Project

General

Profile

Activity

From 02/17/2014 to 03/18/2014

03/18/2014

11:56 PM Revision 381850b1 (ceph): Merge pull request #1497 from dachary/wip-jerasure
remove gf-complete / jerasure sub modules
Reviewed-by: Sage Weil <sage@inktank.com>
Loïc Dachary
11:28 PM Revision e9eb641f (ceph): remove gf-complete / jerasure sub modules
and add the source files in the tree.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
10:59 PM Revision 8b77995f (ceph): Merge pull request #1494 from dachary/wip-gitmodule-mirrors
build: add gf-complete/jerasure to gitmodule_mirrors Sage Weil
10:47 PM Revision fdcf3eb4 (ceph): ReplicatedPG::do_op: delay if snapdir is unreadable
Since all we really need on a snapdir is the context, we really only
need it to be !missing. However, it might becom...
Samuel Just
10:26 PM Revision 362d370d (ceph): Merge pull request #1125 from ceph/wip-mon-docs
wip-mon-docs: Better explain required number of monitors & how to troubleshoot a monitor
Signed-off-by: Joao Eduardo...
João Eduardo Luís
10:23 PM Revision 7088885e (ceph): internal: ignore ext4 recovery msg
plana43 kernel: [ 21.179205] EXT4-fs (sda1): INFO: recovery required on readonly filesystem
is harmless.
Signed-o...
Sage Weil
10:19 PM Revision 6252d28d (ceph): distros: add wheezy
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:19 PM Revision 0bfc365d (ceph): distros: add rhel 6.4
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
10:02 PM Revision cb194770 (ceph): Merge pull request #20 from ceph/wip-distros
symlink all distros facets to a common set of 'supported' targets wusui
10:01 PM Revision 5679ae2a (ceph): Merge branch 'firefly'
Sage Weil
10:00 PM Revision 8e748c0c (ceph): ceph.conf: tolerate 500ms of clock drift (up from 250)
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:54 PM Revision 7f7a9988 (ceph): mds/Locker: fix null deref on cap import
The session Connection* may be NULL.
Fixes: #7708
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:28 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
Sage Weil
09:04 PM Revision 4221e0dd (ceph): build: add gf-complete/jerasure to gitmodule_mirrors
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
09:03 PM Revision a27ead67 (ceph): distros: add 14.04 to supported list
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:56 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
Yep. This particular object was written back in November, though, so it predates the fix by some time (and in fact m... Sage Weil
08:52 PM Bug #7779: osd: object file can have too many xattrs, get E2BIG
This exact bug is why we made the changes to xattr handling and no longer store unlimited numbers in the filesystem. ... Greg Farnum
06:44 PM Bug #7779 (Resolved): osd: object file can have too many xattrs, get E2BIG
if an object has too many xattrs on it, you get E2BIG from listxattr. one such object:... Sage Weil
08:55 PM Revision 8d4c4676 (ceph): distros: test rhel/centos 6.5 instead of 6.4
Sage Weil
08:44 PM Revision 25d04fba (ceph): osd: dump priority queue state on dequeue at level 30
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:39 PM Revision 99f4e9dd (ceph): symlink all distros facets to a common set of 'supported' targets
This makes it easier to maintain the supported/tested targets.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:22 PM Revision 4a3464ce (ceph): common/PrioritizedQueue: include first item's cost in dump
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:22 PM Revision ff11965c (ceph): osd: fix OpWQ dump locking
The pqueue is protected by the wq lock, not by qlock; for example, see
OpWQ::_enqueue. qlock protects the pg_for_pro...
Sage Weil
08:16 PM Revision 8bd89442 (ceph): common/PrioritizedQueue: fix remove_by_class() corner case
If i is the first entry, then setting cur = begin() sets us up to point at
something that we are about to delete. Mo...
Sage Weil
08:16 PM Revision de576d5b (ceph): common/PrioritizedQueue: constify a few things
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:09 PM Revision f1e3bc9a (ceph): doc/dev/cache-pool: describe the tiering agent
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:07 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
David Zafman
07:35 PM Revision d7284268 (ceph): PG::start_peering_interval: always send_notify if !primary
Otherwise, we might get into a situation where the primary
forgets about a stray pg. This is simpler and does not
in...
Samuel Just
07:29 PM Revision 77e46d0d (ceph): ReplicatedPG: don't skip missing if sentries is empty on pgls
Formerly, if sentries is empty, we skip missing. In general,
we need to continue adding items from missing until we ...
Samuel Just
07:09 PM Revision b4420ffb (ceph): PG::find_best_info: fix log_tail component
The previous logic should have kept the current best info if it found a
replica which best could log-recover, but p c...
Samuel Just
06:07 PM Revision 06bfdfc9 (ceph): Merge pull request #1491 from dachary/wip-submodules
erasure-code: jerasure and gf-complete moved to ceph namespace
Reviewed-by: Alfredo Deza <alfredo.deza@inktank.com>
Alfredo Deza
06:00 PM Revision 1ddae7e2 (ceph): erasure-code: jerasure and gf-complete moved to ceph namespace
for maintenance purposes
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
05:49 PM Revision f8632699 (ceph): Merge pull request #1490 from ceph/wip-6806
mon: Properly handle errors from 'cmd_getval()' when needed
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:35 PM Revision 652056ed (ceph): mon: Properly handle errors from 'cmd_getval()' when needed
Not handling the error return from cmd_getval() may leave uninitialzied
values, which can cause issues, specially wit...
Joao Eduardo Luis
04:35 PM Revision 074c8808 (ceph): mon: Monitor: handle invalid 'quorum' command argument
Don't rely on client side validation of possible command arguments.
Signed-off-by: Joao Eduardo Luis <joao.luis@inkt...
Joao Eduardo Luis
04:35 PM Revision 01a0f2d3 (ceph): mon: OSDMonitor: don't rely on client-side validation for command argum...
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
03:57 PM Bug #7776: client lockdep crash
ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137408 Samuel Just
03:03 PM Bug #7776 (Resolved): client lockdep crash
2014-03-18T14:50:40.839 INFO:teuthology.task.workunit.client.0.err:[10.214.131.15]: -3> 2014-03-18 14:48:00.14746... Samuel Just
03:45 PM Bug #7777 (Resolved): 2014-03-18T12:48:30.368 INFO:teuthology.task.rados.rados.0.err:[10.214.132....
is_missing_object(snapdir)->wait_for_unreadable
2014-03-18T12:48:27.770 INFO:teuthology.task.thrashosds.thrasher:T...
Samuel Just
02:47 PM Revision fcbacff7 (ceph): Merge pull request #1489 from dachary/wip-7757
erasure-code: disable SSE extensions
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
02:46 PM Revision 543c642b (ceph): erasure-code: disable SSE extensions
Until jerasure-2 / gf-complete is able to detect them at runtime.
http://tracker.ceph.com/issues/7757 refs #7757
Si...
Loïc Dachary
02:45 PM Revision bd12d376 (ceph): Merge pull request #1488 from dachary/wip-jerasure-2
erasure-code: update jerasure v2 submodule
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
02:32 PM rgw Bug #7702: osd thrashing + rgw = timeouts
this affects the dumpling-x/stress-split tests, and *would* affect rados thrashing if we had an rgw workload in there. Sage Weil
02:28 PM rgw Documentation #7434 (In Progress): rgw: doc user/group quota
I have a local branch where this is in progress. I'll try and put it up at the end of the week after I finish the rel... John Wilkins
02:25 PM Bug #7398: osd: ERANGE from clone
Seems that there is a stale ssc from a previous interval (?) mucking up the calc_clone_subsets process. Testing a br... Samuel Just
12:36 PM Bug #7398: osd: ERANGE from clone
ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137259/remote
With logging.
Samuel Just
01:54 PM Revision d7f3eb34 (ceph): knfs: make it a list
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:41 PM Bug #6633: osd: pgls vs osd restart/peering race misses objects
backported to dumpling. Sage Weil
12:40 PM rgw Feature #7774 (Resolved): rgw: cache decoded user and bucket info
Instead of having to access raw objects and then decode them for each request. Needs an invalidation mechanism that i... Yehuda Sadeh
12:34 PM Bug #7733: start_new_interval: always notify if !primary
Samuel Just
12:30 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
Samuel Just
12:30 PM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
Samuel Just
11:40 AM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
Samuel Just
12:05 PM Feature #7767 (Fix Under Review): messenger:buffer reads
Yehuda Sadeh
08:43 AM Feature #7767 (Resolved): messenger:buffer reads
The way we read message involves with multiple smallish reads, which can have a big performance impact. Need to buffe... Yehuda Sadeh
11:22 AM RADOS Feature #7770 (New): "ceph osd crush set" should handle ingestion of non-compiled crush maps
"ceph osd crush dump" will output a decompiled version of the crush map in a format of choice. It would be nice to be... Brian Andrus
10:49 AM Bug #6806 (Pending Backport): mon: audit cmd_getval() calls to make sure they handle failures cor...
Sage Weil
09:42 AM Bug #6806 (Fix Under Review): mon: audit cmd_getval() calls to make sure they handle failures cor...
Joao Eduardo Luis
10:39 AM Revision 1c5411a7 (ceph): erasure-code: update gf-complete v1 submodule
Point to https://bitbucket.org/dachary/gf-complete/branch/v1 which
aggregates the pending pull requests required by C...
Loïc Dachary
10:08 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
Yep, you need the xfs-dev headers to build Ceph now. Greg Farnum
01:45 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
invalidate this bug report Xinxin Shu
01:38 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
in order to avoid these errors, i think we should check xfs lib , not xfs header file Xinxin Shu
01:36 AM Bug #7756 (Rejected): cannot get through configuration when configure.ac check xfs.h
when i used configure.ac to config ceph, i get an error "configure: error: xfs/xfs.h not found (--without-libxfs to d... Xinxin Shu
09:24 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
Hi,
well, there is nothing else in dmesg, except several hours before this hang.
This servers are running about...
Olivier Bonvalet
09:07 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
Hi Olivier,
Can you attach the entire dmesg or at least a few minutes worth of
messages prior to the assertion fa...
Ilya Dryomov
09:00 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
and in a 3.13.5 kernel too :... Olivier Bonvalet
08:47 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
Hi,
same thing with a 3.13.5 kernel :...
Olivier Bonvalet
08:50 AM Revision d5e38d4a (ceph): erasure-code: update jerasure v2 submodule
to include the latest compilation warning fixes.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
08:17 AM Bug #7765: Bogus bandwidth statistics during pg creation
On the attachment, around 09:40 is some actual client I/O maxing out the cluster. Around 09:55 is where I start crea... John Spray
08:13 AM Bug #7765 (Can't reproduce): Bogus bandwidth statistics during pg creation

Noticed this while growing the number of PGs in an existing pool on a cluster running firefly branch....
John Spray
07:18 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
About the systemd not playing well with ceph-deploy, I am still doubtful because the way ceph-deploy is working with ... Alfredo Deza
07:00 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
I tried to replicate this with ceph-deploy and boy was it a nightmare to get there.
FC19 panics a few seconds afte...
Alfredo Deza
05:28 AM CephFS Feature #7764 (Resolved): InoTable/SessionMap/ manipulator (cephfs-table-tool)

Some bugs might create a situation where the metadata/journal may be okay but recovery fails because one of the glo...
John Spray
05:25 AM CephFS Feature #7763 (Resolved): journal-tool: import
Given a binary journal dump, insert it back into the metadata pool.
John Spray
05:23 AM CephFS Feature #7762 (Rejected): journal-tool: backwards-search after corrupt regions
When a corrupt region is encountered, use the start pointers to walk from the end of the log back to the latest valid... John Spray
05:22 AM CephFS Feature #7352: mds: make classes encode/decode-able
related, on journal-tool branch have got to a point where dencoder can handle getting the inodes out of .inode object... John Spray
05:20 AM CephFS Feature #7761 (Resolved): journal-tool: forwards-search through corrupt regions

When corruption is encountered, search forward byte by byte for the next sentinel word.
John Spray
05:18 AM CephFS Feature #7760 (Resolved): journal-tool: implement splice

Simple implementation based on new ENoOp event type that allows us to selectively blank out regions in existing log.
John Spray
05:17 AM CephFS Feature #7759 (Resolved): journal-tool: roll in resetter/dumper from MDS

To provide the capabilities in one convenient place and remove a few LOC from the MDS.
John Spray
05:15 AM CephFS Feature #7758 (Resolved): journal-tool: complete filtering
Already done:
--path
--range
Remaining to do:
--by-inode <inodeno>
--by-dirfrag <frag id>:[dentry]
--by-...
John Spray
03:56 AM Revision fb7b1f87 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:52 AM Revision 7bc9ade2 (ceph): Merge pull request #1384 from dachary/wip-7599
upgrade jerasure to version 2
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:51 AM Revision 390f57b4 (ceph): Merge pull request #1486 from ceph/wip-cli-err
ceph.in: Better error on bad arg to 'tell'
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Sage Weil
02:52 AM Feature #7757 (Resolved): erasure-code: enable jerasure-2 SSE optimizations
gf-complete, the library used by jerasure-2, decides to use SSE instructions based on CPU features found at compile t... Loïc Dachary
01:41 AM Revision e26ad135 (ceph): Merge pull request #1479 from ceph/wip-rados-outfile
tools/rados: Allow binary file output of omap data
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:39 AM Revision d0975d17 (ceph): Merge pull request #1480 from ceph/wip-remotebit-dump
mds: Fix remotebit::dump for less common types
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:26 AM Revision 29976607 (ceph): knfs: async export
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
01:08 AM Revision 1822a1cc (ceph): Merge pull request #229 from dachary/wip-ec-pool
ceph_manager: update ec_pool creation parameters Sage Weil

03/17/2014

11:48 PM Revision 6acfa6d6 (ceph): ceph_manager: update ec_pool creation parameters
As of https://github.com/ceph/ceph/pull/1477 the erasure code parameters
are controled via the osd erasure-code-profi...
Loïc Dachary
11:26 PM Revision 27ed6569 (ceph): Merge pull request #1477 from dachary/wip-erasure-code-profiles
replace properties with erasure code profiles
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:23 PM Revision 4f1b372e (ceph): osd: use erasure code profile when building the PGBackend
The PGBackend::build_pg_backend() prototype is modified to add an
OSDMapRef which is used to get the profile stored i...
Loïc Dachary
11:23 PM Revision 57743447 (ceph): mon: add crush ruleset name to osd pool create
The ruleset to be used for the new erasure coded pool was expected in
the properties, under the name crush_ruleset. I...
Loïc Dachary
11:23 PM Revision f8aa1eda (ceph): mon: set the profile and ruleset defaults early
The poolstr is removed from the prepare_pool_crush_ruleset prototype
because it no longer decides for the default rul...
Loïc Dachary
11:23 PM Revision 5c1db3b6 (ceph): osd: create erasure_code_profile in OSDMap::build_simple
The "default" erasure_code_profile is set by OSDMap::build_simple using
the osd_pool_default_erasure_code_profile def...
Loïc Dachary
11:23 PM Revision b85330eb (ceph): osd: create the erasure-code ruleset in OSDMap::build_simple
Using the "default" profile, add the matching erasure-code ruleset.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:23 PM Revision 8cf85f04 (ceph): mon: add osd crush create-erasure functional tests
Cleanup the TEST_crush_rule_all function from redundant leftovers.
Explicitly test crush rule rm instead of implicitl...
Loïc Dachary
11:23 PM Revision b2730118 (ceph): osd,mon: use profile instead of properties
The qa and functional tests are adapted to the new command prototype
requiring a profile instead of a list of propert...
Loïc Dachary
11:23 PM Revision eac224a4 (ceph): doc: update the erasure-code dev documentation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
11:23 PM Revision 063de51e (ceph): osd: obsolete pg_pool_t properties with erasure_code_profile
The generic map properties is only used for erasure code and should be
specialized. It is obsoleted by a string that ...
Loïc Dachary
11:23 PM Revision 173e9580 (ceph): mon: OSDMonitor use erasure_code_profile instead of properties
The prepare_pool_properties is replaced with the
parse_erasure_code_profile method which looks up the same content fr...
Loïc Dachary
11:23 PM Revision 04d2fd10 (ceph): mon: add the erasure-code-profile {set,get,rm,ls} MonCommand
"erasure-code-profile set" parses the key=value pairs given in argument
and stores them in OSDMap::erasure_code_profi...
Loïc Dachary
11:21 PM Revision fa1d957c (ceph): mon/Paxos: commit only after entire quorum acks
If a subset of the quorum accepts the proposal and we commit, we will start
sharing the new state. However, the mon ...
Sage Weil
11:19 PM Revision 1048763e (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
11:16 PM Revision a42e197f (ceph): rados/monthrash: add pool create/delete tests
This is sufficient to trigger #7736 when combined with mon thrashing and
mon msg delay injection.
Signed-off-by: Sag...
Sage Weil
11:11 PM Revision 2b90be2b (ceph): ceph_manager: default to 16 initial pgs per pool
1 is really too few for anything to happen at a
reasonable rate.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:11 PM Revision 847462b4 (ceph): ceph_manager::wait_for_clean: reset timeout if we make progress
Fixes: #7748
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:03 PM Revision 76beb5ce (ceph): Merge pull request #1487 from ceph/wip-7738
os/FileJournal: return errors on make_writeable() if reopen fails
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:37 PM Revision aed07440 (ceph): os/FileJournal: return errors on make_writeable() if reopen fails
This is why #7738 is resulting in a crash instead of an error.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
10:34 PM Revision c31f38c7 (ceph): ReplicatedPG: if !obc->obs->exists, lock snapdir obc if exists
Otherwise, backfill might slip in during a copyfrom.
Fixes: #7728
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:33 PM Revision 9ee10842 (ceph): ReplicatedPG: disallow trans which atomically create and remove an object
There are a few problems with such a transaction:
1) We don't really have a way to represent it in the log
2) How doe...
Samuel Just
09:48 PM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Hello Greg,
Can we backport this fix to dumpling?
Guang Yang
08:52 PM Feature #7599 (Resolved): erasure-code : upgrade to jerasure-2
Sage Weil
08:38 PM Bug #7755 (Resolved): auth_log selection depends on the primary identity and can cause a loop
calc_ec_acting assumes the first valid osd will be primary, this is not necessarily so with primary affinity. We can... Samuel Just
07:15 PM Revision f0944003 (ceph): Add file to store mirror location of module's.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
07:10 PM Revision a4261af7 (ceph): Merge pull request #227 from ceph/wip-7749
Pass '--object-sync-timeout 30' to radosgw-agent
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
07:00 PM Revision ef2edcd3 (ceph): Pass '--object-sync-timeout 30' to radosgw-agent
http://tracker.ceph.com/issues/7749
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
06:42 PM Revision 7f177b3a (ceph): Merge pull request #226 from ceph/wip-7714
prevent undefined values in finally block Zack Cerza
04:49 PM Revision ec362e89 (ceph): Merge pull request #1481 from ceph/wip-tmap2omap-warn
mds: avoid spurious TMAP2OMAP warning
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:33 PM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
Loïc Dachary
09:12 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
"work in progress":https://github.com/ceph/ceph/pull/1477 Loïc Dachary
04:22 PM Bug #7736 (Pending Backport): mon: can expose stale state
Sage Weil
03:29 PM Bug #7736: mon: can expose stale state
Sage Weil
04:45 AM Bug #7736: mon: can expose stale state
Joao Eduardo Luis
04:43 AM Bug #7736: mon: can expose stale state
This works for me.
Also noticed that a custom crafted message could trigger a commit with the old code. Apparentl...
Joao Eduardo Luis
04:21 PM Revision a9f8a9e4 (ceph): ceph.in: Better error on bad arg to 'tell'
Previously would get a rather enigmatic error:
UnboundLocalError: local variable 'ret' referenced before assignment...
John Spray
04:19 PM Revision 98e27d7b (ceph): Fix max_job_time timeout
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
04:12 PM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
Samuel Just
10:48 AM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
Samuel Just
04:04 PM Bug #7738 (Pending Backport): osd: journal crash on startup on wheezy
Sage Weil
04:04 PM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
Sage Weil
03:40 PM Bug #7738 (Fix Under Review): osd: journal crash on startup on wheezy
As far as I can tell the problem is that the journal symlink isn't always present when we reopen the journal for writ... Sage Weil
03:48 PM Revision 514b5e3e (ceph): mon: add helper to selection functions implementing tests
The call_TEST_functions will lookup SHARE_MON_TEST_* shell functions and
run them after creating a mon. Each is expec...
Loïc Dachary
03:48 PM Revision 1a451f2e (ceph): mon: functional tests teardown must be run on error
otherwise daemons will keep running and interfere with tests happening
afterwards.
Signed-off-by: Loic Dachary <loic...
Loïc Dachary
03:48 PM Revision e4b4b1f1 (ceph): osd: OSDMap::erasure_code_profile accessors
For both the incremental and the OSDMap fields.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
03:48 PM Revision c4f8f265 (ceph): osd: add OSDMap::erasure_code_profile
A map of key=value properties to be interpreted by the erasure code
plugins. For instance profile["default"] = { "k":...
Loïc Dachary
03:43 PM Revision bdd96c62 (ceph): mon/Elector: bootstrap on timeout
Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This...
Sage Weil
03:43 PM Revision a3e57b72 (ceph): mon: only learn peer addresses when monmap == 0
It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ...
Sage Weil
03:43 PM Revision 68fcc63c (ceph): mon: tell MonmapMonitor first about winning an election
It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i...
Sage Weil
03:43 PM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
Sage Weil
10:04 AM Bug #7713: "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:parallel-firef...
actually, the problem is probably that dumpling still has the bug. Sage Weil
10:03 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
this was #7709, now fixed Sage Weil
03:42 PM Revision 2b9bd267 (ceph): mds: avoid spurious TMAP2OMAP warning
The message "one or more OSDs do not support TMAP2OMAP" was printed
incorrectly when zero OSDs were up (and therefore...
John Spray
03:37 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
commit:5e7a98911e6a6db525d65981034d28065a045e47 Josh Durgin
03:28 PM Revision e073a062 (ceph): mon: tell MonmapMonitor first about winning an election
It is important in the bootstrap case that the very first paxos round
also codify the contents of the monmap itself i...
Sage Weil
03:28 PM Revision 143ec028 (ceph): mon/Elector: bootstrap on timeout
Currently if an election times out we call a new
election. If we have never joined a quorum, bootstrap
instead. This...
Sage Weil
03:27 PM Revision 21ed5420 (ceph): ceph.in: do not allow using 'tell' with interactive mode
This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult...
Joao Eduardo Luis
03:19 PM Revision 4f1a56ed (ceph): Merge pull request #1483 from ceph/wip-7611.emperor
mon: Monitor: make sure received command is valid before handling it
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:17 PM Revision 35aed15f (ceph): Merge pull request #1482 from ceph/wip-7611
ceph.in: do not allow using 'tell' with interactive mode
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:10 PM Revision 1996fd89 (ceph): mon: only learn peer addresses when monmap == 0
It is only safe to dynamically update the address for a peer mon in our
monmap if we are in the midst of the initial ...
Sage Weil
02:49 PM Revision d0fc52d9 (ceph): ceph.in: do not allow using 'tell' with interactive mode
This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult...
Joao Eduardo Luis
02:49 PM Revision 57c8fd96 (ceph): prevent undefined values in finally block
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
02:48 PM Revision 78d94cd1 (ceph): mon: Monitor: make sure received command is valid before handling it
Fixes: 7611
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Joao Eduardo Luis
02:48 PM Revision 7e9ece25 (ceph): Monitor: pull command mapping out of _allowed_command()
We want to be able to validate commands against both the leader and
local command sets, so make that functionality ge...
Greg Farnum
02:44 PM Revision e39c213c (ceph): ceph.in: do not allow using 'tell' with interactive mode
This avoids a lot of hassle when dealing with to whom tell each command
on interactive mode, and even more so if mult...
Joao Eduardo Luis
02:42 PM Revision 8f542dba (ceph): schedule_suite.sh: turn up journal log too
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:42 PM Revision d3c294d2 (ceph): Make distro kernels work on Trusty.
Some grub changes and package names caused them to fail on trusty.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
02:28 PM Revision b2af217b (ceph): mds: Fix remotebit::dump for less common types
This was hitting an assertion when used on anything
other than a regular/symlink/dir. Now covers
all types.
Signed-...
John Spray
01:56 PM Revision eb6cd3a6 (ceph): nkfs: 6h timeout of kernel build
Yes, NFS reexport is slow. But at the moment appears to be reliable.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:56 PM Revision 9d77ce17 (ceph): tools/rados: Allow binary file output of omap data
Extends getomapval and getompaheader to take an output
file argument the same way 'get' does. Removes misleading
'-o...
John Spray
01:53 PM rbd Feature #7746: Capacity Management: rbd df
Confirmed that this doesn't just affect RBD pools but affects any pool, as the data is generated from reading the off... Neil Levine
10:14 AM rbd Feature #7746 (Resolved): Capacity Management: rbd df
Currently, ceph df shows two sets of statistics: global and pool.
For global, the output is generated from aggrega...
Neil Levine
01:22 PM Bug #7751 (Closed): os: LevelDBStore: needs to check iter->status() during get()
We are ignoring the status of the iterator during 'LevelDBStore::get()' -- we're also ignoring the state of the itera... Joao Eduardo Luis
01:04 PM CephFS Bug #7750 (Can't reproduce): Attempting to mount a kNFS export of a sub-directory of a CephFS fil...
Hi,
I have run into the following issue when trying to export a subset of a CephFS filesystem via NFS:
Machine ...
David McBride
01:03 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
This looks like network issues - the run was killed, so there are no logs from radosgw to confirm. Josh Durgin
01:00 PM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
Fixed in teuthology commit:ef2edcd3a96a2118d793b7a102688f60fa100f52 Josh Durgin
11:58 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
A different approach: https://github.com/ceph/teuthology/pull/227 Zack Cerza
11:23 AM rgw Bug #7749 (Fix Under Review): radosgw-agent: worker.DataWorker.wait_for_object() should bail on r...
Zack Cerza
11:22 AM rgw Bug #7749: radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests.ConnectionE...
https://github.com/ceph/radosgw-agent/pull/9 Zack Cerza
11:16 AM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
Currently, the method will do this forever if a connection goes down:... Zack Cerza
10:40 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
Samuel Just
10:09 AM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
whitelisted this Sage Weil
10:03 AM Feature #7717: Per CRUSH bucket used/available space
Neil Levine
09:22 AM Fix #6780 (Closed): monitor errors when checking for quorum status
Joao Eduardo Luis
09:13 AM Fix #6780: monitor errors when checking for quorum status
can no longer reproduce this on firefly. any objections on closing? Joao Eduardo Luis
08:48 AM Revision d4d6ff07 (ceph): mon,osd,erasure-code: update copyright notices
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:48 AM Revision bcc74879 (ceph): common,erasure-code,mon: s/erasure-code-//
The parameters to erasure code do not need to be prefixed with the
erasure-code- string. There only are erasure-code ...
Loïc Dachary
08:48 AM Revision de62572c (ceph): erasure-code: remove dependency to the global context
Instead of relying on derr to display error messages, add them to an
ostream parameter given in argument to load() an...
Loïc Dachary
08:48 AM Revision e6d9066f (ceph): erasure-code: add ostream to factory()
Modify calls to ErasureCodePlugin::factory() to provide the new
ostream argument.
Signed-off-by: Loic Dachary <loic@...
Loïc Dachary
08:48 AM Revision be319983 (ceph): erasure-code: make libcommon include liberasure-code
So that it can be used in OSDMap which is part of libcommon.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
08:48 AM Revision 6a16eac7 (ceph): mon: create crush_ruleset_create_erasure helper
Move the code bloc verbatim, from "osd crush rule create-erasure" to the
new crush_ruleset_create_erasure() method he...
Loïc Dachary
08:48 AM Revision 402e646a (ceph): mon: crush_ruleset_create_erasure reduce verbosity
Only add error message to the stream, not informative messages because
they depend on the caller context.
Signed-off...
Loïc Dachary
08:48 AM Revision 8e07dbc0 (ceph): mon: crush_ruleset_create_erasure error codes
Replace goto reply with error return and meaningfull error codes.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
08:48 AM Revision 370e000e (ceph): mon: crush_ruleset_create_erasure set ruleset
Use get_rule_id() instead of rule_exists() to test the existence of a
ruleset and preserve the ruleset.
Signed-off-b...
Loïc Dachary
08:48 AM Revision 96224883 (ceph): mon: crush_ruleset_create_erasure s/rule/err/
Avoid using rule instead of ruleset to help clarify the
terminology. Using err instead is also clearer in the context...
Loïc Dachary
08:48 AM Revision 3bc607ae (ceph): mon: crush_ruleset_create_erasure indent
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:48 AM Revision 9850ab27 (ceph): mon: crush_ruleset_create_erasure s/_map//
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:48 AM Revision cf259461 (ceph): mon: create-erasure uses crush_ruleset_create_erasure
Create the ruleset and branch depending on the result:
* If it succeeds, wait
* If it already exists and is pending ...
Loïc Dachary
08:48 AM Revision 32e122bd (ceph): mon: add pool name to prepare_pool_crush_ruleset
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:48 AM Revision b7db487a (ceph): mon: pool create erasure implicit ruleset creation
If the crush_ruleset parameter is missing, set it to the pool name.
If the crush_ruleset parameter is set to a name ...
Loïc Dachary
08:48 AM Revision 29862f6f (ceph): mon: tests for pool create erasure implicit ruleset creation
* Remove the tests checking that a missing or wrong crush_ruleset
parameters triggered an error.
* Add a test check...
Loïc Dachary
08:19 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
Sage Weil
08:00 AM Bug #7611 (Fix Under Review): All mon nodes crash when running "ceph tell osd.X" and using the "v...
Joao Eduardo Luis

03/16/2014

07:57 PM Revision bf7f773b (ceph): Merge pull request #1462 from ceph/wip-cache-last-epoch-clean
mon: fix caching for min_last_epoch_clean
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
07:12 PM Revision ce9bfb87 (ceph): Merge pull request #1474 from ceph/wip-7740
OSD::handle_pg_query: on dne pg, send lb=hobject_t() if deleting
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:32 PM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
31a667918069ac72c70080dcacd6ff3b6d58f07b David Zafman
04:37 PM Revision 2f9a7484 (ceph): Merge pull request #1473 from ceph/wip-7719
PG: clear want_pg_temp in clear_primary_state only if primary
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:26 PM Feature #7662 (In Progress): add a "ec profiles" map to OSDMap
Loïc Dachary
10:36 AM Feature #7662 (Fix Under Review): add a "ec profiles" map to OSDMap
*ABANDONNED* "work in progress":https://github.com/ceph/ceph/pull/1475
I've set it to urgent so someone can decide...
Loïc Dachary
12:54 PM Bug #7744 (Can't reproduce): osd: assert(last_e.version.version < e.version.version)
I currently have 2 OSDs that won't start and it's preventing my
cluster from running my VMs.
My cluster is running ...
Kevinsky Dy
12:11 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
Sage Weil
12:10 PM rgw Bug #7743 (Can't reproduce): Max retries exceeded with url: /admin/opstate?client-id=radosgw-agen...
ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133582... Sage Weil
12:09 PM rgw Bug #7742 (Resolved): FAIL: s3tests.functional.test_s3.test_region_bucket_create_master_access_re...
ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587
this may be a dup of the...
Sage Weil
12:08 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
ubuntu@teuthology:/a/teuthology-2014-03-15_23:00:27-rgw-firefly-distro-basic-plana/133587... Sage Weil
09:36 AM Bug #7719 (Resolved): failed to become clean
Sage Weil
04:47 AM Revision e9a3c8e2 (ceph): Merge pull request #1471 from ceph/wip-7684
client: force getattr when inline data is missing
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:42 AM Revision 1ae33147 (ceph): client: force getattr when inline data is missing
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
02:39 AM Revision 4fdeafef (ceph): Merge pull request #1467 from ceph/wip-7684
Wip 7684
http://pulpito.ceph.com/sage-2014-03-15_09:12:44-fs-wip-7684-testing-basic-plana
Reviewed-by: Sage Weil <s...
Sage Weil
12:58 AM Revision 04de7817 (ceph): OSD::handle_pg_query: on dne pg, send lb=hobject_t() if deleting
We will set lb=hobject_t() if we resurrect the pg. In that case,
we need to have sent that to the primary before han...
Samuel Just

