemu-kvm guest hangs on disk write with rbd storage
Was your cluster healthy and showing no slow requests? It looks like the vm didn't have rbd caching enabled, so unles... Josh Durgin
02:07 PM Bug #5818: leveldb 1.12: hang on shutdown (mon)
Sage Weil
11:34 AM Bug #5818: leveldb 1.12: hang on shutdown (mon)
looks like this: https://code.google.com/p/leveldb/issues/detail?id=125 Sage Weil
11:29 AM Bug #5818: leveldb 1.12: hang on shutdown (mon)
(&*#@ leveldb:... Sage Weil
01:07 PM rgw Feature #4339 (Resolved): rgw: multisite: metadata sync agent: update sync processing state
Ian Colle
01:07 PM rgw Feature #4338 (Resolved): rgw: multisite: metadata sync agent: implement delta changes sync
Ian Colle
01:07 PM rgw Feature #4337 (Resolved): rgw: multisite: metadata sync agent: implement full sync
Ian Colle
01:05 PM devops Bug #5763 (Resolved): ceph-deploy new [IP] should error out
Merged into ceph-deploy master
Hash: a334df3
Alfredo Deza
01:03 PM rgw Feature #5603 (In Progress): rgw: teuthology test to check secondary region creation
Ian Colle
01:03 PM rgw Feature #5602 (In Progress): rgw: teuthology task to test default region as master region
Ian Colle
01:01 PM devops Feature #4766 (Rejected): ceph-deploy: commands should continue to execute the next argument in c...
Given the whole system is idempotent, I think it is better to fail as soon as there is an error so the user can look ... Neil Levine
12:56 PM devops Bug #5839 (Resolved): Move `mon` to the new structure
Merged into ceph-deploy master
Hash: d7d6e0638f07c3693327d68ce8283b2c8fa5c444
Alfredo Deza
07:03 AM devops Bug #5839 (Resolved): Move `mon` to the new structure
We keep seeing issues with `ceph-deploy mon` commands but they are extremely difficult to investigate because we are ... Alfredo Deza
12:07 PM rgw Bug #5415 (Resolved): rgw: failing valgrind leak checks
Sage Weil
11:54 AM devops Feature #5845 (Rejected): Automate ceph-deploy push to ceph-extras.
Ian Colle
10:55 AM Fix #5844 (Resolved): osd: snaptrimmer should throttle itself
Cuttlefish still has some problems when operating with large snapshots on cluster with large amount of objects (~100G... Andrey Korolyov
10:14 AM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
Using 'x-container-meta-{key}' to update object custom metadata should be disallowed, since it's supposed to be used ... Alexandre Marangone
10:04 AM rgw Feature #5842 (Resolved): rgw: integrate multi-region s3tests into teuthology task
Yehuda Sadeh
09:26 AM Bug #5832 (Duplicate): mon scrub mismatch
looks like it.. scrub picked up extra osdmap keys, which is how this is manifesting Sage Weil
04:05 AM Revision 3accf1c6 (ceph): rgw.py: adding a safety check
Correcting a bug where specifying
a rgw server for a client but not specifying
a system user would throw an exception...
Joe Buck
02:12 AM Revision 9110c7d8 (ceph): rgw: add log settings to example config
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
02:12 AM Revision 1787a72e (ceph): radosgw-agent: get verbose logs from the agent
This makes it a lot easier to debug.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:12 AM Revision 1ec9c1b4 (ceph): radosgw-agent: move zone extraction to helper
This will be useful for other tasks.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:12 AM Revision fdde3658 (ceph): rgw: don't make domain_root pool the same as zone root
These are supposed to be separate pools.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:11 AM Revision d79a2db5 (ceph): rgw: create system users with the --system flag
without this they have no special permissions
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:11 AM Revision 3eb62d2a (ceph): rgy.py: make log_(data|metadata) configurable
The log_data and log_metadata are made configurable
via the YAML file and default to false
(meaning neither data nor ...
Joe Buck
01:27 AM Revision ef036bd4 (ceph): Merge branch 'wip-5831' into next
Yehuda Sadeh
01:27 AM Revision 60679a0a (ceph): Merge branch 'wip-5810' into next
Yehuda Sadeh
01:27 AM Revision ae153813 (ceph): rgw: only fetch cors info when needed
Fixes: #5831
This commit moves around the cors handling code. Beforehand
we were unnecessarily reading the cors head...
Yehuda Sadeh
01:26 AM Revision b139a7cd (ceph): rgw: don't read cors attrs if there's no bucket in operation
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Yehuda Sadeh
01:26 AM Revision 43c27125 (ceph): rgw: rename sync-type to update-type
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Yehuda Sadeh
01:25 AM Revision bbac69cc (ceph): rgw: only check version if meta object exists
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Yehuda Sadeh
12:49 AM rgw Bug #5831 (Resolved): rgw: CORS info read for every request
Wip-5831 landed to next Ian Colle
12:33 AM Revision 189e04fa (ceph): rgw_sync_agent: fix a bunch of issues
- Read ceph.conf from stored copy that includes overrides
- Get system users and keys from cluster instead of reading...
Josh Durgin
12:33 AM Revision ef68b988 (ceph): radosgw-agent: rename task to match tool name
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
12:33 AM Revision f930f39b (ceph): rgw_sync_agent: add new rgw_sync_agent task
This pulls access data out of the rgw task and off disk,
and then downloads, sets up, and runs an rgw sync agent
in t...
Greg Farnum
12:33 AM Revision ad6a9e53 (ceph): rgw: ignore exit status when removing base apache dir
subdirs have already been removed, and this only needs to succeed once
per host.
Signed-off-by: Josh Durgin <josh.du...
Josh Durgin
12:06 AM Revision 48357d66 (ceph): Fix for #5836 (--lock-many with vms)
This makes --lock-many work when --machine-type vps is passed.
Before it wasn't handled correctly and guests were not...
Sandon Van Ness

08/01/2013

10:47 PM Revision 6256d681 (ceph): Add the definition of PG temp to the glossary
it is not easy to figure out what a PG temp is just by reading the
code although it is easy to understand with an exa...
Loïc Dachary
07:56 PM Revision 78b7307d (ceph): Debian ceph-deploy test. Added more supported distro yamls.
Added debian 7.0 (wheezy) testing for ceph-deploy. I also added
yaml files for other distro's supported by downburst ...
Sandon Van Ness
07:33 PM Revision 88b7d029 (ceph): Fix for Debian wheezy (remove vda from block device list)
On debian wheezy its mount output uses device-by-label and makes
our normal method of checking if a device is mounted...
Sandon Van Ness
06:39 PM Bug #5503 (New): osd: ceph --admin-daemon interface doesn't handle spaces in names
Manually tested creating keys with spaces in key and val. David suggested maybe testing objnames with space too. Pr... Dan Mick
06:11 PM Revision ab1f4386 (ceph): Merge pull request #478 from dalgaaf/wip-da-spec-req
Fix BuildRequires in SPEC file
Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
Gary Lowell
05:28 PM Revision 1552a4b9 (ceph): rgw.py: check for empty client config
Fixes a bug where an rgw client without
a system user specified would cause teuthology
to error out.
Signed-off-by: ...
Joe Buck
03:48 PM devops Bug #5835 (Resolved): Change text in package builds
Currently contains the following:
Ceph is a distributed network file system designed to provide excellent performa...
Neil Levine
03:45 PM Documentation #5834 (Resolved): Change Availability text in all of the man pages
The current man pages for ceph, rbd etc contain this paragraph:
AVAILABILITY
<COMMAND> is part of the C...
Neil Levine
03:34 PM Bug #5320 (Resolved): osd/ReplicatedPG.cc: 4753: FAILED assert(!pg_log.get_missing().is_missing(s...
...because it didn't need to be. Samuel Just
03:23 PM Bug #5320 (Pending Backport): osd/ReplicatedPG.cc: 4753: FAILED assert(!pg_log.get_missing().is_m...
This never actually got backported. Samuel Just
01:01 PM Revision caaaf2c2 (ceph): ceph.spec.in: merge back JUnit handling from SUSE spec
Merge back what we have in the (open)SUSE ceph spec file for JUnit.
Add missing Requires and the package is named jun...
Danny Al-Gaaf
01:00 PM Revision cbf3a11c (ceph): ceph.spec.in: move junit BuildRequires to the cephfs-java subpackage
JUnit is only needed by cephfs-java. Move the BuildRequires to this
subpackage.
Signed-off-by: Danny Al-Gaaf <danny....
Danny Al-Gaaf
01:00 PM Revision 4a957962 (ceph): ceph.spec.in: use snappy-devel only on RHEL derivatives
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
01:00 PM Revision 17b460c5 (ceph): ceph.spec.in: add missing buildrequires for Fedora
This patch adds two buildrequires to the ceph.spec file, that are needed
to build the rpms under Fedora. Danny Al-Gaa...
Erik Logtenberg
12:30 PM Bug #5084 (Resolved): osd: slow peering after osd restart (bobtail)
278c7b59228f614addf830cb0afff4988c9bc8cb probably took care of this? Samuel Just
12:28 PM Bug #5297 (Resolved): Slow requests after restarting an OSD (post peering)
This got merged. Samuel Just
12:25 PM Bug #5832 (Duplicate): mon scrub mismatch
/a/teuthology-2013-08-01_01:00:21-rados-next-testing-basic-plana/92213/remote
Related to #5754?
Samuel Just
12:10 PM rgw Bug #5831 (Resolved): rgw: CORS info read for every request
This is really not needed, only need to do it in the CORS related requests. Yehuda Sadeh
11:42 AM devops Bug #5617 (Resolved): ceph-deploy: log ceph version to ceph.log
Merged to ceph-deploy master branch
Hash: fc7a8e542b97d8f14fa46a80404d433075cd6ef5
Alfredo Deza
09:10 AM devops Bug #5617 (Fix Under Review): ceph-deploy: log ceph version to ceph.log
A pull request is ready to be reviewed that addresses this problem: https://github.com/ceph/ceph-deploy/pull/28 Alfredo Deza
11:02 AM rgw Bug #5789 (Resolved): rgw: can't authenticate cors requests
Tested cuttledish, that's indeed a post-cuttlefish regression, no need to backport. Yehuda Sadeh
10:55 AM Bug #5799: SIGABRT in build_push_op -> object_info_t::decode
Scheduled run: samuelj-5799-0
Job scheduled with ID 92924
Job scheduled with ID 92925
Job scheduled with ID 9292...
Samuel Just
10:24 AM Revision ef20542c (ceph): Fix for Swift key command
When creating a secret key for the Swift user, the command without the --gen-secret option generates an empty key. JP François
10:14 AM devops Bug #5499: ceph-deploy --cluster clustername osd prepare fails
Alfredo Deza wrote:
> Can you confirm the actual output in the node that is failing
I am sorry but we just rebuil...
Robert Sander
09:47 AM devops Bug #5499 (Need More Info): ceph-deploy --cluster clustername osd prepare fails
Can you confirm the actual output in the node that is failing when you run:... Alfredo Deza
09:58 AM Bug #5784 (Resolved): ceph_test_rados_watch_notify segfault
wip-5784 merged into next Ian Colle
09:48 AM Bug #5815 (Resolved): rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/mds/setm...
wip-5815 merged into next Ian Colle
09:26 AM CephFS Documentation #5797: Document unstable nature of CephFS
Pull request submitted: https://github.com/ceph/ceph/pull/479 Scott Devoid
06:01 AM Revision bbd558ad (ceph): Merge branch 'wip-5815' into next
Reviewed-by: Sage Weil <sage@inktank.com> Dan Mick
05:53 AM devops Bug #5738 (Resolved): Do not `rm- rf` the mon directory when calling destroy
Merged into `ceph-deploy` master
Hash: 19144079c6592840328d3695578d6c3a7d52fe37
Alfredo Deza
04:25 AM Revision 317d6982 (ceph): Merge branch 'wip-5784' into next
Reviewed-by: Samuel Just <sam.just@inktank.com> David Zafman
01:37 AM Bug #5823 (Can't reproduce): cpu load on cluster node is very high, client can't get data on pg ...
ceph version 0.61.7 (8f010aff684e820ecc837c25ac77c7a05d7191ff)
env: 3 cluster nodes (10 osds/node), use dedicated...
Khanh Nguyen Dang Quoc
01:11 AM Revision dc1d95d7 (ceph): rest/test.py: expect_nofail() to allow examination of reason
Also remove unused MyException
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
01:11 AM Revision c9e8ff2b (ceph): rest/test.py: retry mds setmap in case epoch has changed
Loop 10 times retrying mds dump/getmap/setmap.
Fixes: #5815
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
01:11 AM Revision c70e59ed (ceph): mon/MDSMonitor: don't call all EINVALs "unrecognized command"
Some of them are valid EINVALs (like mds setmap with the wrong epochnum)
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
01:08 AM Revision bf0061bf (ceph): Merge tag 'v0.67-rc3' into next
v0.67-rc3 Sage Weil
12:04 AM Revision 4a6eff88 (ceph): Verify that deleting op never in check_latest_map_ops map
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman

07/31/2013

11:39 PM Bug #5822 (Resolved): ceph_argparse.py: parsing of required arguments broken
Relatively-recent changes I made to ceph_argparse.py were not caught by existing (lacking) tests;
commands can be ap...
Dan Mick
11:02 PM Revision 7f76c1ce (ceph): rgw.py: refactoring to separate user creation
By separating out the user creation from
generating the region/zone info, we can generate
users for RGW tests that ru...
Joe Buck
10:51 PM Revision 600e6aca (ceph): osdc: op left in check_lastest_map_ops
Call op_cancel_map_check before cancel_op() in send_linger()
Fixes: #5784
Signed-off-by: David Zafman <david.zafman...
David Zafman
10:34 PM Revision 175feb95 (ceph): rgw_rados.cc: fix invalid iterator comparison
The iterator should be compared against the end() function of
the same iter() from region_conn_map.
CID 1058791 (#1 ...
Danny Al-Gaaf
09:18 PM Revision 8c8e9a14 (ceph): rgw.py: change --secret-key to --secret
A 'user create' call was being passed to radosgw-admin
with '--secret-key' instead of the valid '--secret'
which was ...
Joe Buck
09:02 PM Revision 1cff5bd5 (ceph): added rgw task before swift
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
08:46 PM Revision b4ed4e2e (ceph): qa/workunits/cephtool/test_daemon.sh: sudo
Fixes: #5814
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:32 PM Revision 1f7127b2 (ceph): s3/swift tests: call radosgw-admin as the right client
This allows the right region and zone info to be read from ceph.conf
Signed-off-by: Josh Durgin <josh.durgin@inktank...
Josh Durgin
08:32 PM Revision 9b2c4fa4 (ceph): s3/swift tests: call radosgw-admin as the right client
This allows the right region and zone info to be read from ceph.conf
Signed-off-by: Josh Durgin <josh.durgin@inktank...
Josh Durgin
07:47 PM Revision 2f2108b3 (ceph): rgw: fix dir creation and keyring
fastcgi_sock dir needs to exist before radosgw starts, and apache-execed radosgw needs an explicit keyring argument.
...
Josh Durgin
07:04 PM Revision c48644d8 (ceph): qa: Add workunit that hangs for manual thrasher testing
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
07:04 PM Revision 5bd061c0 (ceph): test: Fix valgrind found "Mismatched free() / delete / delete []"
Use delete[] in set_argv() so that valgrind runs clean
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
07:04 PM Revision d651658d (ceph): osdc: Add asserts that client_lock is held
Clarify locking by indicating that client_lock is held
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
06:12 PM Bug #5815 (Fix Under Review): rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/...
Fix test failure by adding 10x retry to "get epoch, set epoch+1".
wip-5815
Dan Mick
02:09 PM Bug #5815: rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/mds/setmap?epoch=11
Also, as Sage points out, "unrecognized command" isn't really useful here.
Dan Mick
02:09 PM Bug #5815: rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/mds/setmap?epoch=11
OK, this is mds setmap racing against the epoch number we got from mds dump. Possible fixes: retry N times or just s... Dan Mick
10:58 AM Bug #5815: rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/mds/setmap?epoch=11
ubuntu@teuthology:/a/teuthology-2013-07-31_01:00:23-rados-next-testing-basic-plana/91048 Samuel Just
10:57 AM Bug #5815 (Resolved): rest/test.py failure: FAILURE: url http://localhost:5000/api/v0.1/mds/setm...
... Samuel Just
04:09 PM CephFS Documentation #5797: Document unstable nature of CephFS
the docs are under <ceph-sources>/doc/cephfs/ Zheng Yan
04:03 PM CephFS Bug #5649: smbtorture test gets ebusy on kclient umount
kclient bug or test script bug ? Zheng Yan
04:01 PM CephFS Bug #5649 (In Progress): smbtorture test gets ebusy on kclient umount
ubuntu@teuthology:/a/teuthology-2013-07-31_01:01:24-fs-next-testing-basic-plana/91313 Tamilarasi muthamizhan
02:44 PM rgw Feature #5821 (Resolved): Alias --secret-key to --secret for radosgw-admin
It seems like 'secret key' and '--secret-key' are the predominant way to refer to the secret for an RGW user but the ... Anonymous
02:41 PM rgw Bug #5820 (Resolved): radosgw-admin should fail on non-valid flags
A bug in the RGW teuthology task was encountered today where the --secret flag for user creation was being passed in ... Anonymous
02:17 PM rbd Feature #5167: openstack: cinder: differential backups
https://review.openstack.org/#/c/35216/ Josh Durgin
02:17 PM rbd Feature #5168: openstack: cinder: rbd as a backup target
https://review.openstack.org/#/c/34346/ Josh Durgin
02:15 PM rbd Feature #5465: openstack: cinder: support resize with rbd
https://review.openstack.org/#/c/36415/ Josh Durgin
01:47 PM Bug #5814 (Resolved): test_daemon.sh - [Errno 13] Permission denied
Sage Weil
01:38 PM Bug #5814: test_daemon.sh - [Errno 13] Permission denied
Dan Mick wrote:
> teuthworker can't passwordless sudo, although ubuntu can; that might complicate things. Should we...
Sage Weil
01:22 PM Bug #5814: test_daemon.sh - [Errno 13] Permission denied
teuthworker can't passwordless sudo, although ubuntu can; that might complicate things. Should we make teuthworker b... Dan Mick
12:54 PM Bug #5814: test_daemon.sh - [Errno 13] Permission denied
Script just needs to sudo I think Sage Weil
10:58 AM Bug #5814: test_daemon.sh - [Errno 13] Permission denied
ubuntu@teuthology:/a/teuthology-2013-07-31_01:00:23-rados-next-testing-basic-plana/91029 Samuel Just
10:55 AM Bug #5814 (Resolved): test_daemon.sh - [Errno 13] Permission denied
2013-07-31T01:56:50.625 INFO:teuthology.task.workunit.client.0.err:[10.214.132.26]: will thrash map for 10 epochs
20...
Samuel Just
01:32 PM devops Bug #5819 (Won't Fix): redhat-rpm-config package needed for debuginfo packages
Just a note to fix up the spec file, or otherwise document the requirement. On rhel, the debug packages are built by... Anonymous
01:09 PM Bug #5784 (Fix Under Review): ceph_test_rados_watch_notify segfault
David Zafman
12:06 PM rgw Feature #5607 (Resolved): s3-tests: new tests for multi region
Yehuda Sadeh
12:06 PM rgw Feature #5606 (Resolved): s3-tests: run in multi region setup
Yehuda Sadeh
12:00 PM rgw Bug #5810 (Rejected): rgw: update_type does not work correctly when meta object does not exist (o...
Ok, after discussing that with Josh, he reminded me that we don't really replay the log. What we do is always fetchin... Yehuda Sadeh
11:11 AM rgw Bug #5810: rgw: update_type does not work correctly when meta object does not exist (or removed)
Issue #2 (not checking versions for removal operations) can be fixed easily.
Was thinking about issue #2. Note tha...
Yehuda Sadeh
11:33 AM Bug #5818 (Won't Fix): leveldb 1.12: hang on shutdown (mon)
ubuntu@teuthology:/a/teuthology-2013-07-31_01:00:23-rados-next-testing-basic-plana/91208
The processes are still r...
Samuel Just
10:23 AM Bug #5799: SIGABRT in build_push_op -> object_info_t::decode
I think this may have been an ext4 xattr error. Either way, we'll have to reproduce it. Samuel Just
09:34 AM devops Bug #5813 (Closed): Normalize ceph-deploy Exceptions for better error reporting
ceph-deploy raises many different types of exceptions which makes it difficult for better reporting of the tool's err... Alfredo Deza
09:21 AM devops Bug #5763: ceph-deploy new [IP] should error out
Added a validator to `ceph-depoy new` so that we prevent this from happening.
Pull request was opened: https://gi...
Alfredo Deza
09:04 AM Bug #5503 (Resolved): osd: ceph --admin-daemon interface doesn't handle spaces in names
Ian Colle
08:14 AM devops Bug #4936 (Resolved): ceph-deploy fails to report errors
I am closing this as the new logging features will log verbosely to the terminal by default.
Errors should be more...
Alfredo Deza
08:02 AM rbd Bug #5812 (Closed): qemu-kvm guest hangs on disk write with rbd storage
qemu-kvm VM with rbd backed storage works until guest tries to write data, then kernel_hung task messages appear.
...
Kevin Fibich
06:10 AM Revision 2b6ac0fa (ceph): rados/.../cephtool: let us run test_daemon.sh too
This needs the mon to be mon.a; rename it.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:08 AM Revision 00dc6344 (ceph): ceph: developer mode: set PATH, too
Otherwise the call to ceph-conf may fail if it is not installed on the
local machine.
Signed-off-by: Sage Weil <sage...
Sage Weil
06:04 AM Revision e70e08c0 (ceph): cephtool/test.sh: add tests for mon daemon command
[Also move into a separatate test script; validate result -sage]
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Sign...
Sage Weil
05:45 AM devops Bug #5728 (Resolved): Capture std(err|out) and exit code for better error reporting
Merged into master ceph-deploy
Hash: a451465438174f68e3d6b216c13387fdaa954fe2
Alfredo Deza
05:28 AM Revision 47d0d64d (ceph): Make all AdminSocket commands use argparse/cmdmap.
Fixes regression in daemon commands with arguments; also resolves
reported bug with existing daemon code for argument...
Dan Mick
12:26 AM Revision 74b344e9 (ceph): Reconnect after running chef task.
Just a simple change to reconnect to SSH after running
ceph-qa-chef to get around things like ulimit changes.
Signed...
Sandon Van Ness
12:13 AM devops Bug #5811 (Resolved): gperftools-{devel,libs}-2.0.11.el6 appears to be broken (centos6/rhel6)
Configure complains that tcmalloc can not be found. The log shows the configure test program failed with sem_init() ... Anonymous

07/30/2013

11:55 PM Revision 3fa1cd20 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
11:17 PM rgw Feature #5604 (In Progress): rgw: teuthology tests to check various user creation issues on multi...
*sigh*
wip-region-sync contains a teuth task that sets up the sync agent (apparently successfully). Unfortunately I'...
Greg Farnum
11:11 PM Bug #5800 (Resolved): admin socket arg validation broken
Sage Weil
06:25 PM Bug #5800 (In Progress): admin socket arg validation broken
Just figuring out test/admin_socket.cc Dan Mick
11:03 PM Revision 736d6a1b (ceph): rgw: fix set_buckets_enabled(), set_bucket_owner()
Fixes: 5808
We cannot call get_bucket_instance_info() at that point,
as the bucket structure wasn't initialized, so ...
Yehuda Sadeh
10:52 PM Revision 0e125e0e (ceph): Objecter: set c->session to NULL if acting is empty
Otherwise, we might leave a session attached to the
CommandOp for an down OSD. handle_osd_map will then
delete the s...
Samuel Just
10:17 PM devops Bug #5777: ceph-deploy: gatherkeys fails on ubuntu precise
does /var/run/ceph/ceph-mon.node01.asok exist? what happens if you do 'ceph --admin-daemon /var/run/ceph/ceph-mon.no... Sage Weil
10:08 PM devops Bug #5777: ceph-deploy: gatherkeys fails on ubuntu precise

root@node01:~# ceph-create-keys -i node01
admin_socket: exception getting command descriptions: [Errno 2] No such ...
vlad karm
07:15 AM devops Bug #5777: ceph-deploy: gatherkeys fails on ubuntu precise
what is the output on the node01 from 'ceph-create-keys -i `hostname`' ? Sage Weil
12:53 AM devops Bug #5777: ceph-deploy: gatherkeys fails on ubuntu precise
Same again on
Ubuntu 13.04 (GNU/Linux 3.8.0-19-generic x86_64)
root@manage:~/cluster# ceph-deploy install --dev ...
vlad karm
09:37 PM Revision 16adb916 (ceph): v0.67-rc3
Gary Lowell
08:31 PM Revision e747fa8e (ceph): Revert "Use dh_installinit to install upstart job files"
This reverts commit 251a6a498d07f7873b0e15b0ca2caf7f12c48f04.
This includes /etc/init.d/radosgw in the ceph package,...
Sage Weil
07:40 PM Revision 60cbed3f (ceph): Merge remote-tracking branch 'gh/wip-mon' into next
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> Sage Weil
07:36 PM Revision 00c2ac5b (ceph): Fix RHEL/centos ceph-deploy installs.
Use a hiphen as a diliminator instead of a dot.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
06:12 PM rbd Feature #5465 (Resolved): openstack: cinder: support resize with rbd
Josh Durgin
06:10 PM rbd Feature #5167 (Resolved): openstack: cinder: differential backups
Josh Durgin
06:10 PM rbd Feature #5168 (Resolved): openstack: cinder: rbd as a backup target
Josh Durgin
05:55 PM rgw Bug #5810 (Rejected): rgw: update_type does not work correctly when meta object does not exist (o...
Two related but separate issues:
- when creating a new object, update-type=update-by-version doesn't work at all (t...
Yehuda Sadeh
05:47 PM Revision e1cd49bd (ceph): ceph_manager: wait 20s before wait_for_clean in test_map_discontinuity
Fixes: #5806
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
05:41 PM Revision bcf467c8 (ceph): Remove now unnecessary try/except/raise that came about as a result of
the previous check-in.
Fixes: #5803
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
05:40 PM Revision 48a977e0 (ceph): Always raise exception if yum install fails. This avoids later confusi...
packages are missing (the old code skipped 'Nothing to do' messages, but these
cases are still errors).
Fixes #5803
...
Warren Usui
04:05 PM rgw Bug #5808 (Resolved): rgw: can't suspend user
Yehuda Sadeh
04:05 PM rgw Bug #5808: rgw: can't suspend user
Fixed, commit:736d6a1bde71919f7469218684c12793a9532aeb Yehuda Sadeh
01:53 PM rgw Bug #5808 (Resolved): rgw: can't suspend user
teuthology-2013-07-30_01:01:13-rgw-next-testing-basic-plana, 89678 Yehuda Sadeh
03:55 PM Bug #5798 (Resolved): librados: mutex assertion in SimpleMessenger::submit_message
Samuel Just
02:53 PM Bug #5798: librados: mutex assertion in SimpleMessenger::submit_message
(gdb) print *this
$5 = {<RefCountedObject> = {_vptr.RefCountedObject = 0xd66500, nref = {val = 140461764831096}}, lo...
Samuel Just
02:45 PM Bug #5798: librados: mutex assertion in SimpleMessenger::submit_message
2013-07-29T10:59:31.528 INFO:teuthology.task.workunit.client.0.out:[10.214.133.35]: [ RUN ] LibRadosCmd.PGCmd
Samuel Just
02:43 PM Bug #5798: librados: mutex assertion in SimpleMessenger::submit_message
binary was ceph_test_rados_api_cmd Samuel Just
12:50 PM Bug #5798: librados: mutex assertion in SimpleMessenger::submit_message
There is a chance that this may be related to #5784. Samuel Just
03:40 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
... Joao Eduardo Luis
02:02 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
Just saw it is; my connection to that machine is however painfully slow. Will update as soon as I figure something else. Joao Eduardo Luis
01:56 PM Bug #5804: mon: binds to 0.0.0.0:6800something port
Is the monitor being specified in 'mon initial members'? Joao Eduardo Luis
03:11 PM Bug #5754: mon: occasional osd full map not trimmed
pretty sure this is https://code.google.com/p/leveldb/issues/detail?id=178. fixed https://code.google.com/p/leveldb/... Sage Weil
02:47 PM CephFS Bug #5367 (Resolved): multiclient tests: kernel mount gets EPERM
We can reopen if we see this again, but the tests are now checking (and chef is setting) the uid for the ubuntu (test... Greg Farnum
02:47 PM CephFS Bug #5761: teuthology: MPI test sometimes fails with a permission denied
Essentially a duplciate of #5637 — mismatched UIDs on different nodes. Greg Farnum
02:30 PM CephFS Bug #5761 (Resolved): teuthology: MPI test sometimes fails with a permission denied
Sage Weil
02:38 PM Bug #5616 (Resolved): repeated mon elections
Sage Weil
10:50 AM Bug #5806 (Resolved): osd: unfound objects on next!
Hopefully fixed with teuthology hack on next: e1cd49bd4558f7491e11b2bffe9355001661f81f Samuel Just
10:38 AM Bug #5806: osd: unfound objects on next!
This is a problem with the test, when we mark an osd up, there is lag before the pgs transitions from active+clean. ... Samuel Just
10:27 AM Bug #5806 (In Progress): osd: unfound objects on next!
Samuel Just
09:28 AM Bug #5806 (Resolved): osd: unfound objects on next!
ubuntu@teuthology:/a/teuthology-2013-07-30_01:00:15-rados-next-testing-basic-plana/89584
cluster is hung in recovery
Sage Weil
07:58 AM CephFS Bug #5805 (Need More Info): mds: crash loading sessionmap
log shows the missing object is snaptable instead of sessionmap. The log does not give us any clue how this happened ... Zheng Yan
07:16 AM CephFS Bug #5805 (Can't reproduce): mds: crash loading sessionmap
ftp://ftp.ts.fujitsu.com/outgoing/mds.0_crash-logs.tar.gz Sage Weil
06:10 AM devops Bug #5728: Capture std(err|out) and exit code for better error reporting
There is a pull request waiting for testing that enables full logging and actual remote actions in the remote host.
...
Alfredo Deza
05:19 AM Revision ebab04e0 (ceph): mon: add missing state name
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:14 AM Revision b8af38b6 (ceph): mon: allow others to sync from us across bootstrap calls
If someone is syncing from us and there is an election, they currently get
reset and have to restart their sync. Thi...
Sage Weil
12:10 AM Revision 634dcf33 (ceph): mon: drop useless sync_reset() calls
These are both right before bootstrap(), which also resets.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
12:07 AM Revision b9c7445b (ceph): More changes for creating vms manually with lock (no config)
Needed some more changes to allow for the case of creating vm's
manually with teuthology-lock instead of letting teut...
Sandon Van Ness

