Activity
From 11/19/2012 to 12/18/2012
12/18/2012
- 10:12 PM Revision 04e7a5ca (ceph): rgw: configurable exit timeout
- Fixes: #3638
rgw exit timeout secs : number of seconds to wait for process
to exit cleanly before forcing exit. If s... - 08:59 PM CephFS Bug #3637: client: not issuing caps for with clients doing shared writes
- The hang occurs because a client requests a max size increase, but doesn't have write caps, so the mds puts it on the...
- 07:53 AM CephFS Bug #3637 (Resolved): client: not issuing caps for with clients doing shared writes
- With 3 clients running ceph-fuse, running the ior command:
/tmp/cephtest/binary/usr/local/bin/ior -e -w -r -W -b 1... - 07:40 PM Bug #3646: pg_temp with two down/out osds
- sounds exactly right
- 07:29 PM Bug #3646: pg_temp with two down/out osds
- It actually does that already. OSDMonitor::remove_redundant_pg_temp(). I'll hook in around there for the fix, doing ...
- 06:42 PM Bug #3646: pg_temp with two down/out osds
- Good point. We can also remove mappings that match the crush result. Although that is a more expensive scan by the m...
- 04:41 PM Bug #3646 (Resolved): pg_temp with two down/out osds
- Encountered on MassEffect, osdmap is attached.
{ "pgid": "2.25",
"osds": [
30,... - 06:08 PM Bug #3647: forgot the auth options for Cephx and added them later: Get msg: 7ff9faaad700 monclie...
- added output for dmesg on ceph1
- 06:04 PM Bug #3647 (Can't reproduce): forgot the auth options for Cephx and added them later: Get msg: 7f...
- Seeing errors when setting up ceph from scratch with the options in the ceph.conf file. I forgot the auth options f...
- 04:23 PM CephFS Feature #3645 (Resolved): Requesting the ability to rename CephFS snapshots inside the ".snap"-di...
- I believe the ability to rename CephFS snapshots can come in handy in many cases. For example, if one wants to imple...
- 02:26 PM Bug #3644 (Resolved): ObjectCacher: discard_set ignores waiters
- IO in flight contained entirely in a discarded section will not be acked to the caller, since the waiters are removed...
- 01:41 PM Bug #3643 (Resolved): default authentication on the client does not work without a config file or...
- On a single node bobtail cluster,the ceph-auth setting is as mentioned below,
ubuntu@burnupi09:/etc/ceph$ sudo cat... - 01:26 PM rbd Bug #3642 (Resolved): librbd: watch is sent with assert version, which fails on resends
- Instead of using an assert version op, establish the watch before reading the header. This hasn't actually caused any...
- 12:01 PM CephFS Bug #3639 (Duplicate): kclient: hit EOF prematurely
Moved to #3641- 10:56 AM CephFS Bug #3639 (Duplicate): kclient: hit EOF prematurely
- Failures seen when running IOR on the kernel client:
WARNING: Task 1 requested transfer of 1048576 bytes,
... - 12:00 PM CephFS Bug #3641 (Resolved): kclient: hit EOF prematurely
Failures seen when running IOR on the kernel client:
WARNING: Task 1 requested transfer of 1048576 bytes,
...- 11:57 AM CephFS Bug #3640 (Duplicate): kclient: hang and kernel panic
Creating a placeholder for the following issue reported by Eric Renfro on the mailing list:
http://thread.gmane....- 11:17 AM rgw Feature #2941 (Fix Under Review): rgw: improve streaming read performance
- 10:36 AM rgw Bug #3638 (Resolved): rgw: configurable exit timeout
- Currently exit timeout is 5 seconds, we should make it configurable, and probably have a higher default.
- 09:46 AM Bug #2784: osd hit suicide timeout
- This bug popped again on v0.55.1
renzhi on IRC stumbled upon it after upgrading from v0.48.2, and has been unable ... - 08:54 AM rbd Bug #3611: rbd.py: segfault with many snapshots
- This survived overnight testing (with the python librbd tests) with 56 passes.
- 08:03 AM Linux kernel client Bug #3519: rbd map hang during system startup
- I looked through the latest log message supplied by Nick
Bartos. I scanned through it to look only at the rbd
acti... - 07:39 AM Linux kernel client Bug #3519: rbd map hang during system startup
- There has been quite a lot of activity on this bug but it's
all been recorded on the mailing list rather than here.
... - 06:40 AM Bug #3624 (In Progress): BUG: workqueue leaked lock or atomic: kworker/0:1/0x00000000/17554 last ...
- Answer to my question, based on evidence in this bug:
The control (yaml) file contains this:
overrides:
... - 04:42 AM Bug #3617: Ceph doesn't support > 65536 PGs(?) and fails silently
- Note how this was on a cluster with *very* few OSDs (4 at the time!) as I originally mentioned and this may play a fa...
- 01:12 AM Revision dbe6fb72 (ceph): crushtool: only dump usage on -h|--help
- Instead, output a useful error message.
Fix error code to be a success.
Add test for the output usage.
Signed-off-... - 01:12 AM Revision 6c7ec2d4 (ceph): crushtool: nicer error message on extra args
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 AM Revision 0dd13025 (ceph): Merge remote-tracking branch 'gh/testing' into next
- 12:38 AM Revision fd482a27 (ceph): ceph.spec.in: Update pre-reqs for ceph-fuse pacakge.
- 12:29 AM Revision 1b67a438 (ceph): Revert "objecter: don't use new tid when retrying notifies"
- This reverts commit c3107009f66bc06b5e14c465142e14120f9a4412.
This appears to be causing problems in the objecter by... - 12:14 AM Feature #3288: docs: document the chooseleaf command in crush
- Commit 9f0510 added docs for multiple crush hierarchies and the examples use chooseleaf, which is still undocumented.
12/17/2012
- 10:59 PM rbd Bug #3611 (Fix Under Review): rbd.py: segfault with many snapshots
- wip-3611 contains a respin of the bad commit. It's passing test_stress_watch with failure injection and the python te...
- 11:09 AM rbd Bug #3611: rbd.py: segfault with many snapshots
- also, ubuntu@teuthology:/a/teuthology-2012-12-15_19:00:04-regression-next-testing-basic/16289
- 11:08 AM rbd Bug #3611: rbd.py: segfault with many snapshots
- recent log: ubuntu@teuthology:/a/teuthology-2012-12-15_19:00:04-regression-next-testing-basic/16281
- 10:53 PM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- Thanks for the logs. All the differences there are zeroes where actual data should be, but the librbd debug log shows...
- 10:41 PM Revision bdc998ef (ceph): mon: OSDMonitor: add option 'mon_max_pool_pg_num' and limit 'pg_num' ac...
- Instead of having a hardcoded default, use a configurable one. It is
limited to 65536 until future testing guarantees... - 10:39 PM Revision 21c47c6a (ceph): osd: debug EMSGSIZE / OSD_WRITETOOBIG
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:39 PM Revision f81ca898 (ceph): doc/release-notes: don't use format 2 rbd images until after osds upgrade
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:14 PM Revision 3c246226 (ceph): crushtool: add --set-chooseleaf-descend-once to help
- We forgot to update this in 88f218181a9e6d2292e2697fc93797d0f6d6e5dc.
Signed-off-by: Sage Weil <sage@inktank.com> - 06:53 PM Revision 874b2732 (ceph): doc/release-notes: 'mon max pool pg num'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:30 PM Feature #1655: gitbuilder aggregator page
- ...
- 04:25 PM Feature #1655: gitbuilder aggregator page
- I'm not sure if anyone else has asked, but any chance of sharing the updated server side cgi script which now has aja...
- 04:10 PM Bug #3617 (In Progress): Ceph doesn't support > 65536 PGs(?) and fails silently
- Looking closer, I have a feeling this was a large # of pgs making a different bug surface. Jim has been running his ...
- 04:03 PM Bug #3617: Ceph doesn't support > 65536 PGs(?) and fails silently
- Note how your commit changed the (default) limit from 65535 to 65536.
- 04:01 PM Bug #3617: Ceph doesn't support > 65536 PGs(?) and fails silently
- The default is now 65536, and can be adjusted using the option 'mon max pool pg num' if higher values are desired.
- 03:57 PM Revision e8b8531e (ceph): doc: fix typo in config file
- The option is host, not hostname
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 02:35 PM Bug #3636 (Resolved): sub_op_modify assert(!missing.is_missing(soid));
- Encountered in Alexandria, fixed in 047aecd90f1dbfb172f48f9d10b67e82b3a8ce15, may it rest in piece.
- 12:40 PM rbd Feature #3635: rbd cli: call "udevadm settle" after use of add/remove kernel interface
- Trivial change. Biggest decision is which libc routine to use to spawn the command...
- 11:42 AM rbd Feature #3635 (Resolved): rbd cli: call "udevadm settle" after use of add/remove kernel interface
- The rbd command line interface creates mappings by sending
output to the /sys/bus/rbd/add file system entry, and rem... - 11:14 AM rgw Feature #3634 (Resolved): rgw: improve teuthology radosgw-admin test
- 11:10 AM rgw Bug #3620: rgw:improve multiple user access keys scalability
- Possibly impacts interoperability
- 11:09 AM rgw Bug #3628: rgw: leak of object parts on partial upload
- Appears to only be in Argonaut
- 09:31 AM rgw Bug #3628: rgw: leak of object parts on partial upload
- Actually, per user, this affects older versions (argonaut), but does not happen in newer version. Looking at the code...
- 10:53 AM rbd Bug #3600: rbd: assert in objectcacher destructor after flatten
- Tried to reproduce this behavior to no avail.
There are operations on the test that do hang for a long time, but a... - 09:49 AM Bug #3624: BUG: workqueue leaked lock or atomic: kworker/0:1/0x00000000/17554 last function: xfs_...
- When XFS gets an I/O error, there is not a lot it can do.
If it happens to involve user data blocks it could continu... - 09:42 AM Bug #3624 (Won't Fix): BUG: workqueue leaked lock or atomic: kworker/0:1/0x00000000/17554 last fu...
- XFS bug
- 09:42 AM Bug #3599 (Resolved): mkcephfs should fail out when ceph.conf has an error
- 09:38 AM Bug #3632: occasional testrados failure: process_8 exited with a signal
- Possibly related to 3611
- 09:14 AM Bug #3629: test_mon_workloadgen.cc: 766: FAILED assert(m->fsid == monc.get_fsid())
- I've gone through the logs again and again, as well as through the code. The logs only show the last couple hundred l...
- 08:08 AM Linux kernel client Bug #2764: xfstest hang; osd socket closed messages
- I have posted a fix for the "socket closed" messages, and it has
been reviewed and will fairly soon be pushed to the... - 07:36 AM Bug #3633 (Resolved): mon: clock drift errors not reported by ceph status
- Using argonat 0.48.2. Today all ceph commands were randomly slow. So I checked all hosts, all monitors (3) and osds (...
12/16/2012
- 08:49 PM Bug #3632: occasional testrados failure: process_8 exited with a signal
- ...
- 08:48 PM Bug #3632 (Resolved): occasional testrados failure: process_8 exited with a signal
- seen several of these in qa, e.g....
- 08:29 PM Revision e9231fe6 (ceph): Makefiles: Two new packages needed in the debian build depdencies.
- The ceph test programs that are now being built by default require the junit
and libboost-program-options packages. ... - 08:29 PM Revision bc9d9d8a (ceph): Refactor rule file to separate arch/indep builds.
- Prior to the ceph fs java bindings, all packages where
architecture depdendent so the packaging rules file
worked OK;... - 12:44 PM rbd Bug #2872 (Resolved): RBD resize command allows image size -1
- 11:02 AM rbd Bug #2689: qemu iozone test hangs
- let's retest this with all of the recent caching fixes?
- 10:46 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- Which in memory maps? Nothing should grow without bound, except perhaps some of the intern monitor messages...
- 04:30 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- Attaching 3 heap profiles from the monitors.
The monitors were under load from the mon workload gen, as well as so... - 10:12 AM Bug #3631 (Resolved): osdc/ObjectCacher.cc: 834: FAILED assert(ob->last_commit_tid < tid) during ...
- old symptom, presumably new bug....
- 09:48 AM CephFS Fix #3630 (Resolved): mds: broken closed connection cleanup
- Consider:
- client->mds REQUEST_CLOSE
- mds->client CLOSE
- client closes con
- mds see fault, goes to stan... - 07:25 AM Bug #3629 (Fix Under Review): test_mon_workloadgen.cc: 766: FAILED assert(m->fsid == monc.get_fsi...
- Pushed a fix to wip-3629.
After looking into what the OSD does in this case and go through the code, I realized th... - 01:45 AM Revision 4bf90782 (ceph): osdc/Objecter: prevent pool dne check from invalidating scan_requests i...
- We iterate over ops and, if the pool dne and other conditions are true,
we will immediately return ENOENT and cancel ...
12/15/2012
- 09:00 PM Bug #3629 (Resolved): test_mon_workloadgen.cc: 766: FAILED assert(m->fsid == monc.get_fsid())
- ...
- 08:33 PM rgw Bug #3628 (Resolved): rgw: leak of object parts on partial upload
- 08:23 PM Bug #3613 (Resolved): Objecter::scan_requests crash
- commit:4bf9078286d58c2cd4e85cb8b31411220a377092
passed 100 iterations of the test (previously failed after ~15). - 05:44 PM Bug #3613: Objecter::scan_requests crash
- the pool dne check invalidated the iterator. switching to map<> and incrementing hte iterator at hte top of the loop
- 03:54 PM Bug #3627 (Resolved): osd: segfault in ~MOSDSubOp during thrashing+rbd_fsx
- ...
- 09:59 AM Bug #3458: aio enabled but not used
- I didn't compile it, it's the version from the ubuntu quantal repository. Is there any way to see which feature have ...
- 09:46 AM Bug #3458 (Need More Info): aio enabled but not used
- this probably means that libaio wasn't found when you compiled the code?
- 09:45 AM rbd Fix #3588 (In Progress): rbd.py's clone should take stripe parms, call rbd_clone2
- 09:45 AM rbd Feature #2601 (Resolved): rbd: Show image size with an "ls"
- 09:44 AM rbd Feature #2634 (Resolved): teuthology: add networking to qemu task
- 09:43 AM rbd Bug #3619 (In Progress): librbd: read_iterate sparse behavior broken
- 09:42 AM rbd Bug #2689: qemu iozone test hangs
- 09:00 AM Bug #3616 (Resolved): osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- 09:00 AM Bug #3603 (Resolved): osd/msgr: mutex assert failure in try_get_pipe
- 09:00 AM Bug #3221 (Resolved): disconnect_session_watchers missing pg
- 09:00 AM Bug #2954 (Resolved): osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/2538528...
- 01:08 AM Revision 601a6c93 (ceph): Merge remote-tracking branch 'gh/next'
- 12:56 AM Revision 6f978aa5 (ceph): doc: draft bobtail release notes
- Signed-off-by: Sage Weil <sage@inktank.com>
12/14/2012
- 11:56 PM Revision 50614811 (ceph): doc: correct meaning of 'pool' in crush
- This was recently made less confusing by renaming the default crush
'pool' type to 'root'. Use this terminology every... - 11:31 PM Revision 286dcbeb (ceph): test: remove underscores from cephfs test names
- Google Test documentation strongly suggests avoiding underscores from
unit test names to avoid accidental conflicts w... - 11:28 PM Revision c9b81510 (ceph): add an fsync-tester workunit to the fuse and kclient suites
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:27 PM Revision 673b6820 (ceph): put fsx back in the kernel suite. Looks like this was lost accidentally?
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 11:24 PM Revision 1ec70aa0 (ceph): qa: add a workunit for fsync-tester
- It turns out that our suites don't exercise fsync, at least not very much
(I couldn't find it in all the places I loo... - 10:32 PM Revision 79db5a40 (ceph): Merge branch 'wip_watch' into next
- 10:20 PM Revision 641b077f (ceph): mkcephfs: fix == -> =
- Another bashism.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:17 PM Revision a7de975d (ceph): lockdep: Decrease lockdep backtrace skip by 1
- Skipping the top 4 (it starts at 0) calls in the
backtrace actually skips the call that does the lock.
Skip 3 instead... - 09:58 PM Revision bf01b7b2 (ceph): map-unmap.sh: use udevadm settle for synchronization
- This script was heuristically using short sleep commands in order to
give udev activity time to complete.
There's a ... - 09:51 PM Revision c728171b (ceph): Merge branch 'wip-upstart' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 09:49 PM Revision e597482f (ceph): upstart: only start when 'upstart' file exists in daemon dir
- We need to distinguish between daemons managed by upstart and sysvinit
(and, eventually, systemd). Only start daemon... - 09:49 PM Revision 96f40b14 (ceph): upstart: make starter jobs consistent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:49 PM Revision 02aca683 (ceph): ceph-disk-activate: mark dir as upstart-managed
- Mark the directory so that upstart will manage the daemon. Eventually,
this should be generalized to allow ceph-disk... - 09:38 PM Revision 6ab7db67 (ceph): ReplicatedPG: use default priority for Backfill messages
- Backfill messages modify the stats on the replica and therefore
must be sent with the same priority as sub_op_modify ... - 09:38 PM Revision 7e133569 (ceph): ReplicatedPG: do not use priority from client op
- There are internal ordering requirements which may be sensitive
to assigned priority. We don't want a mix of priorit... - 07:15 PM rbd Bug #3611: rbd.py: segfault with many snapshots
- It looks like the op in the objecter has been corrupted, similar to #3613. In this case, op->objver ends up pointing ...
- 07:00 PM Revision b63940ca (ceph): Merge branch 'wip-3610' into next
- 06:31 PM CephFS Bug #3625: client: EEXIST error on multiple clients to create
- I made some commits to wip-3625, which resolve the EEXIST, but now the test returns an EIO...
- 03:31 PM CephFS Bug #3625 (Resolved): client: EEXIST error on multiple clients to create
- Discovered with IOR shared file test on ceph-fuse, if multiple clients attempt to create a file at the same time (do ...
- 05:53 PM Revision 8d73f3e9 (ceph): Fix comment in sample.ceph.conf
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 04:21 PM Revision 9f051024 (ceph): crush-map.rst: add info about multiple crush heirarchies
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:07 PM rbd Bug #3589 (Resolved): rbd.py should check for method existence before calling new methods
- 03:51 PM CephFS Feature #3626 (Resolved): mds: debug mode to generate traceless replies to clients
- 03:50 PM Bug #3616: osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- 03:50 PM Bug #3221: disconnect_session_watchers missing pg
- 03:50 PM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- 11:08 AM Bug #2954 (In Progress): osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/2538...
- recent log: ubuntu@teuthology:/a/teuthology-2012-12-13_19:00:03-regression-next-testing-basic/13809...
- 12:43 PM Bug #3602 (Resolved): ceph-fuse crashed when client tries to ceph-fuse mount without keyring
- The fix was cherry-picked into wip-stable-fuse and merged to stable.
- 11:15 AM Bug #3623: libcephfs Caps.ReadZero lockdep weirdness
- The fix for this has been merged to next, so we should stop seeing these in qa.
- 10:46 AM Bug #3623: libcephfs Caps.ReadZero lockdep weirdness
- recent log: ubuntu@teuthology:/a/teuthology-2012-12-13_19:00:03-regression-next-testing-basic/13713...
- 11:13 AM CephFS Bug #3610 (Resolved): client: Possible lock cycle in client/objectcacher
- 11:13 AM CephFS Bug #3610: client: Possible lock cycle in client/objectcacher
- Merged wip-3610 to next.
- 10:56 AM Bug #3624 (Won't Fix): BUG: workqueue leaked lock or atomic: kworker/0:1/0x00000000/17554 last fu...
- log: ubuntu@teuthology:/a/teuthology-2012-12-13_19:00:03-regression-next-testing-basic/13746...
- 07:28 AM rbd Bug #2410: hung xfstest #68
- This appears to be an XFS problem, where the file
system is having trouble getting space in its
journal. I inquire... - 07:13 AM rbd Bug #2608: rbd: hung xfstest 270
- We should re-evaluate this with XFS found in newer kernels.
Maybe this should just be closed and re-opened (or open
... - 07:11 AM Linux kernel client Bug #2764: xfstest hang; osd socket closed messages
- I'm pretty sure the "socket closed" messages are fairly
harmless, and the cod that issues them should be changed
to... - 06:08 AM rbd Feature #3418: krbd: write path (layering)
- I did a little research on this before starting on the write
path. This work will require the kernel rbd client, th... - 06:00 AM rbd Feature #3417: krbd: read path (layering)
- Work on this really started in November 2012.
In October there were a number of cleanup tasks we agreed
should ge... - 03:49 AM Revision f16e5717 (ceph): client: Add config option to inject sleep for tick
- Testing the tick delay with a fork/suspend is causing
corruption in the lockdep code. This approach uses
a config op... - 01:43 AM Revision 8cf367cb (ceph): rbd.py: check for new librbd methods before use
- This way attempting to use format 2 images works when you upgrade the
python bindings before librbd, and attempting t... - 12:27 AM Revision c9894ff0 (ceph): osd: up != acting okay on mkpg
- This can happen when:
- mon sends create pg
- it gets created
- osd remaps the pg to a different osd
but osd...
12/13/2012
- 11:48 PM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- Attached files as requested.
Compare was stopped early to save on file size. - 11:38 PM Revision e3ed28eb (ceph): mon: OSDMonitor: don't allow creation of pools with > 65535 pgs
- There are some limitations to the number of possible pg's per pool, and
by allowing the 'osd pool create' command to ... - 10:46 PM Revision 8103414a (ceph): rbd: handle images disappearing while in ls -l
- rbd.list() returns a list of names, but nothing stops them from
going away before rbd.open(); check for ENOENT and ig... - 10:23 PM Bug #3623 (Duplicate): libcephfs Caps.ReadZero lockdep weirdness
- nm, dup of #3610
- 10:05 PM Bug #3623 (Duplicate): libcephfs Caps.ReadZero lockdep weirdness
- ...