03/15/2014

10:30 PM Revision 4dd94a00 (ceph): Merge pull request #1469 from ceph/wip-7718
PG::issue_repop: only adjust peer_info last_updates if not temp
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
10:29 PM Revision 677b30c3 (ceph): Merge pull request #1468 from ceph/wip-7732
PG::build_might_have_unfound: check pg_whomai, not osd whoami
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
08:58 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-15_17:09:08-rados:thrash-firefly-distro-basic-plana... Sage Weil
08:16 PM Revision affcc119 (ceph): Merge pull request #1470 from ceph/wip-7712
osd/ReplicatedPG: fix enqueue_front race
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
07:39 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
Sage Weil
06:12 PM Revision 2c875593 (ceph): multimds: fix misc -> fs/misc paths
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:39 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
Samuel Just
05:07 PM Bug #7736 (Fix Under Review): mon: can expose stale state
Sage Weil
02:15 PM Bug #7736: mon: can expose stale state
This *is* committed state. Looks like we need to wait for everybody to ack or for leases to expire before responding ... Greg Farnum
09:52 AM Bug #7736 (Resolved): mon: can expose stale state
teuthology-2014-03-14_19:00:49-rados-dumpling-testing-basic-plana/130941
here is a deletion on the primary:...
Sage Weil
04:55 PM Revision 9e218402 (ceph): mds: include inline data in lock messages
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
04:54 PM Revision 5b3422a6 (ceph): mds: fix corner case of pushing inline data
Following sequence of events can happen.
- Client releases an inode, queues cap release message.
- A 'lookup' reply...
Yan, Zheng
04:18 PM Revision 75971726 (ceph): upgrade/dumpling-x/stress-split: tolerate legacy crush tunables
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:17 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
Yehuda Sadeh
03:30 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
Sage Weil
03:30 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
Sage Weil
11:15 AM CephFS Bug #7739 (Resolved): mds: uninitialized field in message
ubuntu@teuthology:/a/teuthology-2014-03-14_23:01:36-multimds-master-testing-basic-plana/131675
hard to map this to...
Sage Weil
10:10 AM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
ubuntu@teuthology:/a/sage-wheezy/130813... Sage Weil
10:09 AM Bug #7737 (Resolved): osd: deletes vs backfill makes degraded go negative
this is the tail end of a rados bench run that was outpacing backfill. once it started to delete objects, the degrad... Sage Weil
04:52 AM Revision b2fcc6e1 (ceph): Remove code duplication from s3 tests.
A new module, s3_utilities.pm has been created. It contains
subroutines common to at least two of the workunits in t...
Warren Usui
01:00 AM Revision 979e8b44 (ceph): PG::build_might_have_unfound: check pg_whomai, not osd whoami
Otherwise, we might skip (2,0) when we are (2,1).
Fixes: #7732
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
12:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
I'm 90% sure this is systemd killing everything in the cgroup when ceph-deploy's ssh session closes. The log file ju... Sage Weil

03/14/2014

11:32 PM Revision 0f75c541 (ceph): osd/ReplicatedPG: fix enqueue_front race
When requeuing and item at the front, we need to shuffle the items in
pg_for_processing if there is an entry for this...
Sage Weil
10:53 PM Revision 5322ecb2 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
John Wilkins
10:52 PM Revision ef1d7c91 (ceph): rados.py: Fixed docstring syntax warnings.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
10:49 PM Revision f476c968 (ceph): Merge pull request #19 from ceph/wip-print
added print task
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
10:46 PM Revision 02b746d4 (ceph): doc: Fixed release notes syntax warnings.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
10:46 PM Revision 752380dc (ceph): added print task
Yuri Weinstein
10:45 PM Revision 9cd67bb2 (ceph): doc: Fixed hyperlink.
Fixes: #7558
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
John Wilkins
10:26 PM Revision c6214f86 (ceph): Merge pull request #1463 from ceph/wip-7698
Reviewed-by: Samuel Just <sam.just@inktank.com> David Zafman
10:19 PM Revision 31a66791 (ceph): tools: Fix ceph_filestore_dump to fully operate on EC pools
Add spg_t and ghobject_t handling
Fixes: #7698
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
10:19 PM Revision 599a8d7f (ceph): test: Add ceph_filestore_dump.sh to test ceph_filestore_dump
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
10:18 PM Revision f633a03e (ceph): tools: Cleanups in ceph_filestore_dump
Fix usage output of ceph_filestore_dump
Add missing error checking
Output full object name
Improve message consistenc...
David Zafman
09:48 PM Revision bbc0d6dd (ceph): PG::issue_repop: only adjust peer_info last_updates if not temp
Temp object repops have version eversion_t() since they don't
actually send log entries. Updating the last_updates h...
Samuel Just
08:30 PM Revision 35f1b042 (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload...
Danny Al-Gaaf
08:29 PM Revision 0a0c1caf (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload...
Danny Al-Gaaf
08:29 PM Revision be0205c3 (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload...
Danny Al-Gaaf
08:26 PM Bug #7735: osd: priorityqueue debug dump crashes
wip-pq Sage Weil
08:21 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
discovered when doing backfill testing with wip-pq:... Mark Nelson
08:23 PM Revision ab91b808 (ceph): mon/OSDMonitor: fix fall-thru case
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:21 PM Revision 0e0a9dbf (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
08:20 PM Revision 208959a0 (ceph): mon/PGMap: cache min_last_epoch_clean
We call this a lot. Only recalculate when we decode or when we apply
an incremental.
Adjust unit test accordingly.
...
Sage Weil
08:20 PM Revision fc850751 (ceph): mon/PGMap: only recalculate min_last_epoch_clean if incremental touches...
If the Incremental updates a value that used to equal the old min, we may
have raised it and need to recalculate it a...
Sage Weil
08:19 PM Revision e941feff (ceph): unittest_ceph_argparse: fix warnings
In file included from test/ceph_argparse.cc:17:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::Assertion...
Sage Weil
08:19 PM Revision 6f9db6c7 (ceph): unittest_mon_pgmap: fix warnings
In file included from test/mon/PGMap.cc:15:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::AssertionResu...
Sage Weil
08:15 PM Revision f2c6ff33 (ceph): tools/: make filenames consistent
_ for source files, - for (shippable) build targets.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:11 PM Revision f2ac06bf (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140312'
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
08:09 PM Revision e3300978 (ceph): PG: clear want_pg_temp in clear_primary_state only if primary
Clearing it in that way in on_shutdown() can cause a stray
shard to clobber the want_pg_temp value created by the pri...
Samuel Just
08:04 PM Revision 74ad3e30 (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140409'
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
06:42 PM Revision 5873b0f0 (ceph): Merge remote-tracking branch 'gh/wip-da-SCA-firefly-20140304'
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
06:36 PM Revision 984f1c3d (ceph): Merge pull request #1454 from ceph/wip-7709
osd/ReplicatedPG: release op locks on on commit+applied
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by:...
Sage Weil
06:28 PM Revision bb755167 (ceph): Merge pull request #1459 from ceph/wip-7696
Wip 7696
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:16 PM Revision da159f8c (ceph): doc/release-notes: note that radosgw's should be upgraded together
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:05 PM Revision a2f3b309 (ceph): Merge pull request #1461 from ceph/wip-7692
mon: on timecheck on monmap 0
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
Sage Weil
06:03 PM Revision a3719e0a (ceph): Merge pull request #1460 from ceph/wip-warning
PGLog: remove unused variable
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:03 PM Bug #7732: stuck recovering with unfound -- build_might_have_unfound bug
Samuel Just
05:58 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
Samuel Just
06:02 PM Revision f1bd59f8 (ceph): mon: only do timecheck with known monmap
If we are still on monmap epoch 0, our mon ranks cannot yet be trusted
since there is not yet a shared source of trut...
Sage Weil
06:00 PM Revision fba88de1 (ceph): ceph-mon: be a bit more verbose on error
Motivated by #7489
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:59 PM Bug #7733 (Resolved): start_new_interval: always notify if !primary
Samuel Just
05:57 PM Revision 62af51cb (ceph): PG::activate: handle peer contigious with primary, but not auth_log
The added case covers a situation where a replica is not contiguous with
the auth_log, but is contiguous with the pri...
Samuel Just
05:51 PM Revision 6aa5d4f1 (ceph): Merge pull request #1458 from ceph/wip-7489
ceph_mon: split postfork() in two and finish postfork just before daemonize
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:45 PM Revision 70d87df7 (ceph): ceph_mon: output error message if unable to bind.
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
05:44 PM Revision 5ad9c166 (ceph): ceph_mon: all output after initial fork go to dout/derr
We were doing it in some cases, and not doing in some other cases. Just
do it throughout.
Signed-off-by: Joao Eduar...
Joao Eduardo Luis
05:39 PM Revision c95234ac (ceph): ceph_mon: split postfork() in two and finish postfork just before daemo...
We split global_init_postfork() in two: start and finish, with the first
keeping much of postfork()'s tasks except cl...
Joao Eduardo Luis
05:29 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
I grabbed and compiled the patched version of FastCGI as a DSO from here:
https://github.com/ceph/mod_fastcgi.git
...
Neil Soman
05:03 PM rgw Bug #7730: Content-length should not required for initiate multipart upload
I'm not sure we actually require it. You're not using the modified fastcgi module and therefore chunked encoding is n... Yehuda Sadeh
03:52 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
We are using the S3 SDK and I am getting a return from RGW claiming that Content-Length must be set. However, accordi... Neil Soman
05:05 PM rbd Bug #7577: rbd info displays extra random char in block prefix
Dan Mick wrote:
> I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is t...
Danny Al-Gaaf
04:52 PM Bug #7712: osd: ENOENT following copy-from
it looks like the requeues get in all sorts of weird orders:
grep --color=auto 3\\.2\( remote/*/log/*osd.5* | egre...
Sage Weil
04:45 PM Bug #7712: osd: ENOENT following copy-from
grep dequeue_op remote/*/log/*osd.5* | grep plana2926152-290
osd.5.3:79 and osd.1.3:681 get reordered
when they...
Sage Weil
10:33 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
2014-03-14T09:47:00.894 INFO:teuthology.task.rados.rados.0.out:[10.214.131.11]: 2625: delete oid 290 current snap is ... Sage Weil
04:36 PM Bug #7659 (In Progress): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing()....
David Zafman
04:20 PM rgw Documentation #7731 (Resolved): Warning about "rgw print continue" should be added to radosgw con...
Here,
http://ceph.com/docs/dumpling/radosgw/config/
Just as there is a warning to turn off FastCgiWrapper on Ce...
Neil Soman
03:59 PM Documentation #6465: admin/build-doc should have some kind of build check for broken links
Actually, it seems like the :ref: syntax at least catches a file name mismatch. We should probably begin converting t... John Wilkins
03:57 PM Documentation #7558 (Resolved): broken link in install/manual-deployment/
Fixed. The file name was incorrect. Probably should be using :ref: syntax instead. John Wilkins
03:31 PM Revision 22c461b5 (ceph): upgrade/dumpling-x: more mon scrub whitelist
There are two log messages; whitelist them both
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
03:30 PM Revision 5676d6e5 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:29 PM Revision ceac36b2 (ceph): doc/release-notes: 0.78 draft nodes; firefly draft notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:21 PM Revision 2e487d8a (ceph): knfs: test v3 and v4
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:13 PM Documentation #7729 (Closed): CAPS with dot (.) notation can be unquoted
Authentication documentation should indicate that CAPS with dot notation do not have to be quoted any longer.
htt...
John Wilkins
03:10 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
Sage Weil
01:28 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
... Sage Weil
02:51 PM Bug #7728 (Resolved): osd/ReplicatedPG.cc: 4999: FAILED assert(got)

ceph version 0.77-859-g0bf5b52 (0bf5b52ae035d9893b5d079abee05bb3114ef51e)
1: (ReplicatedPG::finish_ctx(Replicate...
Samuel Just
02:47 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
Samuel Just
02:46 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
issue_repop sets the last_update for stored peer_info to repop->v which is eversion_t() for temp objects. Testing fix. Samuel Just
12:58 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
... Sage Weil
02:37 PM Feature #7698: Add EC handling to ceph_filestore_dump
Ready to go into either master or firefly branches. David Zafman
02:17 PM Documentation #7727 (Resolved): CRUSH "chassis" bucket type
We should note that there is a new "chassis" default bucket type. It might go here:
http://ceph.com/docs/master/ra...
John Wilkins
02:09 PM Documentation #7726 (Resolved): Quick Start Requires Updating
With size = 3 by default, the cluster as defined by the quick start guide will never get to an active + clean state u... John Wilkins
02:06 PM Documentation #7725 (Resolved): osd pool default size need updating
The default value for size is now 3.
http://ceph.com/docs/master/rados/configuration/pool-pg-config-ref/
John Wilkins
02:04 PM Documentation #7724: filestore xattr use omap removed
It's a good idea to doc it, but in general we don't support reverting versions and should not give the appearance of ... Greg Farnum
02:01 PM Documentation #7724 (Resolved): filestore xattr use omap removed
Ceph Documentation needs to indicate that filestore xattr use omap was removed and specify the version. Users reverti... John Wilkins
01:59 PM Feature #7723 (New): Cancel RADOS Bench writes and still do reads
Right now in RADOS bench if you write some data out with the --no-cleanup flag but ctrl+c or kill the process before ... Mark Nelson
01:55 PM devops Cleanup #7722 (Resolved): Make /admin/build-doc distro independent
The script for building Ceph documentation under admin/build-doc is currently Debian/Ubuntu only. This limits communi... John Wilkins
01:52 PM Documentation #7721 (Closed): Document the process to migrate from RBD format 1 to format 2 images
There is a mention of that in the RBD man page, but I think we should also document it on ceph.com with some warning ... Alexandre Marangone
01:08 PM Bug #7719 (Resolved): failed to become clean
Stuck in remapped due to deleted pg shard clobbering want_pg_temp from primary.
2014-03-14T08:07:26.245 INFO:teuth...
Samuel Just
01:00 PM rbd Bug #6480: librbd crashed qemu-system-x86_64
Still getting these crashes multiple times a week across a dozen guests on separate hosts. These guests are video sur... Mike Dawson
12:51 PM Feature #7717 (Closed): Per CRUSH bucket used/available space
When using multiple pools spread across different failure domains it can be difficult to know how much space is avail... Alexandre Marangone
12:30 PM devops Feature #7716 (Resolved): Build debug packages for EL6
The debug packages for el6 are not available for releases >0.67.3.
http://ceph.com/rpm-dumpling/el6/x86_64/
http:...
Alexandre Marangone
12:07 PM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---... Yuri Weinstein
11:51 AM Bug #7216 (Can't reproduce): ASSERT AuthMonitor::update_from_paxos on 0.72.2
Joao Eduardo Luis
09:43 AM Bug #7216 (New): ASSERT AuthMonitor::update_from_paxos on 0.72.2
Ian Colle
11:35 AM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
Sage Weil
11:28 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
Sage Weil
11:22 AM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-13_19:33:10-upgrade:dumpling-x:parallel-firefly---... Yuri Weinstein
11:05 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
Sage Weil
05:50 AM Bug #7692: mon: monitor fails to form quorum
We are now seeing a more generalized failure were no monitor is able to form quorum (from ceph-deploy):... Alfredo Deza
10:51 AM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
Sage Weil
06:02 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
Here's the thing: as is, ceph-mon is being run as a daemon. That entails dissociating it from its running terminal, ... Joao Eduardo Luis
05:10 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
Tools like 'ceph-mon' are used by other tools to abstract ceph management and those tools will almost always check ex... Alfredo Deza
04:48 AM Bug #7489: `ceph-mon` is silent after non-zero exit status
This only happens when the monitor is running as a daemon, which I would think is the expected result: all output is ... Joao Eduardo Luis
10:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
Sage Weil
09:59 AM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
Sage Weil
09:57 AM Bug #7576: osd: large skew in pg epochs (dumpling)
That doesn't seem like it's addressing the issue the right way. We've deliberately set it so that PGs which don't get... Greg Farnum
09:40 AM Bug #7576: osd: large skew in pg epochs (dumpling)
How about this: in OSDService, add
Mutex pg_epoch_lock;
Cond pg_epoch_cond;
multiset<epoch_t> pg_epochs;
ma...
Sage Weil
09:50 AM Fix #7711 (New): OpTracker output doesn't include op size for subops
Been discussing the OpTracker dumps on the mailing list and realized the subops don't contain transaction size inform... Greg Farnum
09:49 AM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
d0d21fae483cfaf5556b18b2f0e113c7d418e90c Landed to Firefly Ian Colle
09:44 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
Sage Weil
09:44 AM Bug #7626 (New): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
Ian Colle
09:42 AM Bug #7497 (Can't reproduce): timeout waiting to go clean
Ian Colle
09:34 AM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
I think we need a log for this.. hopefully we will hit it now that things are cranked up on the nightlies? Sage Weil
09:21 AM Bug #7710 (Fix Under Review): Multiple rados bench instance will overwrite the metadata object
Ian Colle
06:53 AM Bug #7710: Multiple rados bench instance will overwrite the metadata object
Please help to review the pull request - https://github.com/ceph/ceph/pull/1457 Guang Yang
06:48 AM Bug #7710 (Resolved): Multiple rados bench instance will overwrite the metadata object
rados bench is useful to benchmark the cluster, however, there is one user case it does not support: read after write... Guang Yang
07:45 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
So don't forget the patch I got accepted into libvirt a few weeks ago.
If you are running a RBD storage pool it wi...
Wido den Hollander
05:02 AM Revision 87c911ce (ceph): osd/ReplicatedPG: release op locks on on commit+applied
We were releasing the op locks when we applied the update but (potentially)
before we committed it. This means that ...
Sage Weil
04:37 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
Zheng Yan
02:12 AM Revision b125c95f (ceph): Merge pull request #18 from ceph/wip-knfs-fsstress
knfs: add fsstress and kernel build Sage Weil
01:34 AM Revision 4773a277 (ceph): knfs: add fsstress and kernel build
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:14 AM Revision 4f43e53c (ceph): Merge pull request #1450 from ceph/wip-7641
debian: make ceph depend on ceph-common >= 0.67
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
12:42 AM Revision e1694b4c (ceph): knfs: restructure a bit
Separate cluster buildup from tasks.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
12:39 AM Revision 7b0eda03 (ceph): nfs -> knfs
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:38 AM Revision c5b557ee (ceph): qa/workunits: misc -> fs/misc
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:36 AM Revision adca6464 (ceph): workunits/misc -> fs/misc
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

03/13/2014

11:44 PM Revision 8c8b3e97 (ceph): PGLog: remove unused variable
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:43 PM Revision 89c3d97c (ceph): Merge pull request #1442 from ceph/wip-magic-bad
osd: tunables instead of hard-coded target dirty/full ratios
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil
11:38 PM Revision fa6887b9 (ceph): osd: set default cache_target_{dirty,full}_ratios based on configurable
These were hard-coded in the pg_pool_t constructor, but that was a dumb
idea.
Note that decoding legacy pg_pool_t's ...
Sage Weil
11:38 PM Revision 282497e8 (ceph): osd: add tunables for cache_min_{flush,evict}_age
Why not.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
11:27 PM Revision 8b4c8cbf (ceph): upgrade/dumpling-x: whitelist mon scrub mismatch
A mixed dumpling/firefly cluster will have each mon independently encode
the full map. Firefly now puts feature bits...
Sage Weil
11:24 PM Revision c452de17 (ceph): Merge pull request #1452 from ceph/wip-7706
Wip 7706
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
10:53 PM Revision d0d21fae (ceph): Merge pull request #1447 from ceph/wip-7703
rgw: manifest hold the actual bucket used for tail objects
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
10:41 PM Bug #7709 (Fix Under Review): osd: RWORDERED does not order reads ack vs write commit
Sage Weil
10:02 PM Bug #7709: osd: RWORDERED does not order reads ack vs write commit
Sage Weil
09:58 PM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
We just fixed ceph_test_rados to wait for commit, not ack. It turns out that the RWORDERED flag is ordering a
wr...
Sage Weil
10:17 PM Revision a72b636b (ceph): mds: fix empty fs rstat
In 81bcf43080a7be8a48aa13b88287cbfac0e01e3e we removed the .ceph directory
but did not adjust the rsubdirs back to 0....
Sage Weil
10:15 PM Revision 5ec49360 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
09:57 PM Revision 2bbf5511 (ceph): ceph_test_rados: wait for commit, not ack
First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha...
Sage Weil
09:55 PM Revision 6c3d4fbe (ceph): ceph_test_rados: wait for commit, not ack
First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha...
Sage Weil
09:52 PM Revision eaf0cdc4 (ceph): Merge pull request #1449 from ceph/wip-7705
ceph_test_rados: wait for commit not ack
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Greg Farnum <g...
Sage Weil
09:49 PM Revision f2124c58 (ceph): ceph_test_rados: wait for commit, not ack
First, this is what we wanted in the first place
Second, if we wait for ACK, we may look at a user_version value tha...
Sage Weil
09:49 PM Revision dd946e0a (ceph): MOSDOp: include reassert_version in print
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:10 PM Bug #7498 (Resolved): stuck in recovery
Sage Weil
09:09 PM Bug #7210: mon: does not validate snapshot removal commands
I would like to see this in the wild before doing the backport. Sage Weil
09:08 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
Jasper Siero wrote:
> I submitted the new log with debug mon = 10 added to the ceph.conf.
> The two processes belo...
Sage Weil
05:09 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
I submitted the new log with debug mon = 10 added to the ceph.conf.
The two processes below also keeps running afte...
Jasper Siero
09:07 PM Revision 73f6b4cb (ceph): config_opts: raise ms_pq_max_tokens_per_priority to 16MB
Recovery messages can get pretty big.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
09:04 PM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
Sage Weil
09:04 PM Revision 2722a0a4 (ceph): PrioritizedQueue: cap costs at max_tokens_per_subqueue
Otherwise, you can get a recovery op in the queue which has a cost
higher than the max token value. It won't get ser...
Samuel Just
09:01 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
... Sage Weil
08:28 PM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
... Zheng Yan
11:01 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
And again:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_23:00:26-fs-firefly-testing-basic-plana/127977/...
Greg Farnum
08:15 PM Revision d72335fe (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
06:33 PM Revision 724f30e8 (ceph): client: Add lookup_parent & lookup_name
Exposing the CEPH_MDS_OP_LOOKUPPARENT and
recently added CEPH_MDS_OP_LOOKUPNAME operations.
lookup_ino and lookup_pa...
John Spray
06:33 PM Revision d2ce0294 (ceph): libcephfs: add ceph_ll_lookup_inode
This is a wrapper to lookup_ino, lookup_parent
and lookup_name, to provide the
caller with the requested inode and it...
John Spray
06:33 PM Revision 88cb1c49 (ceph): tools: Create ceph-client-debug
For exposing test/dev functionality which uses
the cephfs client interface.
Initially just provides lookup-by-ino.
...
John Spray
06:30 PM Revision f1f28268 (ceph): mds: Return EINVAL for parent lookup on root ino
This was the behaviour before 8d6b25a1, and distinguishes
the general failure to find a parent (ESTALE) from the spec...
John Spray
06:25 PM Revision a19ef011 (ceph): rgw: manifest hold the actual bucket used for tail objects
Fixes: 7703
Object can be copied between different buckets, so we need to keep track
of which bucket is used for nami...
Yehuda Sadeh
06:24 PM Revision 33b889f3 (ceph): rbd-fuse: fix signed/unsigned warning
rbd_fuse/rbd-fuse.c: In function 'enumerate_images':
rbd_fuse/rbd-fuse.c:113:2: warning: comparison between signed an...
Sage Weil
05:48 PM Revision c973e46c (ceph): mds/Mutation.h: init export_dir with NULL in ctor
CID 1188167 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "export_d...
Danny Al-Gaaf
05:39 PM Revision fd383a95 (ceph): mds/Migrator.h: init some members of import_state_t in ctor
CID 1188166 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "state" is...
Danny Al-Gaaf
05:30 PM Revision 5a53aa82 (ceph): mds/Migrator.h: init some export_state_t members in ctor
CID 1188165 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "state" is...
Danny Al-Gaaf
04:59 PM Revision b10692fb (ceph): CInode::encode_cap_message: add assert for cap
CID 716913 (#1 of 1): Dereference after null check (FORWARD_NULL)
5. var_deref_op: Dereferencing null pointer "cap".
...
Danny Al-Gaaf
04:50 PM Revision 2daed5ff (ceph): test-upgrade-firefly: skip watch-notify system test
This also fails on mixed version clusters due to watch on a
non-existent object returning ENOENT in firefly and 0 in ...
Josh Durgin
04:35 PM Bug #7648 (Won't Fix): ceph-mon corner case denial of service
This only works on osd.0; for other osds, both dumpling and emperor behave (with bogus output)... Sage Weil
04:28 PM Bug #7706 (Pending Backport): osd: PrioritizedQueue can starve
Sage Weil
01:58 PM Bug #7706 (Resolved): osd: PrioritizedQueue can starve
starvation caused by pq max token limit Samuel Just
04:27 PM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
Sage Weil
09:30 AM Bug #7704 (In Progress): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-...
I think this is a manifestation of the full osdmap encoding features, which aren't specified for dumpling and can thu... Sage Weil
08:59 AM Bug #7704: "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-plana suite
Also see in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---... Yuri Weinstein
08:55 AM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_17:27:09-upgrade:dumpling-x:parallel-firefly---... Yuri Weinstein
04:21 PM Revision 58e35a4b (ceph): test_filejournal.cc: use strncpy and terminate with '\0'
CID 966632 (#1 of 1): Copy into fixed size buffer (STRING_OVERFLOW)
2. fixed_size_dest: You might overrun the 200 by...
Danny Al-Gaaf
04:10 PM Bug #7635 (Duplicate): failed to recover before timeout expired
Samuel Just
03:44 PM Revision 0073bc25 (ceph): Merge pull request #1433 from fractalcat/fix-crypto-init-race-condition
Work around race condition in libnss
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:40 PM Revision bc7aa221 (ceph): Merge pull request #1443 from fghaas/doc-fix
doc: fix formatting on PG recommendation
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:32 PM Bug #7208 (Resolved): CEPH_FEATURE_CRUSH_V2 feature mismatch
this was fixed when i fixed up the default crush tunables to be firefly not optimal Sage Weil
03:27 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats
Sage Weil
06:53 AM CephFS Bug #7565: Failed assert in check_rstats
ubuntu@teuthology:/a/teuthology-2014-03-12_04:55:11-multimds-master-testing-basic-plana/127691
failed on trivial_s...
Sage Weil
02:59 PM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
Sage Weil
11:39 AM Bug #7705: ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong version")
wip-7705 Sage Weil
10:01 AM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
... Sage Weil
02:22 PM Revision 44aaaaff (ceph): Work around race condition in libnss
This change prevents a segfault in ceph::crypto::init when using NSS and
calling rados_connect from multiple threads ...
Sharif Olorin
02:22 PM Revision a2784baa (ceph): Add unit test for race condition in libnss
This isn't in test/crypto.cc because common_init_finish is called prior
to running any tests. Will not build the test...
Sharif Olorin
01:14 PM devops Feature #7239: ceph-deploy: install cephfs java bindings
I deployed Ceph to a cluster that I intended to run Hadoop on. In this case, a typical setup is to have the cephfs cl... Noah Watkins
12:51 PM devops Feature #7239 (Need More Info): ceph-deploy: install cephfs java bindings
Could you please elaborate why you think ceph-deploy should be in charge of installing a dependency like java binding... Alfredo Deza
01:10 PM Revision fe8a715c (ceph): Make the configuration "filestore merge threshold" can be negative whic...
1. We are trying to create the PG folder up to several levels with a standalone tool to prevent it from runtime split... Guang Yang
11:54 AM devops Bug #7598 (Need More Info): ceph-disk-activate error with ceph-deploy
I can't replicate this behavior *at all*. I do know why that is the error that comes about though.
What happens is...
Alfredo Deza
11:20 AM rgw Bug #7703 (Fix Under Review): rgw: fail to copy object > 512k between buckets
Yehuda Sadeh
10:35 AM Revision 27f06346 (ceph): doc: fix formatting on PG recommendation
Previous commit (047287afbe0ddfaaafd05e9dbf25c1c7dea9a1be) broke
formatting on the formula, and also made mixed formu...
Florian Haas
10:21 AM Revision 7cf81ce2 (ceph): libcephfs/test.cc: shutdown cmount at end of MountNonExist
CID 966624 (#5 of 5): Resource leak (RESOURCE_LEAK)
17. leaked_storage: Variable "cmount" going out of scope leaks t...
Danny Al-Gaaf
10:00 AM rgw Bug #7702 (Need More Info): osd thrashing + rgw = timeouts
Sage Weil
09:41 AM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
Sage Weil
09:40 AM Bug #7260 (Can't reproduce): rados api test LibRadosList.ListObjectsNS failed
reopen if we see this now that the enumerator/iterator changes are in place Sage Weil
09:38 AM Bug #7259 (Resolved): ceph mon crash in master branch
Sage Weil
08:48 AM Revision 269cf138 (ceph): libcephfs/test.cc: shutdown cmount
CID 743410 (#17 of 17): Resource leak (RESOURCE_LEAK)
65. leaked_storage: Variable "cmount" going out of scope leaks...
Danny Al-Gaaf
08:03 AM Revision 94acb6b3 (ceph): test_librbd.cc: add missing va_end() to test_ls_pp
CID 1054877 (#1 of 1): Missing varargs init or cleanup (VARARGS)
17. missing_va_end: va_end was not called for "ap"....
Danny Al-Gaaf
06:49 AM Revision fb4ca940 (ceph): mailmap: Danny Al-Gaaf name normalization
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
06:29 AM Bug #7593: Disk saturation during PG folder splitting
Thanks Sage very much for the comments.
To begin with, I propose a change here - https://github.com/ceph/ceph/pull...
Guang Yang
04:32 AM Revision fb8ff445 (ceph): doc/release-notes: note that WATCH can get ENOENT now
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:30 AM Revision 90a21d8c (ceph): qa/workunit/rados/test-upgrade-firefly: skip watch-notify test
A watch on a non-existent object now returns ENOENT in firefly; skip this
test as it will fail on a hybrid or upgrade...
Sage Weil
01:33 AM Revision fce63aa8 (ceph): Merge pull request #1440 from ceph/wip-7649
Wip 7649
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
12:09 AM Revision b5d2df4a (ceph): Merge pull request #1441 from ceph/wip-7671
Wip 7671
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil

03/12/2014

11:26 PM Revision 2cbad1b1 (ceph): test/librados/watch_notify: create foo before watching
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:26 PM Revision 9d549eb2 (ceph): test/system/st_rados_watch: expect ENOENT for watch on non-existent object
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:45 PM Revision a5235956 (ceph): Merge pull request #1439 from ceph/wip-7682
ReplicatedPG::already_(complete|ack) should skip temp object ops
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
10:37 PM Revision efdee0d3 (ceph): upgrade/dumpling-x: upgrade final client node for final test
This means the final workloads are running firefly code.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:56 PM Revision b23a141d (ceph): RGWListBucketMultiparts: init max_uploads/default_max with 0
CID 717377 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "max_upload...
Danny Al-Gaaf
09:49 PM Revision 7fb5e146 (ceph): upgrade/dumpling-x: full librados tests after full upgrade
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:37 PM Revision 4057a306 (ceph): AbstractWrite: initialize m_snap_seq with 0
CID 717223 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_snap_seq...
Danny Al-Gaaf
09:07 PM Revision 90a2654f (ceph): ReplicatedPG::already_(complete|ack) should skip temp object ops
We clearly won't get dup ops on these repops, and they don't
have meaningful versions since they don't carry log
entr...
Samuel Just
09:02 PM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
This fails due to issue #7703. Yehuda Sadeh
08:59 PM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
The new manifest does not hold bucket marker info which is needed, as when we're copying object between buckets we ne... Yehuda Sadeh
08:03 PM Revision 72bc1ef8 (ceph): AdminSocket: initialize m_getdescs_hook in the constructor
CID 717212 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_getdesc...
Danny Al-Gaaf
07:27 PM Revision f7529cf4 (ceph): RGWPutCORS_ObjStore_S3::get_params: check data before dereference
CID 1063697 (#1 of 1): Explicit null dereferenced (FORWARD_NULL)
5. var_deref_model: Passing null pointer "data" to ...
Danny Al-Gaaf
07:09 PM Revision 5334d5c8 (ceph): mds/Server.cc: check straydn before dereference
ID 1019554 (#1 of 1): Dereference after null check (FORWARD_NULL)
13. var_deref_model: Passing null pointer "straydn...
Danny Al-Gaaf
07:05 PM Revision f6b3a0b7 (ceph): Merge pull request #1423 from fractalcat/respect-python-env
Update Python hashbang to respect environment Sage Weil
06:57 PM Revision 45f54539 (ceph): Merge pull request #1434 from ceph/wip-7695
build-doc: fix checks for required commands for non-debian
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:55 PM Revision bbc228fc (ceph): Merge pull request #1438 from fghaas/doc-fix
doc: Add "nearest power of two" to PG rule-of-thumb
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:51 PM Revision 047287af (ceph): doc: Add "nearest power of two" to PG rule-of-thumb
Following an IRC discussion, it emerged that it would be helpful
to explain the merit of choosing a number of PGs per...
Florian Haas
06:37 PM Bug #7696: osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
Samuel Just
10:07 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
Primary and replica disagree on last_backfill for some reason.
-3> 2014-03-12 03:31:58.711369 7feaff6c9700 10 ...
Samuel Just
06:32 PM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
Samuel Just
06:09 PM Revision 7bb03598 (ceph): OSDMonitor::prepare_pool_op: add missing break in case
CID 1191886 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This case (value 34) is not termin...
Danny Al-Gaaf
05:46 PM Revision bcd41c0f (ceph): Merge pull request #1436 from ceph/wip-7681
ECBackend: when removing the temp obj, use the right shard
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:44 PM Revision f52af306 (ceph): Merge pull request #1437 from ceph/wip-7650
tools/rados/rados.cc: use write_full for sync_write for ec pools
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:38 PM Revision a4a91ccd (ceph): PG: do not wait for flushed before activation
This should reduce the sting of the previous commit somewhat. We wait
for the activation transactions to clear prior...
Samuel Just
05:38 PM Revision a576eb32 (ceph): PG: do not serve requests until replicas have activated
There are two problems:
1) We choose the min last_update amoung peers with the max local-les
value as an upper bound ...
Samuel Just
05:34 PM Revision 980d2b59 (ceph): ECBackend: when removing the temp obj, use the right shard
Introduced in d0b1094ff7b98ef9262ecb45ee8324853003a77c
Fixes: #7681
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
05:32 PM Bug #7626 (Need More Info): After updating ceph from 0.75 to 0.77 one of the three monitors can't...
Sage Weil
05:28 PM Revision dc00661d (ceph): osd_types: print lb if incomplete even if empty
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
05:09 PM Revision 8e76e4e4 (ceph): build-doc: fix checks for required commands for non-debian
Fixes: 7695
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf
05:09 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
Sage Weil
04:50 PM Revision 85e7f4d8 (ceph): Merge pull request #1412 from ceph/wip-libxfs-flag
FileStore: support compiling without libxfs
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
04:04 PM rgw Bug #7702 (Resolved): osd thrashing + rgw = timeouts
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl... Yuri Weinstein
03:57 PM Revision 1ccabd80 (ceph): lock: allow -a with --brief
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:45 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
Sage Weil
02:12 PM Bug #7682: osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first == repop->v)
Samuel Just
02:46 PM Feature #7701 (Resolved): Filterable querying interface for PGMonitor