07/29/2013

11:34 PM Revision d41b4e5e (ceph): Fixing teuthology-lock for os-type instead of vm-type.
Teuthology got updated to use --os-type and os_type in yaml
instead of --vm-type. I added this to teuthology but forg...
Sandon Van Ness
11:09 PM Revision f7d1902c (ceph): mon/Paxos: be more vocal about calling elections
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:11 PM Revision eb6e6da1 (ceph): rgw: keep a region connection map
Fixes: #5793
Beforehand all remote copies were going to the master region
which was awfully wrong.
Signed-off-by: Y...
Yehuda Sadeh
10:11 PM Revision f10c2e74 (ceph): rgw: cors subresource needs to be in canonical auth header
Fixes: #5789
This was fixed before, however, might have been lost due to
recent refactoring + merge.
Signed-off-by:...
Yehuda Sadeh
10:09 PM Revision 3f5352ac (ceph): Merge pull request #463 from toabctl/upstart-handling
Use dh_installinit to install upstart job files
Reviewed-by: Gaudenz Steinlin <gaudenz@debian.org>
Sage Weil
10:06 PM Revision acd16d1a (ceph): rgw: read / write bucket attributes from bucket instance
and not from bucket entry point.
Fixes: #5770
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Greg Fa...
Yehuda Sadeh
10:06 PM Revision 68730d80 (ceph): rgw: track bucket instance oid
We now keep the bucket instance oid in rgw_bucket. The reason
we need it is that the bucket might have been created b...
Yehuda Sadeh
10:06 PM Revision b5e74485 (ceph): rgw: set bucket attrs are a bucket instance meta operation
Need to do the action through the bucket instance handler
and not through the bucket handler, otherwise it's wrongly
...
Yehuda Sadeh
09:31 PM Bug #5804 (Resolved): mon: binds to 0.0.0.0:6800something port
it keeps binding to 0.0.0.0:6801 instead of the mon addr.. why? Sage Weil
09:10 PM Revision 99a79c6c (ceph): rados_util: adjust-ulimits, not enable-coredump
This was responsible for the lost_unfound test breakage.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:45 PM Revision 8284e192 (ceph): ceph_manager: wait for all_up in test_map_discontinuity
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:13 PM Revision f3eda634 (ceph): mon/PGMonitor: fix 'pg dump_[pools_]json'
Use the correct type for the dumpcontents arg. Fixes the dump_pools_json
output and avoids these errors:
2013-07-29...
Sage Weil
08:01 PM Revision 099ac518 (ceph): mon: fix xml element name
Should be the type, not the name.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
07:49 PM Revision ee9f04c5 (ceph): check_new_interval must compare old acting with old osdmap
When trying to establish if the old acting set is either empty or
smaller than the min_size of the osdmap,
pg_interva...
Loïc Dachary
07:49 PM Revision 1f13d8ac (ceph): OSD: suspend tp timeout while taking pg lock in OpWQ
If N op_tp threads are configured, and recovery_max_active
is set to a sufficiently large number, all N op_tp threads...
Samuel Just
07:49 PM Revision f1bd4e5b (ceph): WorkQueue: fix bracing on reset_tp_timeout
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
07:12 PM Revision e703942c (ceph): ceph_manager: allow-experimental-feature now causes an EINVAL
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
07:12 PM Revision a6cd9fea (ceph): osd: get initial full map after a map gap
If there is a gap in our map history, get the full range of maps that
the mon has. Make sure the first one is a full...
Sage Weil
07:11 PM Revision e24b5022 (ceph): osd: fix off-by-one in map gap logic
If we have map 250, and monitor's first is 251, but sends 260, we can
request the intervening range.
Fixes: #5784
Si...
Sage Weil
06:00 PM Revision 1cb3216c (ceph): Merge pull request #425 from dachary/wip-5527
unit tests for sharedptr_registry
Reviewed-by: Samuel Just <sam.just@inktank.com>
athanatos
04:09 PM Revision 9dac3fe8 (ceph): s3tests: clone correct branch
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
04:09 PM Revision 3b3816df (ceph): s3tests: clone correct branch
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
04:01 PM Bug #5800 (Resolved): admin socket arg validation broken
flab:src 04:00 PM $ ./ceph daemon mon.a config set debug_ms 1
*** DEVELOPER MODE: setting PYTHONPATH and LD_LIBRARY_...
Sage Weil
03:52 PM rgw Bug #5789: rgw: can't authenticate cors requests
I think it only broke post cuttlefish, then probably not. Yehuda Sadeh
03:50 PM rgw Bug #5789 (Pending Backport): rgw: can't authenticate cors requests
In next, commit:f10c2e746ef5b9921b808450e75f2a90070e05bc.
Does this need backports? An earlier iteration of this b...
Greg Farnum
10:35 AM rgw Bug #5789 (Fix Under Review): rgw: can't authenticate cors requests
Yehuda Sadeh
10:26 AM rgw Bug #5789 (Resolved): rgw: can't authenticate cors requests
Yehuda Sadeh
03:49 PM rgw Bug #5793 (Resolved): rgw: cross region copy requests not always going to the correct region
Fixed in next commit:eb6e6da1a90d3d94d623650556d78e56d04ab3a1 Greg Farnum
10:40 AM rgw Bug #5793 (Fix Under Review): rgw: cross region copy requests not always going to the correct region
Yehuda Sadeh
10:36 AM rgw Bug #5793 (Resolved): rgw: cross region copy requests not always going to the correct region
Because instead of a region connection map, we only keep a single connection that points at the master region. Yehuda Sadeh
03:48 PM rgw Bug #5791 (Resolved): rgw: bucket set_attr operations are logged in wrong metadata section
Fixed in next commit:b5e74485d94d033478f791535423a8b8bef88326 Greg Farnum
10:45 AM rgw Bug #5791 (Fix Under Review): rgw: bucket set_attr operations are logged in wrong metadata section
Yehuda Sadeh
10:32 AM rgw Bug #5791: rgw: bucket set_attr operations are logged in wrong metadata section
these operations are done on the bucket instance, however, they're being logged to the bucket section (and not to buc... Yehuda Sadeh
10:29 AM rgw Bug #5791 (Resolved): rgw: bucket set_attr operations are logged in wrong metadata section
Yehuda Sadeh
03:47 PM rgw Bug #5790 (Resolved): rgw: access correct bucket instance object
Fixed in next, commit:68730d80c8aa393a583c92052ef5ffd11efe17a6 Greg Farnum
10:45 AM rgw Bug #5790 (Fix Under Review): rgw: access correct bucket instance object
Yehuda Sadeh
10:29 AM rgw Bug #5790 (Resolved): rgw: access correct bucket instance object
For buckets that were created before the bucket entrypoint - instance split, the bucket entry point holds the bucket ... Yehuda Sadeh
03:46 PM rgw Bug #5770 (Resolved): rgw: cors, bucket attrs info kept on bucket entry point instead of bucket i...
Fixed in next, commit:acd16d1aed0f6146c84a377be9fef1d7f54c6bed Greg Farnum
10:45 AM rgw Bug #5770 (Fix Under Review): rgw: cors, bucket attrs info kept on bucket entry point instead of ...
Yehuda Sadeh
03:15 PM Revision 3f13751f (ceph): Merge pull request #20 from ceph/double-requirements
fix double requirements issue Zack Cerza
03:09 PM Revision 17fa5440 (ceph): fix double requirements issue
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
03:06 PM devops Bug #5738 (Fix Under Review): Do not `rm- rf` the mon directory when calling destroy
wip-5738 Sage Weil
02:50 PM devops Bug #5777 (Resolved): ceph-deploy: gatherkeys fails on ubuntu precise
seems to work fine on ceph version 0.67-rc2-184-g1cb3216-1precise, ie the latest next branch. Tamilarasi muthamizhan
02:15 PM Bug #5798: librados: mutex assertion in SimpleMessenger::submit_message
Samuel Just
02:13 PM Bug #5798 (In Progress): librados: mutex assertion in SimpleMessenger::submit_message
Samuel Just
12:54 PM Bug #5798 (Resolved): librados: mutex assertion in SimpleMessenger::submit_message
... Sage Weil
02:15 PM Bug #5799 (In Progress): SIGABRT in build_push_op -> object_info_t::decode
Samuel Just
01:29 PM Bug #5799 (Resolved): SIGABRT in build_push_op -> object_info_t::decode
... Sage Weil
02:11 PM Bug #5749: osd: unfound objects on cuttlefish
oops wrong bug Sage Weil
01:45 PM Bug #5749 (In Progress): osd: unfound objects on cuttlefish
Sage Weil
02:10 PM Bug #5748 (Resolved): osd: unfound object test is failing to produce unfound objects
teuthology.git bug, commit:99a79c6c1f2927b73003f13e9b08be892fa7cd50 Sage Weil
01:59 PM Bug #5748 (In Progress): osd: unfound object test is failing to produce unfound objects
Samuel Just
02:01 PM Bug #5780 (Resolved): the size of the old acting set should be compared with the min_size of the ...
Loïc Dachary
01:53 PM Bug #5784: ceph_test_rados_watch_notify segfault
Samuel Just
01:52 PM Bug #5784 (Resolved): ceph_test_rados_watch_notify segfault
Samuel Just
01:50 PM Bug #5783 (Resolved): osd: recovery timeout
The first appeared not to be hung. The second should be fixed with teuthology commit 8284e19226a2f15435974af99bc3d80... Samuel Just
01:29 PM Bug #5783: osd: recovery timeout
ubuntu@teuthology:/a/teuthology-2013-07-29_09:44:34-rados-next-testing-basic-plana/88630 Sage Weil
01:33 PM CephFS Bug #5649 (Resolved): smbtorture test gets ebusy on kclient umount
Sage Weil
01:33 PM Bug #5779 (Resolved): ceph-rest-api: missing requests dependency onpackage?
Sage Weil
01:14 PM Bug #5786 (Resolved): mon/rest-api: pg dump test gives mon bad command?
Sage Weil
01:11 PM rbd Bug #5426: librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::complete()
nevermind, the PerfCounters is invalid too, with m_lower_bound = 22777856, m_upper_bound = 0 Josh Durgin
01:06 PM rbd Bug #5426: librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::complete()
Reproduced after 22 tries with no debugging on. Couldn't reproduce without debugging, but this is a start.
The Per...
Josh Durgin
12:59 PM rbd Bug #5488: librbd: deadlock in image refresh
Another potential deadlock popped up: md_lock vs librados' lock ordering. Still trying to find which callback takes t... Josh Durgin
12:53 PM Revision 251a6a49 (ceph): Use dh_installinit to install upstart job files
Signed-off-by: Thomas Bechtold <thomasbechtold@jpberlin.de> Thomas Bechtold
12:46 PM CephFS Documentation #5797 (Resolved): Document unstable nature of CephFS
Apparently CephFS is not production-ready, especially not in multi-mds configurations?
>nhm: We should probably pu...
Scott Devoid
12:24 PM Feature #5796 (New): formatter: send output to ostream
Instead of accumulating the result in memory and doing a final f->flush(outputbuffer), set the output/sink (ostream!)... Sage Weil
12:12 PM Bug #5782 (Resolved): osd: off-by-one on map gap handling?
Sage Weil
10:36 AM Bug #5792 (Resolved): ceph-deploy mon create hangs on fedora18 vm's
Aall the nightlies are hanging on fedora when running ceph-deploy mon create. example:
2013-07-28T01:18:11.681 DEB...
Sandon Van Ness
10:10 AM devops Bug #5405 (Resolved): ceph-deploy: transient pushy exception on install
Sage Weil
09:58 AM devops Feature #5016 (Resolved): ceph-deploy: gitbuilders for release packages
All ceph-deploy gitbuilders are happy now. Anonymous
09:34 AM devops Bug #5778: gitbuilders use cryptopp instead of nss libraries
if the configure fix isn't quick, let's add the --without-cryptopp Sage Weil
09:11 AM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
Greg Farnum wrote:
> If the inode is >4MB, shouldn't the oset have more than one object? Sounds like maybe we lost t...
Sage Weil
09:08 AM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
If the inode is >4MB, shouldn't the oset have more than one object? Sounds like maybe we lost track of an in-flight w... Greg Farnum
03:43 AM Revision b62845e7 (ceph): doc/changelog/v0.61.7
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

07/28/2013

11:17 PM Revision ee18322e (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
11:17 PM Revision a46f60af (ceph): doc/dev/repo-lab-access: notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:42 PM Revision 7a1d6d3e (ceph): ceph_test_rados: print version banner on startup
It is helpful when looking at qa run logs to see what version of the
tester is running.
Signed-off-by: Sage Weil <sa...
Sage Weil
10:42 PM Revision 12c1f115 (ceph): ceph_test_rados: print version banner on startup
It is helpful when looking at qa run logs to see what version of the
tester is running.
Signed-off-by: Sage Weil <sa...
Sage Weil
10:34 PM Revision 86769f05 (ceph): ceph_test_rados: add --pool <name> arg
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit bcfbd0a3ffae6947464d930f636c8b35d1331e9d)
Sage Weil
10:29 PM Revision 74c1bec2 (ceph): ceph-authtool: fix cli tests
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:27 PM Revision 7b683f7f (ceph): test/system/*: parse CEPH_ARGS environment
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:26 PM Revision be732159 (ceph): Merge pull request #474 from dalgaaf/wip-da-next-fix-help
Add missing commands to help/usage and manpage of ceph-authtool
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
10:24 PM Bug #5780: the size of the old acting set should be compared with the min_size of the old osdmap
Sam - please review Ian Colle
05:11 AM Bug #5780 (Fix Under Review): the size of the old acting set should be compared with the min_size...
Loïc Dachary
04:47 AM Bug #5780 (Resolved): the size of the old acting set should be compared with the min_size of the ...
"work in progress":https://github.com/dachary/ceph/tree/wip-5780
"pg_interval_t::check_new_interval":https://githu...
Loïc Dachary
10:19 PM rgw Bug #5416 (Resolved): --help output needs --rgw-zone option
Ian Colle
04:55 PM rgw Bug #5416: --help output needs --rgw-zone option
Issue should be closed as https://github.com/ceph/ceph/commit/7a7fca46fb1e8e3a121279b45fa9ce687d29b788 fixed it. Christophe Courtaut
10:09 PM Revision 0158f0db (ceph): adjust-ulimits: 16k open files
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:03 PM Revision 2f921c33 (ceph): upgrade-parallel/stress-split: only upgrade on the first node
In particular, we need the client and half the osds to stay at cuttlefish.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:39 PM Revision 347b5a20 (ceph): ceph-authtool.8: add missing commands to man page
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:25 PM Revision 86b26328 (ceph): ceph_authtool.cc: update help/usage text
Added implemented but not listed commands to the help/usage text:
* -g shortcut for --gen-key
* -a shortcut for --a...
Danny Al-Gaaf
08:52 PM Bug #5788 (Resolved): ceph: try new, fallback to old can race with daemon upgrade
- cli tries new style, gets EINVAL
- mon upgrades from old -> new
- cli tries old style, gets EINVAL
it should p...
Sage Weil
03:24 PM CephFS Bug #5787 (Need More Info): client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
Sage Weil
03:24 PM CephFS Bug #5787 (Duplicate): client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
... Sage Weil
03:19 PM Revision 4b6c569a (ceph): mon/DataHealthService: do not name xml key after mon
The name might be something like '0', which is illegal. This should be
the *type*, not name.
Signed-off-by: Sage We...
Sage Weil
09:28 AM Bug #5786 (Resolved): mon/rest-api: pg dump test gives mon bad command?
... Sage Weil
09:17 AM Bug #5785 (Resolved): librados: deadlock during shutdown
the monc locking for librados shutdown looks broken. although the whole thing appears a bit wonky.... Sage Weil
09:10 AM Bug #5749: osd: unfound objects on cuttlefish
HEALTH_WARN 2 pgs recovering; 2 pgs stuck unclean; recovery 101/1942 degraded (5.201%); 24/971 unfound (2.472%)
root...
Sage Weil
09:05 AM Bug #5782 (Fix Under Review): osd: off-by-one on map gap handling?
wip-5782 Sage Weil
08:21 AM Bug #5782 (Resolved): osd: off-by-one on map gap handling?
off by one on map gap... Sage Weil
08:28 AM Bug #5784 (Resolved): ceph_test_rados_watch_notify segfault
... Sage Weil
08:24 AM Bug #5783 (Resolved): osd: recovery timeout
no obvious crashes.... Sage Weil
07:59 AM CephFS Bug #5367: multiclient tests: kernel mount gets EPERM
ah, a few do! the ones this test failed on don't, but maybe they were reimaged since then. Sage Weil
02:09 AM CephFS Bug #5367: multiclient tests: kernel mount gets EPERM
can't reproduce locally. Is it possible your clients have different 'username -> uid' mapping? Zheng Yan
03:57 AM Revision fb8882b5 (ceph): upgrade-parallel: run cuttlefish api tests against cuttlefish/dumpling ...
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:36 AM Revision d5a1d0a4 (ceph): upgrade-fs: specify fs
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:29 AM Revision 419e90e3 (ceph): upgrade-parallel: run cuttlefish s3tests against hybrid cluster
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:26 AM Revision 7646133e (ceph): upgrade-parallel: restart mon after starting osd thrasher
The tell mon.* currently blocks forever if all mons aren't up. Sage Weil
12:56 AM Revision 496c6773 (ceph): ceph_manager, dump_stuck: fix injectargs args
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:34 AM Revision dd3b0865 (ceph): Merge pull request #464 from toabctl/fuse-utils-obsolete
Remove fuse-utils from Recommends in debian/control
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:32 AM Revision 6881ab3b (ceph): debian, rpm: make python-ceph depend on python-requests
For ceph-rest-api.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil

07/27/2013

07:30 PM Revision 73adf333 (ceph): radosgw-admin: fix typo in import
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
06:40 PM Bug #5779: ceph-rest-api: missing requests dependency onpackage?
please review commit:6881ab3b39259adcd7aed7026ccae1cba1db7aa1 Sage Weil
05:49 PM Bug #5779 (Fix Under Review): ceph-rest-api: missing requests dependency onpackage?
Sage Weil
07:35 AM Bug #5779 (Resolved): ceph-rest-api: missing requests dependency onpackage?
in qa i see... Sage Weil
05:51 PM Bug #5754: mon: occasional osd full map not trimmed
a mon transaction dump clearly shows the key being removed, and it is then visible later.
other evidence that this...
Sage Weil
03:11 PM Revision 6b16cd1a (ceph): unit tests for sharedptr_registry
Covers 100% of the LOC and all the expected behavior, including thread
safety.
The sharedptr_registry is made friend...
Loïc Dachary
03:11 PM Revision 2ec480b1 (ceph): replace in_method_t with a counter
A single counter ( waiting ) accurately reflects the number of
waiters, regardless of the method waiting. It is enoug...
Loïc Dachary
02:49 PM Revision 45ce9b0b (ceph): valgrind: suppress curl, gnutlss, libfcgi leaks
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:48 PM Revision a039d4ad (ceph): ceph_manager: don't mark out an out osd on kill_osd(..., mark_out=True)
Fixes
2013-07-27T02:02:23.879 INFO:teuthology.task.thrashosds.thrasher:Recovered, killing an osd
2013-07-27T02:02:23...
Sage Weil
02:33 PM Revision b5250fdc (ceph): Merge pull request #471 from dalgaaf/wip-da-fix-pylint
Cleanup minor issues from pylint
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:47 PM devops Bug #5777: ceph-deploy: gatherkeys fails on ubuntu precise
Same here
Ubuntu 12.04.2 LTS (GNU/Linux 3.2.0-49-generic x86_64)
# ceph version 0.61.7 (8f010aff684e820ecc837c25...
vlad karm
09:37 AM Revision 09ee092f (ceph): pybind/rbd.py: remove unused import of 'pointer'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:37 AM Revision 24601180 (ceph): cephfs.py: remove unused imports
Removed ctypes, c_uint64, c_ubyte, pointer, CFUNCTYPE since they
are not used in the code.
Signed-off-by: Danny Al-G...
Danny Al-Gaaf
09:37 AM Revision 865d5e92 (ceph): rados.py: fix bad indentation
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:36 AM Revision 6eadb870 (ceph): ceph_argparse.py: add missing spaces after comma
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:35 AM Revision da4d23ec (ceph): ceph_argparse.py: remove unnecessary semicolons
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:32 AM Revision a48b391f (ceph): ceph_rest_api.py: fix bad indentation
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
07:54 AM devops Bug #4924 (Need More Info): ceph-deploy: gatherkeys fails on raring (cuttlefish)
Can you add 'debug mon = 20' and 'debug ms = 1' and 'debug monc = 20' to your ceph.conf, restart ceph-mon, and attach... Sage Weil
07:18 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
I'm still seeing this with the latest cuttlefish on ubuntu 13.04.
after doing ceph-deploy install ceph-dmon1 and t...
Zoltan Arnold Nagy
06:22 AM Revision a3135633 (ceph): rgw: free resolver on shutdown
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:22 AM Revision 25948319 (ceph): rgw: fix leak of RGWDataChangesLog::renew_thread
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:22 AM Revision 59b13ceb (ceph): rgw: fix up signal handling
OMG libfcgi is annoying with shutdown and signals. You need to close
the fd *and* resend a signal to ensure that you...
Sage Weil
05:28 AM Revision bd0e35f2 (ceph): test/admin_socket: fix admin_socket unit tests
Command is now JSON!
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:14 AM Revision 94865368 (ceph): rgw: fix RGWFormatter_Plain
Needs dump_format_unqouted.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:08 AM Revision 535d8701 (ceph): common/admin_socket: do not populate empty help strings
Hidden commands have no help string. Make this consistent: the m_help
entry is always there, but may be empty.
Sign...
Sage Weil
04:47 AM Revision b4bde3cb (ceph): common/perf_counters: fix unit tests
The commands are now in json.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:47 AM Revision a8c1a2a2 (ceph): common/Formatter: add dump_format_unquoted()
Sometimes a savvy caller wants to format the output but doesn't want it
quoted.
Signed-off-by: Sage Weil <sage@inkta...
Sage Weil
04:47 AM Revision 2aa9afa5 (ceph): common/perf_counters: fix missing decimal in time, quoting
We shouldn't quote integer or float values. Also easier to use
dump_unsigned.
Signed-off-by: Sage Weil <sage@inktan...
Sage Weil
04:38 AM Revision 8af47755 (ceph): ceph-rest-api: clean up options/environment
ceph-rest-api:
* create app from wrapper by calling generate_app()
* pass args to generate_app() (early parsed in wra...
Dan Mick
04:38 AM Revision 0041e9f8 (ceph): rados.py: missing parameter to make_ex()
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
04:06 AM Revision 629326aa (ceph): qa/fs/.gitignore
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:06 AM Revision 803a1fdd (ceph): ceph_test_admin_socket: fix unit test
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:53 AM Revision 3584dce2 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Sandon Van Ness
02:51 AM Revision ba9e71a3 (ceph): Test multi distro on ceph-deploy.
Test multiple distro's (ubuntu, centos, rhel, fedora) on
ceph-deploy
Signed-off-by: Sandon Van Ness <sandon@inktank....
Sandon Van Ness
01:31 AM Revision a4193541 (ceph): message: Fix asserts that dont' trigger
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
David Zafman
01:23 AM Revision 4c15d73f (ceph): rados: add rest-api test
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:21 AM Revision 404f6d24 (ceph): rest-api: rename
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:20 AM Revision 3f0340f4 (ceph): Add rest_api, a new task that starts up /usr/bin/ceph-rest-api running
as a daemon.
Fixes: 5613
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
12:26 AM Revision a9ca6234 (ceph): librados: EINVAL on a negative osd id
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:24 AM Revision 3f93691b (ceph): ceph.in: make osdids() (and mon, mds) work on old mons
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
12:14 AM Revision 4b739005 (ceph): osd: humor coverity
CID 1058392: Out-of-bounds access (OVERRUN_DYNAMIC) [select issue]
CID 1058391 (#1 of 1): Out-of-bounds access (OVER...
Sage Weil