- 10:05 PM Revision 24523913 (ceph): rgw_op: enforce minimum part size in multi-part uploads
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 08:48 PM Revision aa2214c3 (ceph): mds: document EXCL -> (MIX or SYNC) transition decision
- Previously (in w26f6a8e48ae575f17c850e28e969d55bceefbc0f), for reasons that
are somewhat obscured by passage of time,... - 07:54 PM Bug #2843 (Can't reproduce): filestore: replay failure on xfs
- 07:53 PM Bug #2819 (Won't Fix): krbd: lockup on large writes, msgr fault injection
- 07:49 PM CephFS Bug #3610 (Fix Under Review): client: Possible lock cycle in client/objectcacher
- This appears to be related to the fork() in the caps.cc test messing up data structures in the lockdep code when its ...
- 06:52 PM Revision f2c083ef (ceph): OSD: disconnect_session_watches obc might not be valid after we relock
- If disconnect_session_watches races with watch removal, the session
might no longer have a valid obc ref. In that ca... - 06:52 PM Revision 97cc55d5 (ceph): OSD: put connection in disconnect_session_watches as well as the session
- obc->watchers now has a ref to the connection as well. This piece of
disconnect_session_watchers essentially paralle... - 06:39 PM Revision c17d628b (ceph): clarify/correct some of sample.ceph.conf
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 05:24 PM Bug #3615: Reproducible OSD crash when recovering the journal
- Samuel was kind enough to clarify a bit on IRC: I should be looking for a pginfo/directory named 6.1bc7, since they'r...
- 04:34 PM Bug #3615: Reproducible OSD crash when recovering the journal
- Thanks, I figured as much when you mentioned the existence of that file.
I still think it's a bug though: I believ... - 02:06 PM Bug #3615 (Rejected): Reproducible OSD crash when recovering the journal
- Running with nobarrier could explain this error if the pginfo file link wasn't flushed when the sync finished. Our u...
- 11:43 AM Bug #3615: Reproducible OSD crash when recovering the journal
- Thanks for the quick reply. I couldn't find a 6.7111 pg. Am I doing something wrong?
# find /var/lib/ceph/osd/ceph... - 10:54 AM Bug #3615 (Need More Info): Reproducible OSD crash when recovering the journal
- on pg 6.7111 the info appears corrupt somehow. can you attach the contents of the meta/.../pginfo file for 6.7111 on...
- 09:15 AM Bug #3615 (Rejected): Reproducible OSD crash when recovering the journal
- Hi,
After an abrupt powercycle of one of the servers, one of the OSDs has trouble booting up. It seems to be getti... - 05:03 PM rbd Bug #3611: rbd.py: segfault with many snapshots
- Finally got a backtrace. It seems something is overwriting a Mutex::Locker on the stack:...
- 04:41 PM Bug #3616: osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- It has happened quite a few times, but I'm afraid it happens at random when adding new OSDs, so I'd have to run with ...
- 01:52 PM Bug #3616: osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- This is probably the crash which characterizes the handle_watch_timeout-push race which wip_watch should take care of...
- 01:20 PM Bug #3616 (Need More Info): osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- Is this something you can reproduce reliably? If so, that would be extremely helpful. For example:
ceph osd tel... - 09:27 AM Bug #3616 (Resolved): osd/ReplicatedPG.cc: 4534: FAILED assert(!missing.is_missing(soid))
- Hi,
On a test cluster of ours with Ceph 0.55, we often see OSDs crash due to an assert() call when we add them and... - 04:30 PM Revision 83ee85b8 (ceph): Merge remote branch 'origin/next'
- 04:29 PM rgw Documentation #2483 (Resolved): doc: radosgw api diffs to swift
- 01:03 PM rgw Documentation #2483: doc: radosgw api diffs to swift
- Done, at commit:6a8a58dc4b71df6d291d67ddad0b5667289d6d3b.
- 04:29 PM Revision e6dd0681 (ceph): qa: echo commands run by rbd map-unmap workunit
- It's hard to figure out what failed without this.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 04:28 PM Feature #2727 (Resolved): filestore: add split
- 04:28 PM Feature #2728 (Resolved): OSD: handle split
- 04:27 PM Bug #3614 (Resolved): osd: mkpg 92.5 up [1] != acting [1,0]" in cluster log
- 04:18 PM Bug #3614 (Fix Under Review): osd: mkpg 92.5 up [1] != acting [1,0]" in cluster log
- 08:26 AM Bug #3614: osd: mkpg 92.5 up [1] != acting [1,0]" in cluster log
- np
- 04:16 PM Bug #3617 (Resolved): Ceph doesn't support > 65536 PGs(?) and fails silently
- Joao wrote a monitor patch that prohibits counts greater than 65535, and it's merged in. I've created #3622 to deal w...
- 11:51 AM Bug #3617 (In Progress): Ceph doesn't support > 65536 PGs(?) and fails silently
- 09:40 AM Bug #3617 (Resolved): Ceph doesn't support > 65536 PGs(?) and fails silently
- Hi,
While playing with a test cluster and trying to size it according to production needs & future growth, we deci... - 04:16 PM Feature #3622 (Rejected): RADOS pools should support more than 65535 PGs
- That's a pretty low limit for a single-pool cluster, since we find users need ~100 PGs/OSD to get good data distribut...
- 03:53 PM CephFS Feature #3568 (Resolved): client: Allow hold_caps_until to be configured
- 03:49 PM CephFS Feature #3621 (Closed): qa: add knfsd reexport tests to qa suite
- 03:46 PM CephFS Cleanup #3423 (Resolved): Install java libraries into the correct directory
- 03:41 PM rgw Bug #3620 (Resolved): rgw:improve multiple user access keys scalability
- One solution would be: instead of keeping the complete user data in the key index, it should just point at the uid in...
- 03:28 PM Bug #3618: 0.55.1 ceph-mon crashes under heavy load
- This is fixed on next, but the commit didn't reach 0.55.1.
- 03:16 PM Bug #3618 (Duplicate): 0.55.1 ceph-mon crashes under heavy load
- This bug is a duplicate of #3495.
- 12:43 PM Bug #3618 (Duplicate): 0.55.1 ceph-mon crashes under heavy load
- Here is the tail of the monitor log: https://pastee.org/e9347
It core dumped:
https://pastee.org/j4maf - 03:28 PM Bug #3495 (Resolved): ceph-mon crash
- Sorry, jumped the gun here. Thought the fix was on 0.55.1 but it is not. It's on next though.
- 03:18 PM Bug #3495 (In Progress): ceph-mon crash
- This bug occurred again on 0.55.1, as described on bug #3618. Re-opening as it appears that there's still something e...
- 03:07 PM Feature #3000 (Resolved): osd: balance recovery vs client io
- 03:02 PM Bug #3592 (Resolved): Assert (oinfo.last_epoch_started == info.last_epoch_started)
- 01:31 PM rbd Bug #3619 (Resolved): librbd: read_iterate sparse behavior broken
- Instead of getting a NULL for a hole, we get a zeroed buffer.
Reported on the ML - 01:28 PM CephFS Bug #3559 (Resolved): mds: not issuing RDCACHE to exclusive client for some files
- Thought more about it, and I think it's right. Committed something to master that describes the logic in a big comment.
- 10:11 AM CephFS Bug #3559 (In Progress): mds: not issuing RDCACHE to exclusive client for some files
- After discussion this apparently needs a bit more thought.
- 10:04 AM CephFS Bug #3559 (Resolved): mds: not issuing RDCACHE to exclusive client for some files
- 01:26 PM Bug #3221 (In Progress): disconnect_session_watchers missing pg
- 01:00 PM rgw Documentation #2991 (Resolved): doc: expand/complete RGW Swift API reference
- 12:54 PM rgw Bug #3297 (Rejected): Rados Gateway does not handle Transfer-Encoding: chunked
- 12:43 PM Bug #3613: Objecter::scan_requests crash
- I don't see any evidence pointing to the recent objecter changes yet. The op->ops vector seems to be invalid though.
- 11:15 AM Linux kernel client Cleanup #3583 (Rejected): Convert tabs to spaces
- yeah this is a no-no for kernel. if you touch a line of code, fix whitespace, otherwise let it be.
- 11:14 AM Linux kernel client Bug #2429: ceph-client: verify_authrizer_reply con method never called
- 10:13 AM Bug #2683 (Can't reproduce): ceph-fuse: crash during fsstress
- We believe this was fixed in the ObjectCacher code changes over the last several months.
- 10:04 AM Bug #2683 (Resolved): ceph-fuse: crash during fsstress
- 06:01 AM Revision 975003bf (ceph): auth: guard decode_decrypt with try block
- This will catch buffer decoding errors (maybe the block is empty) and
return an error string.
May fix (or possibly p... - 05:14 AM Revision ae100cfd (ceph): mount.fuse.ceph: add ceph-fuse mount helper
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:14 AM Revision 448db479 (ceph): mount.fuse.ceph: strip out noauto option
- mount -a uses this, but also passes it to mount.fuse.ceph, and libceph
complains:
fuse: unknown option `noauto'
Sig... - 03:40 AM Revision ac92e4d6 (ceph): /etc/init.d/ceph: fs_type assignment syntax error
- This handles the remainder of 3581; it's a lot like the problem in
mkcephfs, but it isn't mkcephfs.
Fixes: #3581
Sig... - 01:17 AM Revision 4605fddc (ceph): filestore: Don't keep checking for syncfs if found
- Valgrind outputs a warning for unrecognized system calls,
and does so for the syscall(__SYS_syncfs,...) and
syscall(_... - 12:24 AM Revision 8e25c8d9 (ceph): v0.55.1
12/12/2012
- 11:30 PM Revision dba09607 (ceph): OSD: pg might be removed during disconnect_session_watches
- We don't hold the osd_lock between the session->watches traversal
and the obc checks.
Signed-off-by: Samuel Just <sa... - 11:30 PM Revision 047aecd9 (ceph): PG,ReplicatedPG: handle_watch_timeout must not write during scrub/degraded
- Currently, handle_watch_timeout will gladly write to an object while
that object is degraded or is being scrubbed. N... - 10:51 PM Revision 0dfe6c84 (ceph): ReplicatedPG:, remove_notify, put session after con
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:50 PM Revision 695bb3b0 (ceph): ReplicatedPG: only put if we cancel evt in unregister_unconnected_watcher
- If we fail to cancel the callback, the callback will fire and
release those resources.
Signed-off-by: Samuel Just <s... - 10:50 PM Revision fdf66b6a (ceph): ReplicatedPG: watchers must grab Connection ref as well
- Session refs are not really valid on their own, the
corresponding Connection must remain live for at least
as long as... - 10:38 PM Revision 5f55b388 (ceph): doc: Updated per comments in the mailing list.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:04 PM Bug #3459 (Resolved): osd crash in CephXAuthorizer::verify_reply
- other bug is #3414, but it doesn't appear related.
going to merge this change in.
- 10:02 PM Bug #3459: osd crash in CephXAuthorizer::verify_reply
- these all appear to be unrelated. i had broken tests in my lock teuthology repo, or they were other bugs.
except ... - 11:44 AM Bug #3459: osd crash in CephXAuthorizer::verify_reply
- The patch looks fine on its face but several tests in the suite failed. I need to track down if they're familiar erro...
- 10:03 PM Bug #3614 (Resolved): osd: mkpg 92.5 up [1] != acting [1,0]" in cluster log
- /var/lib/teuthworker/archive/sage-2012-12-11_19:47:13-rados-wip-3459-testing-basic/11975
- 09:49 PM Revision 9d714560 (ceph): docs: better documentation of new rgw feature
- Document rgw_extended_http_attrs config option.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:45 PM Revision 87087245 (ceph): rgw: option to provide alternative s3 put obj success code
- Fixes: #3529
Added a new option: rgw_s3_success_create_obj_status.
Expected values are 0, 200, 201, 204. A value of 0... - 09:45 PM Revision 3a95d976 (ceph): rgw: configurable list of object attributes
- Fixes: #3535
New object attributes are now configurable. A list
can be specified via the 'rgw extended http attrs'
co... - 09:08 PM Revision bece012c (ceph): doc: document swift compatibility
- Add a table that specifies swift features compatibility
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:08 PM Revision 88229a49 (ceph): docs: add rgw POST object as supported feature
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:00 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
- Ah, I wasn't aware of this bug. The commit you mentioned is 323a52ee909621ed0169b86e158370394ba36f62. It makes remo...
- 06:40 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
- SamL did some stuff involving projected xattrs; was this problem included in that set of changes or is it more compli...
- 07:43 PM Bug #3581 (Resolved): init script errors after upgrade from 0.48 to 0.55
- above fix in
commit:ac92e4d6bd453ffc77e88ab3ec2d2015b70ba854 - 07:35 PM Bug #3581: init script errors after upgrade from 0.48 to 0.55
- I think this still needs...
- 07:33 PM Bug #3581: init script errors after upgrade from 0.48 to 0.55
- I was mistaken about the commit above; that fixes the issue for mkcephfs, but not for init-ceph.in. That bug still e...
- 06:38 PM CephFS Bug #3369 (Resolved): journaled two client session close events
- Sage merged that workaround a long time ago, and I think Zheng's recent patches might have fixed some potential root ...
- 05:35 PM Bug #3613 (Resolved): Objecter::scan_requests crash
- One of the failures in #3459 was due to testrados_watch_notify crashing:...
- 05:21 PM Bug #3221: disconnect_session_watchers missing pg
- This has popped up again.
I think the easy fix is to make the map reference pg's and obc's by name, and do the loo... - 05:20 PM Bug #3612 (Duplicate): disconnect_session_watches assert(pg) failed
- dup of #3221
- 03:12 PM Bug #3612: disconnect_session_watches assert(pg) failed
- The assert is bad, no guarantee that the pg is still around after we drop the watch_lock. remove_watchers_and_notifi...
- 03:09 PM Bug #3612 (Duplicate): disconnect_session_watches assert(pg) failed
- ...
- 04:13 PM rbd Bug #3611: rbd.py: segfault with many snapshots
- Downgrading priority since this isn't an actual bug.
- 03:41 PM rbd Bug #3611: rbd.py: segfault with many snapshots
- Without lockdep, I could not reproduce a crash.
Running with lockdep enabled results in this backtrace:... - 11:52 AM rbd Bug #3611 (Resolved): rbd.py: segfault with many snapshots
- From the nightly python api tests, test_many_snaps failed with a segfault in all runs.
Logs are in:... - 03:35 PM Bug #3603: osd/msgr: mutex assert failure in try_get_pipe
- Yep, this definitely looks to be that bug. Sam has a branch he's testing at wip_watch.
- 02:21 PM Bug #3603 (In Progress): osd/msgr: mutex assert failure in try_get_pipe
- Well, I dug into this a bit despite the lack of messenger logging, but Sam is pretty sure this is related to a ref-co...
- 02:00 PM rgw Bug #3453 (Resolved): rgw: Resume download fails because of mismatched ETags that should match
- 01:45 PM rgw Feature #3535 (Resolved): rgw: configurable list of http attributes
- 01:39 PM rgw Feature #3529 (Resolved): rgw: configurable success status response for put obj
- 12:23 PM Bug #3606: Current -next causes failed assert in ceph-osd
- Took an alternative route to making the packages, and the commit does in fact resolve the issue. Sorry for the trouble.
- 09:29 AM Bug #3606: Current -next causes failed assert in ceph-osd
- I've applied the most recent set of patches, and still get the same crash: https://pastee.org/n8bnq
I suppose I co... - 10:31 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- Are we failing to clean up forwarded messages? That would certainly be a pretty bad leak that we need to deal with as...
- 10:04 AM Bug #3609: mon: track down the Monitor's memory consuption sources
- Looks like it make sense that mon.c has a bigger memory consumption, from what the profile indicates. Apparently, mos...
- 09:13 AM Bug #3609 (Resolved): mon: track down the Monitor's memory consuption sources
- Left a couple of monitors running overnight with heap profiling active.
Don't have the logs, as I wasn't expecting... - 09:56 AM Bug #3608: librbd rbd_remove returns wrong errno when image does not exist
- EBUSY is returned from rbd_remove when there are still watchers on the header (i.e. the image is still open, or a pre...
- 02:04 AM Bug #3608 (Can't reproduce): librbd rbd_remove returns wrong errno when image does not exist
- I'm currently working with librbd and noticed that rbd_remove returns an errno of -16 (EBUSY) when the specified imag...
- 09:20 AM CephFS Bug #3610 (Resolved): client: Possible lock cycle in client/objectcacher
- Teuthology reported this lock cycle while running test_libcephfs. It was triggered by the Caps.ReadZero test.
For... - 08:14 AM Bug #3607: FileStore::_write conditional code for HAVE_SYNC_FILE_RANGE seems wrong
- the if needs to go in the #ifdef, yeah.. but hte way it's split across the if () guts is messy. can you just clean i...
- 08:07 AM Bug #3607: FileStore::_write conditional code for HAVE_SYNC_FILE_RANGE seems wrong
- Tracked this down to https://github.com/ceph/ceph/commit/1477ec73e354972664424b3d98d78a20c24a2ff4 but I still can't r...
- 06:27 AM Revision 64cefe2c (ceph): PG,ReplicatedPG: move write_blocked_by_scrub logic into a helper
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:46 AM Bug #3550: mon: Ceph fails to work when IP address is changed on the host
- That's a once or twice thing in a life time. Shouldn't happen often. As Sage pointed out before, there are ways to de...
- 01:49 AM Revision 54618afa (ceph): docs: fix spacing in radosgw config-ref
- Needed to add an extra empty line between header and properties.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:18 AM Revision 8e6a5353 (ceph): qa: exclude some more xfstests
- These worked on a newer kernel, but I forgot I had not updated it for the final image.
Signed-off-by: Josh Durgin <j... - 01:16 AM Revision 84f90a09 (ceph): Merge branch 'next'
- 01:15 AM Revision caea0cbf (ceph): os/JournalingObjectStore: un-break op quiescing during journal replay
- Commit d9dce4e9273adb4279519d65a0d8bfdfecb5c516 broke journal replay
because the commit thread may try to do a commit... - 01:07 AM Revision 6a8a58dc (ceph): doc: document swift compatibility
- Add a table that specifies swift features compatibility
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 01:07 AM Revision cf28e787 (ceph): docs: add rgw POST object as supported feature
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:47 AM Revision f0d85b73 (ceph): Merge branch 'next'
- 12:39 AM Revision 326dd347 (ceph): Merge remote branch 'origin/wip-double-notify' into next
- Reviewed-by: Sage Weil <sage.weil@inktank.com>
12/11/2012
- 11:44 PM Revision 39501822 (ceph): st_rados_watch: tolerate extra notifies
- With retries, it's possible for notifies to be received more than once
when they are resent to different OSDs, since ... - 11:11 PM Revision f2dbe5ed (ceph): CephManager: add ability to test split
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 11:08 PM Revision 29307d3b (ceph): mds: shutdown cleanly if can't authenticate
- Fixes: #3590
This was triggered when tried to run mds with cephx enabled
against a mon without cephx support. We didn... - 11:07 PM Revision 6007088c (ceph): Merge remote-tracking branch 'gh/wip-conf' into next
- Reviewed-by: Greg Farnu <greg@inktank.com>
- 10:07 PM Revision 0cd84b3a (ceph): New ssh task that adds keys for node -> node ssh.
- This generates a new keypair, pushes it to all nodes
in the context and adds all hosts to all other hosts
.ssh/author... - 10:07 PM Revision 0890d48a (ceph): Adding a Hadoop task.
- This task configures and starts a Hadoop cluster.
It does not run any jobs, that must be done after
this task runs.
C... - 10:07 PM Revision b916f679 (ceph): pexec.py: Parse out role ID from the back.
- Also, do not assume that the command needs to run from a specific directory.
Signed-off-by: Joe Buck <jbbuck@gmail.com> - 08:38 PM Bug #3607 (Resolved): FileStore::_write conditional code for HAVE_SYNC_FILE_RANGE seems wrong
- I won't claim to fully understand this, but it looks wrong:...
- 07:46 PM Bug #3606: Current -next causes failed assert in ceph-osd
- I build the package with the provided specfile, but in such a way that it used a .55 source checkout and patched with...
- 07:35 PM Bug #3606 (Resolved): Current -next causes failed assert in ceph-osd
- this was just fixed in next a couple hours ago, commit:caea0cbf9f63d74506d69a596dd3f78097d68da5
by the way, the du... - 06:49 PM Bug #3606 (Resolved): Current -next causes failed assert in ceph-osd
- After making packages from 0.55 + the contents of the next branch, one (only one of 8) OSD will not start, and produc...
- 07:13 PM Revision c3107009 (ceph): objecter: don't use new tid when retrying notifies
- Watches update the on-disk state in the OSD, and aren't idempotent,
so refreshing them must be treated as a separate ... - 06:08 PM Revision dfd31036 (ceph): client: Fix for #3184 cfuse segv with no keyring
- Fixes bug #3184 where the ceph-fuse client segfaults if authx is
enabled but no keyring file is present. This was du... - 06:08 PM Revision acebcce9 (ceph): mon: Monitor: resolve keyring option to a file before loading keyring
- Otherwise our keyring default location, or any other similarly formatted
location, will be taken as the actual locati... - 06:04 PM Bug #3459 (Fix Under Review): osd crash in CephXAuthorizer::verify_reply
- the try/catch may be treating hte symptom, but it's definitley correct, and the binary for the qa run is long gone so...
- 05:59 PM Bug #3459: osd crash in CephXAuthorizer::verify_reply
- wth, i could have sworn i pushed something that added a try/catch block around the decode, but now i don't see it. p...