On larger clusters with 100,000s or millions of PGs, dumping everything for external tools becomes inefficient.
...
John Spray
02:38 PM Feature #7700 (New): Create a health severity between OK and WARN

I think the name we liked best so far was NOTICE.
For each WARN "health check" a la #7192, reconsider its severi...
John Spray
02:04 PM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-12_01:35:02-upgrade:dumpling-x:stress-split-firefl... Yuri Weinstein
01:25 PM rbd Bug #7577: rbd info displays extra random char in block prefix
I'm not working on this, just calling imprecations from the bleachers. :) I think the issue is that, if the string ... Dan Mick
09:55 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Dan van der Ster wrote:
> Danny Al-Gaaf wrote:
> > Dan van der Ster wrote:
> > > The other solution would be to co...
Danny Al-Gaaf
09:32 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Danny Al-Gaaf wrote:
> Dan van der Ster wrote:
> > The other solution would be to copy block_name_prefix to a local...
Dan van der Ster
09:29 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Dan van der Ster wrote:
> The other solution would be to copy block_name_prefix to a local null terminated in the fu...
Danny Al-Gaaf
09:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
The other solution would be to copy block_name_prefix to a local null terminated in the function where it is printed ... Dan van der Ster
09:20 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Do you take a look at it (or do you have already a fix?) or should I?
The problem is that block_name_prefix in rbd...
Danny Al-Gaaf
09:08 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Yeah, but I think it's data-dependent; must be max len and not have a zero byte directly after... Dan Mick
03:17 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Dan Mick wrote:
> Why I feel some guilt here: :)
>
> commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
> Author: D...
Danny Al-Gaaf
03:05 AM rbd Bug #7577: rbd info displays extra random char in block prefix
I just rebuilt from current git dumpling head on my machine -- cannot reproduce. So I wonder this is something subtle... Dan van der Ster
01:24 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a...
Neil Soman
01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
Neil Soman wrote:
> So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a...
Neil Soman
01:21 PM rgw Bug #7502: S3 API - deleting object always returns 204 regardless of object is existing or not
So I actually don't think this is a bug. AWS now returns 204 unconditionally. In fact, you get a 204 even if you atte... Neil Soman
11:57 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
Sage Weil
09:50 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
./admin/build-doc runs even if e.g. ditaa or ant isn't installed on the system. The script part checking for the bina... Danny Al-Gaaf
11:31 AM Feature #7192: An easier-to-process health report
This sounds great to me. I assume we'd keep the 'detail' section as optional as it can get quite (!) big. Sage Weil
11:02 AM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
David Zafman
10:46 AM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
Sage Weil
10:45 AM Bug #7256 (Duplicate): ceph osd crashed at ReplicatedPG::trim_object on next
Samuel Just
10:44 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
Sage Weil
10:06 AM Feature #7662: add a "ec profiles" map to OSDMap
s/properties/ec profile/g Loïc Dachary
09:24 AM rbd Bug #7693 (Closed): virsh domblkinfo fails with 'Bad file descriptor'
Found that the 'domblkinfo' command fails while 'domblklist' and 'domblkstat' commands function normally.
## Envir...
Michael Kidd
06:35 AM Bug #7692: mon: monitor fails to form quorum
at first glance, problem has nothing to do with the 0.0.0.0 ip.
This looks like it's early deployment, therefore t...
Joao Eduardo Luis
06:09 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
For some reason it is looking at 0.0.0.0 and of course that fails:... Alfredo Deza
04:54 AM Revision c55da14a (ceph): Merge pull request #1362 from dachary/wip-7548
doc: erasure coded pool developer and operations documentation
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:41 AM Revision 01a93a2a (ceph): Merge pull request #1425 from ceph/wip-rbd-fuse-enumerate
rbd-fuse: fix enumerate_images() image names buffer size issue
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:38 AM Revision 9987e486 (ceph): Merge pull request #1424 from fractalcat/thread-safety-doc-update
rados_connect not thread-safe when using nss (documentation)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:33 AM Revision 32fdca6d (ceph): Merge pull request #1411 from ceph/wip-7076-dumpling
dumpling backport of watchers check for rbd_remove() Sage Weil
04:30 AM Revision e3f8dd03 (ceph): Merge pull request #1419 from ceph/wip-doc-prereq
doc: update build prerequisites Sage Weil
04:29 AM Revision 004bf3b2 (ceph): Merge pull request #1415 from ceph/wip-build-doc
doc: release-process documentation updates
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:25 AM Revision bd2defb9 (ceph): Merge pull request #1409 from enovance/wip-brag
ceph-brag enhancements
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:22 AM Revision dc82cd78 (ceph): debian: make ceph depend on ceph-common >= 0.67
The older versions of ceph-common (ceph CLI, in particular) can't talk to
newer clusters. The primary change happene...
Sage Weil
04:11 AM Revision d5442a57 (ceph): multimds: new (separate) suite for multi-mds tests
Eventually we can merge this into the fs suite, but for now it is useful
to segregate the test cases.
Start with a d...
Sage Weil
04:07 AM Revision 88efa65e (ceph): Revert "fs/basic: multimds"
This reverts commit aea501beb744dd6f6ec2b60678cefc7fae6761b0.
Let's put this in a separate subdir for now. It won't...
Sage Weil
02:23 AM Revision f1840bce (ceph): Merge pull request #1427 from ceph/wip-6889
rgw: don't log system requests in usage log
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:20 AM Revision b70db7e7 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
02:16 AM Revision a18cd6dd (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
02:16 AM Revision cfbbcf7c (ceph): upgrade/dumpling-x/stress-split: use dumpling workunits
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:04 AM Revision bfbfcf84 (ceph): Merge pull request #1422 from salehe/docfix-1
rados.py: fix typo in Ioctx::read() docstring Sage Weil
01:54 AM Revision b455846d (ceph): Handle newer btrfstools.
Newer btfs userland tools needs a -f like xfs instead of a prompt
for yes. Trusty needs this change.
Signed-off-by: ...
Sandon Van Ness
01:48 AM Revision e5b65b45 (ceph): Merge pull request #222 from ceph/wip-trusty
Handle newer btrfstools. wusui
01:23 AM Revision a890ef09 (ceph): Merge pull request #1432 from ceph/wip-7687
rgw: don't overwrite bucket entry data when syncing user stats
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:19 AM Revision d5737107 (ceph): rgw: don't overwrite bucket entry data when syncing user stats
Fixes: #7687
When syncing user bucket stats we overwritten the entire entry with the
passed in entry. We should only ...
Yehuda Sadeh
01:15 AM Revision a5a94ae3 (ceph): Handle newer btrfstools.
Newer btfs userland tools needs a -f like xfs instead of a prompt
for yes. Trusty needs this change.
Signed-off-by: ...
Sandon Van Ness
01:13 AM CephFS Bug #1318: directories disappear across multiple rsyncs
please check if there was file recovery involved (MDCache::do_file_recover ) Zheng Yan
01:11 AM Revision c0b1c107 (ceph): Merge pull request #16 from ceph/wip-hint-tests
rados/singleton-nomsgr: add allocation hint test
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
01:09 AM Revision d72c2bbc (ceph): Merge pull request #1400 from ceph/wip-hint-tests
wip-hint-tests
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:03 AM Revision 2fbd7720 (ceph): qa/workunits/cephtool/test.sh: fix thrash (more)
If I have to touch this again I will remove it. Ugh. This time,
ubuntu@teuthology:/var/lib/teuthworker/archive/teu...
Sage Weil

03/11/2014

11:38 PM Revision a459c4e2 (ceph): Merge pull request #1417 from ceph/wip-7663
Wip 7663
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:05 PM Revision 0b31cf48 (ceph): Merge pull request #1416 from ceph/wip-div
More log handling fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:02 PM Revision f4196cc3 (ceph): doc/release-notes: firefly draft release notes
Some updates; still incomplete.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
11:02 PM Revision 64a6b26b (ceph): doc/release-notes: fill in some firefly history
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:00 PM Revision 1a9f6c32 (ceph): Merge pull request #17 from ceph/wip-final_load_fix
fixed final_load problem wusui
10:40 PM Revision 72094a85 (ceph): fixed final_load problem
Yuri Weinstein
08:55 PM Revision 1c611330 (ceph): radosbench: cleanup will probably take longer than writing the objects
With thrashing, cleanup will require recovering the degraded objects
first, while the initial write out doesn't since...
Samuel Just
07:30 PM devops Bug #7641 (Fix Under Review): packaging: ceph upgrade from cuttlefish to emperor is incomplete
It's sort of the other way around. ceph doesn't depend on version of the stuff in ceph-common at all, but ceph-commo... Sage Weil
07:24 PM Bug #7689: librados: ENOENT on ioctx create
downgrading thsi weirdness until i see it again Sage Weil
06:05 PM Bug #7689: librados: ENOENT on ioctx create
actually, no mon_command creating the pool appears in the logs. does not jive with the teuthology log. Sage Weil
04:54 PM Bug #7689 (Duplicate): librados: ENOENT on ioctx create
I think this is a race with pool creation, mon quorum changes, and new client startup getting a not-quite-fresh osdma... Sage Weil
07:23 PM rgw Bug #6889 (Pending Backport): rgw: usage log: don't log system user operations
Sage Weil
09:31 AM rgw Bug #6889 (Fix Under Review): rgw: usage log: don't log system user operations
Yehuda Sadeh
07:15 PM Revision 24774a81 (ceph): osd/ReplicatedPG: fix typo
This is the object count, not the dirty object count. Broken by
00bf3b56743830a4a9c5d6765946a4e68f530c57.
Reported-...
Sage Weil
07:11 PM Revision 728bd3c5 (ceph): upgrade/dumpling-x: upgrade mon before osd
The MDS needs to see the TMAP2OMAP feature bit in the osdmap. THe mons
have to encode the feature bits passed by the...
Sage Weil
06:43 PM Revision 28a1d77a (ceph): Merge pull request #1430 from ceph/wip-7674
osd/ReplicatedPG: do not include hit_set objects in full calculation
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
06:22 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
Sage Weil
06:14 PM rgw Bug #7687 (Fix Under Review): rgw: bucket creation time is not set
Yehuda Sadeh
06:09 PM rgw Bug #7687: rgw: bucket creation time is not set
actually it's set, but then it's overwritten. Yehuda Sadeh
03:09 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
Yehuda Sadeh
06:20 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
7635 Sage Weil
06:19 PM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
fixed by teuthology commit:57259b54beb746b31b70bb3a92de18d604002b0a Sage Weil
06:15 PM Bug #7631 (In Progress): command 'dump_ops_in_flight' not found
David Zafman
06:14 PM Revision 3d5a4b5a (ceph): ReplicatedPG: CEPH_OSD_OP_WATCH return -ENOENT if !obs.exists
Fixes: #7671
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
06:10 PM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
Samuel Just
05:53 PM Revision 00bf3b56 (ceph): osd/ReplicatedPG: do not include hit_set objects in full calculation
If we have a low target and there are hit_set objects (which cannot be
evicted), we can get stuck in a full state and...
Sage Weil
05:23 PM Revision f57121ac (ceph): Merge pull request #1418 from ceph/wip-7672
PG::choose_acting: filter CRUSH_ITEM_NONE out of have
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:18 PM Revision 18d80656 (ceph): Merge pull request #1429 from ceph/wip-7592-final
Wip 7592 final
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:17 PM Bug #7682 (In Progress): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->fir...
David Zafman
12:59 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124761/teutholog... David Zafman
05:04 PM Revision 9df52611 (ceph): Merge pull request #1428 from ceph/wip-is_down-boolean
OSDMap: clarify is_{down,in}() definitions
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:00 PM Revision 59834d60 (ceph): Merge pull request #1410 from ceph/wip-flock
mds: fix owner check of file lock
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:59 PM Revision 0752f284 (ceph): Merge pull request #1385 from ceph/wip-nfs-export
mds: introduce LOOKUPNAME MDS request
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:51 PM Revision 1836b6c7 (ceph): osd: hit_set_persist(): Verify all objects aren't degraded
Fixes: #7592
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
04:41 PM Revision a9a826ad (ceph): Merge pull request #220 from ceph/wip-print
Add print task. wusui
04:41 PM Bug #7688 (Won't Fix): warn at fs/btrfs/extent-tree.c:5748 __btrfs_free_extent+0x9ce/0xa20
... Sage Weil
04:38 PM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
Sage Weil
01:01 PM Bug #7663 (Fix Under Review): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10....
Samuel Just
04:37 PM Revision 42ef8ba5 (ceph): rgw: don't log system requests in usage log
Fixes: 6889
System requets should not be logged in the usage log.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
04:17 PM devops Bug #7617: ceph-deploy uninstall should document why it doesn't remove all relevant packages
The problem is that qemu-kvm depends on librbd1, and if you remove the latter, that means removing the former. That ... Dan Mick
04:13 PM Revision 6700dd06 (ceph): rgw: off-by-one in rgw_trim_whitespace()
Fixes: #7543
Backport: dumpling
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Ray Lv <raylv@yahoo-in...
Ray Lv
04:11 PM rbd Bug #7577: rbd info displays extra random char in block prefix
Why I feel some guilt here: :)
commit 9a45ffb769c7c821196a8471009d0f9a4216c0d4
Author: Dan Mick <dan.mick@inktank...
Dan Mick
04:10 PM rbd Bug #7577: rbd info displays extra random char in block prefix
True, I don't see any attempt to add a nul. Oddly, it looks like there was half a plan to do so in librbd/internal.c... Dan Mick
01:18 PM rbd Bug #7577: rbd info displays extra random char in block prefix
I'm not current on my c++, but I'm pretty sure Danny's correct. Looking at the code, rbd.cc just does a cout of the 2... Dan van der Ster
01:13 PM rbd Bug #7577: rbd info displays extra random char in block prefix
Sent this in email, but: u007f sounds like maybe a 0x7f character?.. Which should be legal 7-bit ASCII, but perhaps i... Dan Mick
07:22 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Here's a bit more with json format:
{"name":"volume-f529978c-0981-4eba-a5b5-7ba8ecc05e1b","size":5368709120,"objec...
Dan van der Ster
06:40 AM rbd Bug #7577: rbd info displays extra random char in block prefix
So this is not a recent regression. I can reproduce on el6.5 with 0.67-0
[root@dvtest1 ceph]# ceph --version
ce...
Dan van der Ster
06:24 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Dan van der Ster wrote:
> My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu di...
Dan van der Ster
06:23 AM rbd Bug #7577: rbd info displays extra random char in block prefix
My earlier diagnsis 0.67.4 vs 0.67.7 was incorrect -- actually that was a el6 vs ubuntu difference.
On my ubuntu 0...
Dan van der Ster
04:11 AM rbd Bug #7577: rbd info displays extra random char in block prefix
Tried to reproduce, but couldn't. Looks to me like missing '\0' termination. Do you get this from all of your 0.67.7 ... Danny Al-Gaaf
04:11 PM Revision 406ff0b7 (ceph): OSDMap: clarify is_{down,in}() definitions
Make it clear that is_down() == !is_up() and is_in() == !is_out().
This is not a functional change.
Signed-off-by: I...
Ilya Dryomov
04:05 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
Sage Weil
01:03 PM Bug #7658 (Fix Under Review): PGLog: _merge_object_divergent_entries: fix the case where prior_ve...
Samuel Just
04:05 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
Sage Weil
01:04 PM Bug #7657 (Fix Under Review): PGLog: fix proc_replica_log divergent entry selection
Samuel Just
03:15 PM rgw Bug #7676 (Fix Under Review): rgw: multi-part upload incompatible with EC backend
Yehuda Sadeh
03:13 PM Bug #7635: failed to recover before timeout expired
It did eventually recover, as it turns out.
2014-03-06 05:40:41.795123 mon.0 10.214.132.32:6789/0 521 : [INF] pgmap ...
Samuel Just
03:02 PM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
Sage Weil
12:07 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
commit:b4fbe4f81348be74c654f3dae1c20a961b99c895 and a later commit fixed feature forwarding, which is needed for the ... Sage Weil
12:04 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
... Sage Weil
10:09 AM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
ubuntu@teuthology:/a/teuthology-2014-03-10_10:33:21-upgrade:dumpling-x:parallel-firefly---basic-plana/124951
mds r...
Sage Weil
03:00 PM Bug #7686 (Duplicate): osd spinning in agent_work
Sage Weil
02:37 PM Bug #7686: osd spinning in agent_work
agent_entry() is hitting a case where there appears to be work to do, but we never evict a hit set archive. In the l... David Zafman
02:08 PM Bug #7686: osd spinning in agent_work
FYI, this was/is on burnupiX after setting an OSD out and bringing it back in. Mark Nelson
02:05 PM Bug #7686 (Duplicate): osd spinning in agent_work
Probably related to the num_dirty/archived hitset issue?
2014-03-11 16:05:15.959964 7fc99340a700 20 osd.0 212 agen...
Samuel Just
02:44 PM devops Feature #7047 (Resolved): rhel7: build process for rbd.ko, ceph.ko kernel modules
The kmods are built as a part of the Red Hat kmod packaging (#6986) at https://github.com/ceph/ceph-kmod-rpm
Speci...
Ken Dreyer
02:40 PM Bug #7681: osd/SnapMapper.cc: 270: FAILED assert(check(oid))
Samuel Just
12:52 PM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))

http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-10_02:30:02-rados-firefly-testing-basic-plana/124677/teuthol...
David Zafman
02:21 PM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
Sage Weil
02:21 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
Sage Weil
09:07 AM rgw Bug #7375: s3_user_quota.pl fails
Sage Weil
02:20 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
Sage Weil
09:07 AM rgw Bug #7374: s3_multipart_upload.pl fails
Sage Weil
02:01 PM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
Samuel Just
02:00 PM Revision fe4ad291 (ceph): rbd-fuse: fix enumerate_images() image names buffer size issue
Image names buffer is fixed at 1024. This turns out to be not enough:
there are at least two "rbd-fuse rbd_list: err...
Ilya Dryomov
01:59 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
Samuel Just
01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
I've turned up the timeout in the tests. Samuel Just
01:59 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
The non-ec ones are probably just an inadequate timeout -- the cleanup is likely to take longer than the writeout. T... Samuel Just
01:57 PM CephFS Bug #7685 (Can't reproduce): hung/failed teuthology test: cfuse_workunit_misc
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_23:00:50-fs-firefly-testing-basic-plana/122094
http://qa-p...
Greg Farnum
01:46 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_23:00:25-fs-firefly-testing-basic-plana/124157/
The teut...
Greg Farnum
01:37 PM Bug #7093 (Resolved): osd: peering can send messages prior to auth
Backported to Emperor and Dumpling Ian Colle
01:35 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Samuel Just
01:31 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
Samuel Just
01:24 PM Bug #5823 (Can't reproduce): cpu load on cluster node is very high, client can't get data on pg ...
Samuel Just
01:20 PM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
can you please rerun the monitor with 'debug mon = 10' and attach the resulting log Joao Eduardo Luis
01:20 PM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
Samuel Just
01:11 PM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
Samuel Just
01:10 PM Bug #7611 (In Progress): All mon nodes crash when running "ceph tell osd.X" and using the "versio...
Joao Eduardo Luis
11:43 AM Bug #7674 (Resolved): Cache pool configuration stalls
Sage Weil
11:00 AM Bug #7674 (Fix Under Review): Cache pool configuration stalls
Sage Weil
10:44 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
No, subusers are useful for S3 as well. Maybe this was by accident, but I'm relying on it already in production, for ... Robin Johnson
09:09 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
Robin, is that still an issue (considering my previous comment), or should we close this one? Yehuda Sadeh
10:42 AM rbd Bug #7125: Assertion failure in rbd_img_obj_callback()
Probably related are:
http://tracker.ceph.com/issues/5876
http://tracker.ceph.com/issues/5662
http://tracker.cep...
Ilya Dryomov
10:29 AM Linux kernel client Bug #7069 (Resolved): CephFS hang when using fscache - several "blocked for more than 120 seconds...
this is fixed in 8fb883f3e30065529e4f35d4b4f355193dcdb7a2, according to milosz. fixed in kernel 3.13 Sage Weil
09:48 AM Linux kernel client Bug #7069 (Need More Info): CephFS hang when using fscache - several "blocked for more than 120 s...
THere are several fscache fixes in the testing branch; perhaps they address this? Sage Weil
10:27 AM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
Sage Weil
10:23 AM Revision 377c9190 (ceph): rados_connect not thread-safe when using nss (documentation)
I'm not sure whether rados_connect is expected to be threadsafe or not,
so this is just a documentation patch rather ...
Sharif Olorin
10:18 AM Bug #7592 (Resolved): hit_set_trim() removal races with backfill
Sage Weil
10:09 AM Bug #7592 (Fix Under Review): hit_set_trim() removal races with backfill
David Zafman
10:15 AM rgw Feature #7680 (Resolved): Use new civetweb git repo for ceph
It seems that the original repo used to fork the ceph civetweb repo from is outdated. The current README on https://g... Danny Al-Gaaf
09:51 AM Linux kernel client Bug #2759: libceph: crush tree algorithm is not understood
We should be testing CRUSH with multiple algorithms Ian Colle
09:46 AM Revision 861e62aa (ceph): Update Python hashbang to respect environment
The /usr/bin/python hashbang causes doc builds to fail when Python3 is
the default Python and Python2 is being used f...
Sharif Olorin
09:44 AM Linux kernel client Bug #2224 (Rejected): Oops in __cfh_to_dentry
Sage Weil
09:44 AM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
Sage Weil
09:37 AM rbd Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
e91fb910653a672560867d4a81aa30f9d5dc0af8 Ian Colle
09:35 AM rbd Bug #7582 (Resolved): "FAIL: test_rbd.TestImage.test_remove_with_watcher" in upgrade:dumpling-x-f...
Sage Weil
09:34 AM rbd Bug #7583 (Resolved): "librbd::ImageCtx: error finding header" in upgrade:dumpling-x-firefly---ba...
Sage Weil
09:33 AM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
Sage Weil
09:32 AM rbd Bug #6577 (Can't reproduce): arm testing: rbd test segfaults at FAILED assert((bool)_front == (bo...
Sage Weil
09:21 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
Sage Weil
09:18 AM rgw Bug #6913 (Duplicate): valgrind issues when running rgw tests
Sage Weil
09:17 AM rgw Bug #6802 (Rejected): ARM: rgw_swift failure (internal server error, 500)
Sage Weil
09:17 AM rgw Bug #6696 (Can't reproduce): Upgrade rgw failure in nightly tests. (/home/ubuntu/cephtest/s3-test...
Sage Weil
09:15 AM rgw Bug #6765 (Rejected): ARM: RGW s3 tests fail.
Sage Weil
09:13 AM rgw Feature #7589: rgw: configurable chunk size
Josh - please review wip-7589 Ian Colle
09:12 AM rgw Feature #7589 (Fix Under Review): rgw: configurable chunk size
Sage Weil
09:10 AM devops Bug #6453: libapache2-mod-fastcgi Packages for Debian Squeeze have incorrect dependencies
Sage Weil
09:08 AM rgw Bug #6911: rgw test failure on the arm set up
this sounds like a 32 bit int (size_t?) overflow Sage Weil
09:07 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Sage Weil
09:06 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
the mon assert is a dup Sage Weil
08:32 AM Revision fa30eb5d (ceph): rados.py: fix typo in Ioctx::read() docstring
Signed-off-by: Mohammad Salehe <salehe+dev@gmail.com> Mohammad Salehe
07:18 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
This looks like it's the writeback deadlock when trying to flush from the client to the OSD on a single memory-constr... Greg Farnum
07:17 AM CephFS Bug #6599 (Resolved): client: invalid iterator dereference in Client::trim_caps
Sage Weil
07:12 AM CephFS Feature #5486: kclient: make it work with selinux
Hmm, Sage notes that maybe it'll work now we support ACLs. Or maybe we can use a special mount option? Greg Farnum
07:00 AM CephFS Bug #2187 (Can't reproduce): pjd chown/00.t failed test 97
Sage Weil
06:59 AM CephFS Bug #2740 (Resolved): mds: crash in Objecter when shutting down too early
Sage Weil
03:40 AM Revision 1249b0bd (ceph): Use pgrep radosgw to determine if rados gateway is running.
Fixes: 7528
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cher...
Warren Usui
03:40 AM Revision 745f72c5 (ceph): Fixed get_status() to find client.radosgw fields inside of ps output.
Fixes: 7375
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cher...
Warren Usui
03:40 AM Revision 880bc3a5 (ceph): Fix get_status() to find client.rados text inside of ps command results.
Added port (fixed value for right now in teuthology) to hostname.
Fixes: 7374
Reviewed-by: Yehuda Sadeh <yehuda@inkta...
Warren Usui
03:00 AM Revision 77c3cecb (ceph): Merge pull request #221 from ceph/wip-brief
lock.py: allow --brief to stand on its own (without --list) wusui
02:53 AM Revision fbd9c154 (ceph): osd: Remove unused checkpoint code
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
02:38 AM Revision 69ed31cc (ceph): lock.py: allow --brief to stand on its own (without --list)
I use --brief all the time, and it's annoying to have to type
the useless --list at the same time.
Signed-off-by: Da...
Dan Mick
01:45 AM Revision d3e3df7a (ceph): mds: fix owner check of file lock
flock and posix lock do not use process ID as owner identifier.
The process ID of who holds the lock is just for F_GE...
Yan, Zheng