07/26/2013

11:58 PM Revision 323bdaa2 (ceph): mon/MonCap: mds needs to subscribe to the osdmap
Usually it can get it from the OSD, but it assumes the mon will also share
and doesn't behave when it does not.
Fixe...
Sage Weil
11:58 PM Revision 14a3e2dd (ceph): remove unused fiemap code
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:29 PM Revision 4fb55a3f (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
11:28 PM Revision 32ff3123 (ceph): added fs, rbd and rgw tasks to upgrade from
bobtail and point releases[v0.61.5, v0.61.6] to cuttlefish.
Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
Tamilarasi muthamizhan
11:27 PM Revision 5849853c (ceph): rados/thrash: add in ext4
Sage Weil
11:25 PM rgw Bug #5415 (Fix Under Review): rgw: failing valgrind leak checks
Sage Weil
11:21 PM Revision 6faf8b68 (ceph): PendingReleaseNotes: note on 'ceph tell <pgid> ...'
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:15 PM Revision c01c200f (ceph): Allow OS version over-ride (distro version)
Read os_version from yaml to over-ride teuthology defaults.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
11:12 PM Revision 0757c60b (ceph): Merge remote-tracking branch 'gh/wip-tell-unified' into next
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
11:11 PM Revision 8985e1c9 (ceph): ceph_argparse, mon: make "tell <pgid>" work (duplicating "pg <pgid>")
It's a wad of special cases, but it implements "tell <pgid>" such that
it has the same effect as "pg <pgid>".
Signed...
Dan Mick
11:11 PM Revision d75b6ea1 (ceph): ceph_argparse.py: make find_cmd_target handle tell <pgid>
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
11:11 PM Revision aa00ace1 (ceph): ceph_rest_api.py: cleanup, more docstrings, unused vars
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
11:11 PM Revision 7b42deef (ceph): ceph_rest_api.py: obtain and handle tell <osd-or-pgid> commands
Contact an OSD that's up to get a list of the commands, and use
them to add to the URL map.
Special treatment throug...
Dan Mick
10:25 PM Revision 6ac8aed0 (ceph): mon/PGMonitor: reset in-core PGMap if on-disk format changes
We might have a sequence like:
- start mon, load pgmap 100
- sync
- including a format upgrade at say v 150
- refre...
Sage Weil
10:18 PM CephFS Bug #5724 (Resolved): ceph-fuse crashed during fs tests using ceph-deploy
this was broken getgroups stuff, disabled now. Sage Weil
10:14 PM Revision c36c280a (ceph): Merge remote-tracking branch 'gh/next'
Conflicts:
src/pybind/ceph_argparse.py
Sage Weil
10:09 PM Revision 0890a6b4 (ceph): Merge pull request #19 from alfredodeza/master
Top Level Cleanup Sage Weil
10:08 PM Revision 10959404 (ceph): Merge pull request #470 from dalgaaf/wip-da-CID-3.v2
Fix several CID issues - v2
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil
09:56 PM Revision de51aac8 (ceph): rgw/rgw_metadata.cc: delete md_log (RGWMetadataLog) in destructor
Call delete on md_log in the destructor.
CID 1054826 (#1 of 1): Resource leak in object (CTOR_DTOR_LEAK)
1. alloc_n...
Danny Al-Gaaf
09:55 PM Revision a45e296c (ceph): rgw/rgw_rest_log.cc: free 'handle' to prevent memory leak
Call complete_list_entries() at end of RGWOp_MDLog_List::execute()
to free the 'handle'.
CID 1054834 (#1-2 of 2): Re...
Danny Al-Gaaf
09:55 PM Revision 94cefc77 (ceph): test_cls_log.cc: fix resource leak, delete 'rop'
Fixes for:
CID 1054838 (#14 of 14): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "rop" going out of scop...
Danny Al-Gaaf
09:55 PM Revision 87f8e8fe (ceph): test_cls_log.cc: remove empty lines
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:55 PM Revision 44f43ff8 (ceph): test_cls_statelog.cc: fix memory leak, delete 'rop'
CID 1054840 (#3 of 3): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "rop" going out of scope leaks
the ...
Danny Al-Gaaf
09:55 PM Bug #5239 (Need More Info): osd: Segmentation fault in ceph-osd / tcmalloc
Sage Weil
09:55 PM Revision 143b843e (ceph): test_cls_version.cc: close some memory leaks
Close some memory leaks caused by calling new() without
freeing the memory already assigned to 'rop'.
CID 1054848 (#...
Danny Al-Gaaf
09:55 PM Revision a08998e8 (ceph): Merge pull request #468 from cernceph/condrestart
add condrestart to the sysvinit script
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
09:54 PM Revision 792280cf (ceph): Merge pull request #467 from dalgaaf/wip-da-next-SCA-cppcheck-1
Fix typical smaller issues from SCA
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
09:20 PM Revision b70a9abc (ceph): upstart: stop ceph-create-keys when the monitor stops
This avoids lingering ceph-create-keys tasks.
Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
(cher...
Sage Weil
09:18 PM Revision f2cddda1 (ceph): rgw: correct socket option name
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:15 PM Revision 699d0a3b (ceph): rgw: add rgw log socket to daemonized radosgw too
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:13 PM Revision 65172a09 (ceph): rgw: pass socket path directly to radosgw
Only radosgw needs this option, and each one will be different, so
remove it from the ceph.conf template.
Signed-off...
Josh Durgin
09:07 PM Revision a90a2b42 (ceph): upstart: stop ceph-create-keys when the monitor stops
This avoids lingering ceph-create-keys tasks.
Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:02 PM Revision 6f996223 (ceph): osd: make open classes on start optional
Some might want the old behavior.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:59 PM Revision c24e652d (ceph): osd: load all classes on startup
This avoid creating a wide window between when ceph-osd is started and
when a request arrives needing a class and it ...
Sage Weil
08:51 PM Revision 67eb7de4 (ceph): ceph_argparse.py, ceph.in: validate_command: stop handling format
We were passing the entire parsed_args Namespace just to look at
and tack on 'format', and that's kinda silly; do it ...
Dan Mick
08:51 PM Revision cb38762b (ceph): ceph.in: admin_socket() now validates command and passes format
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
08:51 PM Revision cd16d73f (ceph): ceph.in: clean up help, fix partial matching on all help
Remove --help-all; too much effort for low benefit
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
08:51 PM Revision c9fcda88 (ceph): OSD: provide newer command descs with module/perm/avail
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
08:51 PM Revision 6e6ceffa (ceph): OSD: "tell <osd.n>" version, bench, dump_pg_recovery_stats: formatted
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
08:51 PM Revision bcbb807c (ceph): PG: add formatted output to pg <pgid> query, list_missing
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
08:51 PM Revision ba6ca582 (ceph): In general, flush in caller of dump worker rather than worker
This allows easier refactoring of workers (no dual flushes when code
changes).
Signed-off-by: Dan Mick <dan.mick@ink...
Dan Mick
08:47 PM Revision 5af48dc7 (ceph): FileStore: fix fd leak in _check_global_replay_guard
Bug introduced in f3f92fe21061e21c8b259df5ef283a61782a44db.
Fixes: #5766
Backport: cuttlefish
Signed-off-by: Samuel ...
Samuel Just
08:46 PM Revision c562b72e (ceph): FileStore: fix fd leak in _check_global_replay_guard
Bug introduced in f3f92fe21061e21c8b259df5ef283a61782a44db.
Fixes: #5766
Backport: cuttlefish
Signed-off-by: Samuel ...
Samuel Just
08:20 PM Revision 1e991ede (ceph): add condrestart to the sysvinit script
We need to be able to condrestart all the ceph services on a
machine, so that we don't restart daemons that are suppo...
Dan van der Ster
08:03 PM Revision 2a1aea7c (ceph): Merge branch 'wip-rgw-versionchecks' into next
Conflicts:
src/rgw/rgw_rest_metadata.h
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com
Greg Farnum
05:48 PM Revision 99ae9471 (ceph): rados: add thrasher which causes map gaps
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
05:47 PM devops Bug #5778 (Resolved): gitbuilders use cryptopp instead of nss libraries
The configure script checks for the libcryptopp package being installed before it checks for nss. This means that ev... Anonymous
05:40 PM Revision a355d9f5 (ceph): ceph_manager: add test_map_discontinuity to thrasher
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
05:37 PM devops Bug #5777 (Resolved): ceph-deploy: gatherkeys fails on ubuntu precise
ceph-deploy gatherkeys fails as ceph-create-keys is stuck up when trying to start the monitor.
this is on ceph -ne...
Tamilarasi muthamizhan
05:31 PM Bug #5776 (Can't reproduce): ceph: passing -1 osd id
i fixed librados to not assert, but still:... Sage Weil
05:17 PM devops Feature #5775 (Resolved): create qemu rbd package for rhel 6.5 - qemu-rbd
Josh Durgin
05:15 PM rbd Feature #5774 (Resolved): test libvirt + qemu on rhel
Josh Durgin
04:58 PM Bug #5767 (Resolved): ceph-deploy + ceph-fuse tests failing on next
Sage Weil
03:27 PM Bug #5767 (In Progress): ceph-deploy + ceph-fuse tests failing on next
oops Sage Weil
03:27 PM Bug #5767 (Resolved): ceph-deploy + ceph-fuse tests failing on next
Sage Weil
01:26 PM Bug #5767 (Resolved): ceph-deploy + ceph-fuse tests failing on next
appear to hang. no admin socket in var/run :(
reproducing with logs
Sage Weil
04:48 PM devops Feature #5773 (Resolved): ceph-deploy: should add more tests to ceph-deploy task
ceph-deploy task in teuthology should be able to do more efficient tests w.r.to osd create like,
picking different...
Tamilarasi muthamizhan
04:44 PM rgw Feature #5607 (In Progress): s3-tests: new tests for multi region
Yehuda Sadeh
04:39 PM Revision a0b51b1f (ceph): samba: run lsof and fuser after shutdown
The clients are pretty regularly reporting busy on unmount when
samba runs above them. This will hopefully give us so...
Greg Farnum
04:30 PM rgw Feature #5606: s3-tests: run in multi region setup
Yehuda Sadeh
03:59 PM rgw Bug #5770 (Resolved): rgw: cors, bucket attrs info kept on bucket entry point instead of bucket i...
Yehuda Sadeh
03:25 PM Bug #5764 (Resolved): mon: problem with pgmap upgrade_format, then sync
Sage Weil
10:36 AM Bug #5764: mon: problem with pgmap upgrade_format, then sync
Sage Weil
09:12 AM Bug #5764 (Resolved): mon: problem with pgmap upgrade_format, then sync
2/3 mons upgrade and form quorum and are happy
last one starts up, loads latest (old format) pgmap
does a sync
doe...
Sage Weil
03:22 PM Bug #5616: repeated mon elections
logs on slider:~samuelj/big_cluster/mons[2] Samuel Just
02:35 PM rbd Bug #5768 (Resolved): rbd-fuse: leak in enumerate_images()
enumerate_images() allocates ibuf and never frees it. Problem is that it returns a list with pointers into it. This n... Yehuda Sadeh
02:07 PM Bug #5752 (Resolved): osd: delayed loading of classes can be problematic if use races with upgrade
Sage Weil
01:57 PM Bug #5766 (Resolved): osd: replay not closing fds? too many open fds on upgrade+restart
leak in _check_global_replay_guard. backported to cuttlefish Samuel Just
09:38 AM Bug #5766 (Resolved): osd: replay not closing fds? too many open fds on upgrade+restart
... Sage Weil
01:24 PM devops Bug #5727 (Resolved): Discover and set the proper OS bindings to use
Pull request https://github.com/ceph/ceph-deploy/pull/22 merged.
Hash: 4ae2768d63531a7458133b632fec4d92959c6e06
Alfredo Deza
10:51 AM Bug #5677 (Resolved): osd/OSD.cc: 5517: FAILED assert(_get_map_bl(epoch, bl))
Samuel Just
09:17 AM CephFS Bug #5765 (New): kclient: High CPU due to raw_spin_lock in ceph_cap_string
During CephFS testing, very high CPU usage was noticed during writes across lots of clients. perf showed that a sign... Mark Nelson
09:12 AM rgw Feature #5604: rgw: teuthology tests to check various user creation issues on multi region enviro...
Getting started on this after discussing how to break up the tasks with Joe. Greg Farnum
06:43 AM devops Bug #5745: ceph-deploy: mds create command errors out EACCES on next branch
Fixed in `next` branch of ceph
Hash: ebb9aceb7971f13ae4032f0943854b2b2c0af28a
And in `master` branch of ceph-de...
Alfredo Deza
05:46 AM devops Bug #5763 (Resolved): ceph-deploy new [IP] should error out
When calling `new` with ceph-deploy, sometimes it is possible a user may use an IP instead of a hostname. The tool sh... Alfredo Deza
05:18 AM Revision 3f598e8c (ceph): AdminSocket users: use generic formatting
All call() routines get a format parameter; all places where
JSONFormatter was created get a new_formatter() instead....
Dan Mick
05:18 AM Revision c7c4c23e (ceph): Formatter, admin_socket: make default formatter be json-pretty
If not given, default to json-pretty; if given but not equal to one
of the formatter choices, return NULL as before. ...
Dan Mick
04:42 AM Revision 4aeb73a5 (ceph): ceph_rest_api.py: reversed test for failed request
A failed request has a response code *outside* the range (200, 300],
not within it.
Signed-off-by: Dan Mick <dan.mic...
Dan Mick
04:41 AM Revision 47d0937c (ceph): rest/test.py: earlier versions of requests.py don't quote ' ' in params
requests 0.12.1 handles queryparams in the URL with embedded
spaces; requests 0.8.2 does not. Avoid the issue by quo...
Dan Mick
03:37 AM Revision 6951d234 (ceph): OSD: tolerate holes in stored maps
We may have holes in stored maps during init_splits_between
and advance_pg. In either case, we should simply skip th...
Samuel Just
03:03 AM Revision fbf74d98 (ceph): ceph_rest_api.py: return error in nonformatted mode
When a nonformatted request is made, currently the only text in the
response is the (probably empty) response buffer....
Dan Mick
02:50 AM Revision f19bcfc9 (ceph): Merge branch 'master' of github.com:ceph/teuthology
Sandon Van Ness
02:50 AM Revision f5170fb4 (ceph): Merge branch 'master' of github.com:ceph/teuthology
Sandon Van Ness
02:50 AM Revision 41cafb1a (ceph): Merge remote-tracking branch 'origin/wip-sandon-vm'
Conflicts:
teuthology/lock.py
teuthology/misc.py
teuthology/task/install.py
Sandon Van Ness
02:50 AM Revision 7207a31e (ceph): Merge remote-tracking branch 'origin/wip-sandon-vm'
Conflicts:
teuthology/lock.py
teuthology/misc.py
teuthology/task/install.py
Sandon Van Ness
01:40 AM Revision 86fc3990 (ceph): Add distro yamls.
Should be no harm to get these in now.
To run on all distros the distros dir should just be symlinked in
the folder ...
Sandon Van Ness
01:06 AM Revision 8b3d7a1b (ceph): ceph_rest_api.py: actually remove the trailing / on baseurl
Lurking bug since version 1...
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
01:02 AM Revision 4c5cc89d (ceph): ceph-deploy: remove workunit branch options
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:58 AM Revision dfabc61c (ceph): mon/MonCap: match param for entity (not name)
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil
12:58 AM Revision ca8ac950 (ceph): mon: translate caps=[k1,v1,k2,v2] into [caps_k1=v1, caps_k2=v2]
The command matching needs key/value pairs.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.m...
Sage Weil
12:12 AM Revision aeb3586b (ceph): added test_mon_destroy option to ceph-deploy task
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
12:01 AM Revision 17aa2d6d (ceph): mon/Paxos: share uncommitted value when leader is/was behind
If the leader has and older lc than we do, and we are sharing states to
bring them up to date, we still want to also ...
Sage Weil
12:01 AM Revision 05b6c7e8 (ceph): mon/Paxos: share uncommitted value when leader is/was behind
If the leader has and older lc than we do, and we are sharing states to
bring them up to date, we still want to also ...
Sage Weil