- 05:19 PM Bug #3507 (Resolved): rados api system tests failure
- commit:c3107009f66bc06b5e14c465142e14120f9a4412
- 04:54 PM Bug #3507 (Fix Under Review): rados api system tests failure
- wip-double-notify
- 05:06 PM Revision 9a40ef01 (ceph): mds: fix journaling issue regarding rstat accounting
- Rename operation can call predirty_journal_parents() several times.
So a directory fragment's rstat can also be modif... - 05:04 PM rbd Bug #3413: rbd bench-write fails with assert when rbd caching turned on
- 04:58 PM rbd Bug #3589 (Fix Under Review): rbd.py should check for method existence before calling new methods
- wip-rbdpy-compat
- 04:53 PM rbd Feature #2568 (Resolved): qa: run xfstests on qemu+rbd
- 04:50 PM rgw Bug #3557 (Resolved): rgw: error reading user info after creating subusers
- Fixed, commit:0639cd9c479d69b077175f0385eb569ebb839349.
- 04:44 PM Revision b9d717cd (ceph): fix build of unittest_formatter
- Add CRYPTO_CXXFLAGS to unittest_formatter_CXXFLAGS to find pk11pub.h to
be included in src/common/ceph_crypto.h.
Sig... - 04:44 PM Revision be372765 (ceph): include/atomic.h: add stdlib.h for size_t
- Include missing stdlib.h needed for size_t.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:34 PM rbd Bug #3600: rbd: assert in objectcacher destructor after flatten
- The hang on selfmanaged_snap_create seems like a monitor issue; bouncing the monitor, or hanging out in gdb long enou...
- 03:17 PM Bug #3590 (Resolved): mds segfault at MonClient::wait_auth_rotating during upgrade
- Fixed, commit:29307d3b32e523da7f25a6c3bc904749790b1e18. Fix would just make it exit gracefully.
- 11:19 AM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- mon is running argonaut, mds is running 0.55+. The problem is that mds doesn't handle gracefully a case where mon rej...
- 02:10 PM CephFS Bug #3370 (Resolved): All nfsd hung trying to lock page(s) on export of kclient ceph
- commit: 2978257c56935878f8a756c6cb169b569e99bb91
- 11:34 AM Bug #3550: mon: Ceph fails to work when IP address is changed on the host
- Real world example of needing to change ip numbers....
john roman john.roman@dreamhost.com via hq.newdream.net... - 09:28 AM CephFS Bug #3597 (Can't reproduce): ceph-fuse: denying root access
- I don't see this behavior with fuse 2.9.0 and latest ceph. Does it happen only on some files? What are the permissi...
- 06:00 AM Revision bcf1461c (ceph): Merge remote-tracking branch 'upstream/wip_split2' into next
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 05:01 AM Subtask #3605 (Resolved): mon: print lookup path when reporting -ENOENT to user-space
- See parent task.
- 04:59 AM Feature #3604 (Resolved): print lookup path when reporting -ENOENT to user-space
- With the advent of 0.55, some users mentioned that the error message is not helpful when the keyring file is not foun...
- 03:03 AM Revision 1699b7dc (ceph): OSD: get_or_create_pg doesn't need an op passed in
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 02:07 AM Bug #3603 (Resolved): osd/msgr: mutex assert failure in try_get_pipe
- This happened on the next branch with a client side objecter change I was testing with 1 osd using vstart and test_st...
- 01:45 AM Revision 6a4fa89a (ceph): LFNIndex: fix move_subdir comments
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:40 AM Revision fdcdca7d (ceph): HashIndex: fix typo in reset_attr documentation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:39 AM Revision 7eac9682 (ceph): HashIndex: init exists in col_split_level and reset_attr
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:31 AM Revision 12673c24 (ceph): PrioritizedQueue: increment ret when removing items from list
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:30 AM Revision 80cca214 (ceph): PrioritizedQueue: move if check out of loop in filter_list_pairs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:08 AM Revision 331c2504 (ceph): Merge remote-tracking branch 'gh/next'
- 12:41 AM Revision a50c7d3b (ceph): config: do not always print config file missing errors
- Do not generate errors each time we fail to open a config file; only
generate one at the end if a search path was spe...
12/10/2012
- 10:44 PM Revision 6fb9a558 (ceph): config: always complain about config parse errors
- Complain about config parsing errors even when it is the default
config file.
We may also want to fail instead of co... - 10:37 PM Revision a5b9939e (ceph): ceph.conf: default to smaller recovery chunk
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 10:34 PM Revision e4d0aeac (ceph): Merge remote-tracking branch 'gh/wip-filestore2' into next
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 10:14 PM Revision 2e7cba7b (ceph): doc: fixed indent in python example.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:53 PM Revision 788992bb (ceph): config_opts.h: adjust recovery defaults
- osd max backfills: 5 was too low for a default, 10
seems to work better in testing. The message
priority system sh... - 08:55 PM Revision 45865285 (ceph): Merge remote-tracking branch 'gh/wip-3559' into next
- Reviewed-by: Sage Weil <sage@inktank.com>
- 08:12 PM Bug #3602: ceph-fuse crashed when client tries to ceph-fuse mount without keyring
- I tried installing ceph-fuse from next branch, and I dont see any segfault.
ubuntu@burnupi62:~$ sudo ceph-fuse -v
... - 05:45 PM Bug #3602: ceph-fuse crashed when client tries to ceph-fuse mount without keyring
- Did you check for similar bugs? Not certain but I believe this has been fixed in a dev release since then. (Maybe sho...
- 05:43 PM Bug #3602 (Resolved): ceph-fuse crashed when client tries to ceph-fuse mount without keyring
- Bug found by Ken:
upgraded argonaut cluster to bobtail [burnupi16, burnupi17, burnupi18] and the client[burnupi62]... - 08:06 PM Revision f7b26958 (ceph): Merge branch 'next'
- 08:06 PM Revision 1bdd5c3b (ceph): Fix qemu options for xfstests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 07:57 PM rbd Bug #3600: rbd: assert in objectcacher destructor after flatten
- Hm #2. Both runs are deadlocked on the mutex IoCtxImpl::selfmanaged_snap_create::mylock. Will look for owner next.
- 07:23 PM rbd Bug #3600: rbd: assert in objectcacher destructor after flatten
- Looking at the code, I don't really see a clean "stop caching" mechanism. While I look, hacked fsx to do only write/...
- 11:40 AM rbd Bug #3600 (Duplicate): rbd: assert in objectcacher destructor after flatten
- From ubuntu@teuthology:/a/teuthology-2012-12-09_19:00:03-regression-master-testing-gcov/10977:...
- 07:52 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- I was able to reproduce this issue on burnupi06[running mds], burnupi07[osds], burnupi08[mon] cluster with debugs on....
- 04:47 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- I am planning to reproduce it with debug on and show it to Greg
- 04:44 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- Not from my end. I'm not working at Inktank, today. I'll be in tomorrow and I hope to make progress on it then.
- 04:12 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- Anything new here?
- 06:51 PM Revision f4be3c8d (ceph): doc: Added sudo to ceph -k command.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:24 PM Revision 37095195 (ceph): doc: Fixed typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:19 PM Revision 47c81a3b (ceph): Makefile.am: add missing flags to some tests targets
- adding CRYPTO_CXXFLAGS to some targets. This is required when
building --with-nss.
Signed-off-by: Yehuda Sadeh <yehu... - 04:49 PM Bug #3593: MDS crash in MDCache.cc _recovered()
- Both of these logs show a respawn because the MDS got removed from the map (generally, for not heartbeating). That ag...
- 04:31 PM Bug #3593: MDS crash in MDCache.cc _recovered()
- Here is a piece of log from an mds dying with ms=1 and mds=20: https://pastee.org/hf3cy
Here's another from another ... - 11:03 AM Bug #3593: MDS crash in MDCache.cc _recovered()
- Oh, I see. It does indeed start with a bunch of broken pipe messages between the MDS and monitor. Can you post more o...
- 10:59 AM Bug #3593: MDS crash in MDCache.cc _recovered()
- At the moment I can't do any more to debug this (until this evening), but I have set the beacon grace to 120 seconds ...
- 10:55 AM Bug #3593: MDS crash in MDCache.cc _recovered()
- This is nothing to do with the pipe changes. It's getting ESHUTDOWN back from the OSD, not out of the local pipe — we...
- 04:46 PM Bug #2437 (Resolved): osd: very slow during recovery
- 04:19 PM Bug #3221: disconnect_session_watchers missing pg
- 04:18 PM Bug #3221: disconnect_session_watchers missing pg
- I think the locking here is just broken. The obc always goes away at PG reset time when it is removed from the sessi...
- 11:37 AM Bug #3221 (In Progress): disconnect_session_watchers missing pg
- recent log: ubuntu@teuthology:/a/teuthology-2012-12-09_19:00:03-regression-master-testing-gcov/10911
- 02:10 PM Bug #3591: auth: could not find secret_id=0
- They were running 0.55. I don't think it's failure to rotate keys, as the secret_id was consistently 0. I'd expect a ...
- 01:56 PM Bug #3591: auth: could not find secret_id=0
- That i can't remember.. but that message shouldn't come up on the server ever unless it is failing to rotate its keys...
- 01:44 PM Bug #3591: auth: could not find secret_id=0
- Did you see it happening with anything other than the kernel clients?
- 01:35 PM Bug #3591: auth: could not find secret_id=0
- Have seen this pop up in several places.
I bet we can find it with 'debug auth = 0/20' (so that it is all logged i... - 01:57 PM Bug #3599 (In Progress): mkcephfs should fail out when ceph.conf has an error
- wip-conf will spam stderr unconditionally about parse errors. There might be other fallout, though, and the behavior...
- 11:37 AM Bug #3599: mkcephfs should fail out when ceph.conf has an error
- I think the "right" fix here would be for things parsing the conf to generate something on stderr if they see the syn...
- 11:24 AM Bug #3599: mkcephfs should fail out when ceph.conf has an error
- mkcephfs is a terrible, terrible thing. You're right that it should, but there are lots and lots of things that it sh...
- 11:16 AM Bug #3599 (Resolved): mkcephfs should fail out when ceph.conf has an error
- In the /etc/ceph/ceph.conf, there was a missing bracket after [mon.b , which did not get caught during mkcephfs. It ...
- 01:14 PM CephFS Bug #3601 (Resolved): client: With multiple clients, file remove doesn't free up space
- If two or more clients have ceph mounted and one client removes a file, the space for that file doesn't get freed on ...
- 01:02 PM CephFS Bug #3572 (Resolved): High CPU after equivalent to node very busy
- commit:ed75ec2cd19b47efcd292b6e23f58e56f4c5bc34
- 12:48 PM Bug #3507: rados api system tests failure
- recent log:
ubuntu@teuthology:/a/teuthology-2012-12-10_07:00:03-regression-testing-master-basic/11115 - 12:38 PM Bug #3578 (Resolved): auth: auth_client_required has not default
- 12:35 PM devops Feature #2699 (In Progress): crowbar: change barclamp-glance to use rbd
- 12:34 PM devops Feature #2583 (Resolved): crowbar: change barclamp-nova to use rbd
- This exists and has been posted on the ceph.com site (and shared with partners) for a while now! Issues with distribu...
- 11:40 AM rbd Bug #3524 (Resolved): test_librbd_fsx: crash after flatten
- That's a different bug. Created #3600 to track it.
- 11:36 AM rbd Bug #3524 (In Progress): test_librbd_fsx: crash after flatten
- recent log :
ubuntu@teuthology:/a/teuthology-2012-12-09_19:00:03-regression-master-testing-gcov/10977 - 11:14 AM Bug #3594 (Duplicate): MDS crash in auth code?
- I believe this is a duplicate of #3593, just with a little less helpful output in the log. :)
- 09:33 AM Bug #3594: MDS crash in auth code?
- Not sure if it's in the auth code. The thread id for the previous message is different than the one that triggered th...
- 11:11 AM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- Since the size isn't an issue, it'd be great if you could:
1) generate a log of qemu-img convert with 'rbd cache ... - 11:05 AM Bug #3538 (Resolved): rbd fsx test causes osd attr value mismatch err
- 11:03 AM Bug #3538: rbd fsx test causes osd attr value mismatch err
- This may have been fixed by 58890cfad5f7bee933baa599a68e6c65993379d4. Watch operations weren't marked as writes, and...
- 11:05 AM Bug #2954 (Resolved): osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/2538528...
- 11:02 AM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- This may have been fixed by 5c8cbd28207195b094799a7bdbad0019669682a8.
- 11:04 AM CephFS Bug #3598 (Resolved): MDS should shut down cleanly on EBLACKLIST
- From #3593, suicide() apparently doesn't turn the MDS off so it asserts and core dumps.
- 09:32 AM CephFS Bug #3597: ceph-fuse: denying root access
- "denying root access"? You mean root can't read the files, but other people can? Or nobody can?
Either way this is... - 08:47 AM CephFS Bug #3597 (Resolved): ceph-fuse: denying root access
- lxo: ceph-fuse also recently started denying root access to files that shouldn't be readable except for root superpo...
- 08:46 AM CephFS Bug #3596 (Can't reproduce): ceph-fuse: crash in mds rejoin
- lxo: ceph-fuse crashes in the destructor of a non-empty xlist of a snap_realm upon mds rejoin. no quick reproducer ...
- 05:17 AM Bug #3595 (Won't Fix): ceph-osd and ceph-mds crash on Debian Squeeze
- Using the official packages for 0.48 and 0.55 on Debian Squeeze always leads to a crash of the ceph-osd and ceph-mds ...
12/09/2012
- 05:44 AM Revision 333b3f43 (ceph): mon: fix leak of pool op reply data
- We pass a pointer because it is an optional argument, but we shouldn't
put the bufferlist on the heap or else we have...
12/08/2012
- 05:32 PM Revision d9dce4e9 (ceph): filestore: simplify op quescing
- The delicate balancing with op_apply_start() and that fact that it can
block was making it very hard to determine how... - 05:32 PM Revision ad4158d1 (ceph): os/JourningObjectStore: drop now-useless max_applying_seq
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:32 PM Revision a88b5849 (ceph): os/JournalingObjectStore: remove unused ops_submitting
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:32 PM Revision f66fe778 (ceph): os/JournalingObjectStore: simplify op_submitting sanity check
- A list is overkill; just use a seq and make sure it increments to ensure
the op_submit_finish calls are in order.
Si... - 05:31 PM Revision d4c6a22d (ceph): rgw: document admin api web interface.
- Signed-off-by: caleb miles <caleb.miles@inktank.com>
- 05:24 PM Revision 25ea0696 (ceph): osd: make pool_stat_t encoding backward compatible with v0.41 and older
- In particular, this is the encoding that is used in precise.
Fixes: #3212
Signed-off-by: Sage Weil <sage@inktank.com> - 05:18 PM Revision 81e567c9 (ceph): Merge remote-tracking branch 'gh/wip-ceph-test' into next
- 05:17 PM Revision e227c709 (ceph): crush/CrushWrapper: do not crash if you move an item with no current home
- This will let us take an existing orphan and place it somewhere.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:16 PM Revision 1acb6910 (ceph): mon: Elector: init elector before each election
- Fixes: #3587
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:12 PM Revision 42d21937 (ceph): Merge branch 'testing' into next
- 05:12 PM Revision f3029833 (ceph): init-ceph: =, not ==
- Reported-by: v@alan.lt
Signed-off-by: Sage Weil <sage@inktank.com> - 11:29 AM Bug #3593: MDS crash in MDCache.cc _recovered()
- This looks like the objecter is trying to send and getting the ESHUTDOWN error code, because the mds tries to reconne...
- 10:40 AM Bug #3593 (Can't reproduce): MDS crash in MDCache.cc _recovered()
- While rsyncing to cephfs, the active mds frequently crashes. Attached is the tail of the logfile of one of them.
- 10:45 AM Bug #3594 (Duplicate): MDS crash in auth code?
- In my three-mds setup, the active MDS frequently loses its active status (and sometimes crashes in the process). Att...
- 09:20 AM Bug #3587 (Resolved): mon: election doesn't finish during heavy mon thrashing
- 09:16 AM Bug #3581: init script errors after upgrade from 0.48 to 0.55
- Fixed (in next and testing branches), thanks!
- 06:32 AM Bug #3581: init script errors after upgrade from 0.48 to 0.55
- Hi,
not all. After apply path I see error "/etc/init.d/ceph: 303: [: btrfs: unexpected operator"
root@bacula-s... - 07:11 AM Revision 8816b39a (ceph): debian: add ceph.postinst to remove /etc/init/ceph.conf on update
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 06:36 AM Revision fc58299e (ceph): PG: remove last_epoch_started asserts in proc_primary_info
- These asserts are valid for a uniform cluster, but they won't hold
for a replica running a version without the info.l... - 06:33 AM Revision 81fdea13 (ceph): auth: set default auth_client_required
- Fixes: #3578
Set auth_client_required to default to "cephx, none".
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 06:33 AM Revision a3908a68 (ceph): auth: changed order of test for legacy and new authentication
- Changed order of test for legacy and new configuration options
in several places.
Signed-off-by: Peter Reiher <reihe... - 06:32 AM Revision 907da185 (ceph): auth: improve logging
- Add some logging around failure cases.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 12:43 AM Revision f9d090ef (ceph): Merge branch 'next'
- Merge of wip-rbd-export-progress
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 12:41 AM Revision 83557330 (ceph): rbd: use ExportContext for progress, not cerr
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
12/07/2012
- 11:49 PM Revision 13e3e586 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 11:48 PM Revision e0761fbd (ceph): doc: Added sudo to the service start command.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:49 PM Revision 778bad12 (ceph): doc: Moved sudo to before ssh instead of before tee.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:34 PM Revision 413b5d0a (ceph): doc: inverted the steps per doc feedback.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:32 PM Revision f098cb91 (ceph): Merge branch 'next'
- Merge of wip-rbd-create:
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 08:51 PM Bug #3592: Assert (oinfo.last_epoch_started == info.last_epoch_started)
- This was fixed in 0756052cff542ab02d653b40c37a645b395f31b3
- 08:23 PM Bug #3592 (Resolved): Assert (oinfo.last_epoch_started == info.last_epoch_started)
- Since upgrading one of my boxes to 0.55 I have been receiving this assert:
(oinfo.last_epoch_started == info.last_... - 08:18 PM Revision 636048db (ceph): mds/locker: Add debugging for excl->mix trans
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 08:18 PM Revision 07b36992 (ceph): mds: move from EXCL to SYNC if nobody wants to write
- We were moving to the MIX even if nobody wanted to write; that is not
useful, since if we only want to read SYNC will... - 08:18 PM Revision fa5a46c7 (ceph): test/libcephfs: Add a test for validating caps
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 08:18 PM Revision 10bf1509 (ceph): client: Add routine to get caps of file/fd
- In order to properly validate the client capabilities,
we need to be able to access them from libcephfs.
Signed-off-... - 06:55 PM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- I ran ...
- 12:44 PM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- It looks like qemu-img info is also reporting the size after using integer division and multiplication by 512, so it ...
- 12:36 PM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- Just reproduced a bad size (504 bytes less) when using qemu-img 1.1.2 to convert a 1024119288 byte file. It seems to ...
- 01:18 AM rbd Bug #3585: Image import via QEMU-IMG results in a corrupt rbd
- All of the imported images are showing the exact same size. TS7 is a qemu-img import and TS6 is a rbd import. Using q...
- 01:05 AM rbd Bug #3585 (In Progress): Image import via QEMU-IMG results in a corrupt rbd
- As a workaround you can use 'rbd import file pool/image' on a raw file. Does the corrupted image show the correct siz...
- 12:21 AM rbd Bug #3585 (Closed): Image import via QEMU-IMG results in a corrupt rbd
- This is a follow on from the mailing list topic VM Corruption on "0.54 when 'client cache = false'". After upgrading ...
- 06:37 PM Revision c1bf2291 (ceph): librbd: bump version for new functions
- copy2, clone2, and create3 are new.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 06:37 PM Revision 57d5c699 (ceph): librbd: clean up after errors in create
- Split format 1 and 2 image creation into separate functions for better
readability. Format 2 requires more error hand... - 06:37 PM Revision efc66148 (ceph): librbd: change internal order parameter to pass-by-value
- It doesn't change in any of these places.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 05:25 PM rbd Bug #3589 (In Progress): rbd.py should check for method existence before calling new methods
- 04:02 PM rbd Bug #3589 (Resolved): rbd.py should check for method existence before calling new methods
- If rbd.py is upgraded past librbd, it should not fail because e.g. rbd_create3 does not exist in the old version.
- 05:24 PM Bug #3591 (Closed): auth: could not find secret_id=0
- User reported that when using kernel rbd, periodically appears in the log:...
- 05:16 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- Can you reproduce this with debug ms = 10, debug auth = 10, debug mds = 10 on?
- 05:14 PM Bug #3590: mds segfault at MonClient::wait_auth_rotating during upgrade
- I restarted the running cluster after removing the entry "auth client required=cephx,none" in ceph.conf and it is sti...
- 05:05 PM Bug #3590 (Resolved): mds segfault at MonClient::wait_auth_rotating during upgrade
- Upgrade from ceph argonaut v0.48.2 to v0.55
Test steps:
1. Running a local cluster burnupi06[mds], burnupi07[os... - 03:59 PM rbd Fix #3588: rbd.py's clone should take stripe parms, call rbd_clone2
- In danger of forgetting about this unless I write it down somewhere:...
- 03:57 PM rbd Fix #3588 (Resolved): rbd.py's clone should take stripe parms, call rbd_clone2
- 03:58 PM rbd Bug #2677 (Resolved): librbd: create does not clean up well
- 11:06 AM rbd Bug #2677 (Fix Under Review): librbd: create does not clean up well
- 12:27 PM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- I changed those calls to ceph_debug_get_* and update the wip-3559 branch.