03/10/2014

11:45 PM Revision ed6a2001 (ceph): Add print task.
Made a task that simply prints the output that is given to it as
an argument. Can be used like any other task (under ...
Yuri Weinstein
11:13 PM Revision ccf9a745 (ceph): Merge pull request #1310 from ceph/wip-doc-documenting-ceph
Wip doc documenting ceph
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:03 PM Revision 8a72de3e (ceph): ReplicatedPG: adjust pending_attrs correctly in copy_from
Otherwise, subsequent reads might not get the correct cached attrs.
Fixes: #7663
Signed-off-by: Samuel Just <sam.jus...
Samuel Just
11:03 PM Revision 6669e4d6 (ceph): ReplicatedPG: _delete_head should adjust pending_attrs
We need the old attr_cache in make_writeable for the clone,
so make the changes to pending_attrs.
Fixes: #7663
Signe...
Samuel Just
11:02 PM Revision 60c1b9a5 (ceph): ReplicatedPG: use pending_attrs in rollback
Otherwise, we won't have the correct attr_cache in
make_writeable for the clone.
Fixes: #7663
Signed-off-by: Samuel ...
Samuel Just
10:58 PM Revision d7c4d6ab (ceph): doc: Added init caps to Signed-off-by: and Fixes:
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
10:54 PM Revision 2b284077 (ceph): doc: update build prerequisites
Based on WIP branch by Gary Lowell <gary.lowell@inktank.com>.
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
Ken Dreyer
10:45 PM Revision 7ac98b2a (ceph): doc: Updated sign-off by to sign-off-by
sign-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
10:06 PM Revision 2e420f9d (ceph): doc: rm duplicate info from release-process
The "just push the new tag" bit is already done in the list of commands
above. Remove this piece, since it's duplicat...
Ken Dreyer
09:14 PM Revision 52a2d692 (ceph): doc: fix reST formatting in release-process
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com> Ken Dreyer
09:14 PM Revision bb737117 (ceph): doc: update release-process for packages
New script to sign rpms in the repo and create the indexes, and
some description of additional packages that might ne...
Gary Lowell
09:14 PM Revision dd5a378d (ceph): doc: misc updates for release-process
Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
Reviewed-by: Ken Dreyer <ken.dreyer@inktank.com>
Gary Lowell
08:43 PM Revision e272f74f (ceph): rgw_rados.h: RGWRegion: initialize cct and store with NULL
CID 1054869 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member "store" i...
Danny Al-Gaaf
08:36 PM Revision 8de88193 (ceph): PG::choose_acting: filter CRUSH_ITEM_NONE out of have
Fixes: #7672
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
07:27 PM Revision c7c9ae3b (ceph): RadosModel.h: initialize CopyFromOp::snap
CID 1093219 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
4. uninit_member: Non-static class member "snap" is...
Danny Al-Gaaf
07:20 PM Revision d7af7eb3 (ceph): RadosModel.h: TestOp: initialize comp with NULL
CID 1135939 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "comp" is...
Danny Al-Gaaf
07:12 PM Revision 9df9f4c7 (ceph): ReplicatedPG.h: CopyResults() initialize final_tx with NULL
CID 1188177 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "final_tx...
Danny Al-Gaaf
07:01 PM Revision 2daabc1e (ceph): scratchtoolpp.cc: check return value of getchar()
CID 716865 (#1 of 1): Unchecked return value from library (CHECKED_RETURN)
1. check_return: Calling function "getcha...
Danny Al-Gaaf
06:58 PM Revision 0f7d954b (ceph): doc: Updated pull request with suggested changes.
signed-off by: John Wilkins <john.wilkins@inktank.com> John Wilkins
06:50 PM Revision a9df888c (ceph): AioTestData: initialize m_ioctx with NULL
CID 717392 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "m_ioctx" ...
Danny Al-Gaaf
06:37 PM Revision 6732c025 (ceph): rgw_rados.h: generator class: initialize manifest with NULL
CID 1188180 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member "manifest...
Danny Al-Gaaf
06:27 PM Revision 61f640cf (ceph): IoCtxImpl: initialize last_objver with 0
CID 717219 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member "last_objve...
Danny Al-Gaaf
05:34 PM Revision b6947c03 (ceph): ECSubWrite: pass some parameter by reference
CID 1188143 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter stats of type ...
Danny Al-Gaaf
05:22 PM Revision 200f7478 (ceph): test/bench/distribution.h: pass rngen_t by reference
CID 1135927 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter rng of type rn...
Danny Al-Gaaf
05:14 PM Revision d61fcfa2 (ceph): ceph-filestore-dump.cc: pass OSDSuperblock by reference
CID 1100693 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter superblock of ...
Danny Al-Gaaf
05:11 PM Bug #7593: Disk saturation during PG folder splitting
At a high level, sure, if you know ahead of time how many objects per PG you expect you can pre-hash the PG directori... Sage Weil
01:26 AM Bug #7593: Disk saturation during PG folder splitting
Hi Sage,
If we would like to make the following changes:
# Bring in a new configuration flag which can be used to...
Guang Yang
05:08 PM devops Bug #7677: Troubleshoot ceph-setup-nightly Jenkins failures
Alfredo - please review. Ian Colle
04:57 PM devops Bug #7677 (Fix Under Review): Troubleshoot ceph-setup-nightly Jenkins failures
Here is the code change to skip the Debian package diffs if they are not present: https://github.com/ceph/ceph-build/... Ken Dreyer
04:55 PM devops Bug #7677 (Resolved): Troubleshoot ceph-setup-nightly Jenkins failures
h3. Background:
Ceph builds in Jenkins are broken up into three separate jobs: ceph-setup, ceph-build, and ceph-pa...
Ken Dreyer
05:07 PM Revision 7e43823f (ceph): doc: Fixed typo.
Signed-off-by: John Wilkins <john.wilkins@inktank.com> John Wilkins
05:05 PM devops Tasks #7678 (Resolved): f20 Jenkins slave
In #7094, we got a new Fedora 20 gitbuilder. We need to add this host to Jenkins as well.
I don't think there are ...
Ken Dreyer
04:54 PM Revision 6cd797b3 (ceph): osd/Watch.cc: pass entity_addr_t by reference
CID 1086832 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter addr of type e...
Danny Al-Gaaf
04:38 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...
135c27ec74be352416d06a9d0ad78e63cf477433 David Zafman
04:29 PM Revision 40095ee2 (ceph): watch_item_t: pass entity_addr_t by reference
CID 1030127 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter addr of type e...
Danny Al-Gaaf
04:28 PM rgw Bug #7676 (Resolved): rgw: multi-part upload incompatible with EC backend
multipart upload uses omap on data object. Need to provide a solution for this. Either we switch the data format for ... Yehuda Sadeh
04:16 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
*wip-doc-prereq* (was "5a811a":https://github.com/ceph/ceph/commit/5a811a0894db2619f5f916c0be85459d0f481265) has been... Ken Dreyer
03:44 PM devops Cleanup #7675 (In Progress): clean up Gary Lowell's WIP branches
Ken Dreyer
03:26 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
*wip-build-doc* has been rebased and submitted for merging here: https://github.com/ceph/ceph/pull/1415 Ken Dreyer
03:18 PM devops Cleanup #7675: clean up Gary Lowell's WIP branches
For the record, today I've reviewed and deleted the following wip branches from Gary.
*wip-lazy-cuttlefish-gl* (wa...
Ken Dreyer
03:13 PM devops Cleanup #7675 (Resolved): clean up Gary Lowell's WIP branches
Gary Lowell had contributed a couple of work-in-progress branches that are still outstanding. Here are the seven that... Ken Dreyer
04:14 PM Revision 62763d56 (ceph): watch_info_t: pass parameter by reference
CID 1030126 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter a of type enti...
Danny Al-Gaaf
04:02 PM Revision 246564bf (ceph): pg_t::get_split_bits: add assert to silence coverity
CID 751330 (#1 of 1): Overflowed return value (INTEGER_OVERFLOW)
overflow_sink: Overflowed or truncated value (or a ...
Danny Al-Gaaf
03:54 PM Revision aba5b7cc (ceph): rbdmap: bugfix upstart script
It seems like the upstart script is lacking a little behind [the initscript](https://github.com/ceph/ceph/blob/master... Stephan Renatus
02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
I believe the error is in the cache pool. Samuel Just
02:20 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
[ERR] 4.3 scrub stat mismatch, got 48/48 objects, 0/0 clones, 21/23 dirty, 9/9
We are overestimating dirty now, ...
Samuel Just
02:17 PM Bug #7674: Cache pool configuration stalls
This was on 0.77-735-gd171418-1saucy which is a couple of days old. I can retest on firefly from today if there have... Mark Nelson
02:15 PM Bug #7674 (Resolved): Cache pool configuration stalls
In testing the following cache pool configuration:... Mark Nelson
02:09 PM Bug #7672: PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
Samuel Just
01:32 PM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
Samuel Just
02:09 PM Bug #7671: watch should return ENOENT if the object does not exist
Samuel Just
12:56 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
Currently, new_obs->exists doesn't get updated, so we create the log entry as a delete which messes everything up. Samuel Just
02:08 PM Bug #7673: "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic...
There are seem to be several of those, so 'major' Yuri Weinstein
02:07 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic-plana/1238... Yuri Weinstein
12:58 PM CephFS Bug #1318: directories disappear across multiple rsyncs
By “this” I meant files with different timestamps from what they were last set to, as in the first paragraph of comme... Alexandre Oliva
12:51 PM CephFS Bug #1318: directories disappear across multiple rsyncs
I'm afraid this still occurs quite often with ceph 0.77 and ceph.ko 3.13.6-gnu. I have a slightly better understandi... Alexandre Oliva
10:23 AM Bug #7592 (In Progress): hit_set_trim() removal races with backfill
David Zafman
10:09 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
Sage Weil
09:44 AM Revision 2e342d6d (ceph): FileStore: support compiling without libxfs
When configured with --without-libxfs, use GenericFileStoreBackend
instead of XfsFileStoreBackend for XFS. At this p...
Ilya Dryomov
09:40 AM Cleanup #7668: remove custom googletest (gtest) copy from source tree
I have no expertise here and am down with making this change if it works out better, but when we initially grabbed gt... Greg Farnum
07:43 AM Cleanup #7668 (Resolved): remove custom googletest (gtest) copy from source tree
Remove the the potentially outdated gtest code from the source tree to keep it up-to-date:
Needed steps:
- since ...
Danny Al-Gaaf
09:32 AM devops Bug #7669 (New): obscure traceback when a partition of type TOBE_UUID can't be mounted
Steps to reproduce:... Loïc Dachary
07:29 AM Revision 4d3c1a19 (ceph): Adds radosgw-agent small file sync test
Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com> Christophe Courtaut
07:29 AM Revision 93f5d607 (ceph): radosgw-admin: don't compare pools for different zones
The actual data locations will be different if they are in the same
cluster.
Signed-off-by: Josh Durgin <josh.durgin...
Josh Durgin
07:29 AM Revision 871fe020 (ceph): rgw: set placement targets for zones
This lets zones use different pools for actual object data.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
07:29 AM Revision 8ba02bfc (ceph): radosgw-agent: add logging to radosgw-admin task tests
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
07:29 AM Revision 1d8dcc4a (ceph): rgw utils: add function to get data log window configuration
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
07:29 AM Revision 55fad94a (ceph): rgw: create clients in all zones when regions are used
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
07:29 AM Revision a74cf330 (ceph): radosgw-admin: ignore 301 test against the same src and dest regions
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
07:29 AM Revision 1143539f (ceph): radosgw-admin: fix typo in data sync test
re-indent and set k.key instead of k.Key
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
07:29 AM Revision dcad92eb (ceph): radosgw-admin: check that data deletions work as well
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
07:29 AM Revision 7cb750c4 (ceph): radosgw-admin: test data sync with more than max-entries objects
For now hard code the max-entries for the radosgw-agent, since
this is the only test that is affected by it.
Signed-...
Josh Durgin
07:24 AM Revision 26266045 (ceph): erasure-code: LARGEST_VECTOR_WORDSIZE is always 16
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:24 AM Revision 2beb2a5a (ceph): erasure-code: upgrade to jerasure version 2
http://tracker.ceph.com/issues/7599 refs #7599
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:24 AM Revision b74115a5 (ceph): autotools: set SIMD_FLAGS with SSE flags
As well as compiler options.
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:21 AM Revision eb6ffdbf (ceph): erasure-code: remove jerasure version 1
http://tracker.ceph.com/issues/7599 refs #7599
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:21 AM Revision 4105ab8b (ceph): erasure-code: use jerasure as submodules
Now that there is a git repository to refer to, it will be good for
maintenance. Pin the version to stable branches.
...
Loïc Dachary
06:35 AM Revision f92d3a56 (ceph): rgw: add data sync test
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
06:29 AM Revision e5a43b75 (ceph): rgw: use different keys for different system users
Only one of these was being used before, due to a bug in
teuthology. This is fixed, and trying to create a second use...
Josh Durgin
06:12 AM Revision c84f72ba (ceph): Merge branch 'master' of https://github.com/enovance/ceph-brag into fir...
Babu Shanmugam
06:11 AM Revision 18506ad6 (ceph): Removed all regular expression parsing and used '-f json' instead
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
05:53 AM Revision cd7986ca (ceph): rbd: check for watchers before trimming an image on 'rbd rm'
Check for watchers before trimming image data to try to avoid getting
into the following situation:
- user does 'r...
Ilya Dryomov
04:35 AM Revision 4cb6b2a1 (ceph): Modified num_bytes attribute in components_count to be a raw integer
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
03:20 AM devops Bug #7605: statup script /etc/init.d/ceph has incorrect slash
I meant:
the correct line should be:
r = sprintf("%.2f", d) instead of
r = sprintf(\"%.2f\", d)
Jan-Willem Michels
02:33 AM Bug #7667 (Resolved): Fix ceph code to build with llvm (clang/clang++)
Currently the code don't compile with clang++ due to non c++ standard usage of VLAs (http://clang.llvm.org/compatibil... Danny Al-Gaaf
12:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
Fixing the agent problem did not make the test pass. I don't think the remainder is an agent issue, but haven't looke... Josh Durgin
12:20 AM Revision 18bdee6d (ceph): MDSMonitor::prepare_command: fix "mds set"
CID 1160828 (#1 of 1): Operands don't affect result (CONSTANT_EXPRESSION_RESULT)
result_independent_of_operands: !cm...
Danny Al-Gaaf

03/09/2014

11:06 PM Revision 78847807 (ceph): osd_types.cc: add missing break in operator<< case handling
CID 1086831 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: This case (value 4635) is not term...
Danny Al-Gaaf
09:27 PM Revision 2cf09089 (ceph): upgrade/dumpling-x: fix order
Make it match the filename.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:58 PM Bug #7666 (Duplicate): librados: lock cycle on shutdown
... Sage Weil
07:22 PM Revision 83731a75 (ceph): ReplicatedPG::finish_ctx: clear object_info if !obs.exists
Otherwise, we see a different object_info_t depending on whether the
transaction deleting the object clears before an...
Samuel Just
07:21 PM Revision 40dc3f8b (ceph): Merge pull request #1405 from ceph/wip-7575
osd: Add hit_set_flushing to track current flushes and prevent races
Reviewed-by: Sage Weil <sage@inktank.com>
Revie...
Sage Weil
07:00 PM Bug #7592: hit_set_trim() removal races with backfill
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-09_03:00:01-rados-firefly-testing-basic-plana/123754 Sage Weil
06:58 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
We hit this again with
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-03-09_03:00:01-rados-firefl...
Sage Weil
05:56 PM Revision f34c742a (ceph): Merge pull request #1406 from dachary/wip-7188-emperor
common: ping existing admin socket before unlink (emperor)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:56 PM Revision a931aaa6 (ceph): Merge pull request #1407 from dachary/wip-7188-dumpling
common: ping existing admin socket before unlink (dumpling)
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:32 PM Revision a7afa145 (ceph): config.cc: add debug_ prefix to subsys logging levels
Add debug_ prefix also for 'ceph --admin-daemon *.asok config show'
as already done e.g. by 'ceph-osd --show-config'....
Danny Al-Gaaf
05:29 PM Revision a4dfbc88 (ceph): workunit: change timeout 1h -> 3h
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:28 PM Revision 55c23a1a (ceph): qa: add script for testing rados allocation hint
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com> Ilya Dryomov
04:56 PM Revision 2474e532 (ceph): Merge pull request #1408 from ceph/wip-da-fix-doc
Fixes and updates for doc
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:22 PM Bug #7655 (Resolved): osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
Sage Weil
11:23 AM Bug #7602: 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys logging levels)
@Sage: do we need a backport to dumpling? Danny Al-Gaaf
10:32 AM Bug #7602 (Resolved): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys lo...
Sage Weil
10:10 AM Bug #7602 (Fix Under Review): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (s...
Danny Al-Gaaf
11:19 AM Bug #7665 (Resolved): Documentation: cleanup and update doc/install/build-ceph.rst
Update build instructions for firefly
* Differentiate package names between RPM and debian based distros.
* Differe...
Danny Al-Gaaf
11:14 AM Feature #7664 (Resolved): systemd service files
Since the most distributions will use systemd in the future, we need native service files to startup the ceph daemons... Danny Al-Gaaf
10:59 AM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
attr_cache is used improperly in _delete_head.
2014-03-08T20:39:21.992 INFO:teuthology.task.rados.rados.1.out:[10....
Samuel Just
10:56 AM Bug #7188 (Resolved): Admin socket files are lost on log rotation calling initctl reload (ubuntu ...
Sage Weil
10:54 AM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
looks like #7575 Sage Weil
10:51 AM Bug #7587 (Duplicate): Failure of LibRadosTwoPoolsPP.PromoteSnap
I'm pretty sure this is due to teh object_t SnapContext map. #7634 Sage Weil
05:06 AM Feature #7662: add a "ec profiles" map to OSDMap
OSDMap has a new field properties, "a named list of properties map":https://github.com/dachary/ceph/blob/wip-erasure-... Loïc Dachary
01:12 AM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
"work in progress":https://github.com/ceph/ceph/pull/1477
to be used instead of pg_pool_t which could be replaced ...
Loïc Dachary
01:18 AM Revision 54ffdcc4 (ceph): get-involved.rst: update information
Added #ceph-devel IRC channel, more mailing lists, wiki and planet.ceph.com.
Signed-off-by: Danny Al-Gaaf <danny.al-...
Danny Al-Gaaf
12:02 AM Revision d1a888e0 (ceph): swift/containerops.rst: fix some typos
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf

03/08/2014

11:58 PM Revision 93b95a28 (ceph): radosgw/troubleshooting.rst: s/ceph-osd/OSD/
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:30 PM Revision 2223a372 (ceph): radosgw/config-ref.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:26 PM Revision 0b9d8936 (ceph): Add missing space in error message
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:19 PM Revision 87618d45 (ceph): session_authentication.rst: fix some typos
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:07 PM Revision 682c6958 (ceph): release-process.rst: fix some typos
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
11:01 PM Revision 72ee3389 (ceph): doc: s/osd/OSD/ if not part of a command
First attempt to unify usage of OSD over rst files.
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
Danny Al-Gaaf
10:31 PM Revision e6660194 (ceph): doc/dev/logs.rst; fix some typos
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
10:25 PM Revision bbd1c4ba (ceph): filestore-filesystem-compat.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
10:22 PM Revision ae123a6d (ceph): corpus.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
10:16 PM Revision cf9f017d (ceph): config.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
10:11 PM Revision 5aaecc72 (ceph): cephx_protocol.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:36 PM Revision e471f404 (ceph): Make try_push_job_info() retry using safe_while
I've noticed sometimes try_push_job_info() fails because of server load
issues. It should try more than once (and now...
Zack Cerza
09:19 PM Revision 73849c11 (ceph): Update safe_while's suggested usage pattern
I didn't love the way safe_while was encouraged to be used and it didn't
fit right with the new no-raising behavior. ...
Zack Cerza
08:58 PM Revision c9809849 (ceph): Add optional _raise parameter
Defaults to True but if set to False, when giving up log a warning
instead of raising an exception.
Signed-off-by: Z...
Zack Cerza
08:16 PM Revision eb667673 (ceph): Pass timeout to _spawn_on_all_clients()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
02:53 PM Revision f5668b36 (ceph): common: ping existing admin socket before unlink
When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a...
Loïc Dachary
02:48 PM Revision 3f5fc965 (ceph): common: ping existing admin socket before unlink
When a daemon initializes it tries to create an admin socket and unlinks
any pre-existing file, regardless. If such a...
Loïc Dachary
02:18 PM Revision 4e01884e (ceph): Log correct action in CephManager.remove_pool()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
02:01 PM Revision 72c63f13 (ceph): Log timeout value
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
01:58 PM Revision b4205cae (ceph): Iterate more sensibly over processes
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
10:27 AM Revision 2cbb0a40 (ceph): architecture.rst: fix typos
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
10:20 AM Revision f581bda5 (ceph): rados: add set-alloc-hint command
Set allocation hint for an object.
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
Ilya Dryomov
10:13 AM Revision a4cbb192 (ceph): rados/operations/control.rst: fix typo
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
09:27 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
Logs lines for *plana166726-98*... Loïc Dachary
09:16 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
Crashing thread *7f991c37a700*... Loïc Dachary
08:56 AM Bug #7588 (In Progress): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyge...
... Loïc Dachary
08:05 AM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
teuthology-2014-03-07_23:00:41-rgw-firefly-testing-basic-plana has the latest Sage Weil
07:00 AM Bug #7188 (Fix Under Review): Admin socket files are lost on log rotation calling initctl reload ...
* "dumpling backport":https://github.com/ceph/ceph/pull/1407
* "emperor backport":https://github.com/ceph/ceph/pull/...
Loïc Dachary
05:17 AM Revision 9bf39e2c (ceph): Broke down sysinfo's format into a histogram with a value and count
so that we just see how many of each version/distro/kernel/os/arch/cpu/etc are running
Signed-off-by: Babu Shanmugam...
Babu Shanmugam
12:53 AM Revision 4d6a74d4 (ceph): TestPGLog::proc_replica_log: call doesn't adjust olog
We don't adjust head with proc_replica_log, don't assert that
it's been adjusted.
Signed-off-by: Samuel Just <sam.ju...
Samuel Just
12:53 AM Revision e830f9ff (ceph): TestPGLog: check on last_update in run_test_case
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:53 AM Revision 7c77ff62 (ceph): TestPGLog: add a test case verifying case where we have the prior_version
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:53 AM Revision 3befb936 (ceph): PGLog::_merge_object_divergent_entries: handle missing.have == prior_ve...
Fixes: #7658
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
12:53 AM Revision 25916681 (ceph): PGLog::proc_replica_log: select divergent log entries correctly
Looking for an entry in olog which matches one of ours might add
extra divergent entries. Instead, do what merge_log...
Samuel Just

03/07/2014

11:46 PM Revision 9db66564 (ceph): upgrade/dumpling-x: do not thrash primary-affinity
We can't do it on a mixed cluster
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
11:27 PM Revision 71b4474b (ceph): client: fix Client::getcwd()
An recent commit made MDS not include dentry trace in LOOKUPPARENT
reply. It broke Client::getcwd. The fix is change ...
Yan, Zheng
11:23 PM Revision db0c3782 (ceph): Merge remote-tracking branch 'gh/wip-7210' into firefly
Reviewed-by: Sage Weil <sage@inktank.com> Sage Weil
11:22 PM Revision 617ce676 (ceph): mds: introduce LOOKUPNAME MDS request
The new MDS request is used for connecting a given inode to its
parent inode. It allows client to have efficient impl...
Yan, Zheng
11:21 PM Revision 1c8c6189 (ceph): qa/workunits/cephtool/test.sh: fix 'osd thrash' test
- fix the wait check for osds to come back up
- make sure they get marked back in, too
Signed-off-by: Sage Weil <sag...
Sage Weil
11:05 PM Revision 20754779 (ceph): Merge pull request #1403 from ceph/wip-7642
mon: fix check for primary-affinity feature bit, and fix a race in similar checks
Reviewed-by: Samuel Just <sam.just...
Sage Weil
10:44 PM Revision b62f9f07 (ceph): mon/OSDMonitor: feature feature check bit arithmetic
Make sure all features are present (instead of just any of them).
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
10:19 PM Revision 21c22595 (ceph): Merge pull request #1404 from ceph/wip-7652
mon: fix infininte pg create msgs for erasure pools
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
10:02 PM Revision 8d52fb70 (ceph): mon/PGMap: send pg create messages to primary, not acting[0]
For erasure pools, these may not match.
In the case of #7652, this caused pg_create messages to be send
indefinitely...
Sage Weil
09:56 PM Revision c8b34f19 (ceph): mon/PGMonitor: improve debugging on PGMap updates slightly
Chasing #7652
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:29 PM Revision b9bcc159 (ceph): mon/OSDMonitor: prevent set primary-affinity unless all OSDs support it
Make sure all running OSDs support the feature before we start using it
(even if the config option is on!).
Fixes: #...
Sage Weil
09:29 PM Revision 819cce2d (ceph): mon/OSDMonitor: make osdmap feature checks non-racy
The check for OSD features may race with the boot of an OSD that does not
have the necessary features. Check the pen...
Sage Weil
09:14 PM Revision 204b3ac7 (ceph): Change default workunit timeout to 1h
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
09:03 PM Revision 9109008a (ceph): stress-split: use dumpling version of rbd.py tests
The firefly version has a test that depends on new behavior.
Fixes: #7643
Signed-off-by: Josh Durgin <josh.durgin@in...
Josh Durgin
08:43 PM Revision 5f7efec1 (ceph): tools/rados/rados.cc: use write_full for sync_write for ec pools
Fixes: #7650
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:06 PM Bug #7587 (In Progress): Failure of LibRadosTwoPoolsPP.PromoteSnap
Sage Weil
08:04 PM Revision ec38bd3c (ceph): Use safe_while's action arg
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
08:02 PM Revision 73f5af2f (ceph): Add optional 'action' parameter to safe_while
This is to make it easier to see what actually timed out when scanning
error logs
Signed-off-by: Zack Cerza <zack.ce...
Zack Cerza
07:49 PM Revision 38fd666a (ceph): qa: workunits/mon/rbd_snaps_ops.sh: ENOTSUP on snap rm from copied pool
'rados cppool' copies the contents but that doesn't make the destination
pool an unmanaged snaps pool. Therefore, we...
Joao Eduardo Luis
07:49 PM Revision c13e1b79 (ceph): mon: OSDMonitor: don't remove unamanaged snaps from not-unmanaged pools
Although we should allow creating unmanaged snaps on not-unamanaged pools,
as long as those pools don't have any mana...
Joao Eduardo Luis
07:48 PM Revision 135c27ec (ceph): osd: Add hit_set_flushing to track current flushes and prevent races
When flushing a HitSet track in hit_set_flushing map so that
agent_load_hit_sets() doesn't try to read it too soon.
...
David Zafman
07:36 PM Revision 7604a1b6 (ceph): Update safe_while users to reflect new defaults
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
07:33 PM Revision 8258c847 (ceph): Change safe_while defaults to 6s 10x no increment
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
07:03 PM Revision 081a5c4b (ceph): Look for ready() in the right place
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
06:33 PM Bug #7636 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.EvictSnap
this is due to the SnapContext object_t map key bug, see #7634 Sage Weil
05:39 PM Revision ad04075b (ceph): Merge pull request #218 from ceph/wip-radosbench-timeout
Introduce a timeout to radosbench's join phase Sage Weil
05:36 PM Revision 1778d358 (ceph): Use a timeout of config.get('time') * 2
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
05:21 PM Revision 0be5f1f0 (ceph): Introduce a timeout to radosbench's join phase
Set to 15min right now.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
05:16 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
ReplicatedPG::start_flush needs to handle the case where a clone is missing Samuel Just
05:08 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
Samuel Just
05:08 PM Bug #7659 (Resolved): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...

ceph version 0.77-746-g65c0738 (65c07386f5e18d543e266c4ae81dcd1a9724df8b)
1: (ReplicatedPG::get_object_context(h...
Samuel Just
05:08 PM Bug #7660 (Rejected): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
Samuel Just
05:08 PM Bug #7660 (Rejected): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...

ceph version 0.77-746-g65c0738 (65c07386f5e18d543e266c4ae81dcd1a9724df8b)
1: (ReplicatedPG::get_object_context(h...
Samuel Just
04:53 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
Samuel Just
04:52 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
Samuel Just
04:38 PM Revision aea501be (ceph): fs/basic: multimds
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:32 PM Revision 0815e4fa (ceph): rados/singleton-nomsgr: add allocation hint test
Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com> Ilya Dryomov
04:20 PM Revision fbb05b73 (ceph): Remove the mds-mon-osd upgrade sequence
It wasn't actually supported.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
04:19 PM Revision 0fd636c4 (ceph): Merge remote-tracking branch 'gh/firefly'
Conflicts:
README
Sage Weil
03:44 PM Bug #7644 (Duplicate): cephx: verify_reply couldn't decrypt with error: error decoding block for ...
same cause as #7642.. missing features due to primary-affinity Sage Weil
03:33 PM Bug #7644 (In Progress): cephx: verify_reply couldn't decrypt with error: error decoding block fo...
Sage Weil
08:53 AM Bug #7644 (Duplicate): cephx: verify_reply couldn't decrypt with error: error decoding block for ...
2014-03-07T01:15:35.712 INFO:teuthology.task.radosbench.radosbench.0.err:[10.214.131.3]: 2014-03-07 01:15:35.712493 7... Sage Weil
03:44 PM Bug #7655: osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
Also caused:
-95> 2014-03-07 15:04:11.803637 7f504ecb4700 10 _merge_object_divergent_entries: merging hoid c520...
Samuel Just
03:19 PM Bug #7655 (Resolved): osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())

ceph version 0.77-757-g8221a8e (8221a8ecba14f80eb7e35e3b1e6fe8487502b2d9)
1: (ReplicatedPG::recover_primary(int,...
Samuel Just
03:34 PM devops Feature #7656: kmod: remove hardcoded "rhel7" branch name
As a bit of context, this feature comes from a suggestion by Sage that it would be nice to be able to build rhel7* br... Ken Dreyer
03:28 PM devops Feature #7656 (Rejected): kmod: remove hardcoded "rhel7" branch name
We have preliminary kmod packages available at http://ceph.com/rpm-testing/rhel7/x86_64/ (source at https://github.co... Ken Dreyer
03:24 PM Bug #7210 (Pending Backport): mon: does not validate snapshot removal commands
Sage Weil
03:23 PM Bug #7210 (Resolved): mon: does not validate snapshot removal commands
Sage Weil
03:05 PM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
Sage Weil
01:30 PM Bug #7642 (Fix Under Review): osd: upgrade stress-split: bad state machine event
Sage Weil
01:15 PM Bug #7642: osd: upgrade stress-split: bad state machine event
the thrasher set primary-affinity, which dumpling doesn't understand, so they disagreed on pg mappings. Sage Weil
10:22 AM Bug #7642 (Need More Info): osd: upgrade stress-split: bad state machine event
Sage Weil
08:30 AM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
... Sage Weil
02:31 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_02:30:02-rados-firefly-testing-basic-plana/1209... Yuri Weinstein
02:27 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-07_02:30:02-rados-firefly-testing-basic-plana/1211... Yuri Weinstein
02:22 PM Bug #7643 (Resolved): librbd: upgrade stress-split: FAIL test_rbd.TestImage.test_remove_with_watcher
Changed the suite to use the dumpling version of python rbd tests in commit:9109008ad7473836c8c408fd68a7eb6353121298 Josh Durgin
08:31 AM Bug #7643 (Resolved): librbd: upgrade stress-split: FAIL test_rbd.TestImage.test_remove_with_watcher
... Sage Weil
02:19 PM Bug #7652 (Resolved): mon not removing from creating_pgs
Sage Weil
01:21 PM Bug #7652 (Resolved): mon not removing from creating_pgs
2014-03-06 22:25:54.839669 7fe7e42b6700 1 -- 10.214.134.34:6789/0 --> 10.214.134.34:6800/41782 -- osd_pg_create(pg3.... Samuel Just
12:49 PM Revision 3dd09e36 (ceph): Removed nw_info from sysinfo
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
12:42 PM Bug #7650: rados bench seq tests not performed at correct IO sizes
Samuel Just
11:22 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
With the fix that was put in place for bug #7610, rados bench appears to not be correctly respecting the -b flag when... Mark Nelson
12:42 PM Bug #7649: ec ceph_test_rados stuck recovering
Samuel Just
10:58 AM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
2014-03-06 21:08:49.685246 7ff6f50d9700 10 osd.1 pg_epoch: 534 pg[4.3s0( v 534'466 lc 13'23 (0'0,534'466] local-les=5... Samuel Just
11:23 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_20:46:32-upgrade:dumpling-x:parallel-firefly---... Yuri Weinstein
10:03 AM Bug #7648 (Resolved): ceph-mon corner case denial of service
ceph-mon corner case denial of service
Improperly positioned (in CRUSH map) OSD may cause mon process to stop resp...
Sheldon Mustard
09:35 AM rgw Bug #7647 (Resolved): Ensure that swift keys don't include backslashes
Currently, when we generate a Swift key it can include a backslash as part of the JSON encoding output, so when peopl... Neil Levine
09:10 AM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
... Sage Weil
09:09 AM devops Bug #7645 (Resolved): mira020 is having problems
Been seeing a lot of jobs get borked because of this:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-07_01...
Zack Cerza
08:51 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
the blocking only happens if the limits are set... which we should probably just disable for the osd since we are alr... Sage Weil
08:06 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
"start_copy":https://github.com/ceph/ceph/blob/88047d0b7741d1e131dc423b83bd9bf4cf7f6b46/src/osd/ReplicatedPG.cc#L5316... Loïc Dachary
06:47 AM Revision 09a317fb (ceph): Made crush_types to be a map of type to count, so we can tell how many ...
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
05:14 AM Revision 88047d0b (ceph): Merge pull request #1399 from jrcresawn/docfix
Changed Availability section of ceph-mds.rst to reference ceph-mds, not ...
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:11 AM Subtask #6586 (Resolved): ErasureCodeJerasure::decode does not use want_to_read
"fixed":https://github.com/ceph/ceph/commit/3650da69 Loïc Dachary
05:11 AM Revision 8221a8ec (ceph): Merge pull request #1394 from ceph/wip-7610
obj_bencher: allocate contentsChars to object_size, not op_size
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:11 AM Revision e53aed28 (ceph): SubmittingPatches: clarify "github fork" in preference to "clone"
Signed-off-by: Dan Mick <dan.mick@inktank.com> Dan Mick
05:09 AM Revision 4b11d072 (ceph): Mark this 'while True' loop with 'finite' comment
If we're going to embark on a mission to rid ourselves of
infinitely-looping while loops, it seems smart to start mar...
Zack Cerza
05:09 AM Revision 1322e05d (ceph): Merge pull request #1371 from ceph/wip-debian-files
packaging: use wildcard for test files in Debian
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:05 AM Cleanup #7388 (Closed): ceph osd find has no format argument
The --format argument is implicit for all commands. Loïc Dachary
05:05 AM Revision c09caf03 (ceph): Merge pull request #1374 from ceph/wip-vstart-paths
test: Use non-default out/ dev/ paths in vstart
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Sage Weil ...
Sage Weil
05:05 AM Revision c9eaa651 (ceph): Changed Availability section of ceph-mds.rst to reference ceph-mds, not...
Signed-off-by: James Ryan Cresawn <jrcresawn@gmail.com> James Ryan Cresawn
05:03 AM Feature #6645 (Closed): EC: [link] BPC (basic pyramid code)
Loïc Dachary
05:01 AM Feature #4929 (Resolved): Erasure encoded placement group
Loïc Dachary
04:49 AM Subtask #5877 (Resolved): Plugable erasure code library
Loïc Dachary
04:48 AM Subtask #5860 (Rejected): PG::calc_acting and friends should use PGBackend to select the acting s...
Done elsewhere Loïc Dachary
04:42 AM Subtask #6888 (Resolved): EC/Tiering: Disallow omap writes on pools which are backed by EC pools
In firefly Loïc Dachary
04:41 AM Subtask #5863 (Rejected): OSD internals must work in terms of cpg_t
Done elsewhere Loïc Dachary
04:40 AM Subtask #5859 (Rejected): GetInfo should use PGBackend methods to determine when peering can cont...
Done elsewhere Loïc Dachary
04:39 AM Subtask #5433 (Rejected): Factor out the ReplicatedPG object replication and client IO logic as a...
Done elsewhere Loïc Dachary
04:32 AM Revision 20bfc978 (ceph): Give up on wait_until_healthy() after 15min
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
04:06 AM Revision 23db6782 (ceph): Merge pull request #1397 from ceph/wip-7638
ReplicatedPG::trim_object: use old_snaps for rollback
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:05 AM Revision 4a0c3a66 (ceph): Merge pull request #1398 from ceph/wip-7634
ReplicatedPG: use hobject_t for snapset_contexts map
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:19 AM Revision 0037ee45 (ceph): Merge pull request #1395 from ceph/wip-7637
osd: fix agent thread shutdown
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
02:52 AM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
On Ubuntu 12.04.2 When cuttlefish is installed, apt-get install ceph to emperor will not upgrade ceph-common... Loïc Dachary
02:00 AM Revision ac6ebf87 (ceph): Merge pull request #217 from ceph/wip-fix-plus
suite: fix + handling Zack Cerza
01:56 AM Revision 94d73bd4 (ceph): suite: fix build_matrix for + case
The + means we should concatenate everything in the directory. Do that.
This was totally broken before (and unused ...
Sage Weil
01:51 AM Revision 136775b4 (ceph): Don't warn on legacy crush tunables
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
01:32 AM Revision 57259b54 (ceph): rados: use backwards compatible args
For ops that default to 0, only add arguments for them if they are
specified in the task config. This lets us use the...
Josh Durgin
01:04 AM Revision 022a6a3e (ceph): Revert "The parallel task expects dicts here..."
This reverts commit 79e348320f3695d085693b7ce0c538a9dfdd182b. Sage Weil
12:57 AM Revision 95d445da (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
12:56 AM Revision 70de7d52 (ceph): Revert "Do not spawn a parallel task if dictionary entry does not exist."
This reverts commit dadc9f7d0b6d9c13ccbc4edeb9f7875fc0ae0cac. Sage Weil
12:32 AM Revision 79e34832 (ceph): The parallel task expects dicts here...
We should fix that at some point.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
12:12 AM Revision 09668a49 (ceph): osd: fix agent thread shutdown
We had an old invariant that agent_queue would have at least 1 entry in
it to simplify some other code paths, but it ...
Sage Weil
12:04 AM Revision bda2fd3d (ceph): upgrade: fix typo in subsection name
It's referred to as workload, not workunit, by the parallel task earlier.
Signed-off-by: Josh Durgin <josh.durgin@in...
Josh Durgin
12:04 AM Revision 487be437 (ceph): upgrade: fix indentation for final-workload
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin

03/06/2014

11:51 PM Revision 06b96ffd (ceph): Merge pull request #1389 from ceph/wip-firefly-misc
fix rest tests; fix COLL_MOVE_RENAME dump
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:51 PM Revision d4b4468c (ceph): Merge pull request #1393 from dachary/wip-7072
logrotate: copy/paste daemon list from ceph-*-all-starter.conf
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:47 PM Revision 7411c3c6 (ceph): logrotate: copy/paste daemon list from *-all-starter.conf
Each upstart/*-all-starter.conf use the same script to find the list of
daemons and their ids. Copy it over to the co...
Loïc Dachary
11:34 PM Revision 6f7c8c79 (ceph): Merge pull request #1392 from ceph/wip-7632
ReplicatedPG: consistently use ctx->at_version.version for stashed objec...
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:30 PM Revision 57c7e198 (ceph): Merge pull request #1391 from ceph/wip-7393
ReplicatedPG: clean up num_dirty adjustments
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
11:29 PM Revision 51461432 (ceph): upgrade/dumpling-x: more indentation
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:27 PM Revision 0bf78e6b (ceph): upgrade/dumpling-x: fix indentation
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
11:16 PM Revision d7892f12 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
11:01 PM Revision b6872b25 (ceph): ReplicatedPG::trim_object: use old_snaps for rollback
We need to rollback the old value of snaps, not the
new one.
Fixes: #7638
Signed-off-by: Samuel Just <sam.just@inkta...
Samuel Just
10:53 PM Revision 7f5fcd7b (ceph): Merge pull request #14 from ceph/wip-final-workload-wusui
Fix parallel workunit issues. Zack Cerza
10:40 PM Revision b5b67d19 (ceph): ReplicatedPG: use hobject_t for snapset_contexts map
Otherwise, two objects with different namespaces but
the same object_t will end up clobbering each other's
contexts.
...
Samuel Just
10:34 PM Revision 182667ae (ceph): Fix parallel workunit issues.
Fixed the spacing of workunits inside 2-workload and 4-final-workland
files. Removed parallel final-workload referen...
Warren Usui
10:27 PM Revision 7d1e97f7 (ceph): Revert "Update rados_api_tests.yaml"
This needs to reference dumpling now.
This reverts commit 8e88922581f80000784072e381867f0b5448cd7f.
Josh Durgin
10:27 PM Revision 7b497e1f (ceph): get test-upgrade-firefly.sh from the dumpling branch
it doesn't exist elsewhere Josh Durgin
09:46 PM Revision b4369307 (ceph): qa/workunits/rest/test.py: do not test 'osd thrash'
This wreaks havoc on our QA because it marks osds up and down and then
immediately after that we try to scrub and som...
Sage Weil
09:44 PM Revision 237f0fb4 (ceph): os/ObjectStore: dump COLL_MOVE_RENAME
This got missed way back in ef7cffc34f3bad4ffc090361ad9030a47584a3bf
(pre-0.71).
Signed-off-by: Sage Weil <sage@inkt...
Sage Weil
09:11 PM Bug #7610 (Resolved): Memory corruption during rados bench
Sage Weil
11:28 AM Bug #7610: Memory corruption during rados bench
Samuel Just
08:11 PM Revision f888ab41 (ceph): ReplicatedPG: consistently use ctx->at_version.version for stashed object
Otherwise, two ops might end up using the same version number.
Fixes: #7632
Signed-off-by: Samuel Just <sam.just@ink...
Samuel Just
08:09 PM Bug #7637 (Resolved): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
Sage Weil
03:39 PM Bug #7637 (In Progress): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
Sage Weil
03:10 PM Bug #7637 (Fix Under Review): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
Sage Weil
01:42 PM Bug #7637 (Resolved): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
-7> 2014-03-04 14:58:03.649200 1a55b700 1 OSD::op_tp worker finish
-6> 2014-03-04 14:58:03.653399 1ff68700 ...
Samuel Just
08:07 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
Sage Weil
04:51 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
... Sage Weil
08:06 PM Bug #7638 (Resolved): snap update rollback not working right
Sage Weil
03:28 PM Bug #7638: snap update rollback not working right
Samuel Just
02:41 PM Bug #7638 (Resolved): snap update rollback not working right
failure_reason: '"2014-03-06 13:29:45.498787 osd.1 10.214.134.34:6809/33548 28 : [ERR]
osd.1 found snap mapper err...
Samuel Just
08:05 PM Bug #7634 (Resolved): osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.len...
Sage Weil
03:28 PM Bug #7634: osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.length() == 0)...
Samuel Just
11:51 AM Bug #7634: osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.length() == 0)...

Also happened:
http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-pla...
David Zafman
11:04 AM Bug #7634 (Resolved): osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.len...

http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118367/teutholo...
David Zafman
08:05 PM Revision eca7e633 (ceph): ReplicatedPG: clean up num_dirty adjustments
Previously, a _delete_head() followed by a recreation on an object in
the same transaction would result in num_dirty ...
Samuel Just
07:35 PM Revision d379b1f1 (ceph): osd: bracket role changes with scrub reg/unreg
Make sure the reg/unreg calls for putting ourselves in the scrub schedule
bracket any PG role changes, or that initia...
Sage Weil
07:35 PM Revision 173116fa (ceph): osd: only register for scrub if we are the PG primary
There is no reason to put non-primary PGs on the scrub schedule as they
will be ignored when the worker comes around....
Guang Yang
07:32 PM Revision c8c2f547 (ceph): Client: fix build issue (lost semicolon)
Signed-off-by: Greg Farnum <greg@inktank.com> Greg Farnum
07:12 PM Revision d1714180 (ceph): obj_bencher: allocate contentsChars to object_size, not op_size
Otherwise, our attempt to sanitize object_size bytes of
data.object_contents will be doomed to memory corruption.
Fi...
Samuel Just
07:01 PM Revision 7403b235 (ceph): Merge pull request #1386 from ceph/wip-7624
ReplicatedPG: ensure clones are readable after find_object_context
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:59 PM Revision cf2f3adf (ceph): Merge pull request #1387 from ceph/wip-7618
ReplicatedPG::wait_for_degraded_object: only recover if found
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
06:54 PM Revision b1ac3aff (ceph): Merge pull request #1320 from ceph/wip-libcephfs-fixes
Wip libcephfs fixes
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:44 PM Revision aa7945ab (ceph): Merge pull request #1379 from ceph/wip-7562
mon: make quorum list (by name) be in quorum order
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:29 PM Fix #6278: osd: throttle snap trimming
We are seeing the very same issue. Is there an ETA or can we sponsor someone to fix it :D ? geraint jones
06:14 PM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
... Sage Weil
06:47 AM devops Bug #7627 (Resolved): ceph-disk: does not start daemons properly under systemd
After creating a cluster with ceph-deploy, the test waits up to 15 minutes to get a HEALTH_OK back, but as the output... Alfredo Deza
05:57 PM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...
David Zafman
04:48 PM Revision bafd76ad (ceph): ReplicatedPG: ensure clones are readable after find_object_context
We only get EAGAIN if the object is missing. We also need the
clone to be readable if we are reading it.
The other ...
Samuel Just
04:15 PM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
there is just one string : C_ObjectOperation_copyget::out_category Loïc Dachary
03:57 PM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
(10:44:51 AM) sjusthm: loicd: that one may be tricky to track down, you'll probably want to find a way for the struct... Samuel Just
10:12 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
Can I help ? Loïc Dachary
03:50 PM Bug #7072 (Resolved): logrotate not sending HUP signal
Sage Weil
03:21 PM Bug #7072 (Fix Under Review): logrotate not sending HUP signal
"work in progress":https://github.com/ceph/ceph/pull/1393 Loïc Dachary
03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
57c7e1981991091fa78ed65940eede3420a47d80 to Firefly Ian Colle
03:30 PM Bug #7393 (Resolved): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 white...
Sage Weil
12:12 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
Samuel Just
03:34 PM Bug #7632 (Resolved): os/FileStore.cc: 2538: FAILED assert(0 == "unexpected error")
Sage Weil
08:55 AM Bug #7632 (Resolved): os/FileStore.cc: 2538: FAILED assert(0 == "unexpected error")
2014-03-06 02:55:55.283863 7eff27ce1700 -1 os/FileStore.cc: In function 'unsigned int FileStore::_do_transaction(Obje... Samuel Just
03:00 PM Bug #7633 (Resolved): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefl...
Sage Weil
01:36 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
wip-final-workload-wusui contains the changes.
https://github.com/ceph/ceph-qa-suite/pull/14 is a pull request for t...
Anonymous
12:49 PM Bug #7633 (In Progress): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-fir...
Sage Weil
12:44 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
this looks like malformed yaml Sage Weil
12:34 PM Bug #7633: "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefly---basic-p...
What is the relation here? Zack Cerza
10:16 AM Bug #7633 (Resolved): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefl...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-03-05_10:33:26-upgrade:dumpling-x:parallel-firefly---basic-p... Yuri Weinstein
02:22 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
Sage Weil
12:12 PM Bug #7636 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.EvictSnap

http://qa-proxy.ceph.com/teuthology/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118451/teutholo...
David Zafman
11:47 AM Bug #7635 (Duplicate): failed to recover before timeout expired
http://pulpito.ceph.com/teuthology-2014-03-06_02:30:01-rados-firefly-distro-basic-plana/118391/
Strange it looks l...
David Zafman
11:32 AM Bug #7601 (Duplicate): "command crashed with signal 6" in rados-firefly-testing-basic-plana suite...
Closing, we'll create a new one if it wasn't 7604 and we have logs. Samuel Just
11:30 AM Bug #7601: "command crashed with signal 6" in rados-firefly-testing-basic-plana suite - hung tests
No logs, probably 7604. Samuel Just
11:01 AM Bug #7624 (Resolved): osd/ECBackend.cc: 1644: FAILED assert(r == 0)
Sage Weil
10:59 AM Bug #7618 (Resolved): osd/ECBackend.cc: 475: FAILED assert(r == 0)
Sage Weil
10:44 AM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
Merged into master as of commit: aa7945a Greg Farnum
10:30 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
Sage Weil
10:29 AM Bug #7590 (Resolved): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap create <base>...
Sage Weil
10:28 AM Bug #7630 (Duplicate): Simple tiering test produces OSD assert
#7604 Greg Farnum
10:28 AM Bug #7630 (Resolved): Simple tiering test produces OSD assert
Sage Weil
07:32 AM Bug #7630: Simple tiering test produces OSD assert
rados bench command run:
/usr/bin/rados -c /tmp/cbt/ceph/ceph.conf -p base -b 4194304 bench 300 write --concurrent...
Mark Nelson
07:31 AM Bug #7630 (Duplicate): Simple tiering test produces OSD assert
An initial teiring test produced the included assert just as rados bench started. pools were on the same physical di... Mark Nelson
09:46 AM Feature #7058: osd primary affinity
https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity Ian Colle
09:24 AM rbd Feature #7455: krbd,kcephfs: support primary-affinity
https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity Ian Colle
09:17 AM rbd Feature #7455 (In Progress): krbd,kcephfs: support primary-affinity
Ian Colle
09:10 AM Feature #7619 (In Progress): objecter: replace client_lock with fine grained read-write locks
Ian Colle
08:43 AM Bug #7210: mon: does not validate snapshot removal commands
Finally got to reproduce this. I was missing the part where we actually needed to remove the image's snapshot using ... Joao Eduardo Luis
03:23 AM Bug #7210: mon: does not validate snapshot removal commands
I've got bitten by this. I have an openstack glance volume, and it contains images and snapshots. I did the following... Wai Peng Yip
08:39 AM Revision 90f5a687 (ceph): 1. Removed name of the pool from pool_metadata
2. Included pool type in pool_metadata
3. Renamed rep_size attribute to size in pool_metadata
Signed-off-by: Babu Sh...
Babu Shanmugam
07:58 AM Revision da97feea (ceph): 1. simplified the 'bytes' info to just be bytes
2. prefix all the members of the components_info with 'num_'
Signed-off-by: Babu Shanmugam <anbu@enovance.com>
Babu Shanmugam
07:38 AM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
Apologies in advance if this is a test misconfiguration.
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-06...
Zack Cerza
07:30 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
can upload the core dump and ceph-mds binary to somewhere? Zheng Yan
06:24 AM Bug #6301: ceph-osd hung by XFS using linux 3.10
One fix has been integrated in kernel commit b3f03bac8132207a20286d5602eda64500c19724
(3.14rc1).
No backport AFA...
Yann Dupont
04:58 AM Revision 9d387d38 (ceph): Merge pull request #1378 from ceph/wip-7487
mon: no crush buckets with type 0 (#7487)
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
03:27 AM Bug #7626 (Closed): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
We are using CentOS 6.5 and Ceph 0.77
After updating to 0.77 one monitor can't start:
cluster 554b69c8-bdca...
Jasper Siero
01:38 AM Revision 697bf8fd (ceph): Merge pull request #1380 from ceph/wip-pool-delete
mon/OSDMonitor: fix pool deletion races
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com>
João Eduardo Luís

03/05/2014

11:58 PM Revision 2adc534a (ceph): mon/OSDMonitor: fix pool deletion checks, races
Unify the pool deletion safety checks into a single set of functions.
Make sure we check the committed state and erro...
Sage Weil
11:51 PM Revision d9e88063 (ceph): ReplicatedPG::wait_for_degraded_object: only recover if found
Fixes: #7618
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:31 PM Revision b563a7c7 (ceph): Merge pull request #1381 from ceph/wip-7618
ReplicatedPG::recover_replicas: do not assume that missing objects are u...
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
11:18 PM Revision 16e3d4d3 (ceph): Merge pull request #1382 from ceph/wip-7616
Wip 7616
Reviewed-by: Sage Weil <sage@inktank.com>
Samuel Just
11:14 PM Revision a222e7a1 (ceph): ReplicatedPG::recover_replicas: do not assume that missing objects are ...
Fixes: #7618
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:13 PM Revision 3f59f029 (ceph): Revert "c_read_operations.cc: fix resource leak"
This reverts commit 3cd751b0a280909510c3e633cc8cd4b9f5e3b2d9.
A rados_release_read_op() has already been performed, ...
David Zafman
10:29 PM Revision a71ddb0b (ceph): mon: make quorum list (by name) be in quorum order
Fixes: #7562
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
10:22 PM Revision b642e388 (ceph): Merge pull request #1343 from ceph/wip-cache-warn-full
mon: warn when cache tier is full
Reviewed-by: Loic Dachary <loic@dachary.org>
Reviewed-by: Greg Farnum <greg@inktan...
Gregory Farnum
10:21 PM Revision 10f66072 (ceph): Merge pull request #1372 from ceph/wip-7607
wip 7607
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
10:19 PM Revision b476d324 (ceph): Merge pull request #1366 from ceph/wip-6820.dumpling
mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump Sage Weil
10:19 PM Revision dd703345 (ceph): Merge pull request #1365 from ceph/wip-6820.emperor
mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump Sage Weil
10:18 PM Revision b093958a (ceph): Merge pull request #1351 from ceph/wip-7248
osd: OSD: limit the value of 'size' and 'count' on 'osd bench'
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
09:39 PM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
Several examples of this in the following run, but here is one job:
http://pulpito.front.sepia.ceph.com/teuthology...
Zack Cerza
09:17 PM Revision 240446e7 (ceph): test: merge unittest_crushwrapper and unittest_crush_wrapper
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:15 PM Revision 772968e6 (ceph): mon/OSDMonitor: disallow crush buckets of type 0
Prevent creation of buckets of type 0 ('osd', 'device', etc.), as they
will confusing the mapping algorithm.
Signed-...
Sage Weil
08:53 PM Revision 8b3934fc (ceph): PGBackend::rollback_stash: remove the correct shard
Fixes: #7616
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:52 PM Revision 1ddec86e (ceph): FileStore::_collection_move_rename: propogate EEXIST
Previously, an EEXIST would get masked by the subsequent clone
operation.
Signed-off-by: Samuel Just <sam.just@inkta...
Samuel Just
08:52 PM Revision ca12e0d9 (ceph): qa/workunits/mon/crush_ops: use expect_false
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:45 PM Revision d3e13a7c (ceph): Merge pull request #1377 from ceph/wip-7584
qa/workunit/rados/test-upgrade-firely.sh
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
08:39 PM Revision 9a8bf66d (ceph): ceph.conf.template: add in sensible erasure coding defaults
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:38 PM Revision c3766c58 (ceph): upgrade/dumpling-x: skip rados api tests that fail against firefly OSDs
Fixes: #7584
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:38 PM Revision e6698af8 (ceph): ceph_manager: fix erasure coding m, k values
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision 9c626e0b (ceph): qa/workunit/rados/test-upgrade-firely.sh
Skip the tests that don't pass when run against firefly OSDs.
Fixes: #7584
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
08:35 PM Revision 561869d9 (ceph): Merge pull request #1376 from ceph/wip-7608
test: Fix tiering test cases to use ---force-nonempty
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
08:31 PM Revision e016e83b (ceph): test: Fix tiering test cases to use ---force-nonempty
Fixes: #7608
Signed-off-by: David Zafman <david.zafman@inktank.com>
David Zafman
08:13 PM Revision e69da0a5 (ceph): Log job PID
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
07:59 PM Revision 05923680 (ceph): mon: warn when pool nears target max objects/bytes
The cache pools will throttle when they reach the target max size, so it
is important to make the administrator aware...
Sage Weil
07:07 PM Revision 8106adee (ceph): Merge pull request #1375 from ceph/wip-pgmap-stat
mon/PGMap: return empty stats if pool is not in sum
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil
06:44 PM Revision f6edceef (ceph): mon/PGMap: return empty stats if pool is not in sum
Greg was right!
When a pool is created, the PGs are not added to the PGMap until the *next*
proposal. Weaken the as...
Sage Weil
06:14 PM Revision c5f0e718 (ceph): Merge pull request #216 from ceph/wip-workunit-timeout
Add a 6h timeout to workunits Sage Weil
05:50 PM Revision dab02408 (ceph): Merge pull request #9 from ceph/wip-upgrade-dumpling
upgrade/dumpling: two fixes Zack Cerza
05:47 PM Bug #7593: Disk saturation during PG folder splitting
Sage Weil wrote:
> It is difficult to delay splitting without breaking the semantics.
Can you elaborate a little bi...
Guang Yang
09:44 AM Bug #7593: Disk saturation during PG folder splitting
It is difficult to delay splitting without breaking the semantics. The simplest way to throttle right now is to incr... Sage Weil
05:46 PM Revision 66ea0710 (ceph): Merge pull request #13 from ceph/wip-upgrade
a few upgrade fixes Zack Cerza
05:43 PM Bug #7623: local 'best' uninitialized in Objecter
osdc/Objecter.cc: In member function 'int Objecter::recalc_op_target(Objecter::Op*)':
warning: osdc/Objecter....
Dan Mick
05:40 PM Bug #7623 (Resolved): local 'best' uninitialized in Objecter
Dan Mick
05:42 PM Bug #7624 (Resolved): osd/ECBackend.cc: 1644: FAILED assert(r == 0)
Reading from clone needs to require readable on the clone.
ceph version 0.77-729-gd9e8806 (d9e8806308dcd6e52c6907...
Samuel Just
05:30 PM Revision f0ac0f67 (ceph): upgrade/dumpling-x/parallel: do all final workloads
Run all of the final workloads in succession instead of in separate tests.
Since we are not concerned about timing in...
Sage Weil
05:27 PM Revision bce605d3 (ceph): upgrade/dumpling-x: do not upgrade client host
If we are running against a mixed cluster for the duration of the upgrade,
we need to make sure we are running the *o...
Sage Weil
05:20 PM Revision 640ff98d (ceph): test: Use non-default out/ dev/ paths in vstart
Currently, running "make check" nukes any existing vstart
setup in the tree. This change makes it use test_dev/ and ...
John Spray
05:17 PM Revision c3c0b080 (ceph): Add a 6h timeout to workunits
The timeout is configurable, but defaults to six hours. It's implemented
by using the 'timeout' command on the remote...
Zack Cerza
04:52 PM Revision 4901347e (ceph): Merge pull request #1373 from ceph/wip-crush-json
crush: revise JSON format for 'item' type
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:30 PM devops Feature #7293 (Resolved): packaging: enable qemu to find librbd on rhev or rhel-osp
This is done and was commited/merged yesterday (wip-2793) sha1 65f3354903fdbdb81468a84b8049ff19c00f91ba Sandon Van Ness
04:28 PM Bug #7580 (Resolved): The package librados2-0.77-0.el6.x86_64.rpm is corrupt and won't install
Looks like the file was truncated during the copy process into the staging area. I re-did the repo's and re-sync'd wi... Sandon Van Ness
04:28 PM Revision 1685c6f7 (ceph): crush: revise JSON format for 'item' type
Commit a7e9a7b648 changed the JSON format of CRUSH rules
such that the 'item' attribute on a step was sometimes
an in...
John Spray
03:59 PM Bug #7621: ceph_test_rados_api_c_read_operations core dumped
Sorry my fault added the rados_release_read_op() call accidentally to the wrong line. It should have been like this:
...
Danny Al-Gaaf
03:18 PM Bug #7621 (Resolved): ceph_test_rados_api_c_read_operations core dumped
3f59f02913f4277f419052d546bb7448f74aec4d David Zafman
03:00 PM Bug #7621 (In Progress): ceph_test_rados_api_c_read_operations core dumped
The rados_release_read_op() that crashed it was added Mar 1 in 3cd751b0.
David Zafman
02:45 PM Bug #7621 (Resolved): ceph_test_rados_api_c_read_operations core dumped
2014-03-05 14:24:27,294.294 INFO:teuthology.task.workunit.client.0.err:[10.214.132.34]: 7fff7f956000-7fff7f957000 r-x... David Zafman
03:32 PM Bug #7618: osd/ECBackend.cc: 475: FAILED assert(r == 0)
Merged 1 fix, found another problem. Samuel Just
01:15 PM Bug #7618 (Resolved): osd/ECBackend.cc: 475: FAILED assert(r == 0)
recover_replicas must not assume that unfound objects are missing
red_to:921600, data_complete:false, omap_recover...
Samuel Just
03:31 PM Bug #7616 (Resolved): broken rollback_stash
Samuel Just
12:48 PM Bug #7616 (Resolved): broken rollback_stash
2014-03-04 22:35:48.598322 7f8e69953700 10 osd.4 459 do_waiters -- start
2014-03-04 22:35:48.598324 7f8e69953700 10 ...
Samuel Just
03:27 PM Bug #7590 (Fix Under Review): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap creat...
Sage Weil
02:47 PM Fix #7562 (Fix Under Review): mon: pretty-print of mon status should keep monitor ranks and names...
Sage Weil
02:24 PM Feature #7442 (Resolved): mon: health warn on pg "full"
Sage Weil
02:21 PM Bug #7607 (Resolved): ReplicatedPG::fill_in_copy_get: omap doesn't get filled in correctly for sm...
Sage Weil
02:19 PM Bug #6820 (Resolved): Bad commandline usage crashed my monitor
Sage Weil
02:18 PM Bug #7248 (Resolved): osd: bench set max size
Sage Weil
02:18 PM rbd Bug #7620 (Can't reproduce): BUG: soft lockup - CPU#0 stuck for 23s!
Noticed this hung job:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-04_19:01:51-rbd-dumpling-testing-bas...
Zack Cerza
02:12 PM Feature #7619 (Resolved): objecter: replace client_lock with fine grained read-write locks
Yehuda Sadeh
01:26 PM Bug #7610: Memory corruption during rados bench
Performed further tests with tcmalloc's HEAPCHECK but without much luck.
I also ran through the same tests with 3x...
Mark Nelson
11:08 AM Bug #7610: Memory corruption during rados bench
Ran rados under valgrind and valgrind is not happy, but I'm not sure it's really telling us much. Sam suspects gener... Mark Nelson
06:24 AM Bug #7610 (Resolved): Memory corruption during rados bench
This is ceph 0.77-655-g195d53a-1saucy
After doing parallel 4194306 byte object writes/reads to EC encoded pools vi...
Mark Nelson
12:56 PM Bug #7487 (Fix Under Review): mon: crashes when moving CRUSH items in zero-weighted tree?
The problem is adding a bucket of type 'osd'; fixing the mon to error out at that stage. Tested this with a normal t... Sage Weil
12:55 PM devops Bug #7617 (Resolved): ceph-deploy uninstall should document why it doesn't remove all relevant pa...
ceph-deploy uninstall on Precise left behind librbd1 and librados2 (dependencies, not explicitly installed); an audit... Dan Mick
12:41 PM Bug #7608 (Resolved): test/librados/tier.cc multiple -ENOTEMPTY failures
Sage Weil
12:30 PM Bug #7608 (Fix Under Review): test/librados/tier.cc multiple -ENOTEMPTY failures
David Zafman
09:37 AM Bug #7608 (In Progress): test/librados/tier.cc multiple -ENOTEMPTY failures
Sage Weil
11:55 AM rgw Bug #7597: hang in rados/test.sh
Unsure if this is identical:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-05_02:30:28-rados-firefly-testin...
Zack Cerza
07:47 AM rgw Bug #7597: hang in rados/test.sh
This job was running for over 60 hours:
http://pulpito.front.sepia.ceph.com/teuthology-2014-03-01_23:02:09-rbd-fir...
Zack Cerza
11:48 AM Feature #7599: erasure-code : upgrade to jerasure-2
suggest "sse detection at runtime":https://bitbucket.org/jimplank/gf-complete/issue/4/sse-capabilities-should-be-chec... Loïc Dachary
12:22 AM Feature #7599 (In Progress): erasure-code : upgrade to jerasure-2
requested release branches https://bitbucket.org/jimplank/jerasure/issue/3/v2-branch and https://bitbucket.org/jimpla... Loïc Dachary
09:59 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
I shouldn't have said anything -- minutes later the problem is now happening again. Matthew Via
09:47 AM CephFS Bug #7613: mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
Stopping the clients that were attempting to mount cephfs (by restarting them) appeared to let the mds start with no ... Matthew Via
08:48 AM CephFS Bug #7613 (Can't reproduce): mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
... Sage Weil
09:45 AM Bug #7611: All mon nodes crash when running "ceph tell osd.X" and using the "version" command
Easily reproduceable on 0.72.2; unable to reproduce on current master. Will further look into it. Joao Eduardo Luis
09:41 AM Bug #7611: All mon nodes crash when running "ceph tell osd.X" and using the "version" command
i think the reason why we never saw this is that nobody uses the interactive command.
joao, this sounds trivial to...
Sage Weil
07:48 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
I'm on 0.72.2 (a913ded2ff138aefb8cb84d347d72164099cfd60)
I did on one of the mon nodes:
$ ceph tell osd.151
...
Volker Voigt
09:26 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Still problem on 3/5/14 run http://pulpito.front.sepia.ceph.com/teuthology-2014-03-04_23:00:33-rgw-firefly-distro-bas... Yuri Weinstein
07:55 AM Revision 60a329f8 (ceph): Merge pull request #1338 from dachary/wip-mailmap
mailmap updates
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com>
Loïc Dachary
07:47 AM Revision d4950a1d (ceph): mailmap: Danny Al-Gaaf affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:47 AM Revision a85d0ef6 (ceph): mailmap: Steve Stock affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:47 AM Revision fdb644a2 (ceph): mailmap: Ron Allred affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:47 AM Revision 0eac1ba0 (ceph): mailmap: Bjørnar Ness affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:47 AM Revision 076bec85 (ceph): mailmap: Christopher O'Connell affiliation
Reviewed-by: Christopher O'Connell <jwriteclub@gmail.com>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:13 AM rbd Bug #7327 (Resolved): Assertion failure in rbd_object_request_destroy()
I see. In any case, it shouldn't crash anymore. If it pops up again,
you'll see something like...
Ilya Dryomov
05:06 AM Support #7609 (Resolved): http://tracker.ceph.com/account/register returns 500 Internal error
I tried to create an account on http://tracker.ceph.com/account/register, but it returned "Internal error" several ti... Volker Voigt
03:36 AM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
__queue_cap_release has code which limits the size of cap release message Zheng Yan
03:29 AM Revision 4cb1cbfb (ceph): ReplicatedPG::fill_in_copy_get: fix omap loop conditions
cursor.omap_offet indicates the most recently recovered key, we continue
filling in at the smallest key k | k > curso...
Samuel Just
03:29 AM Revision 11393ab7 (ceph): ReplicatedPG::fill_in_copy_get: remove extraneous if statement
This should leave the behavior unchanged.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
03:23 AM Revision 8fdfece9 (ceph): ReplicatedPG::fill_in_copy_get: fix early return bug
This is not a leak: we are in an else block where cb must
be NULL. The fix as introduced did not include braces on
t...
Samuel Just
03:22 AM Revision 4bf28df2 (ceph): Merge remote-tracking branch 'upstream/wip-7447' into firefly
Reviewed-by: Greg Farnum <greg@inktank.com> Samuel Just
02:55 AM Revision 364fed81 (ceph): packaging: use wildcard for test files in Debian
we can also use test_* instead of listing all test_xx files while
building debian package
Reviewed-by: Ken Dreyer <...
huang jun
02:02 AM Revision 225eb4a7 (ceph): Merge pull request #1370 from ceph/wip-7293
Make symlink of librbd to qemu's folder so it can detect it.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
12:15 AM Revision 65f33549 (ceph): Make symlink of librbd to qemu's folder so it can detect it.
Per issue #7293.
Signed-off-by: Sandon Van Ness <sandon@inktank.com>
Sandon Van Ness
12:09 AM Revision fb510c29 (ceph): Merge pull request #12 from ceph/wip-final-workload-wusui
Fix dumpling-x upgrade suite. wusui

03/04/2014

11:45 PM Revision 1929196d (ceph): Fix dumpling-x upgrade suite.
final-workload references were added (replacing second task
reference)
Fixes: 7606
Signed-off-by: Warren Usui <warre...
Warren Usui
11:29 PM Revision 308ea1bd (ceph): ECMsgTypes: fix constructor temp_added/temp_removed ordering to match u...
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:29 PM Revision f2a4eec1 (ceph): PGBackend/ECBackend: handle temp objects correctly
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
11:29 PM Revision d0b1094f (ceph): ECBackend,ReplicatedPG: delete temp if we didn't get the transaction
We always send the transaction for operations on temp objects,
but if we didn't get the final transacition on the act...
Samuel Just
11:27 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
You think the msg pointer is invalid, and so it's overflowing?
I'm a little concerned at just closing this unless we...
Greg Farnum
06:52 PM CephFS Bug #4722 (Can't reproduce): kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
it's more likely there is no pre-allocated message. variable 'msg' is pointing to the pre-allocated message list. Zheng Yan
11:00 PM Revision 3e219961 (ceph): ReplicatedPG::finish_ctx: use correct snapdir prior version in events
Fixes: #7595
Reviewed-by: Greg Farnum <greg@inktank.com>
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
09:24 PM Revision a7057e10 (ceph): doc: Improve CloudStack RBD documentation
Wido den Hollander
08:13 PM Revision 31eb533b (ceph): librados.cc: remove unused variable cpp_category
[src/librados/librados.cc:3083]: (style) Variable 'cpp_category' is
assigned a value that is never used.
Signed-off...
Danny Al-Gaaf
08:03 PM Bug #7608 (Resolved): test/librados/tier.cc multiple -ENOTEMPTY failures