07/25/2013

11:03 PM Revision 063c71f0 (ceph): rgw: expose the version of synced items to the poster
To support this, we add an optional out argument to
RGWMetadatManager::put() and fill in the read_version. When the
f...
Greg Farnum
11:03 PM Revision 81b62b5c (ceph): rgw: return the update status on sync requests
Add new STATUS_APPLIED, then specify the RGWX_UPDATE_STATUS header
based on that return code when doing metadata puts...
Greg Farnum
11:00 PM Revision 18eabd33 (ceph): rgw: pass the sync mode into the RGWMetadataManager::put() calls.
Signed-off-by: Greg Farnum <greg@inktank.com> Greg Farnum
11:00 PM Revision 8ffc4ca9 (ceph): rgw: add sync state parsing code and REST interface
Specify the param "sync-type" as one of "always", "update-by-version",
"update-by-timestamp". It defaults to always.
...
Greg Farnum
10:59 PM Revision 4f9855e4 (ceph): rgw: add preliminary support for sync update policies on metadata sync
We want to be able to conditionally apply new updates:
1) if we already have a newer version than the sync is applyin...
Greg Farnum
10:33 PM Revision c2c8a080 (ceph): Added --os-type argument to run.py
Because for some reason it was never there before?
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
10:24 PM Revision 176aa394 (ceph): remove old push_to_kclient.pl
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:21 PM Revision 09a664e2 (ceph): Merge remote-tracking branch 'gh/cuttlefish-next' into cuttlefish
Sage Weil
10:13 PM CephFS Bug #5762 (Resolved): teuthology: Failed MPI runs lead to a hung test instead of a failure
Observed with #5761, the MPI run is reporting failure but the pexec task never seems to end. I'm not sure what point ... Greg Farnum
10:12 PM CephFS Bug #5761 (Resolved): teuthology: MPI test sometimes fails with a permission denied
End of the log:... Greg Farnum
09:53 PM Bug #5752 (Fix Under Review): osd: delayed loading of classes can be problematic if use races wit...
Sage Weil
01:01 PM Bug #5752 (Resolved): osd: delayed loading of classes can be problematic if use races with upgrade
- install old osd
- start
- install new package
- try to use a class
-> old osd tries to load new cls_rgw and g...
Sage Weil
09:45 PM Revision 810cca1d (ceph): Added get_distro() to misc.py
Since getting the ostype is used multiple places I made a
function for it and modified the existing code to use
said ...
Sandon Van Ness
09:30 PM Revision ebb9aceb (ceph): ceph-disk: use new dumpling-style osd caps if we can, or fall back to o...
Signed-off-by: Alfredo Deza <alfredo@deza.pe>
Reviewed-by: Sage Weil <sage@inktank.com>
Alfredo Deza
09:24 PM Revision 57933b6f (ceph): Fix priority so it only is added once.
Needed for baremetal so the sed doesn't keep adding
the priority line in the repos file.
Signed-off-by: Sandon Van N...
Sandon Van Ness
09:14 PM Bug #5677: osd/OSD.cc: 5517: FAILED assert(_get_map_bl(epoch, bl))
Samuel Just wrote:
> Added wip-5677 to ceph-qa-suite and teuthology gits.
for the teuthology.git change, let's ha...
Sage Weil
08:50 PM Bug #5677 (Fix Under Review): osd/OSD.cc: 5517: FAILED assert(_get_map_bl(epoch, bl))
Added wip-5677 to ceph-qa-suite and teuthology gits. Samuel Just
08:40 PM Bug #5677: osd/OSD.cc: 5517: FAILED assert(_get_map_bl(epoch, bl))
Fix merged, 6951d2345a5d837c3b14103bd4d8f5ee4407c937, still working on getting the test to be reliable so I can add i... Samuel Just
09:01 PM Revision b46fb62d (ceph): osd: Don't put functional code inside of an assert
Fix assert in OSDService::get_map()
Signed-off-by: David Zafman <david.zafman@inktank.com>
Reviewed-by: Sage Weil <s...
David Zafman
08:57 PM Revision c9957329 (ceph): upgrade-parallel: fix rgw syntax
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:57 PM Revision 3c781bdb (ceph): upgrade-parallel/rados: fix mon restarts
Sage Weil
08:54 PM Revision 77ee5a07 (ceph): ceph_manager: try both new and old tell mon.* syntax
So we can test old code with new teuthology (e.g., upgrade testing)
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:49 PM Revision 7373cb3d (ceph): removed ceph-deploy branch option to make it run against arbitrary branch
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
08:44 PM Revision 2a1a8b54 (ceph): removed ceph-deploy branch option
so the nightlies can run ceph-deploy against any arbitrary branch
Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
Tamilarasi muthamizhan
07:46 PM Revision 5796d763 (ceph): schedule_suite: less ceph-deploy client debugging
Sage Weil
07:45 PM Revision 6914efa6 (ceph): schedule_suite.sh: select ceph-dpeloy branch
Sage Weil
06:40 PM Revision 27a0b866 (ceph): ceph_argparse.py: wrong variable used if valid() fails for Ceph{Osd}Name
self.t isn't valid in the failure case; use t
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
06:34 PM Revision df9b8777 (ceph): Merge remote-tracking branch 'gh/next'
Conflicts:
PendingReleaseNotes
Sage Weil
06:33 PM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
A short inspection suggests ceph_osdc_alloc_request is setting iov_len 4 bytes too large, but there may be some later... Josh Durgin
06:31 PM rbd Bug #5760 (Resolved): libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front....
From http://lists.ceph.com/pipermail/ceph-users-ceph.com/2013-July/003105.html:... Josh Durgin
06:33 PM Revision c5419785 (ceph): Merge pull request #456 from dalgaaf/wip-da-CID-1
Fix CID issues
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil
06:31 PM Revision 096af5ed (ceph): Merge pull request #465 from dalgaaf/wip-da-CID-2
Fix some more CID issues
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Sage Weil
06:10 PM Revision f653aa57 (ceph): config_opts.h: increase xfs,btrfs wbthrottle defaults
Also increase fd limit defaults to accomodate the larger number
of fds.
Fixes: #5692
Signed-off-by: Samuel Just <sam...
Samuel Just
06:07 PM Revision e52f64ef (ceph): upgrade-cuttlefish: run on xfs, not /
Sage Weil
06:02 PM Feature #5759 (Rejected): ceph caps processing should pass dict of key:val pairs for caps
ceph_argparse.py etc. don't handle dicts of strings, but the caps in particular
could really use it. Look into addi...
Dan Mick
05:59 PM Bug #5750 (Resolved): mon: paxos doesn't share uncommitted if leader has older last_committed
Sage Weil
11:10 AM Bug #5750 (Resolved): mon: paxos doesn't share uncommitted if leader has older last_committed
teuthology-2013-07-24_20:00:05-rados-cuttlefish-testing-basic/81777
teuthology-2013-07-24_22:44:24-rados-next-testin...
Sage Weil
05:48 PM Revision ddaf6d5a (ceph): Merge remote-tracking branch 'gh/next'
Conflicts:
configure.ac
src/ceph.in
src/pybind/ceph_argparse.py
Sage Weil
05:38 PM Revision 78214af3 (ceph): doc/release-notes: v0.61.7
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:37 PM Revision b0535fcf (ceph): HashIndex: reset attr upon split or merge completion
A replay of an in progress merge or split might make
our counts unreliable.
Fixes: #5723
Signed-off-by: Samuel Just ...
Samuel Just
05:37 PM Revision 8f73302b (ceph): test/filestore/store_test: add test for 5723
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commi...
Samuel Just
05:34 PM Revision 6a7b9e5f (ceph): FileStore::_collection_rename: fix global replay guard
If the replay is being replayed, we might have already
performed the rename, skip it. Also, we must set the
collecti...
Samuel Just
05:33 PM Revision 870c474c (ceph): FileStore::_collection_rename: fix global replay guard
If the replay is being replayed, we might have already
performed the rename, skip it. Also, we must set the
collecti...
Samuel Just
05:32 PM Revision 37a4c4af (ceph): test/filestore/store_test: add test for 5723
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
05:32 PM Revision 0dc3efdd (ceph): HashIndex: reset attr upon split or merge completion
A replay of an in progress merge or split might make
our counts unreliable.
Fixes: #5723
Signed-off-by: Samuel Just ...
Samuel Just
05:18 PM Revision 2c986703 (ceph): modified workunit branch to cuttlefish
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
05:12 PM Revision cb3ee1e4 (ceph): rgw/rgw_metadata.h: init prefix in initialization list
For performance reasons: init 'prefix' with META_LOG_OBJ_PREFIX
in the initialization list of RGWMetadataLog instead ...
Danny Al-Gaaf
05:07 PM Revision 6bc0d041 (ceph): test_rgw_admin_log.cc: remove unused variable 'creds'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:06 PM Revision dda1014a (ceph): test_rgw_admin_log.cc: use static_cast<>() instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:04 PM Revision 8f45a73a (ceph): test_rgw_admin_opstate.cc: remove unused variable 'creds'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:03 PM Revision e4dfe8ab (ceph): test_rgw_admin_meta.cc: remove unused variable 'creds'
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:01 PM Revision 9d4c42f6 (ceph): test_rgw_admin_opstate.cc: use static_cast<>() instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:58 PM Revision 4c778e26 (ceph): test_rgw_admin_meta.cc: use static_cast<>() instead of C-Style cast
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:49 PM Revision a164f575 (ceph): Merge tag 'v0.67-rc2' into next
v0.67-rc2 Sage Weil
04:19 PM rgw Feature #5680 (Resolved): rgw: teuthology: merge in changes to enable multiple regions
https://github.com/ceph/teuthology/commit/8ad065dc9c4d9fc0772614f5b3555e1c3f8939fa Josh Durgin
04:18 PM rgw Feature #5747 (Resolved): radosgw-agent: RESTful api to control agent
See commit message for usage: https://github.com/ceph/radosgw-agent/commit/c796d022d8b51f084870f284289770322104b687 Josh Durgin
04:10 PM Revision 803db7d7 (ceph): schedule_suite.sh: don't need full ms debug on mons
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:34 PM Bug #5723 (Resolved): OSD seemingly loses objects during crash
Sage Weil
10:38 AM Bug #5723 (Pending Backport): OSD seemingly loses objects during crash
Samuel Just
09:35 AM Bug #5723 (Fix Under Review): OSD seemingly loses objects during crash
Sage Weil
03:34 PM Bug #5714 (Resolved): osd/ReplicatedPG.cc: 7564: FAILED assert(0 == "erroneously present object")
Sage Weil
03:34 PM Bug #5517 (Resolved): osd: stuck peering on cuttlefish
Sage Weil
03:13 PM rbd Cleanup #5757 (Resolved): remove any fiemap reference from rbd.cc
- remove any reference to the now obsolete and unused fiemap functionality
- Don't link the rbd tool with fiemap.c...
Yehuda Sadeh
02:34 PM devops Bug #5745 (Resolved): ceph-deploy: mds create command errors out EACCES on next branch
Sage Weil
11:43 AM devops Bug #5745 (In Progress): ceph-deploy: mds create command errors out EACCES on next branch
actually, not suite. see wip-5745, except that isn't right either. it should try that command, and if it fails, try... Sage Weil
11:38 AM devops Bug #5745: ceph-deploy: mds create command errors out EACCES on next branch
pushed fix to ceph-deploy master Sage Weil
02:03 PM Bug #5749: osd: unfound objects on cuttlefish
Kicked off small group sjust-5749-0 with logging. Samuel Just
01:54 PM Bug #5749: osd: unfound objects on cuttlefish
pg 0.50. ceph pg 0.50 query hung. gdb showed no obviously deadlocked threads (and none holding a pg lock), though it... Samuel Just
09:51 AM Bug #5749 (Duplicate): osd: unfound objects on cuttlefish
ubuntu@teuthology:/a/sage-2013-07-24_22:59:52-rados-cuttlefish-next-testing-basic/82345 Sage Weil
01:42 PM RADOS Fix #5756 (New): ceph: tell {osd,mon}.* hugely slower than cuttlefish
this is commonl used enough that it is probably classified as a performance/usability regression. we should parallel... Sage Weil
01:30 PM Bug #5754 (Resolved): mon: occasional osd full map not trimmed
seems to happen after sync doing catchup, but the txn dumps so far confirm it is removed.
reproduced about 20% of ...
Sage Weil
01:16 PM Bug #5743 (Resolved): ceph_rest_api.py: config sections should fall back from specific to general
commit:0b8cad1805bd72c7359b21cfdbc05c2c7b887e44 Dan Mick
01:11 PM CephFS Bug #5753 (Duplicate): ceph-fuse: segfault when getting back a traceless rename op
... Greg Farnum
11:40 AM CephFS Bug #5649: smbtorture test gets ebusy on kclient umount
Also I think we get it with ceph-fuse too. If we're lucky it's not actually a Ceph bug. Greg Farnum
11:39 AM CephFS Bug #5649: smbtorture test gets ebusy on kclient umount
Saw this again yesterday, logs at /a/teuthology-2013-07-24_01:01:06-fs-next-testing-basic/80639. I'm updating teuthol... Greg Farnum
11:13 AM Bug #5692 (Resolved): RADOS performance regression in 0.65
Samuel Just
10:40 AM Bug #5625 (Resolved): osd: scrub finds 20 missing objects on cuttlefish
Doesn't actually need backport... Samuel Just
10:05 AM Bug #5746: ceph cli interactive mode completely broken
Are we sure this is urgent? I've never actually seen anybody use the interactive mode before. Greg Farnum
08:37 AM Bug #5748 (Resolved): osd: unfound object test is failing to produce unfound objects
ubuntu@teuthology:/a/teuthology-2013-07-24_22:44:24-rados-next-testing-basic/82104
ubuntu@teuthology:/a/teuthology-2...
Sage Weil
05:39 AM Revision a8b70f03 (ceph): doc/release-notes: v0.67-rc2
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:44 AM Revision 8f010aff (ceph): v0.61.7
Gary Lowell
01:09 AM Revision 75a78417 (ceph): upgrade-cuttlefish: test upgrades to new point releases
This only covers rados tests currently. We should expand this to include rgw,
rbd, and cephfs workloads.
Signed-off...
Sage Weil