- 12:16 PM Revision bc6f7268 (ceph): mon: PGMonitor: erase entries from 'creating_pgs_by_osd' when set is empty
- This patch avoids sending empty MOSDPGCreate's every tick.
Fixes: #3571
Signed-off-by: Joao Eduardo Luis <joao.luis... - 12:10 PM Revision f81d7207 (ceph): doc/install/os-recommendations: fix syncfs notes
- For argonaut, squeeze and wheezy lack syncfs.
For bobtail, only older kernels are problematic; we don't depend on gl... - 12:09 PM Revision 4d43c863 (ceph): doc: fix bobtail version in os-recommendations
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:04 PM Revision e1c27fe1 (ceph): mon: Monitor: rework 'paxos' to a list instead of a vector
- After adding the gv patches, during Monitor::recovered_leader() we started
waking up contexts following the order of ... - 12:00 PM Revision 58f6798f (ceph): Merge branch 'testing' into next
- 11:25 AM Revision 533f847c (ceph): Merge remote-tracking branch 'gh/wip_doc'
- 09:07 AM Bug #3569: Monitor & OSD failures when an OSD clock is wrong
- Oh... scratch that. Only after a closer look after reproducing the bug did I notice that what I saw was from VIRT; RS...
- 08:46 AM Bug #3569: Monitor & OSD failures when an OSD clock is wrong
- Might not be related, but when I triggered bug #3587 earlier today I noticed that the monitor started consuming over ...
- 08:38 AM Bug #3587 (Fix Under Review): mon: election doesn't finish during heavy mon thrashing
- Haven't been able to reproduce the bug since commit e6c15e73543593fc55ba3846197fb7f83f949bb7 from wip-3587.
- 05:18 AM Bug #3587: mon: election doesn't finish during heavy mon thrashing
- This is being caused by the fact that, from the other monitors point-of-view, mon.a never left the quorum, thus they ...
- 04:19 AM Bug #3587 (Resolved): mon: election doesn't finish during heavy mon thrashing
- While trying to trigger #3495 using...
- 08:36 AM Bug #3495 (Resolved): ceph-mon crash
- 08:36 AM Bug #3495: ceph-mon crash
- Good to know Matthew. I haven't been able to reproduce it either since using a patched version.
And the patch has ... - 07:46 AM Bug #3495: ceph-mon crash
- I was encountering this particular bug, causing all my monitors to crash shortly after start. I patched my 0.55 pack...
- 04:21 AM Bug #3495: ceph-mon crash
- Managed to trigger this bug using...
- 06:53 AM Revision 15d89937 (ceph): PG: update info.last_update_started in split_into
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:53 AM Revision 9f169ac0 (ceph): OSD: account for split in project_pg_history
- split causes a new interval.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:53 AM Revision 27071f3b (ceph): OSD: store current pg epoch in info and load at that epoch
- Prior to split, this did not matter. With split, however, it's
crucial that a pg go through advance_pg() for the map... - 06:53 AM Revision fb738506 (ceph): PG: set child up/acting in split_into
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:53 AM Revision 338f3688 (ceph): OSDMonitor: require --allow-experimental-feature to increase pg_num
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:52 AM Revision 3f412e88 (ceph): OSD: do _remove_pg in add_newly_split_pg is pool if gone
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:51 AM Revision 5f8a3634 (ceph): PG: split ops for child objects into child
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:51 AM Revision 9835e190 (ceph): osd/: mark info.stats as invalid after split, fix in scrub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:51 AM Revision 19e6861d (ceph): osd/: dirty info and log on child during split
- Otherwise, the log may not get written out.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:51 AM Revision 9981bee5 (ceph): OSD: add initial split support
- PGs are split after updating to the map on which they split.
OSD::activate_map populates the set of currently "splitt... - 04:16 AM Bug #3571 (Resolved): MOSDPGCreate is unconditionally generated at max frequency by monitors
- 04:10 AM Bug #3582 (Resolved): Some wrong info on OS recommendations
- commit:f81d7207663633d82ad591d438c5a7ddbee26ff3
- 04:01 AM RADOS Feature #3586 (Resolved): CRUSH: separate library
- 12:56 AM Revision 58890cfa (ceph): librados: watch() should set the WRITE flag on the op
- This caused a bug where the watch operation bypassed the is_degraded()
check in the write path and the repop got sent... - 12:56 AM Revision f2914af5 (ceph): HashIndex: fix list_by_hash handling of next->is_max()
- get_path_str() should not handle hobject_t::get_max(). get_path_str()
now asserts that the passed object is not max ...
12/06/2012
- 11:58 PM Revision 0c010949 (ceph): rbd: remove block-by-block messages when exporting
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:20 PM Revision ef24f531 (ceph): doc: Change per doc request.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:25 PM Revision ca1a4db4 (ceph): release: add note about 'ceph osd create' syntax
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 05:16 PM Bug #3584: Ranlib fails from 64-bit client on a file in 32-bit based Ceph cluster.
- (two 3.6.7-4.fc17.i686 and three 3.5.3-1.fc17.i686, precisely)
2. mount it from a 64-bit Linux machine (3.6.7-4.fc... - 05:05 PM Bug #3584 (Resolved): Ranlib fails from 64-bit client on a file in 32-bit based Ceph cluster.
I could setup 32-bit Ceph cluster just fine, so I tried to mount it from 64-bit machine and tried a compilation of ...- 03:34 PM Bug #3581 (Resolved): init script errors after upgrade from 0.48 to 0.55
- commit:0a137d76bd9ee924c43a42abc33f4c6c06a03d5e
- 02:23 PM Bug #3459 (In Progress): osd crash in CephXAuthorizer::verify_reply
- 02:21 PM Bug #3459: osd crash in CephXAuthorizer::verify_reply
- A user reports this same crash today in IRC with 0.55:
https://pastee.org/f4dgd - 01:30 PM Revision 214c7a17 (ceph): client: Allow cap release timeout to be configured
- The delay for releasing an inode's capability is
hardcoded to 5 seconds. This patch takes the timeout
value from a c... - 01:27 PM Revision 0a137d76 (ceph): mkcephfs: fix fs_type assignment typo
- Reported-by: Matthew Via <via@matthewvia.info>
Signed-off-by: Sage Weil <sage@inktank.com> - 01:26 PM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- Verified just means we agree it's a bug. New->Verified->In Progress->Need Review->Testing->Resolved is the simple pa...
- 10:17 AM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- How was this bug verified? Would you provide the test and its description in this bug, please.
- 01:26 PM Revision 4c31598e (ceph): upstart: fix radosgw upstart job
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:26 PM Revision 47266cda (ceph): upstart: rename ceph -> ceph-all
- This avoids a conflict with the sysvinit job.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:28 AM rbd Bug #3562 (Can't reproduce): incorrect progress shown for rbd resize image
- Neither Josh nor I have a good theory for how this even could have happened, and I can't reproduce it, so...reopen if...
- 11:12 AM Linux kernel client Cleanup #3583: Convert tabs to spaces
- I think we should avoid doing changes that make it hard to see the history. Specifically, swiping spaces to tabs conv...
- 11:08 AM Linux kernel client Cleanup #3583 (Rejected): Convert tabs to spaces
- It was recently suggested that there are places in the client where we use spaces for indentation instead of tabs as ...
- 09:35 AM Bug #3571: MOSDPGCreate is unconditionally generated at max frequency by monitors
- 09:35 AM Bug #3571: MOSDPGCreate is unconditionally generated at max frequency by monitors
- Proposed fix on wip-3571 commit 5d9decaa7118ec7a3ce152ecd29bd6120e1a9078
- 08:07 AM Bug #3582 (Resolved): Some wrong info on OS recommendations
- http://ceph.com/docs/master/install/os-recommendations/
Neither Debian Squeeze nor wheezy should be listed as havi... - 06:52 AM Bug #3495: ceph-mon crash
- Sure. I'll try to reproduce this bug again before bobtail is released. From the looks of it, messing with the MDS eno...
- 05:27 AM Bug #3495: ceph-mon crash
- > If you have the chance, could you try commit 46c55a19e72ae1f16037807fda8abe59b671f7d3 on wip-3495? It should fix th...
- 06:47 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- libcephtools is wrapping the monitor interaction stuff; i think this belongs in libcephfs, we just need to advertise ...
- 06:43 AM rgw Feature #3443: radosgw - Add Log messages to indicate restart, attempt, success and failure
- we could make the script print a warning of there are .'s in the host line? it's hard, though, because sometimes the...
- 06:41 AM CephFS Feature #3575: ceph-fuse: Add support for forget_multi
- yay! i think this is the answer to #3289.
actually, i think the normal invalidate will work too, one inode at a t... - 05:47 AM CephFS Fix #2215: ceph-fuse does not invalidate page cache
- wip-2215 looks good to me!
- 05:33 AM CephFS Bug #3572: High CPU after equivalent to node very busy
- Ah, nice catch! We just need to cycle through the list once to requeue the requests for the MDS. If Yan's patch loo...
- 03:39 AM Revision 7ab00a79 (ceph): .gitignore: Add m4 macro directories to ignore list
- 02:19 AM Revision 0d2e8858 (ceph): Merge branch 'next'
- 02:18 AM Revision 3e98d1af (ceph): Merge branch 'testing' into next
- 02:17 AM Revision b7b72429 (ceph): rbd: update manpage for import/export
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:39 AM Revision 7f906b5a (ceph): Merge branch 'next'
- Pull in fixes for 3567 and 3524
- 01:38 AM Revision 64ecc870 (ceph): Striper: use local variable inside if() that tested it
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit 917a6f296323164f9d79df94916932722e66fc0a) - 01:38 AM Revision b2ccf11d (ceph): librbd: handle parent change while async I/Os are in flight
- During a test_librbd_fsx run including flatten, ImageCtx->parent
was being dereferenced while null. Between the time... - 01:38 AM Revision e9653f27 (ceph): librbd: hold AioCompletion lock while modifying global state
- C_AioRead::finish needs to add in each chunk of a partial read
request to the 'partial' map in the AioCompletion's st... - 01:05 AM Revision 917a6f29 (ceph): Striper: use local variable inside if() that tested it
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 01:05 AM Revision 41e16a3b (ceph): librbd: handle parent change while async I/Os are in flight
- During a test_librbd_fsx run including flatten, ImageCtx->parent
was being dereferenced while null. Between the time... - 01:05 AM Revision a55700cc (ceph): librbd: hold AioCompletion lock while modifying global state
- C_AioRead::finish needs to add in each chunk of a partial read
request to the 'partial' map in the AioCompletion's st... - 12:17 AM Revision 90d81562 (ceph): qemu: set qemu cache mode based on rbd cache setting
- If we don't do this, qemu assumes no caching is used and doesn't send flushes.
Signed-off-by: Josh Durgin <josh.durg... - 12:08 AM Revision 4acc0789 (ceph): Merge branch 'next'
12/05/2012
- 11:58 PM Revision 50af4734 (ceph): Add xfstests on rbd inside qemu
- We may want to prune these later, since they take a long time.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 11:55 PM Revision 930bb550 (ceph): Merge branch 'next'
- 11:54 PM Revision 2a5549cc (ceph): qa: add script for running xfstests in a vm
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 11:46 PM Bug #3513: rgw log show error
- hi Yehuda,
i hve given the space in relevant place and tried with as u r example . its not working ..
Yehuda Sad... - 10:33 PM Revision 27793255 (ceph): rgw: fix rgw_tools get_obj()
- The original implementation broke whenever data exceeded
the chunk size. Also don't keep cache for objects that
excee... - 10:11 PM Bug #3581 (Resolved): init script errors after upgrade from 0.48 to 0.55
- I upgraded from o.48 (latest stable) to 0.55. Ceph seems to start fine using:...
- 09:23 PM CephFS Fix #2215: ceph-fuse does not invalidate page cache
- Running in teuthology with the multiclient test, I see a segfault in one of the fuse clients on the plana nodes. Wit...
- 08:50 PM Revision cb19e994 (ceph): doc: ceph osd create takes a uuid, not an osd id
- This was updated by 36e7b077a77fa0a6c87289f400391c85dcdb1d42, but
accidentally reverted in later changes.
Signed-off... - 07:34 PM Revision 993ff143 (ceph): PG: add split_into to populate child members
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision f2a23916 (ceph): os/: add filestore collection_split
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision bd463863 (ceph): test/store_test: add simple tests for collection_split
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision a48dee54 (ceph): os/: Add failure CollectionIndex failure injection
- Several pieces of HashIndex involve multi-step operations
which are sensitive to OSD crashes. This patch introduces
... - 07:34 PM Revision fdc5e5d1 (ceph): os/: Add CollectionIndex::prep_delete
- If an unlink is interupted between removing the file
and updating the subdir attribute, the attribute will
overestima... - 07:34 PM Revision fec47cad (ceph): OSD: don't wait for superblock writes in handle_osd_map
- Instead, pass the pinned maps into a Context and clear the
cache after the transaction is applied.
Signed-off-by: Sa... - 07:34 PM Revision f4f6bd7f (ceph): OSD: dispatch_context only discard transaction if contexts empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision b8a37fdf (ceph): PGMonitor,OSD: don't send creates on split
- Splits will be handled when the map update effecting the split is
processed for the splitting pg on each OSD. This w... - 07:34 PM Revision b6c49b48 (ceph): mon/OSDMonitor: enable split in Monitor
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision 36c0fd22 (ceph): PrioritizedQueue: allow caller to get items removed by removed_by_filter
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:34 PM Revision 6e67a27f (ceph): osd/: splitting a pg now triggers a new interval
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:33 PM Revision a83d13a3 (ceph): OSD: ignore queries on now deleted pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:10 PM rbd Feature #3580 (Resolved): rbd import from stdin could try harder to sparsify images
- rbd import from stdin currently seeks over full blocks of zeros that it gets from
stdin; it could try harder to accu... - 05:56 PM rbd Bug #3556 (Resolved): rbd rm command fails to remove the new format rbd image completely
- This was fixed by reverting the tmap_rm-of-a-nonexistent-key behavior (the reverting commit is 5aecf2c092edcabc3b757a...
- 05:52 PM rbd Bug #3133 (Duplicate): perfcounters: sigfpe when rbd caching is enabled
- #3521 is the same problem
- 05:50 PM Bug #3536 (Resolved): librados: client.glance authentication error (1) Operation not permitted
- 05:47 PM Bug #3567 (Resolved): librbd: striping completions modifying global state outside lock
- commit:a55700cc0aea0ff79e55c6bf78e9757b81fe9425
- 05:47 PM Bug #3428 (Resolved): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- 11:34 AM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- Recent logs: ubuntu@teuthology:/a/teuthology-2012-12-04_19:00:05-regression-next-testing-basic/8664...
- 11:30 AM Bug #3428 (In Progress): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- ubuntu@teuthology:/a/teuthology-2012-12-04_19:00:05-regression-next-testing-basic/8665
- 05:47 PM rbd Bug #3524 (Resolved): test_librbd_fsx: crash after flatten
- commit:41e16a3b40efb80a5ed7a5587438569ca86c85a3
- 05:17 PM CephFS Bug #3579 (Resolved): kclient: Use less secure random number generator so we don't consume entropy
The routines __choose_mds() and ceph_mdsmap_get_random_mds() call the kernel get_random_bytes() which gets random n...- 05:05 PM CephFS Bug #3572: High CPU after equivalent to node very busy
- There is already a fix for this in wip-fs branch. I'm not clear if we need to be processing through the list once or...
- 04:42 PM CephFS Bug #3572: High CPU after equivalent to node very busy
- There is a bug in this routine:...
- 06:14 AM CephFS Bug #3572: High CPU after equivalent to node very busy
- The good news is that we don't need high quality entropy here; the crappy stuff will do...
- 04:24 PM CephFS Bug #3554 (Resolved): Logs broken after a rotation
- commit:dc93132d8cc1edf83b7e0a603b366cde6750f4d6
- 12:36 PM CephFS Bug #3554 (Fix Under Review): Logs broken after a rotation
- 02:10 PM Bug #3578 (Resolved): auth: auth_client_required has not default
- Looking at the code following a complaint on irc, auth_client_required has no default, so any client not specifying e...
- 01:24 PM CephFS Bug #3404 (Resolved): oops in strlen() from set_request_path_attr()
- Commit: f18b417f1e80f3d9053ea07958d87f87bd20c138
https://github.com/ceph/ceph-client/commit/f18b417f1e80f3d905... - 12:48 PM Bug #3576: scripe scripts broken after upgrade to 0.55
- Yes, after removing /etc/init/ceph.conf it works as expected. Thanks! :)
- 12:43 PM Bug #3576: scripe scripts broken after upgrade to 0.55
- The problem here is that a new upstart script (/etc/init/ceph.conf) is aliasing the init.d-style scripts. We're proba...
- 11:35 AM Bug #3576 (Resolved): scripe scripts broken after upgrade to 0.55
- I just installed ceph 0.55 on a quantal system and now the service scripts seem to be broken:
~# service ceph rest... - 12:35 PM CephFS Bug #3370 (Fix Under Review): All nfsd hung trying to lock page(s) on export of kclient ceph
- 12:04 PM Bug #3495: ceph-mon crash
- Thanks Artem. Your log confirmed my suspicions regarding to what the bug was.
If you have the chance, could you tr... - 11:07 AM Bug #3495: ceph-mon crash
- Attached is the file with a paxos=10 log.
- 09:45 AM Bug #3495: ceph-mon crash
- ...
- 09:36 AM Bug #3495: ceph-mon crash
- > Could you open a separate bug with the crash you see with the multithreaded object listing?
I might be able late... - 08:39 AM Bug #3495: ceph-mon crash
- Could you open a separate bug with the crash you see with the multithreaded object listing? There is some shared stat...
- 06:33 AM Bug #3495: ceph-mon crash
- (As a workaround I'm now doing "nice rados -p {pool} ls > {pool}.ids" and reading ids from the file).
- 06:32 AM Bug #3495: ceph-mon crash
- > Are you doing anything in particular to trigger this bug?
With Ceph 0.54 I've noticed that... - 06:21 AM Bug #3495: ceph-mon crash
- I'm not doing anything special, the usual librados uploads and removes. There is also a recovery in background: "reco...
- 05:45 AM Bug #3495: ceph-mon crash
- Artem,
The good news is that, given the bug being triggered yet again on the same spot, it would appear to be loca... - 02:59 AM Bug #3495 (In Progress): ceph-mon crash
- Thanks for following up on this. And thanks for cranking up the debug levels! :-)
- 12:56 AM Bug #3495: ceph-mon crash
- "FAILED assert(have_pending)" still happens with Ceph 0.55.
I have attached the logs. - 11:39 AM Bug #3577 (Can't reproduce): osd missing reported by osd_recovery.test_incomplete_pgs workload
- Logs: ubuntu@teuthology:/a/teuthology-2012-12-04_19:00:05-regression-next-testing-basic/8592...
- 11:14 AM CephFS Feature #3575 (New): ceph-fuse: Add support for forget_multi
- A new function in fuse (as of 2.9) supports dropping multiple inodes from the cache in one upcall.
- 11:12 AM CephFS Feature #3574 (New): ceph-fuse: Add support for write_buf
A new function (as of fuse 2.9) 'write_buf' in the fuse lowlevel interface supports doing I/O through a pipe allowi...- 11:10 AM CephFS Feature #3573 (Rejected): ceph-fuse: Add ioctl support
- 11:08 AM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- Sorry for the delay. I just installed 0.55 and it doesn't crash anymore (I didn't change the ceph.conf at all). Thank...
- 11:01 AM rgw Feature #3443: radosgw - Add Log messages to indicate restart, attempt, success and failure
- To clairify, forget the possible issue with syntax checking in mkcephfs or starting and stopping ceph. That's a tota...
- 08:45 AM rgw Feature #3443: radosgw - Add Log messages to indicate restart, attempt, success and failure
- here's a specific example from bobtail tesing:
ceph.conf contained:
[client.radosgw.gateway]
... - 07:47 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- Noah has created a libcephtools library for the admin socket stuff. Should we add it there, or a separate libcephadm...
- 06:46 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- Sweet.
I'm a bit leary about exposing the caps via libcephfs.. that's an implementation detail that users shouldn'... - 06:30 AM CephFS Bug #3559 (Fix Under Review): mds: not issuing RDCACHE to exclusive client for some files
- That fixed it. With your fix it now passes my test. I cherry-picked your fix into wip-3559.
- 06:12 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- Yeah your right - the fix I proposed doesn't work because it ends up in mix state eventually. Testing your patch.
- 05:58 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- I don't think we can alloc CACHE caps in the excl->mix state because caching isn't allowed in mix. Generally speakin...
- 12:48 AM Revision 4cdc30b9 (ceph): Merge remote-tracking branch 'origin/wip-mds' into next
- Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:26 AM Revision 8e78cd82 (ceph): dropping xfs test 183 for now as it causes nightly failure
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:20 AM Revision cea082c6 (ceph): dropping test 183 as it is causing nightly failures
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:08 AM Revision 307d291a (ceph): kernel: add kclient ffsb back in
12/04/2012
- 11:42 PM Revision 3986564b (ceph): Dropping xfs tests 179 and 183 as they are causing nightly failures
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:05 PM Revision 3ef741ac (ceph): Merge branch 'wip-filestore' into next
- Reviewed-by: Sam Just <sam.just@inktank.com>
- 10:52 PM Revision f3bd3564 (ceph): Merge branch 'wip-msgr-delay-queue' into next
- 10:50 PM Revision 727c37a7 (ceph): mds: journal remote inode's projected parent
- Server::_rename_prepare() adds remote inode's parent instead of
projected parent to the journal. So during journal re... - 10:50 PM Revision 3f69f729 (ceph): mds: don't create bloom filter for incomplete dir
- Creating bloom filter for incomplete dir that was added by log
replay will confuse subsequent dir lookup and can crea... - 10:48 PM Revision 724d5aaa (ceph): doc: added some descriptions in ms-ref and filestore-config-ref
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:43 PM Revision 3cf2197c (ceph): doc: write descriptions for the remaining msgr options
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 07:41 PM Revision 0756052c (ceph): PG: remove last_epoch_started asserts in proc_primary_info
- These asserts are valid for a uniform cluster, but they won't hold
for a replica running a version without the info.l... - 06:58 PM Revision b76f12d4 (ceph): doc: Edited striping section. Modified stripe graphic to pretty print. ...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:59 PM CephFS Bug #3572 (Resolved): High CPU after equivalent to node very busy
- I dropped a ceph kernel client node into the debugger and left it there a while. After resuming execution the machin...