Test against 784110c523fb3641752770f2ffe4a1bc20db5c7b
2014-03-04 18:27:18,975.975 INFO:teuthology.orchestra.run....
David Zafman
07:33 PM Bug #7601: "command crashed with signal 6" in rados-firefly-testing-basic-plana suite - hung tests
nvm Samuel Just
02:28 PM Bug #7601 (Duplicate): "command crashed with signal 6" in rados-firefly-testing-basic-plana suite...
We have none of latest rados runs on firefly completed cleanly, below is one of issues we are seeing.
Logs are in ...
Yuri Weinstein
07:27 PM Bug #7447 (Resolved): osd: copy_from temp objects interact awkwardly with backfill
Samuel Just
07:27 PM Bug #7604 (Resolved): osd/ReplicatedPG.cc: 5460: FAILED assert(cop->rval >= 0)
Samuel Just
03:22 PM Bug #7604 (Resolved): osd/ReplicatedPG.cc: 5460: FAILED assert(cop->rval >= 0)
~305,omap-set-vals 0~17634] 3.d889b14d snapc 8=[8,7,6] ack+ondisk+write e20) v4
0> 2014-03-04 14:42:57.209524 7...
Samuel Just
06:50 PM Revision c2cc1789 (ceph): ECBackend.cc: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
06:32 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
For the record, the Git repo has moved to the Ceph org: https://github.com/ceph/ceph-kmod-rpm
I've updated "the Je...
Ken Dreyer
05:02 PM Bug #7607 (Resolved): ReplicatedPG::fill_in_copy_get: omap doesn't get filled in correctly for sm...
Samuel Just
04:25 PM Revision 35ae7ed9 (ceph): ceph_argparse.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
03:48 PM Documentation #6465: admin/build-doc should have some kind of build check for broken links
John, do you need help resolving this? I really think that build checking buys us enough to warrant getting this wor... Dan Mick
03:42 PM devops Bug #7605 (Resolved): statup script /etc/init.d/ceph has incorrect slash
for centos / redhat users, the file /etc/init.d/ceph , which is the start-up script, line 326 is:
defaultweight="$...
Jan-Willem Michels
03:28 PM Revision c218c999 (ceph): Merge pull request #1357 from ceph/wip-dumpling-removewq
OSD: ping tphandle during pg removal
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
03:21 PM Bug #7595 (Resolved): osd/ReplicatedPG.cc: 2236: FAILED assert(snapset.seq)
Samuel Just
07:14 AM Bug #7595 (Fix Under Review): osd/ReplicatedPG.cc: 2236: FAILED assert(snapset.seq)
Samuel Just
07:13 AM Bug #7595 (Resolved): osd/ReplicatedPG.cc: 2236: FAILED assert(snapset.seq)
ReplicatedPG::finish_ctx() has wrong prior_version for DELETE snapdir op.
-6> 2014-03-03 21:12:18.647133 7f87c...
Samuel Just
03:21 PM Bug #7563 (Resolved): osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_up...
Samuel Just
03:02 PM Bug #7602 (Resolved): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys lo...
$ ./ceph-osd --show-config  | grep debug_
debug_none = 0/5
debug_lockdep = 0/1
debug_context = 0/1
debug_crush = ...
Danny Al-Gaaf
02:43 PM Revision 8c2b2d34 (ceph): PG.h: use !empty() instead of size() > 0
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision 39fc1db3 (ceph): KeyValueStore: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision 8f63fdb4 (ceph): Formatter::new_formatter(): pass const function parameter by reference
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision c2f3f2b5 (ceph): close file descriptor in error case
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision f8369094 (ceph): test_o_trunc.c: reduce scope of some variables
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision 35f20803 (ceph): SyntheticClient::play_trace: reduce scope of local variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision e4c4aaed (ceph): ErasureCodePlugin.cc: reduce scope of local variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision 3a786cad (ceph): test_o_trunc.c: fix indentation to kernel style (tabs, 8 spaces)
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:43 PM Revision 9e52695a (ceph): PG::generate_past_intervals: reduce scope of variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
12:30 PM Feature #7599 (Resolved): erasure-code : upgrade to jerasure-2
"work in progress":https://github.com/ceph/ceph/pull/1384
"gf-complete":https://bitbucket.org/jimplank/gf-complete...
Loïc Dachary
12:11 PM Revision 8bacdb63 (ceph): mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump
Code would assume a formatter would always be defined. If a 'plain'
formatter or even an invalid formatter were to be...
Joao Eduardo Luis
12:09 PM Revision 5133dd60 (ceph): mon: OSDMonitor: don't crash if formatter is invalid during osd crush dump
Code would assume a formatter would always be defined. If a 'plain'
formatter or even an invalid formatter were to be...
Joao Eduardo Luis
11:42 AM devops Bug #7598 (Can't reproduce): ceph-disk-activate error with ceph-deploy
ceph-disk-activate throws the following error to ceph-deploy yet it successfully creates the osd, please note this wa... Sheldon Mustard
11:41 AM Revision 4938212b (ceph): Merge pull request #1360 from enovance/wip-brag
Fixes for ceph-brag
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
11:23 AM Revision 724ad025 (ceph): doc: update the operator create pool reference
Include erasure code information. A choice is made to display properties
that should be documented as part of the era...
Loïc Dachary
11:20 AM devops Tasks #7230: Rebuild sync-agent packages for dumpling repo
Haven't seen any new commits to the repo yet so still waiting for the changes josh wanted to push before I made new p... Sandon Van Ness
11:04 AM devops Bug #7427 (Resolved): sha1 does not exist on gitbuilder, install fails
This was resolved either by using a different boost function or the code was reverted in ceph. Builds are now complet... Sandon Van Ness
10:45 AM rgw Bug #7597: hang in rados/test.sh
I was wrong, it's not a network problem.
From vpm104:...
Zack Cerza
08:47 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
Looking into a particular hung job:... Zack Cerza
08:52 AM Revision 74614106 (ceph): doc: erasure coded pool developer documentation
With a structure similar to doc/dev/cache-pool.rst
http://tracker.ceph.com/issues/7548 refs #7548
Signed-off-by: Lo...
Loïc Dachary
08:46 AM Revision 46b9f655 (ceph): Merge remote-tracking branch 'brag/master' into firefly
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
07:01 AM Revision 6d323c04 (ceph): mailmap: Mike Lundy affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
05:43 AM Revision d223d3a7 (ceph): Merge pull request #1352 from dachary/wip-7578
common: -- support for env_to_vec
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:37 AM Revision bcea57d6 (ceph): Merge pull request #1342 from ceph/wip-cache-add
mon: add 'osd tier add-cache ...' command (DNM until after wip-tier-add)
Reviewed-by: Loic Dachary <loic@dachary.org>
Sage Weil
05:36 AM Revision 397e8443 (ceph): Merge pull request #1335 from ceph/wip-tier-add
mon: prevent non-empty pools from being added as tiers
Reviewed-by: Greg Farnum <greg@inktank.com>
Sage Weil
05:19 AM Revision 48e55d98 (ceph): Merge pull request #1358 from ceph/wip-2288
mds: check projected xattr when handling setxattr
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:16 AM Revision eddf7b68 (ceph): osd/ReplicatedPG: fix agent division by zero
If the pool is empty we cannot divide by the object count.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:16 AM Revision 0e5fd0e3 (ceph): osd: make default bloom hit set fpp configurable
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:16 AM Revision 62e0eb7f (ceph): mon/OSDMonitor: handle 'osd tier add ...' race/corner case
If you have two racing requests to add two different pools as a tier, the
committed checks will pass but they proposa...
Sage Weil
05:16 AM Revision c029c2fb (ceph): mon/OSDMonitor: add 'osd tier add-cache <pool> <size>' command
This is a friendlier interface for setting up a cache tier with some
reasonable defaults (defined via config options)...
Sage Weil
05:16 AM Revision 241b9e81 (ceph): mon/OSDMonitor: fix some whitespace
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:16 AM Revision 49e54aba (ceph): mon/OSDMonitor: fix race in 'osd tier remove ...'
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:15 AM Revision 1684f1db (ceph): Merge pull request #1353 from ceph/wip-messenger-shutdown
msg: Make SimpleMessenger shutdown safer
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:11 AM Revision 08efb458 (ceph): OSDMonitor: do not add non-empty tier pool unless forced
In general, users should not use non-empty pools as new tiers or else
things can behave strangely:
- the data sets ...
Sage Weil
03:26 AM Subtask #7548 (Fix Under Review): Basic docs for Erasure Coding
Loïc Dachary
02:55 AM Revision 12909bb6 (ceph): mds: check projected xattr when handling setxattr
Fixes: #2288
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
01:05 AM Revision 198b0aa2 (ceph): Merge pull request #1354 from ceph/wip-7563
Wip 7563
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
12:59 AM Revision adb04f81 (ceph): Removed branch ref to fix http://tracker.ceph.com/issues/7584
Yuri Weinstein
12:38 AM Revision 192a27ca (ceph): Merge pull request #1355 from ceph/wip-osd-verbosity
osd: be a bit more verbose on startup
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
12:35 AM Revision 24711cd4 (ceph): OSD: ping tphandle during pg removal
Fixes: #6528
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry pic...
Samuel Just
12:16 AM Bug #7593 (Resolved): Disk saturation during PG folder splitting
This bug is a follow-up for issue 7207 (http://tracker.ceph.com/issues/7207), with the lock contention issue fixed, w... Guang Yang
12:07 AM Revision 8e889225 (ceph): Update rados_api_tests.yaml
Removed branch ref to fix http://tracker.ceph.com/issues/7584 Yuri Weinstein
12:05 AM Revision 97f35960 (ceph): TestPGLog::proc_replica_log: add prior_version to some entries
Otherwise, the test logs are invalid.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
12:05 AM Revision 6b6065ab (ceph): TestPGLog::proc_replica_log: adjust to corrected proc_replica_log behavior
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:05 AM Revision 9a64947c (ceph): TestPGLog::proc_replica_log: adjust wonky test
This test didn't quite make sense since the divergent entry
cannot be from a newer epoch. It also didn't quite match...
Samuel Just
12:05 AM Revision 20fe162e (ceph): TestPGLog: tests for proc_replica_log/merge_log equivalence
We need the merge_log and proc_replica_log paths to result in the
same missing set. This patch adds some machinery f...
Samuel Just
12:05 AM Revision b0357abc (ceph): PG.h:PGLogEntryHandler: remove silly cant_rollback logic
Also, we now call rollback in a reverse order, so there is no
need to reverse the entries again.
Signed-off-by: Samu...
Samuel Just
12:05 AM Revision 200e2964 (ceph): PGLog::proc_replica_log: _merge_divergent_entries based on truncated olog
We can't merge using the primary's log since we haven't decided whether
to send them a complete log yet. Thus, merge...
Samuel Just
12:05 AM Revision c99b7e19 (ceph): PG,PGLog: replace _merge_old_entry with _merge_object_divergent_entries
The _merge_old_entry structure had trouble distinguishing between the
following cases:
missing: foo, 1,1
merge_old_e...
Samuel Just
12:05 AM Revision 3cc9e226 (ceph): TestPGLog: not worth maintaining tests of assert behavior
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:05 AM Revision 9e43dd6e (ceph): TestPGLog: ignore merge_old_entry return value
No callers use the merge_old_entry return value. _merge_divergent_entries
won't have one.
Signed-off-by: Samuel Jus...
Samuel Just
12:05 AM Revision ff329ac5 (ceph): TestPGLog:rewind_divergent_log: set prior_version for delete
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
12:05 AM Revision 3dc4f10a (ceph): TestPGLog::merge_old_entry: we no longer use merge_old_entry this way
This needs to be replaced with an equivalent test of
_merge_object_divergent_entries.
Signed-off-by: Samuel Just <sa...
Samuel Just
12:05 AM Revision 86b21e0b (ceph): TestPGLog::merge_old_entry: ne.version cannot be oe.version
Otherwise, it would not be divergent!
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just

03/03/2014

10:48 PM CephFS Bug #2679 (Can't reproduce): POSIX file lock not released on process termination
Zheng Yan
10:47 PM Revision dda72dee (ceph): Merge pull request #1356 from ceph/wip-7458
osd: stray pg ref on shutdown
Reviewed-by: Samuel Just <sam.just@inktank.com>
David Zafman
09:53 PM Revision a234053d (ceph): OSD,config_opts: log osd state changes at level 0 instead
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:43 PM Bug #7578 (Resolved): end of options ( -- ) disables CEPH_ARGS
Sage Weil
09:24 AM Bug #7578 (Fix Under Review): end of options ( -- ) disables CEPH_ARGS
Loïc Dachary
09:37 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
Sage Weil
09:20 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
commit:48e55d9 is in master and contains the simpler handle_client_setxattr() fix discussed above. Thanks Zheng! Greg Farnum
06:31 PM CephFS Bug #2288 (Resolved): libcephfs: setxattr returns EEXIST following removexattr
Zheng Yan
08:47 PM Revision 963fb881 (ceph): Merge pull request #215 from dachary/wip-ec-pool
ceph-manager: fix ec_pool parameters Zack Cerza
07:21 PM Revision fd9c29b9 (ceph): Merge pull request #1341 from ceph/wip-osd-status
osd: 'status' admin socket command
Reviewed-by: Loic Dachary <loic@dachary.org>
Sage Weil
07:16 PM Revision 68890b20 (ceph): osd: be a bit more verbose on startup
load_pgs can take a while and it is nice to know what ceph-osd is doing
without cranking up logging.
Did a quick aud...
Sage Weil
07:05 PM Revision 4e06dfd9 (ceph): msg: Make SimpleMessenger shutdown safer
...in the case where no dispatchers were ever added, previously
we would throw an assertion in wait().
Signed-off-by...
John Spray
06:50 PM Bug #7592 (Resolved): hit_set_trim() removal races with backfill

/a/dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana/111513
osd.4 the primary was backfillin...
David Zafman
06:41 PM Revision 82f62b1e (ceph): Merge pull request #1329 from ceph/wip-doc-cache-pool
fix up docs for cache pools
These are definitely not complete, but they bring a few of the commands more up to date ...
Gregory Farnum
06:37 PM Revision bd9913ce (ceph): Merge branch 'wip-hint' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
Ilya Dryomov
06:33 PM Revision 64568023 (ceph): osd: add SETALLOCHINT operation
This is primarily for librbd/krbd's benefit and is supposed to combat
fragmentation:
"... knowing that rbd images ha...
Ilya Dryomov
06:33 PM Revision 391257c0 (ceph): FileStore: refactor FS detection checks a bit
Refactor FS detection checks in FileStore::_detect_fs() so that they
look the same as the ones in FileStore::mkfs(). ...
Ilya Dryomov
06:33 PM Revision 1f5b796f (ceph): FileStore: introduce XfsFileStoreBackend class
Introduce XfsFileStoreBackend class, currently the only filestore
backend implementing SETALLOCHINT op. This commit ...
Ilya Dryomov
06:33 PM Revision 8e49bc32 (ceph): FileStore: add option to cap alloc hint size
Add a new config option, filestore_max_alloc_hint_size, to cap
SETALLOCHINT hint size. The unit is a byte, the defau...
Ilya Dryomov
06:33 PM Revision 371a80cb (ceph): librbd: prefix rbd writes with CEPH_OSD_OP_SETALLOCHINT osd op
In an effort to reduce fragmentation, prefix every rbd write with
a CEPH_OSD_OP_SETALLOCHINT osd op with an expected_...
Ilya Dryomov
06:17 PM CephFS Bug #2445 (Can't reproduce): crash when removing a non-empty directory
Zheng Yan
06:16 PM CephFS Bug #1877 (Can't reproduce): ceph.ko (3.1.6) oopses upon cephfs set_layout of a symlink to a dir
Zheng Yan
05:17 PM Revision 8982734a (ceph): common: -- support for env_to_vec
When CEPH_ARGS is parsed each side of the -- must be appended to the
corresponding side of the existing argument list...
Loïc Dachary
05:07 PM Revision 28c29c1d (ceph): Revert "ObjectCacher: remove unused target/max setters"
This reverts commit e1a49e5386c3ed4a6bc4870f01630349cb04d749. Josh Durgin
05:04 PM Revision d00a9272 (ceph): Revert "librbd: remove limit on number of objects in the cache"
Disabling this limit causes too much memory usage in some
workloads.
This reverts commit 0559d31db29ea83bdb6cec72b83...
Josh Durgin
05:01 PM Bug #7590 (Resolved): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap create <base>...
... Sage Weil
04:57 PM rgw Feature #7589 (Resolved): rgw: configurable chunk size
Yehuda Sadeh
04:51 PM Revision 195d53a7 (ceph): rgw: off-by-one in rgw_trim_whitespace()
Fixes: #7543
Backport: dumpling
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Ray Lv <raylv@yahoo-in...
Ray Lv
04:24 PM Revision b7274170 (ceph): Merge pull request #11 from ceph/wip-7581
increase verbosity for OSDs for ceph-deploy tests Zack Cerza
04:24 PM Revision 3006f231 (ceph): Merge pull request #207 from ceph/wip-7356
helper for bombing out of infinite loops Zack Cerza
04:16 PM Bug #7563: osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_update)
We may need to backport a version of this to dumpling/emperor. Samuel Just
03:35 PM Bug #7563: osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_update)
Samuel Just
04:15 PM Bug #6313 (Duplicate): dumpling: FAILED assert(latest->is_update()) from recover_primary()
I've got a better explanatino in 7563, so I'm marking this one as a dup. Samuel Just
03:34 PM Bug #6313 (In Progress): dumpling: FAILED assert(latest->is_update()) from recover_primary()
Samuel Just
03:34 PM Bug #6313 (Fix Under Review): dumpling: FAILED assert(latest->is_update()) from recover_primary()
Samuel Just
01:48 PM Bug #6313: dumpling: FAILED assert(latest->is_update()) from recover_primary()

Seen
/a/dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana/111683
David Zafman
04:11 PM Cleanup #7586: deprecate rados_pool_create
... Loïc Dachary
02:33 PM Cleanup #7586 (New): deprecate rados_pool_create
"rados_pool_create":http://ceph.com/docs/master/rados/api/librados/#rados_pool_create must support properties to enab... Loïc Dachary
04:04 PM Revision 2bf27024 (ceph): increase verbosity for OSDs for ceph-deploy tests
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
04:00 PM Bug #7588 (Resolved): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::...
"ceph-osd.1.log.gz":http://dachary.org/loic/ceph-osd.1.log.gz
"dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-t...
David Zafman
03:59 PM Revision 37e78173 (ceph): In database delete Session.flush() has to be called appropriately, to a...
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
03:59 PM Revision f3d64919 (ceph): Following changes are made
1. Increased the String length for distro, version and os_desc columns in osds_info table
2. Corrected version inform...
Babu Shanmugam
03:59 PM Revision 3cc8b275 (ceph): Modifed the String variables in db.py to be of fixed length to support ...
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
03:58 PM Revision 30a5bdb8 (ceph): Added an instruction in 'How to deploy' field in README.md
Signed-off-by: Babu Shanmugam <anbu@enovance.com> Babu Shanmugam
03:57 PM Bug #7587 (Duplicate): Failure of LibRadosTwoPoolsPP.PromoteSnap

/a/dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana/111697
2014-03-01T01:20:56.946 INFO:teu...
David Zafman
03:56 PM Bug #6003: journal Unable to read past sequence 406 ...
/a/dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana/111738... David Zafman
03:35 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
Samuel Just
03:28 PM Revision aca6ac34 (ceph): qa: workunits: cephtool: test 'osd bench' limits
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
03:08 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
123ff9e18a27c6517a291aab1e0613b27d70d711 David Zafman
12:42 PM Bug #7458 (Fix Under Review): osd: stray pg ref on shutdown
David Zafman
03:08 PM Feature #7438: EC: adapt watch/notify stress test for EC and add to nightly
David Zafman
12:42 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
David Zafman
03:03 PM Revision 09099c9e (ceph): osd: 'status' admin socket command
Basic stuff, like what state is the OSD in, and what osdmap epoch are
we on.
Signed-off-by: Sage Weil <sage@inktank....
Sage Weil
02:59 PM Revision ffdfb846 (ceph): Merge pull request #1327 from dachary/wip-7423
osd: do not attempt to read past the object size
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:41 PM Revision 25a9bd32 (ceph): osd: OSD: limit the value of 'size' and 'count' on 'osd bench'
Otherwise, a high enough 'count' value will trigger all sorts of timeouts
on the OSD; a low enough 'size' value will ...
Joao Eduardo Luis
01:58 PM devops Bug #7585 (Resolved): ceph-deploy should handle requiretty failures
This is unacceptable:... Alfredo Deza
12:43 PM Bug #7406 (New): Seg fault in find_object_context()in recent master rados run
David Zafman
10:23 AM Bug #7406 (In Progress): Seg fault in find_object_context()in recent master rados run
David Zafman
12:08 PM rbd Bug #7327: Assertion failure in rbd_object_request_destroy()
Ilya Dryomov wrote:
>[snip]
> Now, a NULL from bio_chain_clone_range() might too be ENOMEM, but it
> might also b...
Nathaniel Filardo
07:42 AM rbd Bug #7327 (Fix Under Review): Assertion failure in rbd_object_request_destroy()
OK, so this turned out to be just a busted error path. After finding
that exact debian rbd.ko and some fiddling wit...
Ilya Dryomov
12:04 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana
Jobs:
111547
111687
111727
David Zafman
10:38 AM rbd Bug #7583 (Resolved): "librbd::ImageCtx: error finding header" in upgrade:dumpling-x-firefly---ba...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-03-01_22:00:03-upgrade:dumpling-x-firefly---basic-plana/1133... Yuri Weinstein
09:53 AM Feature #7442 (Fix Under Review): mon: health warn on pg "full"
Sage Weil
09:52 AM Linux kernel client Feature #6163 (Resolved): support caching pool and redirects
Sage Weil
09:42 AM Bug #7576: osd: large skew in pg epochs (dumpling)
Hmm, this is partly deliberate — we allow PGs to move forward "at their own pace", so if they aren't getting any acti... Greg Farnum
09:34 AM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...
Sage Weil
09:19 AM Bug #7448 (In Progress): os/FileJournal.cc: FAILED assert(fd >= 0)
Joao Eduardo Luis
09:14 AM rbd Bug #7582 (Resolved): "FAIL: test_rbd.TestImage.test_remove_with_watcher" in upgrade:dumpling-x-f...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-03-01_22:00:03-upgrade:dumpling-x-firefly---basic-plana/1134... Yuri Weinstein
08:46 AM rgw Bug #7543 (Pending Backport): rgw: off-by-one bug in rgw_trim_whitespace()
Yehuda Sadeh
08:28 AM Revision ef25135e (ceph): erasure-code: test rados put and get
Check that rados put immediately followed by rados get retrieves exactly
the same content.
http://tracker.ceph.com/i...
Loïc Dachary
08:28 AM Revision cababd92 (ceph): mon: add mon-test-helpers.sh to EXTRA_DIST
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:28 AM Revision eb21bc80 (ceph): osd: helper to create an OSD for functional tests
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
08:28 AM Revision 0b612d10 (ceph): mon: prepend current directory to PATH for tests
So that binaries found in the source directory are always prefered to
installed binaries or scripts.
Signed-off-by: ...
Loïc Dachary
08:28 AM Revision 927153f5 (ceph): osd: do not attempt to read past the object size
When reading from a replicated pool, trying to read more than the object
size results in a short read that does not g...
Loïc Dachary
07:56 AM Revision 9dd6e34c (ceph): mailmap: Mouad Benchchaoui affiliation
Signed-off-by: Loic Dachary <loic@dachary.org> Loïc Dachary
07:55 AM Revision e7820512 (ceph): mailmap: Andrey Kuznetsov affiliation
Reviewed-by: Andrey Kuznetsov <Andrey_Kuznetsov@epam.com>
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:55 AM Revision 7b6d4171 (ceph): mailmap: Wang, Yaguang affiliation
and name normalization
Reviewed-by: Wang, Yaguang <yaguang.wang@intel.com>
Signed-off-by: Loic Dachary <loic@dachary...
Loïc Dachary
06:59 AM Bug #7423 (Resolved): erasure code: ./rados get retrieves a larger object
Sage Weil
06:55 AM CephFS Bug #1874 (Can't reproduce): Running `git gc` on a bare git repository hosted by ceph results in ...
Greg Farnum
06:31 AM CephFS Bug #1874: Running `git gc` on a bare git repository hosted by ceph results in a bus error.
Hi,
I have since moved on, but (as it happens) am currently investigating the production use of Ceph at the Univer...
David McBride
06:51 AM Feature #7571 (Fix Under Review): erasure code: implicit ruleset creation when a pool is created
Loïc Dachary
06:20 AM Bug #7580 (Resolved): The package librados2-0.77-0.el6.x86_64.rpm is corrupt and won't install
While updating to the new 0.77 version of Ceph I encountered the following problem:
The new librados2 package is o...
Jasper Siero
05:06 AM Revision 10f87fc6 (ceph): Merge pull request #1344 from ceph/wip-7539
Wip 7539
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:56 AM Bug #7116: mon: pg_temp left behind if pool deleted while pg_temp exist
Is there a way cleanup orphaned pg_temp's that are in a cluster from before this patch existed? We still have quite a... Dan van der Ster
12:11 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
Hi,
not sure if it's the same bug or not :
> Assertion failure in rbd_img_obj_callback() at line 2133
> rbd_asse...
Olivier Bonvalet

03/02/2014

11:07 PM Revision 16b1cc45 (ceph): Merge pull request #1345 from leseb/wip-ceph-disk-typo
Fix typo ceph-disk
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
10:51 PM Revision 855edc6e (ceph): Fix typo ceph-disk
Fix typo
Signed-off-by: Sébastien Han <sebastien.han@enovance.com>
Sébastien Han
09:05 PM Bug #7539 (Resolved): Firefly EC pool massive memory leak during writes
Sage Weil
08:51 PM Revision 4e4f4cc1 (ceph): Merge pull request #1322 from ceph/wip-librados-end-iterator
librados: fix ObjectIterator::operator= for the end iterator
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
12:55 PM Bug #7538 (Resolved): librados: rados ls crashes on firefly due to segfault in ObjectIterator::op...
Sage Weil
09:59 AM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...

Log came from dzafman-2014-02-28_12:09:58-rados:thrash-wip-7458-testing-basic-plana/111634
David Zafman
08:32 AM Bug #7578 (Resolved): end of options ( -- ) disables CEPH_ARGS
"work in progress":https://github.com/ceph/ceph/pull/1352
When -- is used on the command line to separate the opti...
Loïc Dachary
07:53 AM Revision 43b7b0b4 (ceph): mailmap: The Linux Box affiliations
Matt Benjamin, Adam C. Emerson and Casey Bodley are with The Linux Box
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
07:41 AM rbd Bug #7577 (Resolved): rbd info displays extra random char in block prefix
The rbd cli in dumpling 0.67.7 displays an extra random char at the end of the block prefix string:
[root@p0100153...
Dan van der Ster
03:56 AM Revision 32a4e903 (ceph): Merge pull request #1337 from ceph/wip-fix-coverity-20140228
Fix different issues found by Coverity
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:54 AM Revision 4bf32c66 (ceph): Merge pull request #1336 from ceph/wip-nfs-export
Wip nfs export
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil

03/01/2014

11:41 PM Revision 7889acbf (ceph): ceph-manager: fix ec_pool parameters
* the crush ruleset and the pool create parameters must be identicals
k=2 m= 1
* the --property argument is invalid...
Loïc Dachary
10:54 PM Revision 59ff572f (ceph): OpTracker: clarify that unregister_inflight_op is only called if enabled
The !tracking_enabled branch actually had a leak which was unreachable
since the caller does the check for tracking_e...
Samuel Just
10:54 PM Revision 718cda6e (ceph): TrackedOp: clear_payload as well in unregister_inflight_op
We want to minimize the cost of maintaining the historic ops.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:54 PM Revision d4118e15 (ceph): MOSDECSubOpWrite: drop transaction, log_entries in clear_buffers
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:54 PM Revision 62fd382f (ceph): osd_types,PG: trim mod_desc for log entries to min size
In the event that mod_desc.bl contains pointers into a large
message buffer, we'd otherwise end up keeping around the...
Samuel Just
10:53 PM Revision fc9b8ef0 (ceph): MOSDOp: drop ops vector in clear_data()
Otherwise, clear_data on MOSDOp will leave essentially
all of the buffers intact. This is a problem since the
OpTrac...
Samuel Just
10:53 PM Revision 1ea59f6c (ceph): ReplicatedPG: delete mark_all_unfound_lost transactions after completion
This was a minor memory leak.
Signed-off-by: Greg Farnum <greg@inktank.com>
Greg Farnum
07:13 PM Bug #7576 (Resolved): osd: large skew in pg epochs (dumpling)
Observed a cluster with pgs at very different pg epochs (~17000 and ~24000). This isn't supposed to happen on start ... Sage Weil
05:46 PM Revision 84ba4cf2 (ceph): Merge pull request #1339 from ceph/wip-7572
mon: fix 'pg dump' JSON output
Reviewed-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
05:13 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...