07/24/2013

11:31 PM Revision 41930b5e (ceph): ceph.spec.in, debian/control: python-ceph depends on python-flask
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
11:26 PM Revision d9cfd0e1 (ceph): modified the task yaml to use modified ceph.restart and wait_for_mon_qu...
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
11:20 PM Revision 806eab59 (ceph): msg/Pipe: hold pipe_lock during important parts of accept()
Previously we did not bother with locking for accept() because we were
not visible to any other threads. However, we...
Sage Weil
11:20 PM Revision 45bda482 (ceph): msg/Pipe: a bit of additional debug output
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 16568d9e1fb8ac0c06ebaa1e1dc1d6a432a5e4d4)
Sage Weil
11:20 PM Revision 611a06ae (ceph): msg/Pipe: do not hold pipe_lock for verify_authorizer()
We shouldn't hold the pipe_lock while doing the ms_verify_authorizer
upcalls.
Fix by unlocking a bit earlier, and ve...
Sage Weil
11:20 PM Revision 7d986517 (ceph): PGLog::rewind_divergent_log: unindex only works from tail, index() instead
Fixes: #5714
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry pick...
Samuel Just
11:20 PM Revision 48105a32 (ceph): msg/Pipe: fix RECONNECT_SEQ behavior
Calling handle_ack() here has no effect because we have already
spliced sent messages back into our out queue. Inste...
Sage Weil
11:20 PM Revision 25f4786a (ceph): msg/Pipe: be a bit more explicit about encoding outgoing messages
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 4282971d47b90484e681ff1a71ae29569dbd1d32)
Sage Weil
11:20 PM Revision 21e27262 (ceph): msg/Pipe: assert lock is held in various helpers
These all require that we hold pipe_lock.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 579...
Sage Weil
11:20 PM Revision ae85a0a1 (ceph): msg/Pipe: avoid creating empty out_q entry
We need to maintain the invariant that all sub queues in out_q are never
empty. Fix discard_requeued_up_to() to avoi...
Sage Weil
11:20 PM Revision 07b9ebf4 (ceph): msg/Pipe: unlock msgr->lock earlier in accept()
Small cleanup. Nothing needs msgr->lock for the previously larger
window.
Signed-off-by: Sage Weil <sage@inktank.co...
Sage Weil
11:20 PM Revision f938a5bf (ceph): msgr: mark_down_all() after, not before, rebind
If we are shutting down all old connections and binding to new ports,
we want to avoid a sequence like:
- close all...
Sage Weil
11:20 PM Revision 540a6f49 (ceph): msgr: adjust nonce on rebind()
We can have a situation where:
- we have a pipe to a peer
- pipe goes to standby (on peer)
- we rebind to a new p...
Sage Weil
11:20 PM Revision 2f696f17 (ceph): msgr: maintain list of accepting pipes
New pipes exist in a sort of limbo before we know who the peer is and
add them to rank_pipe. Keep a list of them in ...
Sage Weil
11:20 PM Revision 1ed51ad5 (ceph): msgr: close accepting_pipes from mark_down_all()
We need to catch these pipes too, particularly when doing a rebind(),
to avoid them leaking through.
Signed-off-by: ...
Sage Weil
11:20 PM Revision ce6a0b74 (ceph): msgr: fix a typo/goto-cross from dd4addef2d
We didn't build or review carefully enough!
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sa...
Greg Farnum
11:20 PM Revision 95b1b5da (ceph): FileStore: add global replay guard for split, collection_rename
In the event of a split or collection rename, we need to ensure that
we don't replay any operations on objects within...
Samuel Just
11:20 PM Revision 850da089 (ceph): ReplicatedPG: replace clean_up_local with a debug check
Stray objects should have been cleaned up in the merge_log
transactions. Only on the primary have those operations
n...
Samuel Just
11:20 PM Revision 7ffc65fc (ceph): PG: start flush on primary only after we process the master log
Once we start serving reads, stray objects must have already
been removed. Therefore, we have to flush all operation...
Samuel Just
11:20 PM Revision c7e2945a (ceph): PG, ReplicatedPG: pass a transaction down to ReplicatedPG::on_change
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commi...
Samuel Just
11:20 PM Revision 2f7979d1 (ceph): ReplicatedPG: track temp collection contents, clear during on_change
We also assert in on_flushed() that the temp collection is actually
empty.
Fixes: #5670
Signed-off-by: Samuel Just <...
Samuel Just
11:20 PM Revision 8aafe131 (ceph): msgr: clear_pipe inside pipe_lock on mark_down_all
Observed a segfault in rebind -> mark_down_all -> clear_pipe -> put that
may have been due to a racing thread clearin...
Sage Weil
11:20 PM Revision 8612e50f (ceph): msgr: clear con->pipe inside pipe_lock on mark_down
We need to do this under protection of the pipe_lock.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked fro...
Sage Weil
11:20 PM Revision db06a509 (ceph): msg/Pipe: goto fail_unlocked on early failures in accept()
Instead of duplicating an incomplete cleanup sequence (that does not
clear_pipe()), goto fail_unlocked and do the cle...
Sage Weil
11:20 PM Revision 1eab0690 (ceph): msgr: reaper: make sure pipe has been cleared (under pipe_lock)
All paths to pipe shutdown should have cleared the con->pipe reference
already. Assert as much.
Also, do it under p...
Sage Weil
11:20 PM Revision d92a43d8 (ceph): OSD: add config option for peering_wq batch size
Large peering_wq batch sizes may excessively delay
peering messages resulting in unreasonably long
peering. This may...
Samuel Just
11:18 PM Revision 0018b45f (ceph): v0.67-rc2
Gary Lowell
11:09 PM Revision fe2019cc (ceph): rest/test.py: cope with older requests.py versions
Older requests.py didn't have r.json (or r.json()); avoid by
decoding the json myself
Signed-off-by: Dan Mick <dan.m...
Dan Mick
10:46 PM Revision 24a56a96 (ceph): ceph-disk: use new get_dev_path helper for list
Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Tested-...
Sage Weil
10:46 PM Revision f46dbc46 (ceph): ceph-disk: handle /dev/foo/bar devices throughout
Assume the last component is the unique device name, even if it appears
under a subdir of /dev.
Signed-off-by: Sage ...
Sage Weil
10:46 PM Revision be12811b (ceph): ceph-disk: add get_dev_name, path helpers
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit e0401591e352ea9653e3276d66aebeb41801eeb3)
Sage Weil
10:46 PM Revision f3ee3e69 (ceph): ceph-disk: refactor list_[all_]partitions
Make these methods work in terms of device *names*, not paths, and fix up
the only direct list_partitions() caller to...
Sage Weil
10:46 PM Revision 05600034 (ceph): ceph-disk: use get_dev_name() helper throughout
This is more robust than the broken split trick.
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from com...
Sage Weil
10:46 PM Revision 0a08c822 (ceph): ceph-disk: reimplement is_partition() using /sys/block
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 5b031e100b40f597752b4917cdbeebb366eb98d7)
Sage Weil
10:46 PM Revision 1f8e4b15 (ceph): ceph-disk: use /sys/block to determine partition device names
Not all devices are basename + number; some have intervening character(s),
like /dev/cciss/c0d1p2.
Signed-off-by: Sa...
Sage Weil
10:46 PM Revision f799dac7 (ceph): ceph-disk: make is_held() smarter about full disks
Handle the case where the device is a full disk. Make the partition
check a bit more robust (don't make assumptions ...
Sage Weil
10:43 PM devops Bug #5345 (Resolved): ceph-disk: handle less common device names
Sage Weil
10:43 PM Bug #5698 (Resolved): mon: paxos mishandles uncommitted values during collect/last phase
Sage Weil
10:42 PM Bug #5737 (Resolved): mon: assert(latest_full > 0) on 0.61.6
Sage Weil
01:30 PM Bug #5737: mon: assert(latest_full > 0) on 0.61.6
Sage Weil
10:35 AM Bug #5737 (In Progress): mon: assert(latest_full > 0) on 0.61.6
Sage Weil
04:02 AM Bug #5737 (Fix Under Review): mon: assert(latest_full > 0) on 0.61.6
Bug is a variable that was not incremented. Why it worked on other stores is beyond me and I will check that once th... Joao Eduardo Luis
03:49 AM Bug #5737 (Resolved): mon: assert(latest_full > 0) on 0.61.6
Code introduced specifically to work around #5704.... Joao Eduardo Luis
10:03 PM devops Bug #5300 (Resolved): ceph-deploy purgedata should give warning if ceph still installed
Resolved with the following commit:
commit b82cf3a4e49b524751a423d25b88592b5096dabf
Author: Gary Lowell <gary.low...
Anonymous
09:46 PM Revision fd1fd664 (ceph): ceph-disk: use new get_dev_path helper for list
Backport: cuttlefish
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Tested-...
Sage Weil
09:45 PM rgw Feature #5747 (Resolved): radosgw-agent: RESTful api to control agent
At this point, we only need it to be functional so that we can get tests going. Functionality:
- execute full sync
...
Yehuda Sadeh
09:43 PM Bug #5746 (Resolved): ceph cli interactive mode completely broken
Somewhere in the reorganization of code, the interactive mode of the ceph cli got
broken. It doesn't print any out...
Dan Mick
09:38 PM Revision 0b8cad18 (ceph): ceph_rest_api.py: allow config section fallback
Try clientname, then 'client', then 'global
Fixes: #5743
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by:...
Dan Mick
08:56 PM Revision d7df620b (ceph): global/signal_handler: poll on the control pipe, too
We also need to poll the control fd/pipe so that we restart the poll loop
when new signal handlers are added. This w...
Sage Weil
08:53 PM Revision 26d0f04b (ceph): Merge branch 'wip-cephtool-cleanup' into next
Reviewed-by: Sage Weil <sage@inktank.com> Dan Mick
08:26 PM Revision 1fcf8e3f (ceph): ceph: make restart take both a list of daemons and other arguments
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Tamil Muthamizhan <tamil@inktank.com>
Sage Weil
08:00 PM Revision 3c9382a7 (ceph): teuth: rgw task example config update
Due to bug #5716, pools need to start with a '.' at present.
Updating the examples to follow this convention.
Signed...
Joe Buck
08:00 PM Revision 4fb5781a (ceph): teuth: fix issue in cleanup code
The post-yield code in create_dirs needed to
be tweaked to correctly delete the {tdir}/apache
directory (if it exists...
Joe Buck
07:12 PM Revision 27f31895 (ceph): mon/OSDMonitor: search for latest full osdmap if record version is missing
In 97462a3213e5e15812c79afc0f54d697b6c498b1 we tried to search for a
recent full osdmap but were looking at the wrong...
Sage Weil
06:56 PM Revision 085f129a (ceph): ceph.in: remove dead code
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
06:56 PM Revision e8394208 (ceph): MonCommands.h: osd pool delete "rw" perms, osd pool set no longer exp
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
06:56 PM Revision 1579c344 (ceph): rest/test.py: osd lspools should be a 'GET'
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
06:56 PM Revision 92855064 (ceph): ceph.in/ceph_argparse.py: move find_cmd_target() to ceph_argparse.py
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
06:55 PM Revision c2131d40 (ceph): mon/OSDMonitor: search for latest full osdmap if record version is missing
In 97462a3213e5e15812c79afc0f54d697b6c498b1 we tried to search for a
recent full osdmap but were looking at the wrong...
Sage Weil
05:25 PM Revision 13aca3b7 (ceph): ceph: wait_for_osds_up
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:25 PM Revision 75136a83 (ceph): ceph: wait-for-osds-up option for restart
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:59 PM Revision afd0d87e (ceph): teuthology: updating RGW task to support regions
Extending the rgw.py task to allow for regions and zones
to be specified in the YAML file.
Signed-off-by: Joe Buck <...
Joe Buck
04:59 PM Revision 88cab471 (ceph): teuth: reworked rgw to support regions / zones
Signed-off-by: Joe Buck <jbbuck@gmail.com> Joe Buck
04:59 PM Revision 6d2434b4 (ceph): rgw: move common rgwadmin function to a new utility file
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
04:59 PM Revision 721280b7 (ceph): task_util: move rados command here
Six copies are replaced with one, with an added option to check status
automatically. This should probably be used in...
Josh Durgin
04:59 PM Revision 8ad065dc (ceph): rgw: add multi-region and zone support
Take client<->zone/region and the associated pools from ceph.conf, so
we don't have to invent a new format to specify...
Josh Durgin
04:48 PM Revision a0559880 (ceph): rgw/rgw_metadata.h: init cur_shard in LogListCtx with 0
CID 1054868 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "cur_shard" ...
Danny Al-Gaaf
04:43 PM Revision ebff1ebd (ceph): rgw/rgw_metadata.cc: fix possible null dereferencing
CID 1054827 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "objv_trac...
Danny Al-Gaaf
04:30 PM Revision 6e6ef015 (ceph): os/ObjectStore.cc: don't fallthrough after OP_OMAP_RMKEYRANGE
CID 1054829 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This case (value 37) is not termi...
Danny Al-Gaaf
04:22 PM Revision 27e38e40 (ceph): mon/Monitor.cc: init scrub_version with 0 in constructor
CID 1019623 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "scrub_versi...
Danny Al-Gaaf
04:12 PM Revision 5b0967f0 (ceph): test: test_store_tool: global init before using LevelDBStore
Fixes a segfault
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
...
Joao Eduardo Luis
04:12 PM Revision 115468c7 (ceph): mon: OSDMonitor: fix a bug introduced on 97462a32
Fixes: #5737
Backport: cuttlefish
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <s...
Joao Eduardo Luis
04:01 PM Revision 732286a2 (ceph): mon/Paxos: only share uncommitted value if it is next
We may have an uncommitted value from our perspective (it is our lc + 1)
when the collector has a much larger lc (bec...
Sage Weil
04:01 PM Revision f598245f (ceph): mon/Paxos: only learn uncommitted value if it is in the future
If an older peer sends an uncommitted value, make sure we only take it
if it is in the future, and at least as new as...
Sage Weil
04:01 PM Revision 18596340 (ceph): mon/Paxos: debug ignored uncommitted values
Signed-off-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 19b29788966eb80ed847630090a16a3d1b810969)
Sage Weil
04:01 PM Revision 938a639e (ceph): mon/Paxos: fix pn for uncommitted value during collect/last phase
During the collect/last exchange, peers share any uncommitted values
with the leader. They are supposed to also shar...
Sage Weil
03:59 PM Revision a7a7d3fc (ceph): test: test_store_tool: global init before using LevelDBStore
Fixes a segfault
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Joao Eduardo Luis
03:58 PM Revision 76cd7ac1 (ceph): mon: OSDMonitor: fix a bug introduced on 97462a32
Fixes: #5737
Backport: cuttlefish
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <s...
Joao Eduardo Luis
03:42 PM Subtask #5433: Factor out the ReplicatedPG object replication and client IO logic as a PGBackend ...
I've reconsidered a bit, and I think it would be easier to leave most of the PG implementation where it is and factor... Samuel Just
03:24 PM devops Bug #5745 (Resolved): ceph-deploy: mds create command errors out EACCES on next branch
mds create command throws EACCES.... Tamilarasi muthamizhan
02:51 PM devops Bug #5734 (Duplicate): ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sys/block...
#5345 Sage Weil
02:50 PM devops Bug #5734 (Pending Backport): ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sy...
Sage Weil
02:46 PM devops Bug #5734 (Resolved): ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sys/block/...
Sage Weil
02:32 PM Bug #5743 (Resolved): ceph_rest_api.py: config sections should fall back from specific to general
ceph-rest-api now demands to find a section named 'client.restapi' (or whatever
-n was set to). It should be able t...
Dan Mick
01:56 PM Bug #5742 (Resolved): daemon hangs on shutdown when running with valgrind
Sage Weil
01:30 PM Bug #5742 (Resolved): daemon hangs on shutdown when running with valgrind
... Sage Weil
12:50 PM Revision 02609438 (ceph): add test requirements to requirements file
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
12:49 PM Revision 545fc274 (ceph): remove test dependencies from setup.py
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
12:43 PM Revision 2d9cb1ff (ceph): fix RST formatting issues in README file
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
12:31 PM Revision b3bd39cb (ceph): removing todo org file from the root of the project
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
12:30 PM Revision 1e4a4d73 (ceph): remove Makefile that attempted to do linting
Signed-off-by: Alfredo Deza <alfredo@deza.pe> Alfredo Deza
11:51 AM Bug #5692: RADOS performance regression in 0.65
Hi Greg,
Here's a run down of the XFS tests:
https://docs.google.com/a/inktank.com/spreadsheet/ccc?key=0Anmmfpo...
Mark Nelson
07:29 AM devops Bug #5738 (Resolved): Do not `rm- rf` the mon directory when calling destroy
After calling `mon destroy` there is a call to remove the mon directory but this can have important data on it, so it... Alfredo Deza
05:43 AM Revision 1cdb3ecf (ceph): configure.ac: Remove -rc suffix from the configure version number.
Remove the rc suffix since RPM complains about. For rc release
builds the "rc" in the git describe string is suffcie...
Gary Lowell
05:00 AM Revision c8d66b7a (ceph): Remove fuse-utils from Recommends in debian/control
The package fuse-utils is obsolete and no longer in Debian unstable. Thomas Bechtold
04:42 AM Revision b7c40ec4 (ceph): configure.ac: Set version number to match git describe.
Workaround for issue with rc1 suffix for rpms.
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Gary Lowell
04:41 AM Revision 139f25f0 (ceph): Merge remote-tracking branch 'gh/next'
Sage Weil
04:41 AM Revision 4444c942 (ceph): doc/release-notes: v0.61.6
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:27 AM Revision 8e4a78f1 (ceph): global/signal_handler: use poll(2) instead of select(2)
Starting with commit 61a298c39c1a6684682e2b749e45a66d073182c8 we delay the
signal handler setup until after lots of o...
Sage Weil
01:00 AM Revision 203c53d9 (ceph): upgrade-parallel/stress-split: fix osd names
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:14 AM Revision 4183b74b (ceph): mon/MonmapMonitor: make 'mon remove ...' idempotent
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