- 04:59 PM Bug #3571 (Resolved): MOSDPGCreate is unconditionally generated at max frequency by monitors
- Sam noticed today that his OSDs were getting an empty MOSDPGCreate message every 30 or 60 seconds. I looked briefly t...
- 03:51 PM Linux kernel client Bug #2506: ceph: ceph_add_cap: couldn't find snap realm NNN
- commit:3384431b6d889486d19d1a1543626fb1a2cff178, which appears in v0.55, should fix the 'snap realm 100' problem. Th...
- 03:31 PM CephFS Feature #3570 (Resolved): teuthology: mds thrasher
- 02:08 PM CephFS Feature #3568 (Fix Under Review): client: Allow hold_caps_until to be configured
- Made this change to the wip-3568 branch. Needs review.
- 11:26 AM CephFS Feature #3568 (Resolved): client: Allow hold_caps_until to be configured
- Client::cap_delay_requeue has a hardcoded timeout of 5 secs. Make this configurable.
- 01:35 PM Revision 2ba9c870 (ceph): mds: journal remote inode's projected parent
- Server::_rename_prepare() adds remote inode's parent instead of
projected parent to the journal. So during journal re... - 01:29 PM Revision 8cd8f250 (ceph): mds: don't create bloom filter for incomplete dir
- Creating bloom filter for incomplete dir that was added by log
replay will confuse subsequent dir lookup and can crea... - 01:27 PM Revision 8c2526a7 (ceph): Merge remote-tracking branch 'gh/wip-mds' into next
- 01:25 PM Revision 3ace9a7c (ceph): logrotate: do not spam stdout
- Avoid anything on stdout that will generate cron emails for people.
Reported-by: Stefan Priebe <s.priebe@profihost.a... - 01:24 PM CephFS Bug #1047: mds: crash on anchor table query
- commit:a3aad3c3c58ffd7cd556275cd1c7dbc69b3eb4dd, which is in v0.55.
- 12:53 PM Bug #3569 (Can't reproduce): Monitor & OSD failures when an OSD clock is wrong
- ...
- 11:36 AM Bug #3526: Commands mentioned in documentation are incomplete ?
- Can you check these commands, John? I don't remember all the syntax, but I'm pretty sure for instance that "pool=cust...
- 11:32 AM Bug #2536: librados crashed while getting stat of an object
- Hey Benjamin, this is the same assert but quite a different call chain — can you create a new bug? Preferably with so...
- 11:24 AM CephFS Bug #3559: mds: not issuing RDCACHE to exclusive client for some files
- I was able to reproduce this with a libcephfs test that creates, opens and closes files, suspends the client for 20 s...
- 05:47 AM Revision b781ac00 (ceph): build: Add RPM release string generated from git describe.
- Fix for bug 3451. Use the commit count and sha1 from git describe to
construct a release string for rpm packages.
C... - 05:42 AM Revision f60c9b66 (ceph): ceph.spec.in: Build debuginfo subpackage.
- This is a partial fix for bug 3471. Enable building of debuginfo package.
Some distributions enable this automatical... - 05:31 AM Revision 2eee9e17 (ceph): Merge branch 'master' of http://github.com/ceph/ceph
- 05:29 AM Revision b5ec1c67 (ceph): Merge branch 'next'
- 04:48 AM Revision a74a4acf (ceph): doc: Added a striping section for Architecture.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:08 AM Revision 690f8175 (ceph): v0.55
- 03:06 AM Revision 234cc081 (ceph): ceph.spec.in: Add SLES and remove Fedora from debug package list.
- 12:02 AM Revision 7fbf9476 (ceph): rgw: fix swift auth concurrency issue
- Fixes: #3565
Originally ops were using static structures, but that
has since changed. Switching swift auth handler to... - 12:02 AM Revision 0639cd9c (ceph): rgw: fix rgw_tools get_obj()
- The original implementation broke whenever data exceeded
the chunk size. Also don't keep cache for objects that
excee...
12/03/2012
- 11:33 PM Revision 595dd0ec (ceph): Merge branch 'next'
- 11:33 PM Revision 26045573 (ceph): test_rados_api_misc: fix dup rmmkey test
- We now expect ENONET as of 9961640f76a950c674c0e7cc2453931088c63fd7
again.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:22 PM rbd Bug #3524 (In Progress): test_librbd_fsx: crash after flatten
- 06:33 PM rbd Bug #3524: test_librbd_fsx: crash after flatten
- I think I found the smoking gun. Two completions are racing to update partial
in add_partial_sparse_result(); there... - 08:57 PM Bug #3567 (In Progress): librbd: striping completions modifying global state outside lock
- 08:57 PM Bug #3567 (Resolved): librbd: striping completions modifying global state outside lock
- C_AioRead::finish places bits of a striped AioRead into the StripedReadResult
object's partial field for later assem... - 08:22 PM Revision f2c7a60c (ceph): doc: Fixed many hyperlinks, a few typos, and some minor clarifications.
- fixes: #3564
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 08:11 PM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- update/status
- 05:02 PM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- I added requested info last week on 11/29. How do I change Status?
- 06:48 PM Revision a7a3cbf8 (ceph): doc: Clarified example for root user.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 03:58 PM rgw Bug #3565 (Resolved): rgw:crash with concurrent requests to swift auth
- Fixed, commit:7fbf9476cb44ce256f4bb2366f46fa20cb570eda.
- 02:26 PM rgw Bug #3565 (Resolved): rgw:crash with concurrent requests to swift auth
- 03:54 PM rbd Bug #3566 (Resolved): log max new = 1 can cause hang on process exit
- Investigating other things entirely, I had set log max err = 1 in [global]; I started
observing occasional hangs, an... - 03:00 PM Documentation #3564 (In Progress): doc: many broken links since rearrangement
- Good idea Sam, it'd be great to have something like that run automatically. Running linkchecker against ceph.com/docs...
- 01:50 PM Documentation #3564: doc: many broken links since rearrangement
- Is there a link checker already running for ceph.com? Something like linkchecker.sourceforge.net?
- 12:25 PM Documentation #3564: doc: many broken links since rearrangement
- Most of the links from the previous structure worked fine. Where the subtree changed, there were some links that brok...
- 11:32 AM Documentation #3564 (In Progress): doc: many broken links since rearrangement
- 11:00 AM Documentation #3564 (Resolved): doc: many broken links since rearrangement
- All the chef links on this page:
http://ceph.com/docs/master/rados/operations/add-or-rm-osds/
Everything referenc... - 11:56 AM Revision 5bea57bf (ceph): config: we still want osd_thread_recovery_timeout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:44 AM Revision e686cb14 (ceph): config: Remove unused options
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 11:44 AM Revision 6b105ae0 (ceph): client: Fix ceph_mount() when subdir is specified
- If a subdirectory is specified to ceph_mount, the
root inode does not have an ino of CEPH_INO_ROOT, so
cwd will fail ... - 11:42 AM Revision 9961640f (ceph): osd: ENOENT on TMAP_RM on non-existent key
- This reverts 29fae494d0b1459c8bb934d42446e0ada7355402 and fixes the
alternate implmentation added by 8e91d00b52808aa1... - 11:42 AM Revision 272e89d9 (ceph): osd: add TMAP_RMSLOPPY op
- Remove a key, but succeed if key already does not exist.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:42 AM Revision 4870b43c (ceph): mds: use TMAP_RMSLOPPY op when removing dentries
- After replay, we don't know if the dentry removal has already been
committed. Use a sloppy removal so that we succee... - 11:42 AM Revision f57a7980 (ceph): osd: EINVAL on unknown TMAP op code
- The old/slow implementation did this, but the optimized version did
not.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:17 AM Bug #2683: ceph-fuse: crash during fsstress
- The hard link bug was only expressed through the libcephfs API, not ceph-fuse.
- 03:44 AM Cleanup #3561 (Resolved): unused config options
12/02/2012
- 10:30 PM Revision 85574a36 (ceph): os/JournalingObjectStore: applied_seq -> max_applied_seq
- Rename applied_seq to max_applied_seq, since it is a bound; there may be
seq's < max_applied_seq that are not applied... - 10:30 PM Revision 52810848 (ceph): os/FileStore: only wait for applying ops to complete before commit
- We can have a large number of operations in the op_wq waiting to be applied
to the fs. Currently, when we want to co... - 06:41 AM Revision c10958e4 (ceph): osd: fix RepModify when past last_peering_reset
- If we apply or commit a RepModify from a prevous perring interval, we need
to free it.
This fixes 'slow request' mes... - 03:32 AM Revision 2d0cfce8 (ceph): Merge remote-tracking branch 'origin/wip-coverity'
- 02:23 AM Revision fab0976d (ceph): Merge remote-tracking branch 'gh/next'
- 12:57 AM Revision 3a064dcf (ceph): rgw: fix uninit var
- CID 745935 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (2): Non-static class member "expiration" is not in... - 12:57 AM Revision 880a1856 (ceph): OutputDataSocket: fix uninit var
- CID 745933 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (2): Non-static class member "data_size" is not ini... - 12:56 AM Revision 648c7f0c (ceph): test/osdc/FakeWriteback: fix uninit var
- CID 745936 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
At (2): Non-static class member "m_off" is not initial... - 12:56 AM Revision 0dac9e69 (ceph): osd: fix missing unlock; simplify
- Instead of a special-case exit, just skip the con replacement. Continue
on to mark the old con down.
CID 745920 (#1...
12/01/2012
- 08:52 PM Revision 3fa2582b (ceph): mds: consider revoking caps in imported caps as issued
- The clients may already send caps release message to the exporting
MDS, so the importing MDS waits for the release me... - 08:52 PM Revision 961bc0c9 (ceph): mds: fix open_remote_inode race
- discover_ino() may return -ENOENT if it races with other FS activities.
so use C_MDC_RetryOpenRemoteIno instead of C_... - 08:52 PM Revision 587aec17 (ceph): mds: fix assertion in handle_cache_expire
- During export, it's possible to get cache expire messages in
DISCOVERING, FREEZING and PREPPING state.
Signed-off-by... - 08:52 PM Revision 1203cd21 (ceph): mds: allow open_remote_ino() to open xlocked dentry
- discover_ino() has a parameter want_xlocked. The parameter indicates
if remote discover handler can proceed when xloc... - 08:52 PM Revision 2a506894 (ceph): mds: use rdlock_try() when checking NULL dentry
- Use rdlock_try() instead can_read() when path_traverse encounters
a NULL dentry. This can partly avoid infinitely wai... - 08:52 PM Revision 0fa48758 (ceph): mds: fix freeze inode deadlock
- CInode::freeze_inode() is used in the case of cross authority rename.
Server::handle_slave_rename_prep() calls it to ... - 08:52 PM Revision 946b263c (ceph): mds: Don't acquire replica object's versionlock
- Both CInode and CDentry's versionlocks are of type LocalLock.
Acquiring LocalLock in replica object is useless and pr... - 08:52 PM Revision ff170ecf (ceph): mds: clear lock flushed if replica is waiting for AC_LOCKFLUSHED
- So eval_gather() will not skip calling scatter_writebehind(),
otherwise the replica lock may be in flushing state for... - 08:52 PM Revision 8f674899 (ceph): mds: call eval() after caps are exported
- For an inode just changed authority, if the new auth MDS want to
change a lock in the inode from 'sync' to 'lock' sta... - 08:52 PM Revision 9bfe540c (ceph): mds: don't forward client request from MDS
- Forwarding client request that was from MDS will trigger assertion
in MDS::forward_message_mds(). MDS only send clien... - 08:52 PM Revision 4cd8ea92 (ceph): mds: drop locks if requiring auth pinning new objects.
- Locker::acquire_locks() skip auth pinning replica object if we only
request a rdlock and the lock is read-lockable. T... - 08:52 PM Revision 5620f3d0 (ceph): mds: allow try_eval to eval unstable locks in freezing object
- Unstable locks hold auth_pins on the object, it prevents the freezing
object become frozen and then unfreeze. So try_... - 08:45 PM Revision 8dcc6c39 (ceph): msg/Pipe: flush delayed messages when stealing/failing pipes
- If we are failing a pipe, flush the incoming messages before we try to
reconnect. Similarly, flush queued messages o... - 07:21 PM Bug #2683: ceph-fuse: crash during fsstress
- Do we think this bug is still there? Haven't seen it in quite a while. Could it have been related to commit:1638f62...
- 03:01 PM Cleanup #3561 (In Progress): unused config options
- Branch wip-3561 has the following options removed:
client_cache_stat_ttl
client_cache_readdir_ttl
client_unmount... - 12:59 PM Feature #3482 (Resolved): sles gitbuilder; release rpms
- 12:41 PM CephFS Bug #3370: All nfsd hung trying to lock page(s) on export of kclient ceph
- It might be that leaving the pages locked for the duration of the read is the wrong thing. My recollection is vague,...
- 11:31 AM CephFS Bug #3370: All nfsd hung trying to lock page(s) on export of kclient ceph
I verified that PG_locked was set in struct page flags field. I suspected that ceph_readpages() was leaving pages ...- 07:14 AM Revision 7794de61 (ceph): rbd: report striping as a feature in rbd info
- Fixes: #3549
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 04:57 AM Revision dccf6ee4 (ceph): ceph-osd: put g_ceph_context before exit
- Signed-off-by: Samuel Just <sam.just@inktank.com>
11/30/2012
- 11:21 PM rbd Bug #3549: rbd: info should report striping
- commit:7794de61b5f4b5c2e20c99e26c8578361d9b0247
- 11:21 PM rbd Bug #3549 (Resolved): rbd: info should report striping
- 10:30 PM rbd Bug #3549: rbd: info should report striping
- Not yet resolved; feature_str() should return striping when enabled.
- 09:08 PM rbd Bug #3549 (Resolved): rbd: info should report striping
- 10:26 PM Bug #3468 (Resolved): rbd snap unprotect succeeds with children
- commit:faf23caa6ad4da81de6f5c5c52151aff49758c04 in master
- 10:04 PM Revision 49f32cee (ceph): ReplicatedPG: only increment active_scrub on primary for final push
- We only queue the _applied_recovered_object callback on the primary for the
final push. It is this callback which de... - 09:45 PM Bug #3489 (Resolved): osd: slow request warnings
- 09:08 PM rbd Bug #3503 (Resolved): rbd: import "-" no longer works
- 09:08 PM Feature #3502 (Resolved): rbd export should support stdout
- 09:08 PM rbd Bug #3547 (Resolved): rbd: suites/iozone.sh failure
- 09:06 PM Bug #3460 (Resolved): ceph monitor crashed in the nightlies
- 09:05 PM rbd Feature #3380 (Resolved): rbd: export and import functions should support stdout
- 09:05 PM CephFS Bug #3367 (Resolved): client: hardlink without original file breaks on unmount
- 09:04 PM Feature #3358 (Resolved): Add pool option for min size to prevent a pg from going active with exc...
- 09:00 PM Bug #3250 (Resolved): debs don't include Contents-<arch>.gz
- 08:59 PM Bug #3209 (Resolved): rbd_fsx_cache_writethrough test failure in the nightlies
- 08:59 PM Bug #3232 (Resolved): osd: 0.15 scrub stat mismatch, got 25/25 objects, 15/15 clones, 50453469/49...
- 08:59 PM Bug #3221 (Resolved): disconnect_session_watchers missing pg
- 08:58 PM CephFS Bug #3111 (Can't reproduce): Multiple MDS inevitable appear assert
- 08:52 PM Bug #3115 (Won't Fix): Cannot compile ceph 0.48.1
- 08:51 PM Bug #3130 (Resolved): osd: crash in SimpleMessenger::reaper
- 08:51 PM Feature #3138 (Rejected): osd: Make filestore_xattr_use_omap=true the default? Or something?
- 08:51 PM Feature #3137 (Resolved): osd: make default osd_journal_size 1GB, if existing (block or file) use...
- 08:49 PM Bug #2897 (Resolved): ceph fuse error segfault
- 08:49 PM Bug #2900 (Resolved): ceph fuse crashed
- 08:48 PM Bug #3067 (Resolved): mon: runaway memory
- 08:47 PM Bug #3061 (Resolved): osd crash during shutdown
- 08:47 PM Bug #3026 (Resolved): ref counting error argonaut
- 08:46 PM Bug #2945 (Won't Fix): package upgrade from v0.46 to v0.48argonaut fails
- 08:46 PM Bug #2908 (Resolved): ceph osd crush remove <name>
- 08:46 PM Bug #2892 (Resolved): ceph health detail kills monitor
- 08:45 PM Bug #2833 (Resolved): LibRBD.TestClone failure with ms fialure injection
- 08:45 PM Bug #2800 (Resolved): osd/ReplicatedPG.cc: 3537: FAILED assert(waiting_for_ondisk.begin()->first ...
- 08:45 PM devops Bug #2783 (Won't Fix): Chef-client fails on oneiric cluster
- 08:44 PM Bug #2765 (Closed): Extremely Long Object Latencies
- 08:44 PM Bug #2766 (Resolved): cephcontext: needs refcount
- 08:42 PM Bug #2762 (Resolved): mon crash ceph::__ceph_assert_fail (assertion=0x63d150 "begin->last_committ...
- 08:41 PM Bug #2610 (Resolved): osd: pg stuck at scrubbing
- 08:40 PM Bug #2233 (Won't Fix): Throttle when there are lots of large conccurent IOs
- 08:40 PM Feature #2227 (Closed): QA: create a test to verify operation with non-default layouts
- 08:38 PM CephFS Bug #3531 (Resolved): mds segfault at _unlink_local_finsh
- commit:44bc687d98f931b15538805d3923492d62dca779
- 08:37 PM CephFS Bug #3210 (Resolved): mds crashed and segfault at unlink_local_finish
- commit:44bc687d98f931b15538805d3923492d62dca779
- 08:37 PM CephFS Bug #1548 (Resolved): metadata inconsistencies and mds crashes
- commit:44bc687d98f931b15538805d3923492d62dca779
- 08:37 PM CephFS Bug #1947 (Resolved): mds: SIGBUS during _mark_dirty
- 08:36 PM rbd Feature #1908 (Resolved): rbd: test map/unmap more extensively
- 08:36 PM rbd Feature #1908: rbd: test map/unmap more extensively
- 08:33 PM RADOS Feature #228 (Resolved): crush unit tests
- 08:32 PM Feature #1299 (Resolved): osd: interface to query/manage missing, unfound, lost objects
- 08:32 PM Messengers Bug #1378 (Resolved): connection race - existing connection not open or connecting
- 08:31 PM Feature #2678 (Rejected): osd, objecter: redirect misdirected requests
- 08:31 PM Cleanup #2230 (Resolved): deprecate 'btrfs devs'
- 08:12 PM Revision 246eb7b2 (ceph): Merge remote-tracking branch 'gh/wip-osd-msgr'
- 08:02 PM Documentation #3382 (Resolved): doc: create page for OS requirements, detailing compatibility for...
- 08:01 PM Documentation #3084 (Resolved): doc: Why and when should I use latest stable kernel and not the 3...
- 08:01 PM Feature #2142 (Resolved): Add support for Ubuntu 12.04 (precise pangolin) in deb repository
- 08:01 PM Subtask #2515 (Resolved): allow collection upgrade to use more than one transaction
- 08:01 PM Subtask #2514 (Resolved): Implement DBObjectMap upgrade from old version
- 08:01 PM Subtask #2513 (Resolved): Update DBObjectMap implementation to ignore collection
- 08:01 PM Subtask #2512 (Resolved): implement upgrade process for collections
- 08:01 PM Subtask #2509 (Resolved): create OSDService to limit pg/osd interface
- 08:01 PM Subtask #2511 (Resolved): Change hobject_t encoding
- 08:01 PM Subtask #2430 (Resolved): simplify pg removal
- 08:01 PM Subtask #2403 (Resolved): remove osd pointer from PG
- 08:01 PM Subtask #2402 (Resolved): audit calls into osd from pg for locking correctness
- 08:01 PM Subtask #2333 (Resolved): create queueing for peering messages
- 08:01 PM Subtask #2282 (Resolved): Handle map updates on a per-pg basis
- 08:01 PM Subtask #2332 (Resolved): move pg queueing into pgs
- 08:00 PM Cleanup #3016 (Resolved): make ceph osd crush set ${id} osd.${id} not require the ID twice
- 07:59 PM Bug #2838 (Resolved): mon: json version of 'osd tree'
- 07:58 PM Feature #3189 (Resolved): osd: use reservations for non-backfill recovery too
- 07:55 PM Feature #3506 (Resolved): mkcephfs: multiple fs optiopns
- 07:20 PM Revision a928b6db (ceph): OSDService: make messengers private
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 07:08 PM Revision 47699f39 (ceph): osd/: make OSDService messenger helpers return ConnectionRef
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:37 PM Revision 494711e6 (ceph): mon: PaxosService: cancel proposal timer after election
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 05:07 PM Bug #3563 (Closed): osd crashed with error "auth: could not find secret_id=2"
- Test : collection:rbd-basic clusters:fixed-3.yaml fs:btrfs.yaml msgr-failures:many.yaml tasks:rbd_cli_copy_old_format...