2014-03-01 00:13:39.895495 7efefcde2700 10 osd.4 pg_epoch: 76 pg[4.1( v 74'1454 lc 17'513 (0'0,74'1454] local-les=7...
David Zafman
05:05 PM Revision e19dffb8 (ceph): mon: fix 'pg dump' JSON output
This was broken by 40bdcb88. The 'acting' array had
the up_primary and acting_primary appended.
Fixes: #7572
Signe...
John Spray
03:58 PM Bug #6736 (Resolved): Bugs in per pool IOPs/recovery statistics
Loïc Dachary
03:56 PM Subtask #5487 (Closed): Factor out ObjectContext / ReplicatedPG::object_contexts
Obsoleted. Loïc Dachary
03:55 PM Subtask #6895 (Rejected): omap needs to be disablable on a per-pool basis, this needs to be requi...
Not needed. Loïc Dachary
03:10 PM Bug #7542 (Resolved): ec misdirected op
Samuel Just
01:26 PM Revision 1a4657a3 (ceph): req_state: fix uninitialized bool var
CID 717359 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
uninit_member: Non-static class member "bucket_exists...
Danny Al-Gaaf
12:45 PM Revision 605e6450 (ceph): Objecter::recalc_op_target: fix uninitialized scalar variable
CID 1160848 (#1 of 1): Uninitialized scalar variable (UNINIT)
uninit_use: Using uninitialized value "best".
Init 'b...
Danny Al-Gaaf
12:33 PM Revision 754a3689 (ceph): PGMonitor: fix uninitialized scalar variable
Fix type handling in dump_stuck_pg_stats. If type is type doesn't
match to known PGMap::STUCK_* type print out a mess...
Danny Al-Gaaf
12:11 PM Revision 1747c589 (ceph): MDCache: fix potential null pointer deref
CID 716921 (#1 of 1): Dereference after null check (FORWARD_NULL)
var_deref_model: Passing null pointer "dir" to fun...
Danny Al-Gaaf
11:10 AM Revision 93c09836 (ceph): MDCache::handle_discover: fix null pointer deref
CID 716990 (#1 of 1): Dereference null return value (NULL_RETURNS)
dereference: Dereferencing a pointer that might b...
Danny Al-Gaaf
10:53 AM Revision 249e2107 (ceph): FileStore: fix resource leak in queue_transactions() blackhole case
CID 1135931 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "ondisk" going out of scope leaks the ...
Danny Al-Gaaf
10:44 AM Revision 3cd751b0 (ceph): c_read_operations.cc: fix resource leak
CID 1188154 (#2 of 2): Resource leak (RESOURCE_LEAK)
overwrite_var: Overwriting "op" in "op = rados_create_read_op()...
Danny Al-Gaaf
10:36 AM Revision ad9b6d2f (ceph): c_write_operations.cc: fix some ioctx resource leaks
CID 1160833 (#3 of 3): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "ioctx" going out of scope leaks the s...
Danny Al-Gaaf
10:16 AM Revision e8533ee4 (ceph): ReplicatedBackend: check result of dynamic_cast to fix null pointer deref
CID 1188135 (#1 of 1): Unchecked dynamic_cast (FORWARD_NULL)
var_deref_model: Passing null pointer "t" to function
...
Danny Al-Gaaf
10:02 AM Revision 8d6b25a1 (ceph): mds: use "lookup-by-ino" helper to handle LOOKUPPARENT request
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
09:48 AM Bug #7572 (Resolved): Bad 'acting' array in JSON 'pg dump' output
Do you happen to know why the commit shows three times as associated to this issue ? Loïc Dachary
09:05 AM Bug #7572 (Fix Under Review): Bad 'acting' array in JSON 'pg dump' output
https://github.com/ceph/ceph/pull/1339 John Spray
08:58 AM Bug #7572 (Resolved): Bad 'acting' array in JSON 'pg dump' output

Example:...
John Spray
09:29 AM RADOS Feature #7573 (New): Add an epoch argument to 'osd crush dump'

For management apps like calamari, we would like to be able to grab the "osd dump" and "crush dump" data reliably f...
John Spray
09:21 AM Revision f3976c16 (ceph): Merge pull request #1334 from kazhang/wip-get-hit_set-parameter
OSDMonitor: enable getting hit set parameters
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
08:22 AM Revision dc20c7d6 (ceph): OSDMonitor: enable getting hit set parameters
We would like to get the hit set parameters: hit_set_type |
hit_set_period | hit_set_count | hit_set_fpp via OSDMonit...
Kai Zhang
05:57 AM Revision 332c0e24 (ceph): Merge pull request #1333 from ceph/wip-s3radoscheck-wusui
Use pgrep radosgw to determine if rados gateway is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
05:43 AM Revision 5b88856c (ceph): Use pgrep radosgw to determine if rados gateway is running.
Fixes: 7528
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
05:13 AM Revision 0ed63fd3 (ceph): client: fix Client::trim_caps()
allow trimming non-auth caps if the issued auth caps include all
caps client wants/uses.
Signed-off-by: Yan, Zheng <...
Yan, Zheng
05:13 AM Revision cdbe413c (ceph): client: update dirfragtree/fragmap according to mds request reply
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:08 AM Revision 63e34639 (ceph): Merge pull request #1326 from ceph/wip-7542
Wip 7542
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
05:04 AM Revision a7b7c311 (ceph): client: use ceph_seq_cmp() to compare cap seq/mseq
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:04 AM Revision 1ddc951b (ceph): client: remove exported caps when handling cap import message
Version 3 cap import message includes the ID of the exported
caps. It allow us to remove the exported caps if we stil...
Yan, Zheng
05:04 AM Revision 4bdecf1c (ceph): client: add imported caps when handling cap export message
Version 3 cap export message includes information about the imported
caps. It allows us to add the imported caps if t...
Yan, Zheng
05:04 AM Revision 0638d612 (ceph): client: add flushing inode to proper list when auth mds changes
add flushing inode to the new auth MDS' flushing caps list
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
05:04 AM Revision 23de48b2 (ceph): client: check inode's cap when looking up dentry
Some inodes in readdir reply may have no caps. Getattr mds request
for these inodes can return -ESTALE. The fix is co...
Yan, Zheng
05:04 AM Revision 214977ab (ceph): client: choose hash function according to dir layout
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
05:04 AM Revision 3dd323e2 (ceph): client: don't send cap release when removing exported cap
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:46 AM Feature #7457 (Fix Under Review): mon: prevent addition of non-empty pools as a tier
Sage Weil
12:24 AM Revision 0bf5f866 (ceph): store_test.cc: fix unchecked return value
CID 1188126 (#1 of 1): Unchecked return value (CHECKED_RETURN)
2. check_return: Calling function "ObjectStore::stat(...
Danny Al-Gaaf

02/28/2014

11:32 PM Revision a01d3ca8 (ceph): Merge pull request #213 from ceph/wip-kdb-except
Allow setting kdb to fail. Alfredo Deza
11:19 PM Revision 7eefe85c (ceph): histogram.h: fix potential div by zero
CID 1188131 (#1 of 1): Division or modulo by zero (DIVIDE_BY_ZERO)
divide_by_zero: In expression "lower_sum * 100000...
Danny Al-Gaaf
11:04 PM Revision 500206d8 (ceph): ReplicatedPG.cc: fix ressource leak, delete cb
CID 1188145 (#1 of 1): Resource leak (RESOURCE_LEAK)
leaked_storage: Variable "cb" going out of scope leaks the stor...
Danny Al-Gaaf
10:16 PM Revision fd507ed3 (ceph): Allow setting kdb to fail.
Some kernels (primarily Debian distro kernels) do not support
setting kdb. Rather than having the entire test fail.
...
Sandon Van Ness
10:09 PM Revision 84decc11 (ceph): Merge pull request #1331 from ceph/wip-cache-pool
mon/OSDMonitor: make default false-positive-probability 5%
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
07:27 PM Revision fbb1ec88 (ceph): ECBackend: don't leak transactions
Fixes: #7539
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
07:26 PM Revision b0d42644 (ceph): OSD::handle_misdirected_op: handle ops to the wrong shard
OSD recomputes op target based on current OSDMap. With an EC pg, we can get
this result:
1) client at map 512 sends a...
Samuel Just
07:13 PM Revision 4f31eb01 (ceph): Merge pull request #212 from ceph/wip-limit
Added --limit option to teuthology-suite. wusui
07:12 PM Revision 123ff9e1 (ceph): osd: stray pg ref on shutdown
Move agent_clear() from only being done when becoming replica
Do it in clear_primary_state() whenever we stop being...
David Zafman
05:35 PM Revision 07ddfcfa (ceph): Merge pull request #1332 from ceph/wip-pg-msg
mon/OSDMonitor: missing space in string
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@da...
Loïc Dachary
05:16 PM Revision 448fc0e9 (ceph): mon/OSDMonitor: missing space in string
Minor glitch. Was printing ..."exceeds per-OSD max of32)"
Signed-off-by: John Spray <john.spray@inktank.com>
John Spray
05:04 PM Revision 4b5338fa (ceph): Merge pull request #211 from ceph/wip-7554
mds_thrash #7554 Zack Cerza
04:34 PM Revision 799cde0a (ceph): Fix python-requests package dependencies.
python-ceph does not require requests, but ceph-common does (for ceph-brag).
Signed-off-by: Dan Mick <dan.mick@inkta...
Dan Mick
04:34 PM Revision 4baa632e (ceph): Merge pull request #1323 from ceph/wip-requests-dependencies
Fix python-requests package dependencies.
Backport: firefly
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
04:16 PM Revision bfad17bf (ceph): librados: fix ObjectIterator::operator= for the end iterator
We can't set a shared_ptr to NULL, we need to reset it instead. Add
another test for various permutations of this.
F...
Josh Durgin
04:11 PM Revision a850a387 (ceph): doc/dev/cache-pool: fix notes
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
04:06 PM Revision f0241c8a (ceph): mon/OSDMonitor: make default false-positive-probability 5%
This is a more conservative default (as in, less memory consumed) for
newly created cache pools.
Signed-off-by: Sage...
Sage Weil
03:40 PM Feature #7571 (Resolved): erasure code: implicit ruleset creation when a pool is created
"work in progress":https://github.com/ceph/ceph/pull/1350
Here is the current, mandatory, sequence to create an er...
Loïc Dachary
03:08 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
Okay, leaving this alone for the moment — that patch is a good start, and I think the MDLog stuff is actually okay (b... Greg Farnum
02:02 PM CephFS Bug #7565: Failed assert in check_rstats
What's the bug with check_rstats? Is num_head_items just not expected to be valid at this stage of replay?
Either ...
Greg Farnum
01:44 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
Unless this part has been fixed by a newer kernel, we still need to deal with it. In particular we were concerned tha... Greg Farnum
12:35 PM Bug #7539: Firefly EC pool massive memory leak during writes
Ran more tests on 0.77-619-gfbb1ec8-1saucy, still seeing lots of memory usage. Ran with optracker debugging, output ... Mark Nelson
06:55 AM Bug #7539: Firefly EC pool massive memory leak during writes
Tested wip-7542 this morning using 0.77-616-g36fda70-1saucy. Still seeing rapid memory growth (without valgrind, abo... Mark Nelson
06:58 AM Feature #7567 (Closed): mon: 'service network', 'cluster network', 'admin network'
Currently clients, daemons, monitor peers, and admins all use the same monitor IP to communicate.
Extend the monma...
Sage Weil
05:09 AM Bug #7423: erasure code: ./rados get retrieves a larger object
It is likely not the proper way to fix it. It seems to work but it may be better to make it so ECBackend.cc does not ... Loïc Dachary
05:07 AM Bug #7423 (Fix Under Review): erasure code: ./rados get retrieves a larger object
Loïc Dachary
12:34 AM Revision bd9748d5 (ceph): Added --limit option to teuthology-suite.
Use --limit to limit the number of jobs being scheduled during
teuthology-suite. Also can be used with schedule_suite...
Yuri Weinstein

02/27/2014

09:29 PM CephFS Cleanup #3742 (Resolved): Remove old Hadoop wrappers and configuration options
Noah Watkins
09:27 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Actually, yeh I'll look at this. Noah Watkins
03:30 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
Is this still an issue, Noah? Greg Farnum
09:23 PM CephFS Bug #4861 (Rejected): Alter Java components to build against Java 1.6 (or 1.7)
Noah Watkins
09:23 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Closing. I'm not sure what the problem is here.. it looks like I am saying that the code builds for a super old versi... Noah Watkins
03:26 PM CephFS Bug #4861: Alter Java components to build against Java 1.6 (or 1.7)
Do you know the state of the Java code right now, Noah? I wonder if this got done already or is still a bug requiring... Greg Farnum
07:29 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
The race still exists, but I don't think it's big problem. Because even if ceph_get_dentry_parent_inode() returns a w... Zheng Yan
04:03 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
Is this still a problem? Greg Farnum
06:39 PM Revision 22825c25 (ceph): mds_thrash: Refactor gevent usage + get traceback
This simplifies the code to make MdsTrash be a greenlet
(as it logically is) rather than encapsulating one that
gets ...
John Spray
06:39 PM Revision 8dfcfa4a (ceph): mds_thrash: Fix a potential getitem on None
get_mds_status returns None for things it can't see,
so have to check for Noneness on all its outputs.
Signed-off-by...
John Spray
05:14 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
who cares 3.5 kernel? Zheng Yan
03:28 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
Sounds like this might require some protocol work and it's in the kernel client — high! Greg Farnum
05:13 PM CephFS Bug #7565: Failed assert in check_rstats
it's CDir::check_rstats() bug, not rstat corruption. Zheng Yan
04:46 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats

This is odd, because it's happening very reproducibly, is not unique to the tip of master, but apparently isn't hap...
John Spray
04:51 PM CephFS Bug #1181: mds: old_inodes crash
Snapshots
See also #4248, which may or may not have anything to do with this.
Greg Farnum
04:50 PM CephFS Bug #926: mds: fix rename between snaprealms
Snapshots Greg Farnum
04:50 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
#7326 Greg Farnum
04:48 PM CephFS Bug #2740: mds: crash in Objecter when shutting down too early
I'm pretty sure this is fixed, but let's check it out and make sure. Greg Farnum
04:45 PM CephFS Bug #3596: ceph-fuse: crash in mds rejoin
Snapshots Greg Farnum
04:44 PM CephFS Bug #2187: pjd chown/00.t failed test 97
This is either an MDS or protocol bug since we've seen it across clients. Greg Farnum
04:43 PM CephFS Bug #2863: client: does not tolerate traceless replies from mds
uclient failure-case: low priority.
I believe we've established that the kclient does not suffer from this issue, ...
Greg Farnum
04:42 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
Confirmed MDS bug! Greg Farnum
04:41 PM Bug #7458: osd: stray pg ref on shutdown
David Zafman
04:40 PM CephFS Bug #2679: POSIX file lock not released on process termination
Let's see if we can reproduce this as it's some combination of kclient, MDS, or protocol bug. Greg Farnum
04:38 PM CephFS Bug #1666: hadoop: time-related meta-data problems
Also see #7564
But low priority, for this is Hadoop
Greg Farnum
04:36 PM CephFS Bug #4212: mds: open_snap_parents isn't called all the times it needs to be
Snapshots Greg Farnum
04:36 PM CephFS Bug #4213: mds: old_parents is never cleaned up
Snapshots Greg Farnum
04:35 PM CephFS Fix #7564: synchronize MDS and client times in a way that makes pjd happy even under clock skew
See also #1666 Greg Farnum
04:28 PM CephFS Fix #7564 (Duplicate): synchronize MDS and client times in a way that makes pjd happy even under ...
See #854. We have ops happen on both the client and the MDS, and so sometimes one time wins and sometimes the other d... Greg Farnum
04:29 PM CephFS Bug #854 (Duplicate): unsynchronized clocks between kernel-client/cmds cause PJD fstest failures
I'm closing this in favor of fix ticket #7564. Greg Farnum
04:13 PM CephFS Bug #1874: Running `git gc` on a bare git repository hosted by ceph results in a bus error.
So basically two things could have gone wrong here:
1) The OSD replied with a bad tid (unlikely)
2) the client forg...
Greg Farnum
04:02 PM CephFS Bug #4370: mds: high-cpu utilization in memorymodel:_sample
Figure out if the current MemoryModel is actually useful for anything — I think it might not be. All the lovely ticke... Greg Farnum
04:01 PM CephFS Bug #3935: kclient: Big directory access bugs (multiple), mixed 32- and 64-bit clients
The hangs sound like generic cap and request waitlisting issues to to me. The empty directory is tickling something i... Greg Farnum
03:57 PM CephFS Bug #4248: mds: replay does not correctly update CInode::first and ::last members
I'm going to leave this at normal even though it's a snapshotting issue — the problem's diagnosed and it's a bug in t... Greg Farnum
03:53 PM CephFS Bug #4134: mds: request locking hang under snaptests
snapshots = low Greg Farnum
03:52 PM CephFS Bug #3719 (Can't reproduce): pjd test 145 failed in the nightly runs
These logs are gone. Greg Farnum
03:45 PM CephFS Bug #4280: mds: crash on lookupsnap
Snapshots = low priority Greg Farnum
03:38 PM CephFS Bug #2445: crash when removing a non-empty directory
Let's validate behavior here — there's a good chance Zheng or somebody fixed whatever bug caused this, and we want to... Greg Farnum
03:32 PM CephFS Bug #1877: ceph.ko (3.1.6) oopses upon cephfs set_layout of a symlink to a dir
Kernel client layout crash = high. Identify if this is still a problem, and if we can trigger it using the vxattrs as... Greg Farnum
03:30 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
Need more info, samba, uclient, etc. Greg Farnum
03:29 PM Bug #7563 (Resolved): osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_up...
2014-02-27 15:13:26.966410 7f65a44d6700 20 _merge_old_entry: oe.prior_version == 0 && already missing, removing missi... Samuel Just
03:27 PM CephFS Bug #4732: uclient: client/Inode.cc: 126: FAILED assert(cap_refs[c] > 0)
The blocker bug is low, so this one can't have a higher priority. Greg Farnum
03:25 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
uclient = low priority, for now. Greg Farnum
03:25 PM Bug #7542: ec misdirected op
wip-7542 Samuel Just
03:25 PM Bug #7539: Firefly EC pool massive memory leak during writes
testing wip-7542 Samuel Just
01:30 PM Bug #7539: Firefly EC pool massive memory leak during writes
ubuntu@teuthology:/a/teuthology-2014-02-26_23:00:27-rados-firefly-testing-basic-plana/106918/remote
Messing up nig...
Samuel Just
03:25 PM CephFS Bug #4188: mds crashes when cow-ing entries in formerly snapshotted dir
Snapshots = low priority. *sigh* Greg Farnum
03:21 PM CephFS Bug #5360: ceph-fuse: failing smbtorture tests
Samba against ceph-fuse (not even using libcephfs) = low priority. Greg Farnum
03:20 PM CephFS Feature #5486: kclient: make it work with selinux
I don't know anything about SELinux, nor its users. What needs to work for us to support SELinux, and how big of a st... Greg Farnum
03:19 PM CephFS Bug #5762: teuthology: Failed MPI runs lead to a hung test instead of a failure
It's a test which we can't use properly. High priority! Greg Farnum
03:18 PM CephFS Bug #6458 (Need More Info): journaler: journal too short during replay
I've bumped up #4708, so if that's the cause of this it'll be fixed when that is. If not, we need more info. Greg Farnum
03:17 PM CephFS Fix #4708: MDS: journaler pre-zeroing is dangerous
#6458 could be a result of this issue, so I'm bumping up the priority. Greg Farnum
03:14 PM CephFS Bug #5950: kcephfs: cephfs set_layout -p 4 gets EINVAL
We want to use the virtual xattrs moving forward, so downgrading a bug in the cephfs tool. Greg Farnum
02:25 PM Revision f12426c3 (ceph): mds_thrash: PEP8-ize whitespace
...so that I can edit the code in a python IDE without
it lighting up like a christmas tree!
Signed-off-by: John Spr...
John Spray
01:38 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I wasn't on 3.8, it was 3.11. Unfortunately I can't use the machines I was experimenting with for this purpose anymor... Peter Waller
01:19 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
Zheng, do you have a specific bug you think this is so we can close it out? Greg Farnum
01:24 PM CephFS Bug #6741: failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
Downgrading: ceph-fuse and snapshots. Greg Farnum
01:23 PM CephFS Bug #6609: teuthology rsync workunit failure
I haven't noticed this in a while, but upgrading as it was a failure across both clients. Greg Farnum
01:22 PM CephFS Bug #5864: cfuse_workunit_suites_ffsb suite on Centos hangs with *** Got Signal Interrupt ***
This is passing in the nightlies, so if there is a bug it has to do with not only ceph-fuse, but ceph-fuse specifical... Greg Farnum
01:20 PM CephFS Bug #7206 (Need More Info): Ceph MDS Hang on hadoop workloads
Greg Farnum
01:18 PM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
We merged this to master in commit:9a040bfd46d141712c32aaa0fa8fc5de93336306, but I guess we missed closing out the ti... Greg Farnum
12:42 PM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
... Greg Farnum
11:48 AM Fix #7560 (Closed): mon: add compat set feature to mark an upgraded pg format in order to disallo...
We do not currently prevent a cuttlefish monitor from running on a dumpling store after an upgrade. Joao Eduardo Luis
11:02 AM Documentation #7558 (Resolved): broken link in install/manual-deployment/
The link under "See Monitor Config Reference - Data for details." is broken. Still think we should be spidering link... Dan Mick
08:21 AM devops Bug #6726: Official packages do not appear to be available for Saucy
We are currently building on both Saucy and Trusty, just need to push packages out to ceph.com
See
http://gitbuil...
Ian Colle
06:41 AM devops Bug #6726: Official packages do not appear to be available for Saucy
Just had a suggestion to use the raring packages from Tim Bishop on the users list.
Would be nice if we could get ...
Michael Potter
07:57 AM Bug #7248 (Fix Under Review): osd: bench set max size
https://github.com/ceph/ceph/pull/1324 Joao Eduardo Luis
06:50 AM CephFS Feature #7325: mds: tool to examine (later, manipulate) dirfrag objects
Is this intended to be an online thing (modifying live MDS state), or something that operates on the RADOS objects (i... John Spray
06:35 AM CephFS Bug #5382: mds: failed objecter assert on shutdown
There was an earlier patch that introduced an "I'm in dispatch" flag, and a more recent one (https://github.com/ceph/... John Spray
03:59 AM Revision 154efb15 (ceph): client: don't update i_max_size when handle reply from non-auth MDS
caps from non-auth mds don't have meaningful max_size
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
03:59 AM Revision 6797d300 (ceph): client: call handle_cap_grant() for cap import message
If client sends cap message that requests new max size during
exporting caps, the exporting MDS will drop the message...
Yan, Zheng
03:59 AM Revision 9476f847 (ceph): client: allow revoking duplicated caps issued by non-auth MDS
Allow revoking duplicated caps issued by non-auth MDS if these caps
are also issued by auth MDS.
Signed-off-by: Yan,...
Yan, Zheng
03:59 AM Revision 5c55eb10 (ceph): client: check mds_wanted for imported cap
The MDS may have incorrect wanted caps after importing caps. So the
client should check the value mds has and send ca...
Yan, Zheng
03:59 AM Revision c1e40c60 (ceph): client: fix race between cap issue and revoke
If we receive new caps from the auth MDS and the non-auth MDS is
revoking the newly issued caps, we should release th...
Yan, Zheng
03:59 AM Revision 30aa2d65 (ceph): client: clear migrate seq when MDS restarts
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:11 AM Revision 9a0ef6a1 (ceph): Fix python-requests package dependencies.
python-ceph does not require requests, but ceph-common does (for ceph-brag).
Signed-off-by: Dan Mick <dan.mick@inkta...
Dan Mick

02/26/2014

11:15 PM Revision 3c87b849 (ceph): Worker logging tweaks
Change some statements' log levels; don't show bootstrap output if there
is no error.
Signed-off-by: Zack Cerza <zac...
Zack Cerza
11:02 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
Dan Mick
10:41 PM Revision 0dcf3f4d (ceph): --dead implies --refresh
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
10:22 PM Revision d42f31e5 (ceph): Symlink worker log after child starts
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
07:13 PM Revision 34478127 (ceph): In find_job_info(), also look for orig.config.yaml
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
06:30 PM Revision fc33eaed (ceph): Merge pull request #1263 from ceph/wip-mds-dumper
mds: Dumper improvements
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:19 PM devops Bug #7429 (Resolved): fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
So I did a lot of testing on Fedora today. This is done so closing it out.
It looks like fedora18 was now kernel...
Sandon Van Ness
10:37 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
Ok so this is done but ceph-deploy tests are still failing...
Also that being said it looks like centos/rhel are r...
Sandon Van Ness
06:19 PM Revision c07a758c (ceph): mds: Add dump-journal-entries
This adds a somewhat-human-readable peer to
the 'dump-journal' command.
Signed-off-by: John Spray <john.spray@inktan...
John Spray
06:19 PM Revision 7a985df6 (ceph): mds: Create MDSUtility as base for Dumper/Resetter
These classes has lots of similar functionality and we may
want to add more similar things in the future.
Also, get ...
John Spray
06:15 PM Revision 410c5074 (ceph): mds: Fix Dumper shutdown
It was shutting down messenger before monclient. This
caused a sometimes-assertion when monclient tried to
reconnect...
John Spray
06:15 PM Revision d774e972 (ceph): Merge pull request #10 from ceph/wip-7485
suites/fs/basic: add mds_creation_retry
Barely-
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
06:10 PM Revision a3e052b6 (ceph): suites/fs/basic: add mds_creation_retry
This invokes the new mds_creation_failure task from
teuthology, ahead of mounting the FS and running the
trivial_sync...
John Spray
06:09 PM Revision f8a2a53c (ceph): Push complete info when reporting jobs as dead
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
05:51 PM Feature #7553 (Resolved): Remove classic scrub

Bobtail was the first release with chunky scrub and had maintained classic scrub code for backwards compatibility. ...
David Zafman
05:47 PM Revision 0db35b95 (ceph): Merge pull request #210 from ceph/wip-queue
Add teuthology-queue command for beanstalk Managmeent. Zack Cerza
05:46 PM Revision 700bb94b (ceph): Merge pull request #208 from ceph/wip-7485
task: Add mds_creation_failure
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:46 PM Revision 9a040bfd (ceph): Merge pull request #1283 from ceph/wip-7485
mon/MDSMonitor: Cope with failures during creation
Reviewed-by: Greg Farnum <greg@inktank.com
Gregory Farnum
05:01 PM CephFS Bug #4746: client: invalidate callback can deadlock
Demoted due to ceph-fuse and FUSE interface work. Greg Farnum
05:00 PM CephFS Bug #4829: client: handling part of MClientForward incorrectly?
Demoting due to uclient and multi-mds. Greg Farnum
04:58 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
Demoting due to uclient and Need More Info. Greg Farnum
04:57 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
Demoting due to multi-mds. Greg Farnum
04:57 PM CephFS Bug #5765: kclient: High CPU due to raw_spin_lock in ceph_cap_string
Demoting due to performance, not correctness. Greg Farnum
04:56 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
Demoting due to uclient. Greg Farnum
04:55 PM CephFS Bug #5382: mds: failed objecter assert on shutdown
I'm pretty sure we had a discussion about your patch, but I can't find the comments and I don't remember the outcome.... Greg Farnum
04:48 PM CephFS Bug #6608: samba teuthology dbench failure
Demoting priority on samba. Greg Farnum
04:47 PM CephFS Bug #7011: ENOTEMPTY on ceph-fuse + snaptest-? test
Demoting priority on ceph-fuse and snapshots. Greg Farnum
04:47 PM CephFS Bug #6613: samba is crashing in teuthology
Demoting priority on samba. Greg Farnum
04:37 PM CephFS Feature #7326: qa: fix flock tests
I don't remember which tests these are; the locktest ones that are racy, or something else? Greg Farnum
04:35 PM CephFS Feature #7352: mds: make classes encode/decode-able
We've already merged in the MDSTable and Journaler header dumping stuff; I think that's all the stuff that you were t... Greg Farnum
04:29 PM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
Again, Zheng got this done. Greg Farnum
04:26 PM CephFS Cleanup #3742: Remove old Hadoop wrappers and configuration options
This is already done, isn't it Noah? At least, the old stuff isn't where it used to be and I didn't see it with the n... Greg Farnum
04:25 PM Linux kernel client Cleanup #2085: kclient: improve mtime update in page_mkwrite
Talk to me about this; what kind of an issue is it (and does it still apply)? Greg Farnum
04:18 PM CephFS Feature #118: kclient: clean pages when throwing out dirty metadata on session teardown
I can't find the referenced ticket anywhere. Anybody know what this is supposed to be and if it still applies? (I thi... Greg Farnum
04:10 PM devops Bug #7552 (Resolved): dregs of mkcephfs still live on
There are still references to mkcephfs in the code. These should be removed and replaced with ceph-deploy if appropri... Ian Colle
03:33 PM Bug #7549: Mon deadlock

I did add a -d to the vstart.sh invocation in the test/vstart_wrapper.sh script.
David Zafman
02:57 PM Bug #7549 (Won't Fix): Mon deadlock

I was running test/vstart_wrapped_tests.sh built from 60c9aafaf0ff033dca22606ea811c792f1cda781. It looks like mult...
David Zafman
03:12 PM Revision 7ba3200f (ceph): mds: fix nested_anchors update during journal replay
check if the inode is anchored/unanchored before updating the inode
Fixes: #7530
Signed-off-by: Yan, Zheng <zheng.z....
Yan, Zheng
03:12 PM Revision 82aba4b0 (ceph): Merge pull request #1319 from ceph/wip-primary-temp-fix
osd/OSDMap: respect temp primary without temp acting
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
02:04 PM Bug #7538 (Fix Under Review): librados: rados ls crashes on firefly due to segfault in ObjectIter...
https://github.com/ceph/ceph/pull/1322 Josh Durgin
01:17 PM Revision 6ba89851 (ceph): fix docstring typo
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
01:03 PM Revision 7cc93751 (ceph): task: Add mds_creation_failure
This is test code to accompany CephFS fix #7485.
Also fix DaemonState.wait_for_exit to clear up its 'proc'
attribute...
John Spray
11:39 AM devops Tasks #7230 (In Progress): Rebuild sync-agent packages for dumpling repo
Talked to Josh and he wants to get some more fixes in which should happen later this week. Sandon Van Ness
10:34 AM devops Tasks #7230: Rebuild sync-agent packages for dumpling repo
Packages are built but I need to test to make sure its working. Sandon Van Ness
10:20 AM Subtask #7548 (Resolved): Basic docs for Erasure Coding
"work in progress":https://github.com/ceph/ceph/pull/1362
Similar to what Greg created for tiering at http://ceph....
Neil Levine
10:18 AM Feature #7547 (Resolved): Basic docs for Cache Tiering functionality
The content at http://ceph.com/docs/master/dev/cache-pool/ is fine for the Firefly release. Can you liaise with John ... Neil Levine
09:46 AM Bug #7545: rados: notify was not recieved in ceph_test_rados_watch_notify with thrashing on emperor
this was from http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-24_19:00:20-rados-emperor-testing-basic-plana/99... Josh Durgin
09:46 AM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
This looks like it might just be a bug in the test. This is all the output from ceph_test_rados_watch_notify, with a ... Josh Durgin
07:15 AM CephFS Bug #7530: mds: failed anchor assert on replay
commit:7ba3200f1e91d803cdf84f96777641f7d18d3c01 Greg Farnum
07:09 AM Revision 1040d1b0 (ceph): osd/OSDMap: respect temp primary without temp acting
be2748c6d540891f2e1a62e7034cb44f7d04bf18 ensured that
if the temp acting mapping contains only CRUSH_ITEM_NONE,
that ...
Samuel Just
05:26 AM Revision aee6925e (ceph): Merge pull request #1264 from ceph/wip-mds-dencoder
mds: Add encode/decode/dump for use with dencoder
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:22 AM rgw Bug #7543: rgw: off-by-one bug in rgw_trim_whitespace()
I've sent a pull request to fix this bug at https://github.com/ceph/ceph/pull/1321
Please help to review it.
Xiangyu Lv
02:38 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
There is an off-by-one bug in rgw_trim_whitespace(). It results in trimming off all characters with input like " t". Xiangyu Lv
04:42 AM Revision 5a6cb3da (ceph): Merge pull request #1317 from ceph/wip-7537
Wip 7537
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
03:57 AM Revision 26f00fc5 (ceph): Make help a bit more obvious. Misc tweeks.
Put each yaml in the job_description on its own line so not so
wide of a line. Make delete default None not False in ...
Sandon Van Ness
02:00 AM Revision 20641b67 (ceph): Merge pull request #1280 from ceph/wip-7374-wusui
Fix sub check() to not exit if rgw is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:59 AM Revision 7eda448b (ceph): Merge pull request #1279 from ceph/wip-7375-wusui
Fixed sub check() to say okay if rgw is running.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:08 AM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
MDS map contains CompatSet::FeatureSet Zheng Yan
12:52 AM Revision 8020dcf7 (ceph): Fixed get_status() to find client.radosgw fields inside of ps output.
Fixes: 7375
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
12:49 AM Revision 8200b8a0 (ceph): Fix get_status() to find client.rados text inside of ps command results.
Added port (fixed value for right now in teuthology) to hostname.
Fixes: 7374
Signed-off-by: Warren Usui <warren.usui...
Warren Usui
12:47 AM Revision be2748c6 (ceph): OSDMap::_pg_to_up_acting_osds: use _acting_primary unless acting is empty
If the temp set for whatever reason has only CRUSH_ITEM_NONE,
we need primary to be -1.
Signed-off-by: Samuel Just <...
Samuel Just

02/25/2014

11:47 PM Revision 0eabbf14 (ceph): Merge pull request #1316 from ceph/dumpling-6922
Dumpling: Prevent extreme PG split multipliers
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:45 PM Revision fe8915ae (ceph): Merge pull request #1315 from ceph/dumpling-hashpspool
mon: OSDMonitor: allow (un)setting 'hashpspool' flag via 'osd pool set'
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:44 PM Revision 87822ccc (ceph): Merge pull request #1314 from ceph/dumpling-osd-pgstatsack
Dumpling osd pgstatsack
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:28 PM Revision f93bf33b (ceph): Merge pull request #1311 from ceph/wip-dz-scrub-fixes
Wip dz scrub fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:27 PM Revision dc079eb3 (ceph): OSDMonitor: when thrashing, only generate valid temp pg mappings
Since backfill peers are no longer placed into the acting set,
temp mappings will never exceed the pool size. Also, ...
Samuel Just
11:24 PM Bug #7542 (Resolved): ec misdirected op
OSD recomputes op target based on current OSDMap. With an EC pg, we can get this result:
1) client at map 512 sends...
Samuel Just
09:34 PM Revision 56675663 (ceph): mon: OSDMonitor: allow (un)setting 'hashpspool' flag via 'osd pool set'
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked fro...
Joao Eduardo Luis
09:10 PM Revision 9d5d931c (ceph): OSDMonitor: use a different approach to prevent extreme multipliers on ...
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commit d8...
Greg Farnum
09:08 PM Revision c0c4448d (ceph): OSDMonitor: prevent extreme multipliers on PG splits
Fixes: #6922
Backport: emperor
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.co...
Greg Farnum
08:42 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
5a6cb3da201ce503b4aef1744c3dc15511d15a13 Samuel Just
12:33 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
11: (OSD::PeeringWQ::_process(std::list<PG*, std::allocator<PG*> > const&, ThreadPool::TPHandle&)+0x12) [0x6a5282]
...
Samuel Just
07:55 PM Bug #7406: Seg fault in find_object_context()in recent master rados run
David Zafman
07:52 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily
David Zafman
12:55 PM Bug #7535: Switching to classic scrub unnecessarily