07/23/2013

11:39 PM Revision 2338a329 (ceph): client: signal mds sessions with Contexts instead of Conds
If we try to open an mds session and the MDS responds with close (aka,
"no"), we call _closed_mds_session() which sig...
Sage Weil
11:38 PM Revision 32075420 (ceph): client: add Context*-based wait_on_list/signal_context_list helpers
These are better when the list may need to be deallocated. Context's are
single-shot and the list is not referenced ...
Sage Weil
11:10 PM Revision e6a30d73 (ceph): Re-create guest if it already exists
In some cases tests fail or nuke fails and the guest is
not properly destroyed. This will look to see if it gets
an e...
Sandon Van Ness
11:09 PM Revision 71b66ebd (ceph): Add distro type to schedule_suite.sh
Also added machinetype to the name.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
10:52 PM Revision 55cc15fb (ceph): Wait a little longer before recreating VMs
Just to allow for the create to still work incase the os
volume is fairly large (takes a while to resize) and in
case...
Sandon Van Ness
10:50 PM Revision 52a886c5 (ceph): Use os_type instead of vm_type. Add os_version
Use os_type instead of vm_type for more generic naming
for when we start re-imaging bare metal. Also added a
os_versi...
Sandon Van Ness
10:44 PM CephFS Bug #5418: kceph: crash in remove_session_caps
I think BUG_ON(session->s_nr_caps > 0) caused the crash . (looks like kdb traps the undefined instruction and prevent... Zheng Yan
10:38 PM Revision 68888862 (ceph): sequential, parallel: allow entries to be references to top-level config
Often we want to build a test collection that substitutes different
sequences of tasks into a parallel/sequential con...
Sage Weil
10:38 PM Revision c1e0812b (ceph): ceph: add wait_for_mon_quorum command
tasks:
...
- ceph.wait_for_mon_quorum: [a, b]
...
will block until the mon quorum consists of exactly [a, b]. This ...
Sage Weil
10:00 PM Revision 1c2062e4 (ceph): upgrade-parallel: add stress-split collection
Sage Weil
09:45 PM Revision 2ce2ce94 (ceph): upgrade-parallel: do staggered updates
Sage Weil
09:42 PM Revision 612a9b35 (ceph): mon: add quorum_names to quorum_status command output
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:33 PM Bug #5722 (Resolved): osd: crash during signal handler setup on startup
Sage Weil
05:54 PM Bug #5722 (Fix Under Review): osd: crash during signal handler setup on startup
Sage Weil
09:41 AM Bug #5722 (Resolved): osd: crash during signal handler setup on startup
probably due to the recent signal handler changes :)... Sage Weil
09:23 PM Revision 9a7a0557 (ceph): ceph-fuse: disable getgroups_cb
It's broken. See #5729.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:05 PM Revision 90212f7c (ceph): added tasks in the yaml
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
09:04 PM Revision cfabede9 (ceph): Merge branch 'wip-formatted-output' into next
Formatted output bugfixes Dan Mick
09:04 PM Revision 2c87d9fc (ceph): mon: PGMap dump shouldn't use strings containing '+' as tags
XML has a problem with tags containing +, like the PG state names.
Use an enclosing array, and name the state and cou...
Dan Mick
09:04 PM Revision 96551f97 (ceph): mon: "status" is missing a close_section for the overall output
Fixes: #5720
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
09:04 PM Revision 3dcfe386 (ceph): mon: "osd stat" needs a flush now that osdmap.print_summary() doesn't
Fixes: #5719
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Dan Mick
09:03 PM Revision 3a69fd04 (ceph): ceph.spec.in: obsolete ceph-libs only on the affected distro
The ceph-libs package existed only on Redhat based distro,
there was e.g. never such a package on SUSE. Therefore: ma...
Danny Al-Gaaf
09:03 PM Revision e4d0eeef (ceph): mon: "mds stat" must open/close section around dump_info
dump_info() got a new field outside the mdsmap section; it's ok for
the overall "report", but not for "mds stat". Ad...
Dan Mick
09:00 PM Revision 82c5e9e0 (ceph): Merge pull request #461 from dalgaaf/wip-da-fix-spec-obsoletes
ceph.spec.in: obsolete ceph-libs only on the affected distro
Reviewed-by: Gary Lowell <gary.lowell@inktank.com>
Gary Lowell
08:59 PM Revision 385b9c89 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
08:59 PM Revision 4479a5ab (ceph): removed a blank line
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
08:52 PM Revision 59ddece1 (ceph): v0.61.6
Gary Lowell
08:32 PM Revision 38c3271d (ceph): mon/OSDMonitor: fix base case for 7fb3804fb workaround
After cluster creation, we have no full map stored and first_committed ==
1. In that case, there is no need for a fu...
Sage Weil
08:32 PM Revision e8077707 (ceph): mon/OSDMonitor: fix base case for 7fb3804fb workaround
After cluster creation, we have no full map stored and first_committed ==
1. In that case, there is no need for a fu...
Sage Weil
08:06 PM Revision e536d66e (ceph): ceph.spec.in: obsolete ceph-libs only on the affected distro
The ceph-libs package existed only on Redhat based distro,
there was e.g. never such a package on SUSE. Therefore: ma...
Danny Al-Gaaf
07:46 PM devops Bug #5734: ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sys/block/<part1>
I confirm, it works (with and without giving journal). Thanks ! Olivier Bonvalet
05:53 PM devops Bug #5734: ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sys/block/<part1>
As far as i can tell this is fixed with the ceph-disk in next, and we just haven't backported the fixes yet. I pushe... Sage Weil
04:12 PM devops Bug #5734 (Duplicate): ceph-deploy osd prepare <part1>:<part2> fails, tries to look up /sys/block...
A user was trying to ceph-deploy osd prepare with two different partitions. Got this:
...
Dan Mick
07:09 PM Revision 8814265f (ceph): Enable libs3 support for debian packages
Thomas Bechtold
06:23 PM Revision e0709ef5 (ceph): Merge remote-tracking branch 'gh/next' into next
Sage Weil
05:46 PM Revision a0edf7aa (ceph): rados: trim more aggressively
Sage Weil
05:16 PM rbd Bug #5464 (Resolved): krbd: modifying mapped image also modifies snapshot
3.9 is EOL Sage Weil
05:05 PM CephFS Bug #5689 (Resolved): ceph-fuse crashed after upgrading from cuttlefish to dumpling
Sage Weil
04:27 PM CephFS Bug #5689: ceph-fuse crashed after upgrading from cuttlefish to dumpling
Couple comments on the wip-5689 branch. Greg Farnum
05:04 PM Bug #5723: OSD seemingly loses objects during crash
removing cephos.phash.in_progress_op, setting cephos.phash.contents, moving the files and restarting seems to have re... Mike Lowe
03:41 PM Bug #5723: OSD seemingly loses objects during crash
You also need to move all of the objects from DIR_D to DIR_D/DIR_7 again Samuel Just
03:35 PM Bug #5723: OSD seemingly loses objects during crash
HashIndex merge needs to verify the collection contents before merging. In the mean time, you can recover by adjusti... Samuel Just
10:04 AM Bug #5723: OSD seemingly loses objects during crash
OSD crashed without writing any logs Mike Lowe
10:01 AM Bug #5723 (Resolved): OSD seemingly loses objects during crash
I had some vm's with the qemu-rbd driver doing a trim operation. One of my osd's crashed and now has an inconsistent... Mike Lowe
04:50 PM Revision f94956cb (ceph): mon: OSDMonitor: work around a full version bug introduced in 7fb3804fb
In 7fb3804fb860dcd0340dd3f7c39eec4315f8e4b6 we moved the full version
stashing logic to the encode_trim_extra() funct...
Joao Eduardo Luis
04:50 PM Revision 10e1de45 (ceph): mon: OSDMonitor: update the osdmap's latest_full with the new full version
We used to do this on encode_full(), but since [1] we no longer rely on
PaxosService to manage the full maps for us. ...
Joao Eduardo Luis
04:48 PM Revision 97462a32 (ceph): mon: OSDMonitor: work around a full version bug introduced in 7fb3804fb
In 7fb3804fb860dcd0340dd3f7c39eec4315f8e4b6 we moved the full version
stashing logic to the encode_trim_extra() funct...
Joao Eduardo Luis
04:24 PM Revision f528108d (ceph): rados: keep fewer osdmaps around
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:22 PM Revision bc8d62fe (ceph): mon: OSDMonitor: get rid of encode_full() as we don't use it.
We have delegated this to encode_trim_extra() since
7fb3804fb860dcd0340dd3f7c39eec4315f8e4b6 -- no need to keep this ...
Joao Eduardo Luis
04:21 PM Revision a815547e (ceph): mon: OSDMonitor: update the osdmap's latest_full with the new full version
We used to do this on encode_full(), but since [1] we no longer rely on
PaxosService to manage the full maps for us. ...
Joao Eduardo Luis
04:18 PM Documentation #3164 (Rejected): doc: "ceph auth add" syntax: * and ... are magic
Sage Weil
03:44 PM Revision f46e8b99 (ceph): doc/release-notes: v0.67-rc1
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:43 PM Revision 7b3b9893 (ceph): qa/workunits/suites/fsync-tester.sh: lsof at end
Trying to track down occasional EBUSY on umount at end of test.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
03:39 PM Bug #5733 (Won't Fix): monitor: validate pg_temp entries from OSDs
Right now the monitor just takes whatever the OSD sends it. We should validate that the pg_temp is valid with the cur... Greg Farnum
03:20 PM CephFS Bug #5731: failed pjd link permissions check
Logs in /a/teuthology-2013-07-20_20:00:55-fs-cuttlefish-testing-basic/75450 Greg Farnum
02:59 PM CephFS Bug #5731 (Can't reproduce): failed pjd link permissions check
We failed a test in pjd link/07.t:... Greg Farnum
03:19 PM CephFS Fix #5729: ceph-fuse: fix getgroups_cb and gids
Yes, yes it is. Which part of it is actually broken? I can't tell from the problem description. Greg Farnum
03:18 PM CephFS Fix #5729: ceph-fuse: fix getgroups_cb and gids
Is this the ticket for "ceph-fuse is crashing everywhere"? Greg Farnum
02:22 PM CephFS Fix #5729 (Resolved): ceph-fuse: fix getgroups_cb and gids
+ * - the cb needs the request handle to be useful; we should get the
+ * gids in the method here in fuse_ll.c...
Sage Weil
03:17 PM RADOS Feature #5732 (New): crush: (optionally?) update parent weights when marking an OSD out
It's a bit unintuitive that after marking an OSD out and waiting for the cluster to quiesce, you get more data moveme... Greg Farnum
02:30 PM devops Feature #5730 (Resolved): Show what command is being executed
To improve the knowledge (and debugging) about what ceph-deploying is doing with ceph behind the scenes we should be ... Alfredo Deza
02:12 PM Bug #5718 (Resolved): MDSMonitor::dump_info new field mdsmap_first_committed outside any section
Dan Mick
12:36 AM Bug #5718 (Fix Under Review): MDSMonitor::dump_info new field mdsmap_first_committed outside any ...
Dan Mick
02:12 PM Bug #5719 (Resolved): OSDMap::print_summary() lost a flush
Dan Mick
12:36 AM Bug #5719 (Fix Under Review): OSDMap::print_summary() lost a flush
Dan Mick
02:12 PM Bug #5720 (Resolved): "mon status" missing a close_section()
Dan Mick
12:36 AM Bug #5720 (Fix Under Review): "mon status" missing a close_section()
Dan Mick
02:12 PM Bug #5721 (Resolved): pgmap pgs_by_state uses field names containing '+'
Dan Mick
12:36 AM Bug #5721 (Fix Under Review): pgmap pgs_by_state uses field names containing '+'
Dan Mick
12:06 AM Bug #5721 (In Progress): pgmap pgs_by_state uses field names containing '+'
With the more-structured status dump, pgmap dump was showing things like "active+clean"
as a tag, which is illegal i...
Dan Mick
12:05 AM Bug #5721 (Resolved): pgmap pgs_by_state uses field names containing '+'
Dan Mick
02:06 PM devops Bug #5728 (Resolved): Capture std(err|out) and exit code for better error reporting
When a remote function is executed and it fails it will usually error out with something similar to:... Alfredo Deza
01:41 PM devops Bug #5489: ceph-deploy: mon destroy throws inappropriate message
I think the answer is both :) Tamilarasi muthamizhan
12:20 PM devops Bug #5489 (Need More Info): ceph-deploy: mon destroy throws inappropriate message
Tamil, is the problem the lack of a timeout with a graceful handling? or is it just the the error message that would ... Alfredo Deza
01:24 PM devops Bug #5727 (Resolved): Discover and set the proper OS bindings to use
ceph-deploy has more than a few different OS it supports (CentOS, Debian, Gentoo, etc...) and in most places (like ce... Alfredo Deza
11:30 AM rbd Bug #5426 (In Progress): librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::com...
Josh Durgin
11:22 AM CephFS Bug #5724 (Resolved): ceph-fuse crashed during fs tests using ceph-deploy
all the fs tests [workloads: blogbench, dbench, fsstress] failed due to the following ceph-fuse crash on next branch.... Tamilarasi muthamizhan
11:12 AM Bug #5700: very high memory usage after update
Hi Mark,
I just uploaded the archive. It's called corin.tar.gz.
While taking the core dump (which took only a ...
Corin Langosch
10:39 AM Bug #5700: very high memory usage after update
Hi Corin,
tcmalloc should be enabled if you are using our packages. Would you mind generating a core dump from on...
Mark Nelson
11:12 AM rbd Bug #5488 (In Progress): librbd: deadlock in image refresh
Sage Weil
11:08 AM Bug #5704 (Resolved): mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttlefish
Sage Weil
10:17 AM Bug #5704: mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttlefish
Sage Weil
10:44 AM devops Bug #5686 (Rejected): ceph-deploy: install command should not restart the daemons when used for u...
ceph-deploy install doesnt actually restart the daemons when used for upgrade purpose. Upgrade takes effect on the da... Tamilarasi muthamizhan
10:40 AM Bug #5692: RADOS performance regression in 0.65
Yikes. Those limits take an awful lot of writeback time in order to flush to disk (5000 IOs/inodes is going to be ~50... Greg Farnum
10:18 AM Bug #5692: RADOS performance regression in 0.65
Ok, after a ton of testing, here are the values on our supermicro node where I stop seeing benefits across the differ... Mark Nelson
07:10 AM devops Bug #5678 (Resolved): ceph-deploy mon destroy broken
Alfredo Deza
06:23 AM Revision 9e734ffe (ceph): Merge branch 'next'
Gary Lowell
06:21 AM Revision 98816e69 (ceph): Merge branch 'next' of github.com:ceph/ceph into next
Gary Lowell
06:19 AM Revision fc6cb81e (ceph): Merge branch 'next'
Gary Lowell
04:04 AM Revision 3f315404 (ceph): qa/workunits/rest/test: cluster_down/up are now idempotent
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:01 AM Revision 84b41987 (ceph): Merge pull request #459 from ceph/unused-spinlock
log: remove unused lock
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:54 AM Revision 88f4a962 (ceph): log: remove unused lock
m_lock is initialized and destroyed, but never used.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
Noah Watkins
01:46 AM Revision 2c5b68c3 (ceph): Merge remote-tracking branch 'gh/next'
Conflicts:
PendingReleaseNotes
Sage Weil
01:28 AM Revision 9626f77f (ceph): Merge pull request #457 from ceph/wip-paxos
paxos fixes
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil
12:20 AM Revision d2881dd7 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite
Tamilarasi muthamizhan
12:19 AM Revision c812ee23 (ceph): task yamls for upgrade-parallel suite
Signed-off-by: tamil <tamil.muthamizhan@inktank.com> Tamilarasi muthamizhan
12:19 AM Revision 093182b7 (ceph): osd/ReplicatedPG: drop repop refs in ~SnapTrimmer
This fixes a leak on shutdown.
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktan...
Sage Weil