- 04:46 PM CephFS Bug #1047: mds: crash on anchor table query
- Sage Weil wrote:
> most likely fixed by yan's patch
commit id? - 12:19 PM CephFS Bug #1047 (Resolved): mds: crash on anchor table query
- most likely fixed by yan's patch
- 04:26 PM Revision 7412bd36 (ceph): Merge remote-tracking branch 'gh/wip-mds-ls2'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 04:22 PM Revision 9cd730bd (ceph): doc: update kernel recs
- Mention which stable kernels we recommend.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:03 PM rbd Bug #3562 (Can't reproduce): incorrect progress shown for rbd resize image
- Logs:ubuntu@teuthology:/a/teuthology-2012-11-30_07:00:03-regression-testing-master-basic/6540...
- 12:18 PM Bug #3406 (Resolved): ceph fuse crashed during blogbench test
- 12:16 PM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- 12:12 PM Bug #3548 (Resolved): osd: sends messages to marked-down peers
- 12:02 PM Cleanup #3561: unused config options
- lets keep
mds_bal_merge_rd
mds_bal_merge_wr
the merge ones will be used later. - 11:17 AM Cleanup #3561 (Resolved): unused config options
- These config options are no longer used or referenced anywhere in the source. Should we remove them?
client_cache... - 11:50 AM Bug #3292 (Resolved): osd crash in handle_osd_ping
- 11:49 AM Bug #3290 (Resolved): libceph: unable to handle osdmap
- 11:48 AM Bug #3212 (Resolved): librados: failed to decode message of type 59 v1: buffer::end_of_buffer
- 11:47 AM Bug #2947 (Can't reproduce): osd: out of order reply
- 11:47 AM Bug #3038 (Resolved): objectcacher: segv in bh_write_commit -> close_object
- 10:52 AM Feature #3219 (Resolved): Run tests in valgrind on gitbuilder
- 08:54 AM rgw Bug #3532 (Resolved): rgw: wrong bucket stats after multipart upload
- 08:54 AM Messengers Bug #3510 (Resolved): messenger doesn't fill in nonce if port is specified
- 02:18 AM Revision dc93132d (ceph): logrotate: fix rotation
- Fixes: #3554
Always reload with Upstart because in some configs the init.d script doesn't work
Signed-off-by: David ... - 01:21 AM Revision 909b92e8 (ceph): mds: assert segements not emtpy in get_current_segment()
- Only one caller can tolerate no segments; make a new
peek_current_segment() for them.
Motivated by paranoia tracking... - 01:21 AM Revision f0c2920e (ceph): mds: be explicit about MDRequest killed state
- Set the killed flag and use that instead of inferring things from
the session xlist.
Signed-off-by: Sage Weil <sage@... - 01:20 AM Revision 41ef9bbb (ceph): mds: drop redundant mdr->committing = true
- journal_and_reply() does this.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:20 AM Revision 44bc687d (ceph): mds: fix request_kill()
- Only request_cleanup() if the request isn't already committing. If it
is, wait for it to commit before we clean up.
... - 01:03 AM Revision 0ffafb31 (ceph): Revert "osd: fix leak of heartbeat con on reset"
- This reverts commit b31a99abda75b9170a5805b02944a0c0c78245b7.
- 12:47 AM Revision abd9e36c (ceph): client: only dump cache on umount if we time out
- We don't want to dump the cache every time an item is trimmed and the
mount_cond gets signaled; this can make umount ... - 12:09 AM Revision b97aaca3 (ceph): msgr: add a delay_until queue that is used to delay deliveries.
- Its life-cycle matches that of delay_queue, and the delayed_delivery
function respects it. For now queue_received is ... - 12:09 AM Revision f454bb59 (ceph): msg/Pipe: refactor msgr delays
- - move all delay state into a single class
- create thread once and only once per Pipe
- adjust debug levels
- discar... - 12:09 AM Revision f0bf6168 (ceph): msg/Pipe: drop queue helpers
- There is a single caller; these only obfuscate.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision 158260b6 (ceph): msg/Pipe: start delay thread *after* we know peer type
- At end of connect(), or end of accept().
Signed-off-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision 6d65fa4e (ceph): msg/Pipe: release dispatch throttle on delayed queue discard
- This avoids leaking into the throttle and deadlocking.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision 90f66980 (ceph): messenger: add the shell of a system to delay incoming Message delivery
- When ms_inject_delay_type matches that of the incoming Connection,
the Pipe sets up a delay queue that it shuttles al... - 12:09 AM Revision 0e92f892 (ceph): msgr: move the delay queue initialization into start_reader
- The Pipe doesn't know the peer type in the constructor. It
doesn't always know in start_reader either, so this needs ... - 12:09 AM Revision 01059e9b (ceph): msgr: clear out the delay queue when stop()ing
- After some brief thought, I believe deleting any messages in the
delay queue is correct -- we are trying to simulate ... - 12:06 AM Revision bea3ecf0 (ceph): rgw: treat lack of swift token as anonymous user access
- Fixes: 3534
If a swift token hasn't been provided, set user as anonymous.
Signed-off-by: Yehuda Sadeh <yehuda@inktan...
11/29/2012
- 11:48 PM Revision c26dc188 (ceph): Merge branch 'next'
- Conflicts:
src/rgw/rgw_admin.cc - 11:47 PM Revision 77711dde (ceph): Merge remote-tracking branch 'gh/wip_next_bugs' into next
- 11:34 PM Revision ef39773c (ceph): Merge remote-tracking branch 'gh/wip-mon-osd-create-fix' into next
- 11:33 PM Revision 6a69083d (ceph): radosgw-admin: close storage before exit
- Fixes: #3560
This will remove watches off notification objects.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:15 PM Revision 3ceaec4c (ceph): osd: use safe con helpers for scrub
- Note that if we don't get a con our behavior largely does not matter, since
we know we are about to get a Reset event... - 11:15 PM Revision b31a99ab (ceph): osd: fix leak of heartbeat con on reset
- If we replace our old con, drop the reference.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:15 PM Revision 774d5bf1 (ceph): osd: move next_osdmap under separate lock
- It doesn't actually interfere with publish_lock, and the current osdmap
ref.
Document what is going on.
Always prec... - 11:15 PM Revision 30832f5a (ceph): osd: make _share_map_outgoing() use a Connection
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:15 PM Revision f865f260 (ceph): osd: use safe con helpers from do_{infos,queries,notifies}
- Ensure we don't reopen connections to downloads.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:04 PM Revision f9056f5b (ceph): test/libcephfs: Test reading an empty file
- This tests a bug (#3490) in the Client::_read_sync
codepath, and should be run with conf->client_read_sync_always
set... - 11:04 PM Revision 7d27e2e9 (ceph): client: Fix for #3490 and config option to test
- If the mds revokes our cache cap, and we follow
the _read_sync() path, on a zero-byte file the
osd returns ENOENT. W... - 09:57 PM Revision 5c8cbd28 (ceph): PG: scrubber.end should be exactly a boundary
- Let scrubber.end be (foo, HEAD, 10) where the oid is foo , HEAD is the
snap, and 10 is the hash and scrubber.begin si... - 09:51 PM Revision e2c4e2f6 (ceph): PG: maintain osd local last_epoch_started for find_best_info
- In order to proceed with peering, we need an osd with a log including
the last commit sent to a client. This transla... - 09:51 PM Revision f4f93f82 (ceph): OSD: history.last_epoch_started should start at 0
- history.last_epoch_started marks a lower bound on the last epoch at
which the pg went active. As with info.last_epoc... - 09:51 PM Revision 8218d8ac (ceph): OSD: get_or_create_pg return null if pool is gone
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:51 PM Revision 206f39e3 (ceph): ReplicatedPG: remove from snap_collections even without objects to trim
- Also, make sure to write_info after updating snap_collections.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 09:51 PM Revision 82517f1b (ceph): hobject_t: make max private
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:50 PM Revision 84983387 (ceph): rgw: fix PUT acls
- This fixes a regression introduced at
17e4c0df44781f5ff1d74f3800722452b6a0fc58. The original
patch fixed error leak, ... - 09:46 PM Revision 0b55fbdb (ceph): Script to install and configure radosgw.
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:23 PM Revision e58008e0 (ceph): Merge branch 'wip-mon-store-errorcheck' into next
- Reviewed-by: Joao Luis <joao.luis@inktank.com>
- 09:07 PM Revision b0b8bfbd (ceph): Merge remote-tracking branch 'origin/wip-rgw-leak' into next
- Conflicts:
src/rgw/rgw_main.cc
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:03 PM Revision 079dd190 (ceph): mon: Monitor: don't allow '+' or '-' prefixed values on parse_pos_long()
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 09:01 PM Revision c6cc476f (ceph): mon: OSDMonitor: return -EINVAL on not-a-uuid during 'osd create'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:39 PM Revision 5bc10ecc (ceph): osd: use OSDService send_message helper from PG context
- Use the OSDService helper to send messages to peers. This ensures that if
we are on an older OSDMap the messages don... - 08:39 PM Revision e18f9ee8 (ceph): osd: add Connection-base send_map(), send_incremental_map()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:39 PM Revision a87361ef (ceph): osd: fix Connection leaks
- Messenger::get_connection() returns a reference. Put it.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:39 PM Revision bd03234c (ceph): osd: simplify active_committed
- Way back in 4b3bb5ab37a05fa001d59f24da7d9c30d650321b we changed this to
pass an entity_inst_t down to fix a race. The... - 08:38 PM Revision ea65dfff (ceph): osd: helpers to blacklist messages to down osds
- There is a race between handle_osd_map -> note_down_osd() and PG threads:
- handle_osd_map -> note_down_osd marks d... - 08:38 PM Revision e1653302 (ceph): osd: use safe OSDService msgr helpers for heartbeats
- Get connections via the OSDService helper.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:39 PM CephFS Bug #3554: Logs broken after a rotation
- /etc/logrotate.d/ceph is doing an invoke-rc.d ceph reload which executes /etc/init.d/ceph which does /usr/bin/ceph-co...
- 11:30 AM CephFS Bug #3554: Logs broken after a rotation
- is this upstart (ceph-deploy) or mkcephfs (initrd)?
- 11:25 AM CephFS Bug #3554: Logs broken after a rotation
- Hey Dan,
I just ran into this issue on my 3node VM on my desktop...
i had noted that mon.a was running, but mon... - 04:13 PM rgw Bug #3534 (Resolved): rgw: no anonymous handling when going through swift
- Done, commit:bea3ecf0746e57f6ac4fb32ef3f13bd328447992.
- 03:31 PM rgw Bug #3532: rgw: wrong bucket stats after multipart upload
- Fix merged to master at commit:6a36ac5bd6f4e3d2ec425a35f8ae9ffa20df138c.
- 03:30 PM rgw Bug #3560 (Resolved): rgw: radosgw-admin doesn't clean up watches
- Fixed, commit:6a69083dcee58bb411f6d81d80055767e1160f27.
- 03:24 PM rgw Bug #3560 (Resolved): rgw: radosgw-admin doesn't clean up watches
- 03:00 PM CephFS Bug #3559 (Resolved): mds: not issuing RDCACHE to exclusive client for some files
- reproduced by kernel tar compile task and ceph-fuse. one part of the trigger for #3490.
- 02:59 PM CephFS Bug #3490 (Resolved): client: ENOENT during kernel_untar_build.sh over fuse
- commit:7d27e2e95c8cb1bb3f5950ff224e49bfd353db9c
hooray!
opening another issue for the RDCACHE caps thing - 01:46 PM rgw Bug #3558 (Resolved): rgw: PUT acls broken (stable)
- Fixed, commit:84983387a220a29540aca64af774bbe7bc6b5ee6.
- 12:44 PM rgw Bug #3558 (Resolved): rgw: PUT acls broken (stable)
- 12:32 PM rgw Bug #3557 (Resolved): rgw: error reading user info after creating subusers
- After creating 100+ subusers, can't read user info.
- 11:17 AM Documentation #3555: {page-num} in ceph osd pool create is not optional
- This is a difference between Bobtail and Argonaut, but it probably shouldn't have been optional in Argonaut so I'd sa...
- 10:45 AM Documentation #3555 (Resolved): {page-num} in ceph osd pool create is not optional
- The documentation on http://ceph.com/docs/master/rados/operations/pools/ claims pg-num is not required but it appears...
- 11:15 AM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- too large of a file. Only did a tar for the osd logs.
- 11:06 AM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- ubuntu@ceph1:/var/log/ceph$ sudo service ceph status
=== mon.a ===
mon.a: running 0.48.2argonaut
=== mds.a ===
... - 11:03 AM rbd Bug #3556 (Resolved): rbd rm command fails to remove the new format rbd image completely
- when a rbd image is created using new format, removing the header followed by removing the rbd image using "rbd rm" d...
- 10:11 AM Bug #3550: mon: Ceph fails to work when IP address is changed on the host
- Deb Barba wrote:
> Sage,
>
> In all due respect, I disagree.
>
> I can see how you do not want a single typo i... - 09:25 AM Bug #3550: mon: Ceph fails to work when IP address is changed on the host
- Sage,
In all due respect, I disagree.
I can see how you do not want a single typo in a config file to mess up t... - 09:04 AM Bug #3550 (Won't Fix): mon: Ceph fails to work when IP address is changed on the host
- Right. There is a manual process for adjusting monitor ips, but it is not very friendly.
We don't want to blindl... - 07:19 AM Bug #3550: mon: Ceph fails to work when IP address is changed on the host
- This has been an recurrent issue among users on IRC, although it's often prompted by misunderstanding of how the moni...
- 09:05 AM CephFS Bug #3551: mds: journaler hang
- this was a broken object (size was < 4MB).
the journaler could handle it more gracefully, but more graceful in t... - 02:11 AM Revision 4c3d5dce (ceph): test_cls_rgw.c: Call to cls_rgw_bucket_complete_op() needs new parameter.
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 01:15 AM Revision 9aacaf77 (ceph): add mon-thrasher singleton
- 12:53 AM Revision 213787fb (ceph): Merge branch 'wip-mon-thrasher'
- 12:53 AM Revision 334d6386 (ceph): Merge branch 'wip-mon-thrasher'
- 12:28 AM Revision ab312f8d (ceph): mon: update Paxos::read()'s successful read check
- It was returning success if it got back an error code; don't do that!
Signed-off-by: Greg Farnum <greg@inktank.com> - 12:28 AM Revision 399f269d (ceph): mon: convert store users with unchecked return codes to just assert on ...
- This will make them much more noticeable and reduce the odds of something
writing data which assumes the previous op ... - 12:28 AM Revision c762f91a (ceph): mon: remove the silly write_bl_ss write_bl_ss_impl distinction
- It was introduced at the same time as all these unchecked return codes,
but I can't tell why.
Signed-off-by: Greg Fa... - 12:28 AM Revision 24d61fa4 (ceph): mon: add WARN_UNUSED_RESULT to the MonitorStore functions that return e...
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:28 AM Revision 3fe7c6cb (ceph): mon: add new get_bl_[sn|ss]_safe functions
- These functions are like the non-safe versions, but assert that
there were no disk errors and have void return types.... - 12:28 AM Revision 60f60ff7 (ceph): mon: In MonitorStore, wrap all uses of ::close and assert success
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:12 AM Revision f5253592 (ceph): task: mon_thrash: thrash monitors while running other tests
- Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
11/28/2012
- 11:25 PM Revision 71361ac6 (ceph): kernel: add rbd map/unmap test
- 11:22 PM Revision dd3a24a6 (ceph): create qa/workunits/rbd/map-unmap.sh
- This adds a bash script that creates an rbd image, then repeatedly
maps and unmaps it for a specified duration (5 min... - 09:56 PM Revision 6a36ac5b (ceph): Merge branch 'wip-3532-2'
- 09:53 PM Revision 5d6da25c (ceph): rgw: bucket check --check-objects
- A new option that goes through the indexed objects, verifies
their actual state and updates the index accordingly.
S... - 09:52 PM Revision e5dc46f6 (ceph): rgw: check_disk_state() removes multipart parts from index
- Besides suggesting changes to the object's index, we also need
to remove the parts that build the object. This only a... - 09:45 PM Bug #3552: After ceph-deploy installation a reboot breaks OSDs
- After several reboots I'm finding this problem to be intermittent. Sometimes I find that the mounts are performed an...
- 04:28 PM Bug #3552: After ceph-deploy installation a reboot breaks OSDs
- Ubuntu 12.04.1 LTS (actually ceph-deploy only supports 12.04 right now anyway)
- 04:23 PM Bug #3552: After ceph-deploy installation a reboot breaks OSDs
- What OS is this? I'm not certain but I'd expect this all to be accomplished via upstart triggers and the existing job...
- 04:17 PM Bug #3552 (Resolved): After ceph-deploy installation a reboot breaks OSDs
- The mounts for OSD partitions on /var/lib/ceph/osd/ceph-* are not added to /etc/fstab nor mounted some other way. Th...
- 09:00 PM Revision 78286b14 (ceph): log: 10,000 recent log entries
- This is what we were (wrongly) doing before, so there are no memory
utilization surprises.
Signed-off-by: Sage Weil ... - 08:59 PM Revision 4de7748b (ceph): log: fix log_max_recent config
- <facepalm>
Signed-off-by: Sage Weil <sage@inktank.com> - 08:35 PM Revision 39b93f58 (ceph): mon: check all uses of fsync in the MonitorStore for errors
- This can sometimes return errors since it's a storage access, and
we're pretty sure ignoring it is the cause of a bro... - 07:59 PM Revision 88a3e7d1 (ceph): Makefile: fix libcephfs for gcov and cleanups
- Adds EXTRALIBS, removes unused CFLAGS.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
Reviewed-by: Joe Buck <jb... - 07:45 PM Revision 80c506d4 (ceph): rbd: fix import from stdin, add test
- Make import work; do I/O in image native block size.
Note: creating sparse images is not currently attempted; could
s... - 07:45 PM Revision fcebe048 (ceph): rbd: allow export to stdout, add tests
- Fixes: #3502
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
(cherr... - 07:29 PM CephFS Bug #3554: Logs broken after a rotation
- it sounds like the /etc/logrotate.d/ceph isn't telling upstart to reload the logs, or that bit of the upstart configs...
- 05:33 PM CephFS Bug #3554 (Resolved): Logs broken after a rotation
- This is a ceph-deploy installation on Ubuntu 12.04 of ceph version 0.54 (commit:60b84b095b1009a305d4d6a5b16f88571cbd3...
- 07:28 PM CephFS Bug #3553 (Need More Info): MDS core dumped running 0.48.2argonaut
- ENXIO from teh OSD means we sent the request to the wrong osd. what version is the osd running?
also, do you have... - 05:26 PM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- ubuntu@ceph1:/var/log/ceph$ uname -a
Linux ceph1 3.2.0-23-virtual #36-Ubuntu SMP Tue Apr 10 22:29:03 UTC 2012 x86_64... - 04:39 PM CephFS Bug #3553: MDS core dumped running 0.48.2argonaut
- This cluster has 3 VM nodes
- 04:35 PM CephFS Bug #3553 (Won't Fix): MDS core dumped running 0.48.2argonaut
- /var/ceph/ceph-mds.a.log shows mds 'comitting suicide':
2012-11-29 00:09:08.569400 7f38fa8b2700 1 mds.0.6 handle_m... - 07:11 PM Revision a1768003 (ceph): mon: fix compiler warning
- signed/unsigned comparison
Signed-off-by: Sage Weil <sage@inktank.com> - 04:25 PM Revision ec2f2617 (ceph): messages/MClientRequest.h: remove twice included sys/types.h
- Fix includes: remove twice included sys/types.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 1f3e5ad2 (ceph): mon/Monitor.cc: remove twice included osd/OSDMap.h
- Fix includes: remove twice included osd/OSDMap.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision e7f8e562 (ceph): mds/journal.cc: remove twice included common/config.h
- Fix includes: remove twice included common/config.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 653f1347 (ceph): os/DBObjectMap.h: remove twice included <string>
- Fix includes: remove twice included <string>
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 428f300f (ceph): mds/Migrator.cc: remove twice included Migrator.h
- Fix includes: remove twice included Migrator.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 82c1f48b (ceph): mds/Resetter.h: remove twice included msg/Messenger.h
- Fix includes: remove twice included msg/Messenger.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 03a4c8c9 (ceph): tools/common.cc: remove twice included headers
- Cleanup includes: Remove twice included sys/stat.h and osd/OSDMap.h.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@b... - 04:25 PM Revision aee71e15 (ceph): osd/OSD.h: remove twice included OpRequest.h
- Fix includes: remove twice included OpRequest.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 93ff160d (ceph): os/IndexManager.cc: remove twice included FlatIndex.h
- Fix includes: remove twice included FlatIndex.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 428d974c (ceph): osdmaptool.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 238f9321 (ceph): rados.cc: remove twice included headers
- Fix includes: remove twice included common/obj_bencher.h and
common/errno.h
Signed-off-by: Danny Al-Gaaf <danny.al-g... - 04:25 PM Revision a0d978f6 (ceph): remove twice included linux/types.h
- Cleanup includes: remove twice included linux/types.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 947b33a2 (ceph): os/DBObjectMap.cc: remove twice included headers
- Fix includes: remove twice included <string> and <tr1/memory>
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 0718c152 (ceph): rgw/rgw_rest.cc: remove twice included rgw_formats.h
- Cleanup includes: Remove twice included rgw_formats.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 1341e6d7 (ceph): crushtool.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 54da979d (ceph): common/pipe.c: remove twice included unistd.h
- Fix includes: remove twice included unistd.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 34f6d291 (ceph): mount/canonicalize.c: remove twice included string.h
- Fix includes: remove twice included string.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 9ac063a8 (ceph): monmaptool.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 1ca3d756 (ceph): include/buffer.h: remove twice included stdio.h
- Fix includes: remove twice included stdio.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision e1431b8e (ceph): librados/RadosClient.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision abc8cb68 (ceph): mds/Dumper.h: remove twice included msg/Messenger.h
- Fix includes: remove twice included msg/Messenger.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision c753f58e (ceph): ceph_mds.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision f8ef4a88 (ceph): client/Client.cc: remove twice included headers
- Fix includes: remove twice included common/config.h". Remove include
of sys/param.h in special __FreeBSD__ section, s... - 04:25 PM Revision 5fb2185c (ceph): client/MetaRequest.cc: remove twice included client/Dentry.h
- Fix includes: remove twice included client/Dentry.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 8a6278ec (ceph): ceph_osd.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 3fa561eb (ceph): ceph_syn.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision f814afad (ceph): fusetrace_ll.cc: remove twice included sys/time.h
- Fix includes: remove twice included sys/time.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision 8a19b89c (ceph): client/SyntheticClient.cc: remove twice included headers
- Fix includes: remove twice included common/config.h and sys/types.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bise... - 04:25 PM Revision 1c0c0558 (ceph): ceph_fuse.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 04:25 PM Revision f65307a0 (ceph): ceph_mon.cc: remove twice included sys/stat.h
- Fix includes: remove twice included sys/stat.h
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> - 03:24 PM rbd Bug #3524: test_librbd_fsx: crash after flatten
- I've reproduced with logs, and am examining the ops. Working theory is that the flatten happened between the first p...
- 03:22 PM rbd Bug #3478 (Closed): rbd: copy destination pool is assumed to be source pool
- commit:81d383073865d221bb825a8990ae9b34bd491bef (next)
commit:3b0c36052806a4574ede6a9f0594dc83f7997bcc (master) - 03:06 PM CephFS Bug #3551 (Can't reproduce): mds: journaler hang
- ...
- 02:33 PM Bug #3550 (Won't Fix): mon: Ceph fails to work when IP address is changed on the host
- I had an incident, where my DHCP server changed all the IP addresses of the nodes in my ceph cluster.
I looked up ... - 01:55 PM rbd Bug #3549 (Resolved): rbd: info should report striping
- feature_str() should have striping added for rbd info. Should rbd ls -l report striping
parms too?.. - 01:35 PM Bug #3548 (Resolved): osd: sends messages to marked-down peers
- the async osdmap updates introduce a new problem:
- handle_osd_map map X marks down osd Y
- pg thread uses map X-... - 01:10 PM Linux kernel client Bug #3525 (Resolved): kclient+iozone hang on ceph-client testing
- My testing did not fail for iozone or direct io using
ceph-fuse.
I get an error when using rbd to back the file s... - 08:35 AM Linux kernel client Bug #3525: kclient+iozone hang on ceph-client testing
- The direct I/O test now passes with my fix. I'm going to do
a final test run of the rebased patches in the testing ... - 08:32 AM Linux kernel client Bug #3525: kclient+iozone hang on ceph-client testing
- I just finished testing my fix with the iozone test and it
appears to have made the hang I saw go away. I'm now run... - 08:16 AM Linux kernel client Bug #3525: kclient+iozone hang on ceph-client testing
- ...
- 12:57 PM rbd Bug #3547 (Resolved): rbd: suites/iozone.sh failure
- ...
- 11:45 AM rbd Bug #3427: krbd: unmap does not remove block device properly
- Indeed, that's where this is from. So, there are running, or lingering, requests on the OSD. Shouldn't it try to kick...
- 08:30 AM rbd Bug #3427 (In Progress): krbd: unmap does not remove block device properly
- ...
- 02:46 AM rbd Bug #3427: krbd: unmap does not remove block device properly
- The same bug hit me in kernel 3.6.7.
Ceph version: 0.54
Kernel log:... - 08:59 AM Bug #3546 (Won't Fix): CEPH 0.48.2 OSD crashed causing kernel RBD clients to reboot
- Here is a stack trace of an OSD crash, after the OSD crashed it caused all of the hosts using the RBD kernel client t...
- 08:34 AM Linux kernel client Bug #3519 (In Progress): rbd map hang during system startup
- I never got around to saying this yesterday. The thing I posted
earlier about the scrub messages can be ignored. I... - 04:51 AM Revision 43ef8c10 (ceph): mon: do not crash on invalid 'mon tell N ...' target
- Fixes: #3545
Signed-off-by: Sage Weil <sage@inktank.com> - 01:29 AM Revision c99d9c3a (ceph): rbd: fix import from stdin, add test
- Make import work; do I/O in image native block size.
Note: creating sparse images is not currently attempted; could
s... - 01:29 AM Revision a738f44b (ceph): rbd: allow export to stdout, add tests
- Fixes: #3502
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 01:29 AM Revision cf2a0454 (ceph): config: make $pid a metavariable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:03 AM Revision e1a9a440 (ceph): fix objectcacher stress test
- 12:55 AM Revision aa37fe76 (ceph): test_rados_api_misc: fix TMAPPUT sorting test
- Several things wrong here.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:24 AM Revision 8850b3c7 (ceph): ceph.spec.in: Fix typo.
11/27/2012
- 11:21 PM Revision a1e08684 (ceph): README: add the libboost-thread-dev dep to the list
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 11:09 PM Revision 054f761f (ceph): ceph.spec.in: Add new test programs to package.
- 10:29 PM Revision b5409935 (ceph): Merge branch 'next'
- 10:28 PM Revision dbb3fb11 (ceph): Makefile: Add test/osdc/FakeWriteback.h to noship-headers.
- 10:13 PM Revision 533a6d04 (ceph): Merge branch 'wip-mds-next' into next
- OSD bits Reviewed-by: Sam Just <sam.just@inktank.com>
MDS bits Reviewed-by: Sage Weil <sage@inktank.com> - 10:13 PM Revision a4439f0f (ceph): osd: move tmapup into a helper
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:13 PM Revision 8e91d00b (ceph): osd: tolerate misordered TMAP updates
- The previous tmap implementation requires that the update stream be
sorted or else it will behave erratically (by pla... - 10:13 PM Revision 29fae494 (ceph): osd: do not ENOENT on missing key on remove
- The MDS may include RM ops in a tmap update for items that were already
removed: after restarting and replaying the j... - 10:13 PM Revision bc77e528 (ceph): osd: verify TMAPPUT data is sorted
- The MDS may try to write unsorted data; make sure it is sorted before
we write it.
Signed-off-by: Sage Weil <sage@in... - 10:13 PM Revision 10b68b2e (ceph): osd: detect (some) misordered ondisk tmaps
- Detect a misordered ondisk tmap... if we are already decoding it. We still
leave the trailing bits unchecked.
Signe... - 10:06 PM Revision 919db194 (ceph): rbd workunit: Add tests for clones across pools
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from... - 10:06 PM Revision 51640750 (ceph): rbd workunit: Make "remove_images" silent
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from... - 10:06 PM Revision ca5549e8 (ceph): rbd workunit: Add tests for cross-pool rename
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from... - 10:06 PM Revision bbd343a1 (ceph): rbd: tests for copy with explicit/implicit pool names
- Validate change to not assume dest pool == src pool
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh... - 10:06 PM Revision e612afc2 (ceph): rbd: fix import pool assumptions
- import allows specifying one image, implicitly or explicitly the
"source" image, even though it's really the destinat... - 10:06 PM Revision 81d38307 (ceph): rbd: change destpool assumptions.
- Don't default destpool to srcpool; it's surprising, and
not useful/helpful enough to violate the convention that
"def... - 10:06 PM Revision 724cfd1b (ceph): rbd: --size fixes
- * require --size/-s for both create *and* resize
* explicitly permit create with size 0.
Signed-off-by: Dan Mick <da... - 10:06 PM Revision 66b148e3 (ceph): rbd: allow parsing image@snap even if --pool given
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
(cherry picked from... - 09:50 PM Revision af5d9e43 (ceph): Makefiles: Use AM_CXXFLAGS for crypto library compiler options
- In configure.ac, add the crypto library compiler flags to AM_CXXFLAGS and in
src/Makefile remove CRYPTO_CXXFLAGS and ... - 09:50 PM Revision 76e26017 (ceph): ObjectContents.h: Fix compiler warning by adding parenthesis
- 09:50 PM Revision 37adf2a9 (ceph): packaging: Add ceph-test debian package
- The ceph-test package includes optional test and benchmarking programs.
- 09:34 PM Revision c04fcaad (ceph): ceph.spec.in: Add rest-bench and ceph-test packages.
- 09:34 PM Revision 1dc0fce9 (ceph): ceph.spec.in: Enable rest-bench and debug configure options
- 09:31 PM Revision 10a35caa (ceph): Makefiles: Update noinst_headers
- Added headers for new tests and benchmarks to the non installed headers
list, so they will be included in the tarball... - 08:56 PM CephFS Bug #1945: blogbench hang on caps
- this might be fixed by commit:854a78669fe057f2bf1bc5a07308b415461e78d7 ...
- 08:54 PM CephFS Bug #3545 (Resolved): Giving bogus injectargs request crashes ceph-mon
- commit:43ef8c10ba55f4c42999cdc34492eb5391d49b68
- 07:21 PM CephFS Bug #3545 (Resolved): Giving bogus injectargs request crashes ceph-mon
- Since I have only 2 ceph-mon's specifying 3 for the id is invalid.
ubuntu@ceph1:/var/log/ceph$ sudo ceph -s
he... - 08:54 PM Revision 8e9554e1 (ceph): Merge remote-tracking branch 'gh/wip-mon-workloadgen' into next
- 08:00 PM Revision 1fcccd3e (ceph): crushtool: rework how verbosity works
- 'verbose' was a bool that would either be passed as one or zero to class
CrushCompile. However, most messages would o... - 08:00 PM Revision f7276dea (ceph): crush: relax the order by which rules and buckets must be defined
- Before we only allowed buckets (say, 'root') to be defined *before*
rules.
With this patch, we allow buckets and rul... - 08:00 PM Revision 31777743 (ceph): mon: Monitor: use existing strict_strtol() on parse_pos_long()
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:00 PM Revision f5029074 (ceph): messages: MLog: make ctor's uuid argument a const
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 08:00 PM Revision e1820d87 (ceph): test: mon: workload generator
- User-space tool that interacts with the monitor, with the objective of
generating a workload mimicking a set of OSDs ... - 08:00 PM Revision 2a681052 (ceph): qa: workunits: mon: add workloadgen's workunit
- Uses test/mon/test_osd_workloadgen to generate a bunch of map
changes
Signed-off-by: Joao Eduardo Luis <joao.luis@in... - 08:00 PM Revision 3112cd8f (ceph): test: mon: run_test.sh: helper script for the mon's workloadgen
- Takes advantage of qa/workunits/mon/workloadgen.sh to avoid duplicating
code.
Signed-off-by: Joao Eduardo Luis <joao... - 07:50 PM Revision 9e8c8617 (ceph): rgw: unaccount multipart parts when completing upload
- We need to do it atomically, so info about parts is sent to
the bucket index objclass.
Signed-off-by: Yehuda Sadeh <... - 06:59 PM CephFS Bug #3544: ./configure checks CFLAGS for jni.h if --with-hadoop is specified but also needs to ch...
- jni.h is also OK for C or C++. Add it CPPFLAGS to fix the problem?
- 06:53 PM CephFS Bug #3544: ./configure checks CFLAGS for jni.h if --with-hadoop is specified but also needs to ch...
- You could probably put a AC_PUSH/POP_LANG[C++] around the JNI checks, and then configure.ac would fail properly. Curr...
- 05:38 PM CephFS Bug #3544 (Won't Fix): ./configure checks CFLAGS for jni.h if --with-hadoop is specified but also...
- If configure is used like so:
CFLAGS="-fno-omit-frame-pointer -g -O2 -I/usr/lib/jvm/java-6-openjdk-amd64/include" CX... - 06:47 PM CephFS Bug #1047: mds: crash on anchor table query
- Hi,
Still have the problem here. ... - 05:31 PM Messengers Feature #3509 (Fix Under Review): msgr: delay injection
- wip-msgr-delay-queue
running it against the rados suite now. - 05:29 PM Revision 15b4ac58 (ceph): Merge remote-tracking branch 'gh/wip-perf' into next
- Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
- 05:28 PM Revision 60d82062 (ceph): Merge remote-tracking branch 'gh/wip-crush' into next
- 04:52 PM Revision d4bc3729 (ceph): fix syncfs handling in error case
- If the call to syncfs() fails, don't try to call syncfs again via
syscall(). If HAVE_SYS_SYNCFS is defined, don't fal... - 03:49 PM Linux kernel client Bug #2506: ceph: ceph_add_cap: couldn't find snap realm NNN
- Re,
Ceph version causes the kernel panics we are encountering:... - 03:47 PM Linux kernel client Bug #2506: ceph: ceph_add_cap: couldn't find snap realm NNN
- Hi Ceph Dev team,
Same problem here, with the last version of Ceph kernel client and the 2 last kernel (linux-imag... - 02:28 PM CephFS Feature #605 (Rejected): mds: verify/repair anchor table
- 02:28 PM CephFS Feature #764 (Rejected): mds: make anchor table scale
- 02:27 PM CephFS Feature #3543 (Closed): mds: new encoding
- 02:27 PM CephFS Feature #3542 (Duplicate): mds: migration path for existing anchors, anchortables, etc.
- 02:27 PM CephFS Feature #3541 (Resolved): mds: robust ino lookup using file backpointers
- Following #3540 and #3863, implement the lookup-by-ino algorithm described in http://www.spinics.net/lists/ceph-devel...
- 02:26 PM CephFS Feature #3540 (Resolved): mds: maintain per-file backpointers on first file object
- Add backtraces to each file object, as described at http://www.spinics.net/lists/ceph-devel/msg11872.html. This ticke...
- 02:25 PM CephFS Feature #3437 (Resolved): client: expose mds session state via admin socket
- 02:25 PM CephFS Feature #3436 (Resolved): client: expose mds requests via admin socket
- 01:56 PM Linux kernel client Bug #3539 (Rejected): null deref at con_work+0x257d/0x2f40 after osd reset under ffsb workload
- commit:7246240c7c186542f73af4fadc744d66440f616f is not in master. false alarm!
- 01:52 PM Linux kernel client Bug #3539: null deref at con_work+0x257d/0x2f40 after osd reset under ffsb workload
- ...
- 12:51 PM Linux kernel client Bug #3539 (Rejected): null deref at con_work+0x257d/0x2f40 after osd reset under ffsb workload
- ...
- 11:22 AM Bug #3538 (Resolved): rbd fsx test causes osd attr value mismatch err
- Logs: ubuntu@teuthology:/a/teuthology-2012-11-23_07:00:03-regression-testing-master-basic/2882...
- 09:25 AM Bug #3521 (Resolved): windows 2008 kvm guest crashes with "floating point exception" when using r...
- 09:24 AM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- merged into next
- 09:10 AM Linux kernel client Bug #3519: rbd map hang during system startup
- This may not be related, but in that log (...16cce/gistfile1.txt)
the first "scrub ok" messages showed up in the sam... - 08:36 AM CephFS Bug #3531 (In Progress): mds segfault at _unlink_local_finsh
- new asserts in wip-mds-ls
- 06:03 AM Revision 9c76ed62 (ceph): Merge branch 'wip-rbd-cmdparse'
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:02 AM Revision ece11b0e (ceph): rbd workunit: Add tests for clones across pools
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:02 AM Revision 0be9b15b (ceph): rbd workunit: Make "remove_images" silent
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 06:02 AM Revision a96ede94 (ceph): rbd workunit: Add tests for cross-pool rename
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 05:38 AM Revision 39180430 (ceph): rbd: tests for copy with explicit/implicit pool names
- Validate change to not assume dest pool == src pool
Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh... - 05:38 AM Revision c2196981 (ceph): rbd: fix import pool assumptions
- import allows specifying one image, implicitly or explicitly the
"source" image, even though it's really the destinat... - 05:37 AM Revision 3b0c3605 (ceph): rbd: change destpool assumptions.
- Don't default destpool to srcpool; it's surprising, and
not useful/helpful enough to violate the convention that
"def... - 05:37 AM Revision 08f47a42 (ceph): rbd: --size fixes
- * require --size/-s for both create *and* resize
* explicitly permit create with size 0.
Signed-off-by: Dan Mick <da... - 05:37 AM Revision e452df6d (ceph): rbd: allow parsing image@snap even if --pool given
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 05:14 AM Revision 854a7866 (ceph): mds: don't add not issued caps when confirming cap receipt
- There is message ordering race in cephfs kernel client. We compose
cap messages when i_ceph_lock is hold. But when ad... - 05:14 AM Revision 57310268 (ceph): mds: don't expire log segment before it's fully flushed
- Expiring log segment before it's fully flushed may cause various
issues during log replay.
Signed-off-by: Yan, Zheng... - 05:14 AM Revision a3aad3c3 (ceph): mds: fix anchor table update
- The reference count of an anchor table entry that corresponds to
directory is number of anchored inodes under the dir... - 05:14 AM Revision 642ffc92 (ceph): mds: check parent inode's versionlock when propagating rstats
- To propagate rstats to one level up, we need lock both parent
inode's nestlock and versionlock.
Signed-off-by: Yan, ... - 05:14 AM Revision 3e988d45 (ceph): osdc/ObjectCacher: touch Objects in lru
- Touch the object when we touch one of it's bh's, and when we touch it
during readx (possibly because it is negative).... - 05:13 AM Revision a41dde3d (ceph): Merge branch 'next'
- 05:13 AM Revision 16215d9c (ceph): osdc/ObjectCacher: remove unused waitfor_{rd,wr}
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:13 AM Revision 011d1e79 (ceph): osdc/ObjectCacher: *do* pin object during write
- This hopefully resolves #3431.
We originally did this in 46897fd4ffc2fe2fc2cc0c39b5d4c510df1e6c25, and
then reverted... - 01:15 AM Revision 88f21818 (ceph): crush: for chooseleaf rules, retry CRUSH map descent from root if leaf ...
- Consider the CRUSH rule
step chooseleaf firstn 0 type <node_type>
This rule means that <n> replicas will be chosen... - 01:15 AM Revision 0cc47ff6 (ceph): crush: introduce CRUSH_TUNABLES2 feature
- For the chooseleaf_descend_once flag.
Signed-off-by: Sage Weil <sage@inktank.com> - 01:15 AM Revision 6efe977f (ceph): mon, osd: adjust msgr requires for CRUSH_TUNABLES2 feature
- Make this code a bit manageable for multiple features.
Signed-off-by: Sage Weil <sage@inktank.com>
11/26/2012
- 11:55 PM Revision 6bc32b20 (ceph): rgw: usage REST api handles cateogories
- Fixes: #3528
The usage REST api was missing the categories filter.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:55 PM Revision 0beeb47c (ceph): rgw: document ops logging setup
- Fixes: #3530
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:30 PM Revision 3a0ee8e4 (ceph): perfcounters: add 'perf' option to disable perf counters
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:30 PM Revision 94423ac9 (ceph): perfcounters: fl -> time, use u64 nsec instead of double
- (Almost) all current float users are actually time values, so switch to
a utime_t-based interface and internally usin... - 11:29 PM Bug #3536: librados: client.glance authentication error (1) Operation not permitted
- I found the solution to solve this issue:
Edit the ceoh.conf file and create a new tag [client.glance]:
@[globa... - 10:08 PM Bug #3536 (Resolved): librados: client.glance authentication error (1) Operation not permitted
- Hi all,
I want to integrate ceph and glance, and enable RBD as glance storage backend. Request commited by defaulf... - 11:04 PM Revision a37c34de (ceph): Search for srcdir/.git in check_version
- Support srcdir != . looking for .git in srcdir when computing the ceph
release and git tag.
Signed-off-by: Alexandre... - 11:04 PM Revision b1c71088 (ceph): logrotate on systems without invoke-rc.d
- The which command doesn't output anything to stdout when it can't find
the given program name, and then [ -x ] passes... - 10:34 PM Bug #3537 (Won't Fix): Logs can run root out of space and crash ceph cluster (need more aggressiv...
- I'd like to see log rotation which prevents a root filesystem from being run out of space. This means that the daily...
- 09:46 PM Linux kernel client Bug #3525: kclient+iozone hang on ceph-client testing
- also, direct io test fails on testing but passes on master. maybe the same bug? it's a shorter test, probably easie...
- 09:19 PM Bug #3431: ceph fuse crashed during fsx test
- commit:011d1e79ab0c690bf2cf8cdb3f87c903e0ef4b9d
- 09:19 PM Bug #3431 (Resolved): ceph fuse crashed during fsx test
- 04:54 PM Bug #3431: ceph fuse crashed during fsx test
- i have an alternate fix pushed to wip-mds-next.. sam, want to take a look?
- 04:46 PM Bug #3431: ceph fuse crashed during fsx test
- recent logs: ubuntu@teuthology:/a/sage-2012-11-25_20:49:20-regression-next-master-basic/4176 ...
- 08:48 PM Revision d72c2c86 (ceph): Removing ceph dirs while scrubbing ceph off the system
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 08:29 PM Revision 74b2a2d9 (ceph): rgw: POST requests not default to init multipart upload
- Fixes: #3516
We don't default to init multipart upload request when
getting S3 POST. This way when the request is not... - 07:15 PM Revision f0c608c0 (ceph): client: add ceph_open_layout interface
- Adds an interface identical to ceph_open() that takes additional
parameters specifying a file layout to use on new fi... - 07:15 PM Revision 1f8c3234 (ceph): java: add ceph_open_layout interface
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 07:08 PM Revision a4c41e20 (ceph): Add objectcacher stress testing
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 06:38 PM Revision caef5acd (ceph): Merge branch 'next'
- 06:37 PM Revision 365ba060 (ceph): qa: add script to run objectcacher tests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 05:57 PM Bug #3270: osd crash during rbd test run
- recent logs: ubuntu@teuthology:/a/teuthology-2012-11-23_19:00:03-regression-master-testing-gcov/3036
- 05:35 PM rgw Feature #3535 (Resolved): rgw: configurable list of http attributes
- 05:27 PM rgw Bug #3534 (Resolved): rgw: no anonymous handling when going through swift
- anonymous requests that go through swift rejected automatically.