07/22/2013

11:30 PM Revision 77cae4bf (ceph): thrashosds: add delay option after recovery
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:33 PM CephFS Bug #5658 (Resolved): kcepht: warning: fs/ceph/inode.c:1000 ceph_fill_trace+0x760/0x900 [ceph]()
Sage Weil
10:32 PM CephFS Bug #4601 (Can't reproduce): symlink with size zero
Sage Weil
10:32 PM CephFS Bug #3641 (Resolved): kclient: hit EOF prematurely
Sage Weil
10:32 PM CephFS Bug #5039: client: unlinking files leaves the cached entry behind
Sage Weil
10:10 PM Revision 6582b31a (ceph): FileStore: disable fd cacher and wbthrottle during replay
The fd cache only works correctly when there is at most 1
inode per hobject_t. This condition is frequently violated...
Samuel Just
10:06 PM Revision 2fd44217 (ceph): PGLog::merge_log, unidex() only works from tail, we index() below anyway
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
10:06 PM Revision 6957dbc7 (ceph): PGLog::rewind_divergent_log: unindex only works from tail, index() instead
Fixes: #5714
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
10:05 PM Revision 046d5cb6 (ceph): src/test/osd/TestPGLog.cc: check that the object remains in log.objects
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
09:51 PM Bug #5720 (Resolved): "mon status" missing a close_section()
output is not valid JSON; overall "mon status" section must be closed
Dan Mick
09:47 PM Revision 3f95f9a4 (ceph): Merge remote-tracking branch 'gh/wip-5624-b' into next
Reviewed-by: David Zafman <david.zafman@inktank.com> Sage Weil
09:45 PM Bug #5719 (Resolved): OSDMap::print_summary() lost a flush
In structuring ceph status, OSDMap::print_summary lost a Formatter.flush() call, but
osd stat was relying on that. ...
Dan Mick
09:44 PM Revision c5025d4a (ceph): rgw: dump progress through swift object copy
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:44 PM Revision 9f05db6b (ceph): rgw: add some comments
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:44 PM Revision 165b0d0a (ceph): PendingReleaseNotes: update about new rgw copy obj response
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:44 PM Revision 6094685e (ceph): rgw: send data back when copying object
Currently doing it only when copying between regions. This is
needed so that the operation doesn't time out (as it ca...
Yehuda Sadeh
09:37 PM Revision c7edf036 (ceph): Merge pull request #458 from ceph/wip-5693
Wip 5693
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
09:36 PM Bug #5718: MDSMonitor::dump_info new field mdsmap_first_committed outside any section
This will add another section, so requires changes to rest/test.py (which validates the
output).
Dan Mick
09:31 PM Bug #5718 (Resolved): MDSMonitor::dump_info new field mdsmap_first_committed outside any section
MDSMonitor::dump_info is called from (at least) two places: the "ceph report" command
and the "ceph mds stat" comman...
Dan Mick
09:32 PM Bug #5717 (Resolved): mds cluster_down doesn't fail, requires change in rest/test.py
commit:3f31540448e20fd6391773d4f3d46d76060b31c8 Sage Weil
09:22 PM Bug #5717 (Resolved): mds cluster_down doesn't fail, requires change in rest/test.py
mds cluster_up and cluster_down are now idempotent; this means rest/test.py can no
longer expect failure on duplicat...
Dan Mick
09:25 PM Revision 1ecdb149 (ceph): rgw: swift, in create bucket set location_constraints
For swift we're setting the location constraint to be the
current region we're in when creating a bucket.
Signed-off...
Yehuda Sadeh
09:24 PM Revision 8a2eb184 (ceph): rgw: translate swift request to s3 when forwarding
When forwarding a swift request to a different region, we
need to use the effective uri, and not just send the one
we...
Yehuda Sadeh
09:13 PM Revision 20baf662 (ceph): mon/Paxos: fix pn for uncommitted value during collect/last phase
During the collect/last exchange, peers share any uncommitted values
with the leader. They are supposed to also shar...
Sage Weil
09:13 PM Revision cfe1395f (ceph): mon/Paxos: add failure injection points
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:13 PM Revision b3253a45 (ceph): mon/Paxos: only learn uncommitted value if it is in the future
If an older peer sends an uncommitted value, make sure we only take it
if it is in the future, and at least as new as...
Sage Weil
09:13 PM Revision 19b29788 (ceph): mon/Paxos: debug ignored uncommitted values
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:13 PM Revision b26b7f6e (ceph): mon/Paxos: only share uncommitted value if it is next
We may have an uncommitted value from our perspective (it is our lc + 1)
when the collector has a much larger lc (bec...
Sage Weil
09:12 PM Revision a61635e8 (ceph): ceph-monstore-tool: dump paxos transactions
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:12 PM Revision 99e60545 (ceph): mon/Paxos: accepted_pn_from has no semantic meaning
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:10 PM Bug #5704 (In Progress): mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttl...
Sage Weil
01:58 AM Bug #5704: mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttlefish
this helped us to remove not working monitors
we just update from link
http://gitbuilder.ceph.com/ceph-deb-prec...
Ilya Stekolnikov
09:10 PM Bug #5677 (In Progress): osd/OSD.cc: 5517: FAILED assert(_get_map_bl(epoch, bl))
Sage Weil
08:12 PM Revision e60d14d9 (ceph): ceph.in: reject --admin-daemon so it can't do harm
Fixes: #3944
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Dan Mick
06:57 PM Revision 835dd973 (ceph): v0.67-rc1
Gary Lowell
06:43 PM Revision 58c78dba (ceph): FileJournal: fix posix_fallocate error handling
From the man page for posix_fallocate:
posix_fallocate() returns zero on success, or an error
number on fail...
Noah Watkins
06:29 PM Bug #5698 (Pending Backport): mon: paxos mishandles uncommitted values during collect/last phase
Sage Weil
06:11 PM Revision 0897d3a8 (ceph): OSD::_make_pg: use createmap, not osdmap
The osd lock is not held at this point, we must use
the createmap passed in.
Fixes: #5656
Signed-off-by: Samuel Just...
Samuel Just
05:40 PM rgw Bug #5716 (Resolved): radosgw-admin: does not validate pool name when creating region
On the next branch, running:... Josh Durgin
05:33 PM Revision 2dbb273d (ceph): src/*: make Context::finish private and switch all users to use complete
Signed-off-by: Samuel Just <sam.just@inktank.com>
Fixes: Sage Weil <sage@inktank.com>
Samuel Just
05:32 PM Revision e71808f6 (ceph): Merge remote-tracking branch 'upstream/next'
Samuel Just
05:31 PM Revision d28c18da (ceph): OSD::RemoveWQ: do not apply_transaction while blocking _try_resurrect_pg
Some callbacks take the osd lock, so we need to avoid blocking an
osd lock holding thread while waiting on a filestor...
Samuel Just
05:31 PM Revision 6c4cd22e (ceph): FileStore: use complete() instead of finish() and delete
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
05:31 PM Revision 9f591a63 (ceph): Finisher: use complete() not finish() and delete
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
05:31 PM Revision 8536ff9a (ceph): common/Cond.h: add a simpler C_SaferCond Context
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
05:22 PM devops Feature #4954: ceph-deploy: help and document need to be updated for osd create
We see a lot of users in IRC not clear about how to use osd create command using path instead of disk.
It would be...
Tamilarasi muthamizhan
05:20 PM Revision 748d0c80 (ceph): Add more stressful thrashing by doing more pg splitting
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
05:11 PM Bug #3676 (Can't reproduce): osd keeps crashing at ReplicatedPG::scan_range()
Sage Weil
05:11 PM Revision 20bc09c6 (ceph): rgw: read attributes when reading bucket entry point
Fixes: #5691
We need to also read the attributes, as bucket might be a legacy
bucket and might have all bucket insta...
Yehuda Sadeh
05:02 PM Revision e84c54ad (ceph): task: mon_clock_skew_check: grab max-skew value from ceph-mon's config
Instead of relying on hardcoded values, obtain the max-skew default from
'ceph-mon --show-config-value mon_clock_drif...
Joao Eduardo Luis
05:02 PM Revision 222b2960 (ceph): admin_socket: loop until the socket command succeeds
Sometimes the thing we're talking to is slow to start, or to register the
command we are running. Loop in that case,...
Sage Weil
04:52 PM Revision eabf2f6a (ceph): ceph.spec.in: Obsolete ceph-libs
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Gary Lowell
04:29 PM Revision 4a4ecde0 (ceph): big: run for 1 hour
Sage Weil
04:29 PM Revision 9b3f59df (ceph): rados: add in the mon/caps.sh tests
Sage Weil
04:27 PM Revision e58b0e93 (ceph): Merge remote-tracking branch 'gh/wip-mon-caps' into next
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> Sage Weil
03:56 PM CephFS Bug #5689 (Fix Under Review): ceph-fuse crashed after upgrading from cuttlefish to dumpling
Sage Weil
02:51 PM CephFS Bug #5689: ceph-fuse crashed after upgrading from cuttlefish to dumpling
the clients sends request_open and gets back closed from the mds, and wait_on_list can't handle the list<Cond*> getti... Sage Weil
01:44 PM CephFS Bug #5689: ceph-fuse crashed after upgrading from cuttlefish to dumpling
logs are copied to mira074.front.sepia.ceph.com:/home/ubuntu/bug_5689/teuthology_run Tamilarasi muthamizhan
03:34 PM Bug #5697 (Duplicate): osd: ENOENT on pull
This is probably also a duplicate of 5699 Samuel Just
03:19 PM Revision db2850c5 (ceph): test_cls_statelog.cc: fix resource leak, delete 'rop' at end of function
CID 1049213 (#3 of 3): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "rop" going out of scope leaks the
...
Danny Al-Gaaf
03:13 PM Bug #5699 (Resolved): osd/ReplicatedPG.cc: 1507: FAILED assert(0) in trim_object
Samuel Just
03:13 PM Bug #5714 (Pending Backport): osd/ReplicatedPG.cc: 7564: FAILED assert(0 == "erroneously present ...
Samuel Just
01:47 PM Bug #5714 (Resolved): osd/ReplicatedPG.cc: 7564: FAILED assert(0 == "erroneously present object")
ubuntu@teuthology:/var/lib/teuthworker/archive/sage-foo/76281
0> 2013-07-21 18:33:18.814774 7f2aed8f2700 -1 osd/Re...
Samuel Just
02:54 PM rgw Feature #5693 (Resolved): rgw: send data through copy operation to avoid timeout
Merged into next in commit:c7edf03691a5cc86726e687d9a140a4fefb07a97 Greg Farnum
02:53 PM rgw Bug #5664 (Resolved): rgw: can't create containers on secondary region via swift
In next as of commit:a7b707cb74fe283fcc296f6dc765c4c1e53ef160 Greg Farnum
02:49 PM Bug #5624 (Resolved): osd: prepare_to_stop() segfaults if we get a signal during startup
commit:3f95f9a45e34af78449427db315321185e87cbcc Sage Weil
02:17 PM devops Bug #5499: ceph-deploy --cluster clustername osd prepare fails
Robert Sander wrote:
> ssh root@node "ceph-disk-prepare --cluster office -- /path/to/mountpoint"
>
> suceeds
I...
Abdi Ibrahim
01:54 PM devops Bug #5678: ceph-deploy mon destroy broken
Gary is helping me out test this as I encountered a few issues, a pull request is open in the meantime: https://githu... Alfredo Deza
01:51 PM Bug #5701 (Duplicate): ENOENT from radosmodel test
Samuel Just
01:49 PM CephFS Bug #5418: kceph: crash in remove_session_caps
registers:... Sage Weil
01:46 PM CephFS Bug #5418: kceph: crash in remove_session_caps
Zheng Yan wrote:
> I need to know which line caused the crash. looks like it was triggered by one of the BUG_ONs in ...
Sage Weil
01:26 PM CephFS Bug #5418: kceph: crash in remove_session_caps
I need to know which line caused the crash. looks like it was triggered by one of the BUG_ONs in remove_session_caps.... Zheng Yan
09:04 AM CephFS Bug #5418: kceph: crash in remove_session_caps
dump attached
i'll leave this box in kdb in case more information is needed
Sage Weil
01:23 PM Bug #3944 (Resolved): ceph tool should prevent --admin-socket
Dan Mick
12:35 PM Revision 5f4f87b0 (ceph): test_cls_statelog.cc: fix resource leak, delete op at end of function
CID 1049214 (#13 of 13): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "op" going out of scope leaks the
...
Danny Al-Gaaf
11:13 AM Bug #5656 (Resolved): ./osd/OSDMap.h: 536: FAILED assert(pools.count(pg.pool()))
0897d3a820ec182ebd74100a370dbadab50de84f Samuel Just
10:49 AM Bug #5656 (In Progress): ./osd/OSDMap.h: 536: FAILED assert(pools.count(pg.pool()))
Samuel Just
10:58 AM Revision 637e106e (ceph): cls/rgw/cls_rgw.cc: init start_key_added with false
Fix for coverity issue:
CID 1049231 (#1 of 1): Uninitialized scalar variable (UNINIT)
uninit_use: Using uninitiali...
Danny Al-Gaaf
10:58 AM Revision c35eeae3 (ceph): test_cls_version.cc: fix ressource leak
CID 1049220 (#18 of 18): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "rop" going out of scope leaks
th...
Danny Al-Gaaf
10:58 AM Revision d3782d80 (ceph): test_cls_version.cc: fix another ressource leak
CID 1049219 (#17 of 17): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "op" going out of scope leaks the
...
Danny Al-Gaaf
10:58 AM Revision 3e943930 (ceph): test_cls_version.cc: fix resource leak, delete before new()
CID 1049217 (#1 of 1): Resource leak (RESOURCE_LEAK)
overwrite_var: Overwriting "op" in "op = new_op()" leaks
the...
Danny Al-Gaaf
10:58 AM Revision 8e8596d2 (ceph): test_cls_version.cc: fix resource leak, delete before new()
Fix some more cases where resource wasn't deleted/freed before
call new().
CID 1049216 (#1-9 of 9): Resource leak (R...
Danny Al-Gaaf
10:58 AM Revision fc1c1c6f (ceph): test_cls_statelog.cc: fix resource leak, delete rop at end of function
CID 1049215 (#12 of 12): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "rop" going out of scope leaks the
...
Danny Al-Gaaf
10:51 AM Bug #5672 (Resolved): osd: stuck in DeletingState::try_stop_deletion
Landed Ian Colle
10:46 AM CephFS Feature #3426: ceph-fuse: build/run on os x
What's the context for this offset? It sounds like we could just implement it client-side if we really wanted to for ... Greg Farnum
10:38 AM Bug #5700: very high memory usage after update
Hi Mark,
Here's the output of ceph osd dump:...
Corin Langosch
10:22 AM Bug #5700: very high memory usage after update
Hi,
Could you tell me a couple of things about your cluster?
How many PGs total across all of your pool?
H...
Mark Nelson
10:36 AM rgw Bug #5691 (Resolved): All bucket ACLs lost after upgrade
Reviewed-by: Greg Farnum <greg@inktank.com>
In next at commit:20bc09c668cca01bc1d27c0a860b384d85585ef5
Thanks for...
Greg Farnum
10:18 AM Bug #5692: RADOS performance regression in 0.65
I don't remember our small-IO performance numbers — is that disk activity you mentioned above accurate for small IO? ... Greg Farnum
10:00 AM Bug #5692: RADOS performance regression in 0.65
<hat eating commencing>
Looks like I jumped the gun last night and must have tried to install the debs for wip-bef...
Mark Nelson
07:16 AM Bug #5692: RADOS performance regression in 0.65
tweaking osd_pool_default_flag_hashpspool doesn't seem to have had an effect on XFS. Interestingly it looks like wip... Mark Nelson
10:03 AM Bug #5652 (Resolved): mon: occasional clock_skew test failure
Sage Weil
09:53 AM devops Bug #5496 (Resolved): Unable to install librados rpm on Fedora 18
Sage Weil
09:41 AM rgw Bug #5676 (Resolved): swift nightly tests failing
Sage Weil
09:40 AM rgw Bug #5374: Avoid relying on keystone's admin token
actually, it's not merged yet. I still need to complete the review on it, hopefully I can get that done soon. Yehuda Sadeh
06:21 AM rgw Bug #5374: Avoid relying on keystone's admin token
This issue need update has a fix has been merged. Christophe Courtaut
08:15 AM devops Bug #5694 (Closed): test_cli uses python 2.7+ constructs
Alfredo Deza
06:38 AM devops Bug #5694: test_cli uses python 2.7+ constructs
Awaiting merge: https://github.com/ceph/ceph-deploy/pull/19 Alfredo Deza
05:56 AM devops Bug #5694 (In Progress): test_cli uses python 2.7+ constructs
I was not aware we were using Python 2.6
We will add that to our testing harness so we can run tests under 2.6 too...
Alfredo Deza
06:36 AM devops Bug #5483 (Resolved): ceph-deploy --cluster othername mon create does not work
Fixed and ready to use from the master branch in the ceph-deploy repo. Alfredo Deza
06:20 AM rgw Feature #4365: rgw: allow setting wildcard keystone role
A pull request with a fix has been proposed here : https://github.com/ceph/ceph/pull/455 Christophe Courtaut
04:42 AM Revision da2cb090 (ceph): Merge pull request #453 from dalgaaf/wip-da-SCA-cppcheck-7
Fix SCA and CID issues
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:40 AM Revision c4563901 (ceph): Merge pull request #451 from dalgaaf/wip-da-SCA-cppcheck-6-v2
Fix some issues from SCA - v2 - against ceph:next
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Reviewed-by: Sage W...
Sage Weil
03:00 AM Revision 3846bf2f (ceph): fuse: fix fuse_getgroups detection
The ac_check_func fails because -lfuse is not in LIBS. This also enables
code that wasn't being compiled, and fixes c...
Noah Watkins

07/21/2013

10:31 PM Bug #5704: mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttlefish
ceph-b.tar.bz2 on sftp cephdrop@ceph.com Ilya Stekolnikov
10:16 PM Bug #5704 (Resolved): mon/OSDMonitor.cc: 132: FAILED assert(latest_bl.length() != 0) on cuttlefish
... Sage Weil
09:45 PM Bug #5656: ./osd/OSDMap.h: 536: FAILED assert(pools.count(pg.pool()))
full logs at: ubuntu@teuthology:/a/sage-foo/76309 Sage Weil
09:30 PM Bug #5692: RADOS performance regression in 0.65
hmm, there is the hashpspool option addition... i woudln't expect that matter for a rados bench workload, though. t... Sage Weil
08:44 PM Bug #5692: RADOS performance regression in 0.65
Glad you did that Sage. I only have the 4MB results so far, but it's looking like the performance regression is stil... Mark Nelson
07:58 PM Bug #5692: RADOS performance regression in 0.65
pushed wip-before, which is just prior to the wbthrottle merge, to confirm this is the source of the trouble. Sage Weil
07:46 PM Bug #5692: RADOS performance regression in 0.65
I suspect it's more than just the byte limit. While large writes are degraded, small writes appear to be hurt even m... Mark Nelson
11:54 AM Bug #5692: RADOS performance regression in 0.65
That probably means the limits are set too low, if the backing disks are providing about the same throughput as the m... Greg Farnum
11:08 AM Bug #5692: RADOS performance regression in 0.65
I should mention journals are on separate SSD drives (8 SSDs total, 3 journals per). Each SSD is capable of about 45... Mark Nelson
11:07 AM Bug #5692: RADOS performance regression in 0.65
Sage pushed wip-5692 that changes the fsycs to fdatasyncs in wb throttle. This doesn't appear to have helped though.... Mark Nelson
01:03 AM Bug #5692: RADOS performance regression in 0.65
I'm placing my bets on this being the writeback throttle. Tunables:... Greg Farnum
09:13 PM Feature #5703 (Duplicate): Allow ceph-deploy to work with non-root account
ceph-deploy should have an option to distribute using a non-root account that has access to sudo. This is the standar... Charles Pritchard
08:45 PM rgw Bug #5702 (Resolved): Radosgw RPM unnecessarily requires mod_fcgid
The radosgw rpm currently requires mod_fcgid. This in turn requires Apache. For an environment (such as nginx) withou... Charles Pritchard
07:56 PM Bug #5701 (Duplicate): ENOENT from radosmodel test
... Sage Weil
09:18 AM Bug #5698: mon: paxos mishandles uncommitted values during collect/last phase
manually verified this behaves with multiple uncommitted values with different pns using the failure injection points... Sage Weil
08:49 AM Bug #5698 (Fix Under Review): mon: paxos mishandles uncommitted values during collect/last phase
see wip-paxos Sage Weil
12:47 AM Bug #5700: very high memory usage after update
Just a small update: I hoped the memory usage would go down after some hours, but it stays high:
ceph version 0.61...
Corin Langosch
 

Also available in: Atom