- 05:11 PM rbd Bug #3524: test_librbd_fsx: crash after flatten
- recent logs: ubuntu@teuthology:/a/sage-2012-11-25_20:49:20-regression-next-master-basic/4332
- 05:10 PM rgw Bug #3532 (Resolved): rgw: wrong bucket stats after multipart upload
- We account the parts twice.
- 05:04 PM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- Logs: ubuntu@teuthology:/a/sage-2012-11-25_20:49:20-regression-next-master-basic/4280
- 05:00 PM CephFS Bug #3531 (Resolved): mds segfault at _unlink_local_finsh
- logs: ubuntu@teuthology:/a/sage-2012-11-25_20:49:20-regression-next-master-basic/4225...
- 04:38 PM Revision 30669d6d (ceph): Merge remote-tracking branch 'gh/wip-upstart' into next
- 04:37 PM Revision 525f942e (ceph): init-ceph: do not make noise about missing devs
- It is pretty normal not to include the devs line in the ceph.conf. Do not
print/warn about it.
Signed-off-by: Sage ... - 04:20 PM rgw Feature #3530 (Resolved): rgw: document ops logging setup
- Done, commit:0beeb47c43f391639882182766b0634cbeba72e5
- 03:13 PM rgw Feature #3530 (Resolved): rgw: document ops logging setup
- 04:20 PM rgw Bug #3528 (Resolved): rgw: usage admin api missing categories filter
- Fixed, commit:6bc32b20086c7cecd58b439b6b7d819b63fdcb73
- 02:40 PM rgw Bug #3528 (Resolved): rgw: usage admin api missing categories filter
- 02:56 PM rgw Feature #3529 (Resolved): rgw: configurable success status response for put obj
- Need to make it configurable. By default we return 200, clients may need to tweak that.
- 02:36 PM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- I've pushed a branch wip-perf that avoid floating point... can you give it a go?
- 02:32 PM rgw Bug #3516 (Resolved): POST /bucket/random throws a 500
- Done, commit:74b2a2d9641b6b1d3572d4706fa0cae34ea9e130.
- 12:57 PM Feature #3527 (Resolved): osd: blacklist should cancel outstanding watches from blacklisted client
- While testing locking/fencing, I noticed that if an rbd client is blacklisted, it
receives ESHUTDOWN from any operat... - 10:53 AM Bug #3286 (Resolved): librbd, kvm, async io hang
- Hooray!
- 10:33 AM rgw Bug #3517 (Resolved): rgw: usage does not account bytes_received, bytes_sent
- 10:33 AM rgw Feature #3442 (Resolved): rgw: support Keystone tokens revocation
- Done, as part of the keystone feature.
- 10:31 AM rgw Bug #3452 (Resolved): rgw: Handling of dates in If-UnModified-Since / Last-Modified seems to have...
- 10:23 AM rgw Bug #3492 (Resolved): rgw: relax date parsing
- Done, commit:ce284552060fe662a65db086e4e87fcfc3bcef7d.
- 10:21 AM rgw Feature #3494: ceph S3 upload slowly
- When using the ceph filesystem, the objects are not necessarily being written to the backend immediately, so any perf...
- 03:37 AM Documentation #3438 (Resolved): Adding/Removing Monitor documentation may be wrong
11/25/2012
- 10:43 PM Revision 9f7ab6e8 (ceph): kernel: remove serial rbd_xfstests job
- 10:42 PM Revision 7ff17ff0 (ceph): xfstests: remove 179 and 182 from parallel test
- 2012-11-25T11:34:51.177 INFO:teuthology.task.rbd.client.2.out:179 [failed, exit status 1] - output mismatch (s...
- 10:27 PM Bug #3286: librbd, kvm, async io hang
- OK, with ceph next @ bc32fc42 (and rbd_cache_size=33554433) it completed the full fio test several times, in contrast...
- 09:29 PM Revision bc32fc42 (ceph): syncfs: check for __NR_syncfs too
- Also make the filestore startup tell us *all* variants that are
supported, not just the first one.
Tested-by: Stefan... - 06:46 PM Bug #3520 (Resolved): Error listing snapshots: (5) Input/output error
- 05:27 PM Bug #3520: Error listing snapshots: (5) Input/output error
- Sage Weil wrote:
> ye yuan wrote:
> > ye yuan wrote:
> > > Sage Weil wrote:
> > > > Change your osd class dir lin... - 08:44 AM Bug #3520: Error listing snapshots: (5) Input/output error
- ye yuan wrote:
> ye yuan wrote:
> > Sage Weil wrote:
> > > Change your osd class dir line to have /usr/lib instead... - 06:36 PM Bug #2536: librados crashed while getting stat of an object
- Hi,
I got the same assertion:
radosgw-admin user create
./log/SubsystemMap.h: In function 'bool ceph::log::Sub... - 05:34 PM Revision 6890675b (ceph): monmap: fix crash from dup initial seed mons
- Fix bug reproduced by
-m hostname,ip_that_hosthname_resolves_to
Backport: argonaut
Reported-by: Drunkard Zhang <go... - 05:18 PM Revision 39d2d08a (ceph): Merge remote-tracking branch 'gh/next'
- 04:37 PM Revision d07d7289 (ceph): run: save original config, too
- 01:19 PM Bug #3526 (Resolved): Commands mentioned in documentation are incomplete ?
- http://ceph.com/docs/master/rados/operations/auth-intro/#ceph-authorization-caps
Maybe it is just me, but commands... - 09:16 AM Linux kernel client Bug #3525 (Resolved): kclient+iozone hang on ceph-client testing
- ...
- 08:44 AM Bug #3501 (Resolved): gitbuilder: rsync out tags
11/24/2012
- 08:52 PM rbd Bug #3524 (Duplicate): test_librbd_fsx: crash after flatten
- ...
- 07:12 PM Bug #3495: ceph-mon crash
- Sorry, marked this as resolved and only noticed the last comment afterwards (silly me).
For the monitor, a good lo... - 07:05 PM Bug #3495 (Resolved): ceph-mon crash
- 07:04 PM Bug #3361 (Resolved): don't log secrets
- 06:51 PM Bug #3279 (Resolved): mon/caps: cap comparison in get-or-create is based on a string literal
- 06:05 PM Revision 7602a055 (ceph): osdc/ObjectCacher: fix BufferHead leak on ENOENT
- This was detected by fsstress over ceph-fuse under valgrind.
Signed-off-by: Sage Weil <sage@inktank.com> - 05:16 PM Revision 8a03d501 (ceph): Merge remote-tracking branch 'gh/wip-mon-misc-fixes' into next
- 03:52 PM Bug #3520: Error listing snapshots: (5) Input/output error
- ye yuan wrote:
> ye yuan wrote:
> > Sage Weil wrote:
> > > Change your osd class dir line to have /usr/lib instead... - 03:45 PM Bug #3520: Error listing snapshots: (5) Input/output error
- ye yuan wrote:
> Sage Weil wrote:
> > Change your osd class dir line to have /usr/lib instead of $(libdir).. that v... - 03:42 PM Bug #3520: Error listing snapshots: (5) Input/output error
- Sage Weil wrote:
> Change your osd class dir line to have /usr/lib instead of $(libdir).. that variable substitution... - 03:25 PM Bug #3520: Error listing snapshots: (5) Input/output error
- Change your osd class dir line to have /usr/lib instead of $(libdir).. that variable substitution does not work.
- 03:17 PM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- Josh Durgin wrote:
> It's more than just perfcounters that use floating point. Crush does too. It might be less like... - 03:14 PM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- It's a matter of correctness, not of probability. Not sure though if crush is being called on the library called thre...
- 03:02 PM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- It's more than just perfcounters that use floating point. Crush does too. It might be less likely to crash from crush...
- 10:08 AM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- Yehuda Sadeh wrote:
> Any reason why this have to be float? We can keep elapsed time in nanoseconds instead.
Good... - 09:52 AM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- Any reason why this have to be float? We can keep elapsed time in nanoseconds instead.
- 09:34 AM Bug #3521: windows 2008 kvm guest crashes with "floating point exception" when using rbd image wi...
- The problem is that qemu doesn't save the floating point state when calling into the storage library code, and the in...
- 09:24 AM rgw Feature #3488 (Resolved): rgw: dump ops log to a socket
- 09:24 AM rbd Feature #3280 (Resolved): fsx: test flatten when cloning
- 09:12 AM Bug #3522 (Duplicate): Error listing snapshots: (5) Input/output error
- #3520
- 09:12 AM Bug #3523 (Duplicate): Error listing snapshots: (5) Input/output error
- #3520
- 03:14 AM Revision df550c9c (ceph): make mkcephfs and init-ceph osd filesystem handling more flexible
- Remove btrfs specific keys and replace them by more generic
keys to be able to replace btrfs with e.g. xfs or ext4 ea...
11/23/2012
- 07:13 PM Revision 96b82ebf (ceph): mon: Monitor: wake up contexts based on paxos machine's state
- When recovering the leader, only wake up a paxos machine's contexts if
the paxos machine is in a state that can handl... - 07:13 PM Revision 3b061ab9 (ceph): mon: AuthMonitor: increase log levels when logging secrets
- Fixes: #3361
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 07:13 PM Revision 7527a1ea (ceph): auth: Keyring: increase log levels when logging secrets
- Fixes: #3361
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 07:13 PM Revision deabdc8a (ceph): auth: cephx: increase log levels when logging secrets
- We understand that logging secrets may be useful when debugging the root
causes for auth issues. However, logging sec... - 07:12 PM Revision d6cf77dc (ceph): crush: CrushWrapper: don't add item to a bucket with != type than wanted
- We take little consideration about the type of the bucket we are adding
an item to. Although this works for the vast ... - 07:12 PM Revision 95e1fe88 (ceph): mon: PGMonitor: check if pg exists when handling 'pg map <PG>'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 06:20 PM Bug #3523 (Duplicate): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 06:03 PM Bug #3522 (Duplicate): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 11:30 AM Bug #3495: ceph-mon crash
- Joao, what kind of ceph configuration would make the logs more useful in the future?
Ceph crashes fairly often here,... - 11:21 AM Bug #3495 (Fix Under Review): ceph-mon crash
- wip-mon-misc-fixes contains commit 96b82ebf870bda5af33624f698785bac6ae78234 that should fix this bug.
The approach... - 10:45 AM Bug #3495: ceph-mon crash
- It appears that this crash is somewhat related with an election, and then something made the 'have_pending' variable ...
- 06:34 AM Bug #3361 (Fix Under Review): don't log secrets
- 06:31 AM Bug #3520: Error listing snapshots: (5) Input/output error
- I had checked folder /usr/lib/rados-classes/ , there were all so files including libcls_rbd.so.
- 02:06 AM Bug #3520 (Resolved): Error listing snapshots: (5) Input/output error
- Hi all,
I build one-node cluster Ceph(0.48, the stable version installed by apt-get) and Ceph -s display HEALTH_OK... - 04:28 AM Bug #3521 (Resolved): windows 2008 kvm guest crashes with "floating point exception" when using r...
- Host: ubuntu 12.10 amd64
Guest: windows 2008 r2
Ceph: 0.48.argonaut2 (the one from the ubuntu repos)
The crash i...
11/22/2012
- 10:59 PM Revision ab8327fe (ceph): Merge remote-tracking branch 'origin/next' into next
- 09:59 PM Revision b2f80359 (ceph): s3tests: fix typo
- 09:59 PM Revision b8e6ce4d (ceph): s3tests: fix typo
- 09:53 PM Revision 1c715a11 (ceph): mds: child directory inherits SGID bit
- Update the inode, not the local variable.
Reported-by: Giorgos Kappes <geokapp@gmail.com>
Signed-off-by: Sage Weil <... - 08:57 PM Revision 3110e5ca (ceph): Merge remote-tracking branch 'origin/next' into next
- 08:55 PM Revision a0e8452a (ceph): Merge branch 'wip-opslog-socket2' into next
- Conflicts:
src/rgw/rgw_main.cc - 05:17 PM Revision 55081c2b (ceph): crush: prevent loops from insert_item
- If the insertion would create a loop, return -EINVAL.
Fixes: #3515
Signed-off-by: Sage Weil <sage@inktank.com> - 04:50 PM Revision b706945a (ceph): Try using syscall() for syncfs if not supported directly by glibc
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 04:35 PM Feature #3476 (Resolved): mon: fix all leaks
- Haven't been able to trigger any further leaks with master since the merge with wip-mon-leaks-fix.
- 10:28 AM Linux kernel client Bug #3519: rbd map hang during system startup
- https://raw.github.com/gist/4132395/7cb5f0150179b012429c6e57749120dd88616cce/gistfile1.txt
- 09:22 AM RADOS Bug #3515 (Resolved): mon: segfault when 'crush set' with different buckets with the same name
11/21/2012
- 10:19 PM Revision 189d073b (ceph): rgw: fix usage accounting
- bytes_sent and bytes_received are no longer accounted
in the req_state, needed to get them out of the ClientIO
object... - 09:27 PM Revision 5126bd70 (ceph): rbd: make snap purge fail if removing a snap fails
- Otherwise we report 100% removed when some may have failed.
Reported-by: Andrey Korolyov <andrey@xdel.ru>
Signed-off... - 09:12 PM Revision 6c1e2b66 (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit f86522cdfcd81b2d28c581ac8b8de6226bc8d1a4) - 09:11 PM Revision 17e4c0df (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
(cherry picked from commit 98a04d76ebffa61c3ba4b033cdd57ac57b2f29f3)... - 08:43 PM Linux kernel client Bug #3519 (Resolved): rbd map hang during system startup
- nick narrowed this down to 50-libceph_resubmit_linger_ops_when_pg_mapping_changes.patch on top of 3.5; everything els...
- 08:34 PM Revision 2b002a8d (ceph): Merge branch 'wip-java-enotdir'
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
Reviewed-by: Joe Buck <jbbuck@gmail.com> - 08:09 PM Revision 5c27bc42 (ceph): rgw: fix cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:09 PM Revision f40f715c (ceph): rgw: signal shuts down fcgi socket
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision 24fde547 (ceph): crypto: fix nss related leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision 7f221a58 (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:08 PM Revision b3b77b6c (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:04 PM Revision ddf377a4 (ceph): rgw: fix cleanup
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:00 PM Revision 820911b2 (ceph): msgr: use get_myaddr and set_myaddr to set the nonce
- We can't set it directly via get_myaddr as its a const ref. Dur.
Signed-off-by: Greg Farnum <greg@inktank.com> - 06:55 PM Revision c31f94d1 (ceph): set the nonce unconditionally on bind
- 05:48 PM Revision afd4da73 (ceph): doc: Added FAQ back into toc tree.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:34 PM Revision 0dbf6e89 (ceph): test_librbd_fsx: Add OP_FLATTEN
- 04:34 PM Revision 7021f1a2 (ceph): test_librbd_fsx: consume saved-image files as test runs
- Avoid consuming lots of disk space by holding only as many file
copies as needed (compare the n-2 file as we make clo... - 04:29 PM Revision ddcf2089 (ceph): workunit: fix indentation
- 03:44 PM rbd Bug #3518 (Can't reproduce): rbd import file --format 2 creates an image named '--format'
- obviously not what was desired, but moreover, not sure how to delete it
- 03:44 PM Revision ffd19b64 (ceph): run xfstests on 3 parallel clients
- 02:27 PM rgw Bug #3517: rgw: usage does not account bytes_received, bytes_sent
- Fixed by commit:189d073b2554ce32de7d6c759f03e08b25b3512e
- 02:08 PM rgw Bug #3517 (Resolved): rgw: usage does not account bytes_received, bytes_sent
- 11:31 AM rgw Bug #3516 (Resolved): POST /bucket/random throws a 500
- According to Yehuda this is making an init multipart upload request and something is triggering the 500. A 4xx is exp...
- 07:36 AM RADOS Bug #3515 (Resolved): mon: segfault when 'crush set' with different buckets with the same name
- Initially reported by user 'LeaChim' in IRC.
Tracked it down to CrushWrapper::insert_item() that will eventually e... - 12:41 AM Revision b35e37fb (ceph): osdc/Striper: fix handling for sparse reads in add_partial_sparse_result()
- If bl_map begins *after* the first item in buffer_extents, we want to
skip only the first buffer extent before doing ... - 12:30 AM Revision 328d72d7 (ceph): rgw: signal shuts down fcgi socket
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
11/20/2012
- 11:48 PM Revision ca086261 (ceph): xfstests: run in parallel on multiple machines
- xfstests itself still seems to have some global dependencies that
make it hard to run more than one instance per node... - 11:30 PM Revision 4eb50e68 (ceph): crypto: fix nss related leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 10:30 PM Linux kernel client Bug #3514 (Resolved): support 32-bit placement seed
- The current ceph_pg struct in the kernel uses 16 bits for the placement seed, limiting the total number of pgs.
- 09:57 PM Revision 1c50db6a (ceph): rgw-logsocket: a task to verify opslog socket works
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:57 PM Revision 26df886d (ceph): rgw-logsocket: a task to verify opslog socket works
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:55 PM Revision 436baa0b (ceph): java: add Java exception for ENOTDIR
- This specialization is useful in the Hadoop CephFS shim. An lstat may
return ENOTENT or ENOTDIR or some other IOExcep... - 09:53 PM Revision 700b5c00 (ceph): qa/run_xfstests.sh: drop tests 174 and 181
- These tests are showing intermittent failures so we'll drop them
from the default list for the time being.
Signed-of... - 09:48 PM Revision 8bb3a150 (ceph): rbd_xfstests: fix the test list, drop 181
- The main purpose of this was to eliminate test 181 from the list.
But I also found the test list that was there was b... - 09:12 PM Revision 57c8116c (ceph): doc: filename change to fix a link.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:21 PM Revision 15f77131 (ceph): doc: fixed links that broke due to new IA.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 04:57 PM Bug #2954: osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/25385282 bytes.
- also:...
- 04:40 PM Bug #2954 (In Progress): osd: scrub stat mismatch, got 18/19 objects, 14/15 clones, 22478527/2538...
- ubuntu@teuthology:/a/teuthology-2012-11-18_19:00:03-regression-master-testing-gcov/1220
2012-11-18 22:02:46.290679... - 04:52 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- er, commit:b35e37fb73c942c9be6c551d9c52d9507bc7fd7f
- 04:39 PM Bug #3428 (Resolved): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- commit:ba1e2cc68b236e2cd79dc2c5821ed47080746a86
- 03:53 PM Revision df3b1b89 (ceph): task/pexec: Output stderr to teuthology log
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 07:15 AM Bug #3513: rgw log show error
- It looks like you've put spaces in your command line, should be '--bucket=<bucket>' and not '--bucket = <bucket>', etc.
- 01:10 AM Revision f86522cd (ceph): rgw: fix xml parser leak
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:52 AM Revision 98a04d76 (ceph): rgw: fix memory leaks
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 12:44 AM Revision 394768bc (ceph): doc: Removed "deprecated" from toctree. Confused some users.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 12:34 AM Revision 739bca15 (ceph): doc: Removing old/unused images.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
11/19/2012
- 11:36 PM Bug #3513 (Resolved): rgw log show error
- hi ,
am using, ubuntu 12.04 lts operating with kernel version '3.2.0-23-generic'
and ceph version '0.52-958-gdb7c... - 04:33 PM Revision d516307d (ceph): task/ceph-fuse: Add log messages for abort
- Signed-off-by: Sam Lang <sam.lang@inktank.com>
- 04:33 PM devops Tasks #3512 (Closed): Publish our fastcgi packages
- Right now, our fastcgi packages are only available from a gitbuilder address. We should have a pretty-published set o...
- 04:04 PM Revision de12ae98 (ceph): Merge branch 'next'
- 03:49 PM Feature #3511 (New): figure out how to best set the heartbeat grace periods
- In Journal Club today we discussed failure detection, and we realized that while much of our failure detection has so...
- 03:06 PM Bug #3431 (Fix Under Review): ceph fuse crashed during fsx test
With the fixes in place, we now get an assertion on readx path during lru cache eviction. I've pushed proposed fix...- 02:48 PM Messengers Bug #3510 (Resolved): messenger doesn't fill in nonce if port is specified
- A user came into irc this morning have trouble getting rebooted OSDs into the cluster. Sam tracked it down to the dae...
- 02:00 PM Bug #3428 (In Progress): osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- 01:31 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- ...and this seems to reproduce it so far:
./test_librbd_fsx -d -W -R -p 10 -t 1 -S 4 -N 300 rbd fsx - 12:55 PM Bug #3428: osdc/Striper.cc: 275: FAILED assert(p->first == end - p->second.second)
- Running test_librbd_fsx I encountered this again (with master, including
the changes in wip-rbd-read):
272 read... - 01:49 PM Feature #3319 (Resolved): java: add unit test target with check:jni,nabounds options
- 01:49 PM CephFS Feature #3338 (Resolved): java: add unit tests for link/unlink/readlink/symlink
- 11:06 AM rgw Feature #3441 (Resolved): rgw: integrate with Keystone
- 11:06 AM rgw Feature #3343 (Resolved): rgw: stripe objects
- 11:06 AM rgw Feature #771 (Resolved): rgw: POST
- 11:06 AM rgw Feature #1717 (Resolved): rgw: support json input
- 05:20 AM Revision f8f452f3 (ceph): Merge remote-tracking branch 'gh/wip-mon-parsing' into next
Also available in: Atom