This was primarily fixed by 7357b6ed4bbc6ef44a80640ffb7e1ddacab10b5e for tracker #7517.
David Zafman
12:10 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily

test/vstart_wrapped_tests.sh output:
pg[0.0( empty local-les=20 n=0 ec=1 les/c 20/20 14/14/6) [0,2,1] r=-1 lpr=14 ...
David Zafman
07:51 PM Revision 9e55f6f2 (ceph): Add missing fedora yamls.
Running a git add first would have been helpfull... Sandon Van Ness
07:51 PM Revision 67ed25f1 (ceph): Run ceph-deploy on fedora19 not old fedora18.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
07:50 PM Revision d741cd99 (ceph): Add missing fedora yamls.
Running a git add first would have been helpfull... Sandon Van Ness
07:42 PM Revision 9fb8231f (ceph): Run ceph-deploy on fedora19 not old fedora18.
Signed-off-by: Sandon Van Ness <sandon@inktank.com> Sandon Van Ness
07:42 PM Revision c1889497 (ceph): osd: fix off-by-one is boot subscription
If we have osdmap N, we want to onetime subscribe
starting at N+1. Among other things, it means we
hear when the NOU...
Sage Weil
07:42 PM Revision 4584f606 (ceph): OSD: use the osdmap_subscribe helper
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherry picked from commit 3c...
Greg Farnum
07:42 PM Revision 61b2aeee (ceph): OSD: create a helper for handling OSDMap subscriptions, and clean them up
We've had some trouble with not clearing out subscription requests and
overloading the monitors (though only because ...
Greg Farnum
07:41 PM Revision d93d67d1 (ceph): monc: new fsub_want_increment( function to make handling subscriptions ...
Provide a subscription-modifying function which will not decrement
the start version.
Signed-off-by: Greg Farnum <gr...
Greg Farnum
07:40 PM Revision 37fbcb95 (ceph): OSD: disable the PGStatsAck timeout when we are reconnecting to a monitor
Previously, the timeout counter started as soon as we issued the reopen,
but if the reconnect process itself took a w...
Greg Farnum
07:40 PM Revision 9be395e8 (ceph): monc: backoff the timeout period when reconnecting
If the monitors are systematically slowing down, we don't want to spam
them with reconnect attempts every three secon...
Greg Farnum
07:40 PM Revision 8f4c20bd (ceph): monc: set "hunting" to true when we reopen the mon session
If we don't have a connecton to a monitor, we want to retry to another
monitor regardless of whether it's the first t...
Greg Farnum
07:39 PM Revision c6317558 (ceph): monc: let users specify a callback when they reopen their monitor session
Then the callback is triggered when a new session is established, and the
daemon can do whatever it likes. There are ...
Greg Farnum
07:34 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
Created and on the index page. Sandon Van Ness
07:13 PM Revision e04f8fd3 (ceph): Add teuthology-queue command for beanstalk Managmeent.
Supports listing entire queue of machine type and deleting test
suite runs from the queue without wiping the entire q...
Sandon Van Ness
06:27 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
Zheng Yan
09:14 AM CephFS Bug #7530: mds: failed anchor assert on replay
config used was (suites/fs/thrash/): ceph/base.yaml ceph-thrash/default.yaml clusters/mds-1active-1standby.yaml debug... John Spray
09:09 AM CephFS Bug #7530: mds: failed anchor assert on replay
Crashed on first try, log at debug-mds=10 attached John Spray
07:04 AM CephFS Bug #7530 (In Progress): mds: failed anchor assert on replay
John Spray
03:47 PM Bug #6922 (Resolved): mon: do not allow unreasonable PG splitting
Sam merged this. Greg Farnum
01:40 PM Bug #6922: mon: do not allow unreasonable PG splitting
PR: https://github.com/ceph/ceph/pull/1316 Greg Farnum
03:14 PM Feature #7540 (Resolved): Spread out deep-scrubs to avoid I/O contention
Parallel deep-scrubs have the potential to cause client I/O contention. A mechanism to spread out deep-scrubs and mak... Brian Andrus
03:02 PM Feature #7288: Deep-scrub throttle
Actually, there's a reservation system which should prevent that. The primary must reserve a slot in itself and each... Samuel Just
02:19 PM Bug #7539 (Resolved): Firefly EC pool massive memory leak during writes
EC pools appear to leak memory rather badly during writes. Looks like messages aren't being properly cleaned up. Ma... Mark Nelson
01:59 PM Bug #7538 (Resolved): librados: rados ls crashes on firefly due to segfault in ObjectIterator::op...
as seen in: http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-23_23:02:27-rbd-firefly-testing-basic-plana/99242/... Josh Durgin
11:45 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
hmm.. the timestamps actually match, so the shard sync failure might be the culprit. Seems like a sync agent issue (a... Yehuda Sadeh
09:36 AM rgw Bug #7526: "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-distro-basic-...
I think the real issue is here, the specific agent error looks like a red herring:... Yehuda Sadeh
11:06 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
This should be fixed in ceph-qa-chef. I will run a new ceph-deploy run on vps and see how it goes. Sandon Van Ness
07:33 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
On the vm I deployed when tracking this, it only took me a 'yum upgrade leveldb' or something similar. I would think... Joao Eduardo Luis
07:19 AM devops Bug #7429: fedora 19 VMs: leveldb must be upgraded to something newer than 1.9.0
All Fedora tests are still failing. We need to address this as soon as possible. I am not sure what entails upgrading... Alfredo Deza
10:48 AM Bug #7448: os/FileJournal.cc: FAILED assert(fd >= 0)
Increasing the priority on this since we cannot seem to get passing tests for ceph-deploy for months. Alfredo Deza
10:47 AM Revision 891343a7 (ceph): rados.py: add aio_remove
Add aio_remove to the Python wrapper.
Signed-off-by: Dan van der Ster <daniel.vanderster@cern.ch>
Dan van der Ster
07:25 AM CephFS Bug #7503: mds start and oops after access to cephfs
fine, ok for the ticket #7531.This one should be closed.
Yann Dupont
07:02 AM CephFS Feature #3863 (In Progress): implement a tool to lookup inode numbers without holding their path
John Spray
05:33 AM devops Bug #7356: Kill all while loops that will never end....
This is going to take some effort because there are over 100 while loops in teuthology that look dangerous.
The in...
Alfredo Deza
05:24 AM Bug #6101: ceph-osd crash on corrupted store
We applied the fix last week the crashing node.
The osd node now runs again, but see that the missing objects gets t...
Daniel Poelzleithner
03:56 AM Revision 9f7f4eda (ceph): Revert "osd/PG: fix assert when deep repair finds no errors"
This reverts commit e3e3328ec8a57f1ae2a2fd9893c51068798720a0. David Zafman
03:56 AM Revision 728e3911 (ceph): osd: Don't include primary's shard in repair result message
Signed-off-by: David Zafman <david.zafman@inktank.com> David Zafman
02:39 AM rbd Bug #7282: Unresponsive rbd-backed Qemu domain causes libvirtd to stall on all connections
The patch has been accepted in libvirt upstream: http://libvirt.org/git/?p=libvirt.git;a=commitdiff;h=60f70542f97805a... Wido den Hollander
12:34 AM Bug #7207: Lock contention at filestore I/O (FileStore::lfn_open) during filestore folder splitti...
Hi Greg,
I got a chance to test against the fix in our cluster (the leaf folder has around 1000 files), there are tw...
Guang Yang

02/24/2014

10:31 PM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
Ah, it sounds like this is happening because the MDS doesn't currently have a good versioning system to prevent too-o... Greg Farnum
10:30 PM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
This'll be a little interesting because the MDS doesn't have local storage. Evaluate if feature sets are best stored ... Greg Farnum
10:11 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
... Greg Farnum
09:22 PM Revision 25919351 (ceph): use itertools for seconds sum
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
09:21 PM Revision 60892ca9 (ceph): tests for the new while helper
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
09:01 PM Revision 38cead63 (ceph): Flip logic of checking whether a branch can report
Previously we checked if the branch being used was in a whitelist of
branches known to contain the reporting feature....
Zack Cerza
08:32 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The kmods are built from a common source RPM because ceph.ko and rbd.ko require libceph.ko to be built and available ... Ken Dreyer
08:29 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Having them in one package is fine for now, but on reflection I do think we are going to need to have these in separa... Neil Levine
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Ken Dreyer
08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
The packages only run depmod, and they leave modprobe to the user or to the tooling. So it sounds like we're good.
...
Ken Dreyer
03:42 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
mount.ceph and 'rbd map' will do the modprobe for the user if it's not already loaded, so there's no need for the pac... Josh Durgin
03:25 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
Does the package install the module into the kernel or does the user have to do modprobe manually?
If it installs ...
Neil Levine
03:20 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
I've unified all three kmods into a single package, available on GitHub: https://github.com/kdreyer-inktank/ceph-kmod... Ken Dreyer
08:09 PM Revision 171a5e1a (ceph): add a helper for while loops
Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com> Alfredo Deza
05:22 PM Revision 3ee71a5c (ceph): doc: troubleshooting-mons.rst: better document how to troubleshoot mons
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> Joao Eduardo Luis
05:17 PM Revision 60c9aafa (ceph): Merge pull request #1308 from ceph/wip-osdmap-inc
mon/OSDMonitor: fix osdmap encode feature logic
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
05:10 PM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
Sage Weil
03:16 PM CephFS Feature #4000: Design a migration path from using the AnchorTable to using lookup-by-ino
Did this already get done with Zheng's work to remove the AnchorTable? Greg Farnum
05:10 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
Sage Weil
05:09 PM CephFS Feature #3999 (Resolved): update CDir encoding
this was revved as part of zheng's omap stuff Sage Weil
05:08 PM Revision 17176015 (ceph): Merge pull request #1302 from ceph/wip-create-null
client: fix possible null dereference in create
Reviewed-by: Greg Farnum <greg@inktank.com>
Gregory Farnum
04:15 PM Linux kernel client Cleanup #2847 (Resolved): libceph: osdmap definition is out of date
Sage Weil
04:15 PM Linux kernel client Feature #6991 (Resolved): support CEPH_FEATURE_OSDMAP_ENC
Sage Weil
02:07 PM rgw Bug #7526 (Resolved): "ERROR:radosgw_agent.worker:syncing entries for shard 59" in rgw-firefly-di...
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98508... Yuri Weinstein
12:14 PM Revision 69082a69 (ceph): mds: add mds_kill_create_at for testing
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
11:24 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Seems related to #7468 Yuri Weinstein
11:23 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-22_23:02:21-rgw-firefly-distro-basic-plana/98483
Error...
Yuri Weinstein
10:20 AM rgw Bug #6936 (Resolved): radosgw-admin allows same user to be created multiple times
Fixed for firefly, commit:53de64122b206d11aa42fd401f88f02f2908e942 Yehuda Sadeh
10:20 AM rgw Bug #6951 (Resolved): rgw: bucket re-create fails when cache is disabled
Fixed for firefly, commit:859ed33ed7f9a96f4783dfb3e130d5eb60c622dd Yehuda Sadeh
10:16 AM rgw Bug #6830 (Resolved): S3 CompleteMultipartUploadResult has empty ETag element
Fixed, commit:2b3e3c834cd0e8b890296fa2b92ebb5de01a1bc1 Yehuda Sadeh
10:15 AM rgw Bug #7064 (Resolved): S3 request to non-existent object in non-existent bucket results in 30 seco...
Fixed, commit:3ed68eb9fac9b3d0bf9111867d609f9ea08fb202 Yehuda Sadeh
09:58 AM devops Bug #7356 (In Progress): Kill all while loops that will never end....
Alfredo Deza
09:46 AM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Consistent on firefly as well - http://pulpito.front.sepia.ceph.com/teuthology-2014-02-22_23:02:06-rbd-firefly-distro... Yuri Weinstein
08:29 AM Bug #7504: Ceph does not specify python2
Yeah I was talking about the shebang.
I understand that you can't do anything but this situation sucks. Instead of d...
Alexandre BIQUE
07:28 AM Bug #7504 (Rejected): Ceph does not specify python2
Alfredo Deza
07:21 AM Bug #7504: Ceph does not specify python2
When you say that ceph scripts should 'use explicitly python2' you mean altering the shebang line?
There is no con...
Alfredo Deza
03:59 AM Revision e92d6024 (ceph): Merge pull request #1303 from ceph/port/temp-failure-retry
compat: avoid unused warn with TEMP_FAILURE_RETRY
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:54 AM Revision 27968a74 (ceph): ceph_test_objectstore: fix i386 build (again)
test/objectstore/store_test.cc: In member function ‘void SyntheticWorkloadState::read()’:
error: test/objectstore/sto...
Sage Weil
03:49 AM Revision 5f53cf13 (ceph): Merge pull request #1307 from ceph/wip-7517
Wip 7517 Sage Weil
03:12 AM Revision 0243d29c (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:11 AM Revision 87ebe461 (ceph): upgrade/dumpling: add recent dumpling point releases
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
03:10 AM Revision bad8e609 (ceph): upgrade/dumpling: upgrade to latest dumpling, not emperor
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
02:23 AM Revision 14ea8157 (ceph): mon/OSDMonitor: fix osdmap encode feature logic
If we are encoding a full map based on an old Incremental that does not
encode the features, fall back to the quorum ...
Sage Weil
01:02 AM Bug #7521 (Won't Fix): Add more events (hold object context) to OpTracker to better analyze perfo...
This ticket is to help on the effort I sent to community for this - http://www.spinics.net/lists/ceph-users/msg07866.... Guang Yang
12:58 AM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
Zheng Yan
12:20 AM Revision 7357b6ed (ceph): PG: skip pg_whoami.osd, not pg_whoami.shard in scrub feature check
Caused by typo in 68184d4574cd507ab3a065693e392917b98e16ec.
Fixes: #7517
Signed-off-by: Samuel Just <sam.just@inktan...
Samuel Just

02/23/2014

11:32 PM Revision ae59ba3c (ceph): Merge pull request #1304 from ceph/wip-last-epoch-clean
mon: fix min_last_epoch_clean handling
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just
11:24 PM Bug #7423: erasure code: ./rados get retrieves a larger object
As of "today":https://github.com/ceph/ceph/commit/24c89bf01c61ecedb3bc7045332c9ed0340b37dc instead of crashing it ret... Loïc Dachary
10:56 PM Revision c6a22b33 (ceph): rados/thrash/workloads: enable copy_from for the ec workloads
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:48 PM Revision dcb9946b (ceph): Merge pull request #1306 from ceph/wip-7512
wip-7512
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
09:35 PM Revision d0359f7c (ceph): PG: clarify same_primary_since updates regarding primary rank
pg_shard_t includes the position, so these checks handle
same osd/different rank properly.
Signed-off-by: Samuel Jus...
Samuel Just
09:35 PM Revision 0442b456 (ceph): Objecter/OSDMap: factor out primary_changed() into static OSDMap method
We need to reuse this logic in OSD::project_pg_history.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
09:35 PM Revision 696fa36d (ceph): OSD::project_pg_history needs to account for acting_primary/up_primary
Fixes: #7512
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:24 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
Hi Greg,
Thanks for the reply.
-bash-4.1$ sudo ceph --version
ceph version 0.76-874-g40bdcb8 (40bdcb88504aea6...
Zhi Zhang
08:15 PM Revision df3ba724 (ceph): mon/PGMap: add unit test for min_last_epoch_clean
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
08:15 PM Revision 73c59a02 (ceph): mon/PGMap: fix osd_epochs update
The insert() call here does not overwrite a previous entry, which means
that the osd_epochs map is never moving forwa...
Sage Weil
08:14 PM Revision 8913ab4b (ceph): ECBackend: skip canceled xattr reads as well
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:10 PM Bug #7520: Lock contention during scrubbing which could potentially hang the OSD for a couple of ...
Pull request - https://github.com/ceph/ceph/pull/1309 Guang Yang
07:41 PM Bug #7520 (Resolved): Lock contention during scrubbing which could potentially hang the OSD for a...
We are using Ceph as object store (via radosgw) and each time the cluster starts doing scrubbing, the performance deg... Guang Yang
07:49 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
Sage Weil
03:07 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
EC pool scrub bug -- reproducible
2014-02-23 15:03:57.195155 7ffbe7183700 10 osd.1 341 dequeue_op 0x51c2b40 finish...
Samuel Just
07:17 PM Revision 0e376ee7 (ceph): compat: avoid unused warn with TEMP_FAILURE_RETRY
The version of TEMP_FAILURE_RETRY found on Linux has a GNU extension
that squashes the unused return value warning wh...
Noah Watkins
07:16 PM Bug #7519 (Can't reproduce): upgrade: osd crash on cuttlefish -> v0.67.1 -> emperor
ubuntu@teuthology:/var/lib/teuthworker/archive/teuthology-2014-02-22_19:40:17-upgrade:dumpling-next---basic-plana/978... Sage Weil
07:00 PM Feature #7518 (Closed): Add inline attrs support to KeyValueStore
"header" is a structure play a role like inode in FileSystem. Attrs are accessed frequently by PG layer, make attrs i... Haomai Wang
06:18 PM Revision 23e538ef (ceph): client: fix possible null dereference in create
There are two paths that jump to the out label for which 'in' can be
NULL and outp can be non-NULL. For those cases ...
Sage Weil
06:05 PM Revision bcc18d48 (ceph): osd: increase default leveldb write buffer, cache size
The FileStore's leveldb currently uses libleveldb's defaults for cache and
write buffer size, which are both 4 MB. In...
Sage Weil
05:49 PM Revision 614a94ab (ceph): Merge pull request #1287 from kdreyer-inktank/redhat-files
packaging: file list adjustments
Tested-by: Huang Jun <hjwsm1989@gmail.com>
Sage Weil
05:45 PM Revision 7842ea91 (ceph): Merge pull request #1265 from ceph/wip-mds-misc
MDS misc. cleanup
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
05:05 PM Revision c4a3a86a (ceph): ceph_test_objectstore: fix i386 build error
We can't swap size_t and uint64_t; just change the len type to match.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
05:03 PM Revision b25c22a2 (ceph): ceph_test_objectstore: fix signed/unsigned warning
In file included from test/objectstore/store_test.cc:33:0:
../src/gtest/include/gtest/gtest.h: In function ‘testing::...
Sage Weil
05:00 PM Revision 9651b18b (ceph): os/ObjectStore: fix rebase errors
These were goofed by d74f1282cd268b4b04cfd9e90ddeac6d1dc6be7e.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:29 PM Bug #6671: FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Someone (I think it was Sam Just) helped me on #ceph to replace this OSD and rebuild data that was missing, so we wor... Tom Lanyon
04:17 PM Revision cfafa0b7 (ceph): README: add build dep
Technically it's a 'make check' dep, but close enough.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
03:52 PM Revision 1340b360 (ceph): erasure-code: test that changing the pool size is not allowed
http://tracker.ceph.com/issues/7360 fixes #7360
Signed-off-by: Loic Dachary <loic@dachary.org>
Loïc Dachary
03:46 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
ubuntu@teuthology:/a/teuthology-2014-02-21_23:02:40-rgw-firefly-testing-basic-plana/96767
with full osd logs
Sage Weil
03:38 PM Revision 0e50f7a0 (ceph): Merge remote-tracking branch 'gh/firefly'
Sage Weil
03:37 PM Revision 57eeebee (ceph): Merge pull request #1290 from ceph/wip-os-doc
os/ObjectStore: document interface Sage Weil
03:29 PM Revision d74f1282 (ceph): os/ObjectStore: document interface
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Allen Samuels
03:25 PM Revision 24c89bf0 (ceph): Merge pull request #1294 from ceph/wip-librados-object-iterator
fix bugs in librados::ObjectIterator
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
03:24 PM Revision 5c4129df (ceph): Merge pull request #1295 from yuyuyu101/keyvaluestore-enhance
Keyvaluestore enhance(backport to firely)
Pulling this into firefly because it doesn't (substantiatively) touch anyt...
Sage Weil
03:12 PM Revision 8ef0d7e6 (ceph): Merge pull request #1297 from ceph/wip-ec-bugs
Wip ec bugs
Reviewed-by: Sage Weil <sage@inktank.com>
Sage Weil
02:48 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
Sage Weil
01:02 PM Feature #7516 (Resolved): mon: reweight-by-pg
The reweight-by-utilization function is important for maintaining a tight distribution of utilizations across lots of... Sage Weil
12:54 PM Feature #7515 (Resolved): mon: 'osd crush reweight-subtree <name> <weight>'
The 'osd crush reweight ...' command only lets you reweight a single item. In a large cluster, it may be helpful to ... Sage Weil
12:21 PM Bug #7493 (Resolved): cephtool/pool_ops failure
commit:70d23b9a0ad9af5ca35a627a7f93c7e610e17549 Sage Weil
08:23 AM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
Sage Weil
07:54 AM Bug #7494 (Resolved): EC filter read op bug
Sage Weil
07:54 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
07:53 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Sage Weil
07:25 AM Bug #7491 (Resolved): rados api crashes
Sage Weil
07:21 AM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
Sage Weil
07:21 AM Feature #7514 (Resolved): qa: add ceph_test_objectstore to rados test suite
Sage Weil
06:00 AM Revision 6d8cb22e (ceph): unittest_ecbackend: fix signed/unsigned warnings
In file included from test/osd/TestECBackend.cc:20:0:
../src/gtest/include/gtest/gtest.h: In instantiation of ‘testin...
Sage Weil
05:56 AM Revision bff4a3bf (ceph): Merge pull request #1301 from ceph/wip-scrub-primary
mon/PGMonitor: fix primary osd check on deep-scrub
gitbuilders are now passing
Sage Weil
05:31 AM Revision fed655e3 (ceph): mon/PGMonitor: fix primary osd check on deep-scrub
s/!=/==/. Logic was reversed.
Broken in 40bdcb88504aea6288d461d29d24d5b0bf7aeebc.
Signed-off-by: Sage Weil <sage@i...
Sage Weil
01:35 AM Revision 5516f8c1 (ceph): Merge pull request #1300 from ceph/wip-7513
PGLog::activate_not_complete typo
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
01:24 AM Revision 7b0f3d90 (ceph): PGLog::activate_not_complete: fix log.complete_to increment typo
info.last_complete should be the entry before log.complete_to.
This appears to have been a typo introduced in
dd7105...
Samuel Just
01:18 AM Revision 885d1963 (ceph): Merge pull request #1298 from ceph/wip-subscribe
osd: fix off-by-one is boot subscription
Reviewed-by: Samuel Just <sam.just@inktank.com>
Samuel Just

02/22/2014

10:55 PM Revision bfb3a247 (ceph): Merge pull request #1299 from ceph/wip-repair
osd/PG: fix assert when a shallow repair has fixed all errors.
Reviewed-by: David Zafman <david.zafman@inktank.com>
David Zafman
09:51 PM Revision e3e3328e (ceph): osd/PG: fix assert when deep repair finds no errors
If there are no deep repairs, we don't want to assert.
Fixes:
-1> 2014-02-21 21:13:56.393087 7f0258ff9700 0 log...
David Zafman
08:37 PM Revision 8b4cf1c0 (ceph): OSDMap: make calc_pg_rank/role const for acting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision 93983c95 (ceph): Objecter: make is_pg_changed static and const for old/newacting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision ace65fec (ceph): OSD: fix query for ec pgs
We need to parse a pg_t and translate it into an spg_t.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:37 PM Revision 9da4d40e (ceph): PGLog: test for missing using the correct shard value
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:37 PM Revision 005b4fad (ceph): Objecter: resend op if primary role changed
Fixes: #7508
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:35 PM Revision 9b852413 (ceph): ECBackend::filter_read_op: clean up read state properly
Fixes: #7494
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
08:35 PM Revision 8593ad76 (ceph): ReplicatedPG::cancel_pull: ECBackend might cancel_pull on a non-missing...
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:35 PM Revision ab4c9a67 (ceph): ECUtil: clear() should reset hashes to -1, not 0
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
08:35 PM Revision b7de0fdb (ceph): ECTransaction: require hash_infos for deleted objects
Otherwise, an append preceded by a delete may not see the
correct HashInfo state since it won't have been cached
unti...
Samuel Just
05:35 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:27 PM Bug #7513: PGLog::activate_not_complete: log.complete_to decrement typo
https://github.com/ceph/ceph/pull/1300 Samuel Just
05:25 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
Samuel Just
05:19 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
merged Samuel Just
01:48 PM Bug #7511 (Fix Under Review): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Sage Weil
04:08 PM Revision 70d23b9a (ceph): osd: fix off-by-one is boot subscription
If we have osdmap N, we want to onetime subscribe
starting at N+1. Among other things, it means we
hear when the NOU...
Sage Weil
03:57 PM Revision 90ebdcc4 (ceph): Rename keyvaluestore_check_backend to keyvaluestore_debug_check_backend
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 4b3bf3e2 (ceph): Make SequencePosition sync by each transaction
Each object modify will increase SequencePosition and sync it to disk
Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
Haomai Wang
01:05 PM Revision dcfe098c (ceph): Remove m_eio in KeyValueStore
KeyValueStore use kv backend to detect errors and nearly can't know the actual
reason for error.
Signed-off-by: Haom...
Haomai Wang
01:05 PM Revision 9543664b (ceph): Remove filestore_inject_stall
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 697411c8 (ceph): Add backend check option to KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 8c4d8659 (ceph): Add config tracker to KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 62c1631f (ceph): Remove eio inject codes in KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision a52d7cd0 (ceph): Add KeyValueStore op thread options
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 3e6a1fc6 (ceph): Add read/write operation to store_test.cc
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision 9ed29581 (ceph): Return 0 when the offset of read exceed the length of object
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:05 PM Revision a9fa341e (ceph): Fix incorrect read and truncate
If the first chunk of object is not read entirely, the current implementation
will contain it entirely which make wro...
Haomai Wang
01:05 PM Revision 2a363d67 (ceph): Unify object level lock in GenericObjectMap
Before we copy lock implementation from DBObjectMap which provide with two locks
for header. Here just unify it to ma...
Haomai Wang
01:05 PM Revision 88bec065 (ceph): Optimize write call add enhance error detect
A single write call may need several keys in the backend kv store. Let get these
keys one time.
Signed-off-by: Haoma...
Haomai Wang
01:05 PM Revision 6314350f (ceph): Remove unnecessary "check_coll" check
The goal of "check_coll" is aimed to ensure the collection is exists. But
the create and delete of collection already...
Haomai Wang
01:05 PM Revision ec8a4193 (ceph): Implement collection_rename interface in KeyValueStore
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision 5eb75927 (ceph): Fix deadlock caused by hold collection obj
Collection is a special object in KeyValueStore, if exists collection modify,
this object will be hold. When exists c...
Haomai Wang
01:04 PM Revision 2b9e893a (ceph): Move perf counter and add op queue reserve throttle
The perf counter of FileStore can shared with other ObjectStore backend, so move
it to ObjectStore and adjust positio...
Haomai Wang
01:04 PM Revision c9fdceee (ceph): Add test for omap interface
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision d7be5404 (ceph): Add get_*_with_header to StripObjectHeader
In some situations, we need to ensure header is held and try to read, so read
interfaces need to accept header argume...
Haomai Wang
01:04 PM Revision 024a1204 (ceph): Use rename operation to make colection_move atomic
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
01:04 PM Revision 4e7f1de9 (ceph): Adjust some interfaces to optimize caller codes
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> Haomai Wang
12:29 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
OSD::project_pg_history needs to take into account up_primary/acting_primary -- testing.
2014-02-22 01:48:56.31806...
Samuel Just
03:28 AM Revision a715c7f2 (ceph): Merge branch 'wip-6685-firefly' into firefly
Reviewed-by: Samuel Just <sam.just@inktank.com> David Zafman
02:30 AM Revision f214c3ec (ceph): Merge pull request #1293 from jwriteclub/doc-update-ceph-osd-note
Added a note that the ceph-osd command requires the cluster option.
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
02:26 AM Revision c2782695 (ceph): Added a note that the ceph-osd command requires the cluster option.
Signed-off-by: Christopher O'Connell <jwriteclub@gmail.com> Christopher O'Connell
02:22 AM Revision 0da25e67 (ceph): librados: implement ObjectIterator copying and assignment
Copied iterators should be independent of each other, and not
rely on the same underlying ListContext or ObjListCtx.
...
Josh Durgin
01:40 AM Revision 72820a84 (ceph): Merge remote-tracking branch 'origin/wip-da-SCA-20140218' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
01:32 AM Revision d9bedb9e (ceph): Added evaluation of cluster and fixed evaluation when setting initial w...
Signed-off-by: Christopher O'Connell <jwriteclub@gmail.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Christopher O'Connell
12:06 AM Revision d8a7befb (ceph): librados: remove extra advance from objects_begin(position)
ObjectIterator::seek() already calls get_next() to update the
iterator's state. Calling it again goes one past where ...
Josh Durgin
12:06 AM Revision 8a0017ac (ceph): librados: don't destroy ObjListCtx when iterator reaches the end
There's no need to destroy it when we've used it once. It'll get destroyed
by the destructor anyway. Now that there's...
Josh Durgin

02/21/2014

11:57 PM Revision 7ae05566 (ceph): Merge pull request #1286 from ceph/wip-corpus
ceph-object-corpus: prune some old releases
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:19 PM Revision a9677e13 (ceph): Revert "ReplicatedPG::recover_backfill: adjust last_backfill to HEAD if...
This reverts commit 545135f3e1c75318940caa2c82ac32a53fc4f957.
Conflicts:
src/osd/ReplicatedPG.cc
David Zafman
10:46 PM Revision 78b65ace (ceph): Merge remote-tracking branch 'origin/port/updates' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
10:18 PM Revision 133ddb7d (ceph): packaging: match all test files
It's tedious to try to keep the list of test files up to date in the RPM
spec file. Use a wildcard to match them all....
Ken Dreyer
10:17 PM Revision 1c129dfc (ceph): packaging: add missing file
Signed-off-by: huangjun <hjwsm1989@gmail.com>
Reviewed-by: Ken Dreyer <ken.dreyer@inktank.com>
huang jun
09:57 PM Revision bd59db21 (ceph): ceph-object-corpus: prune some old releases
We do not need to test these old object encodings as they are covered by
later object collections.
Signed-off-by: Sa...
Sage Weil
09:51 PM Revision 6e284806 (ceph): schedule_suite: debug filestore = 20 too
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:15 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
... Sage Weil
09:05 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
ha, this apears to be what is breaking the unit tests on firefly/master:
http://gitbuilder.sepia.ceph.com/gitbuilder...
Sage Weil
04:21 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
Experiment:
ceph osd set noup
ceph osd down 1
<osd 1 is down>
ceph osd unset noup
Expected:
<osd 1 is back u...
Dan Mick
09:10 PM Revision 68f62660 (ceph): Merge remote-tracking branch 'origin/wip-6936' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:09 PM Revision 8ebc2a26 (ceph): Merge remote-tracking branch 'origin/wip-7099' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:08 PM Revision 731d483b (ceph): Merge remote-tracking branch 'origin/wip-6830' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:07 PM Revision a19b460a (ceph): Merge remote-tracking branch 'origin/wip-6951' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:06 PM Revision 0aac04a2 (ceph): Merge remote-tracking branch 'origin/wip-7064' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:05 PM Revision d509e53d (ceph): Merge remote-tracking branch 'origin/wip-7271' into firefly
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
09:01 PM Revision ae61abf0 (ceph): Merge pull request #205 from kdreyer-inktank/jenkins
jenkins: fail fast during job execution Alfredo Deza
09:00 PM Revision 76046cf3 (ceph): dencoder: check for radosgw build option
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
09:00 PM Revision 5373ee24 (ceph): osd: use ceph scoped shared_ptr
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> Noah Watkins
08:59 PM Revision a4f091cd (ceph): Merge pull request #8 from ceph/yuriw
Added new dumpling-emperor-x upgrade suite Zack Cerza
08:10 PM Revision f9d8c10c (ceph): removed leftover dirs again
Yuri Weinstein
07:32 PM Bug #6685 (Resolved): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
a9677e136ee4753b86ed1151ca6ff08e4b63473d David Zafman
07:22 PM Bug #6685: osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")

The fix 545135f3e1c75318940caa2c82ac32a53fc4f957 went in because it was thought that a race was occurring betwe...
David Zafman
02:15 PM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
David Zafman
07:31 PM Revision fee57a48 (ceph): removed one upgrade-sequence step and re-named the rest of steps
Yuri Weinstein
07:25 PM Revision 7e625d27 (ceph): Merge pull request #206 from ceph/wip-osd-debug
schedule_suite: debug osd = 20 for the time being Zack Cerza
07:15 PM Revision 70e217f0 (ceph): schedule_suite: debug osd = 20 for the time being
This will make it easier to chase the first pass of firefly bugs.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:20 PM Revision 084c6aed (ceph): Merge pull request #203 from ceph/wip-devstack
Add devstack task Alfredo Deza
06:11 PM Revision a53454ba (ceph): jenkins: fail fast during job execution
Jenkins will dynamically write the commands in its database into a
script and run it with "-x" and "-e" in order to d...
Ken Dreyer
06:08 PM Revision 6671d02d (ceph): Merge pull request #204 from ceph/wip-fix7397-wusui
Do not spawn a parallel task if dictionary entry does not exist. Zack Cerza
05:40 PM Revision fd6f61d6 (ceph): removed unfinished stress-split suite from
Yuri Weinstein
05:30 PM Revision 8ba6a2b0 (ceph): removed obsolete suite from upgrades dir and added dumpling-emperor-x p...
Yuri Weinstein
05:23 PM Revision ca600a2e (ceph): Add unit test for task.devstack.parse_os_table()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
04:22 PM Revision 0ebb1f83 (ceph): mon/MDSMonitor: Cope with failures during creation
Previously an MDS which failed in state CREATING could be
assigned the sequence BOOT->STANDBY->REPLAY at its next
sta...
John Spray
04:18 PM Revision 54116135 (ceph): Add debug output for reconnect() failures
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:57 PM Revision 05842e9f (ceph): Add explanations to asserts
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:43 PM Revision cfb7b948 (ceph): Guard against ctx.config being unset or None
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
03:15 PM CephFS Bug #7503: mds start and oops after access to cephfs
Ok for explanation, and as already said, all that data was test data, so I can loose it without problems. I also full... Yann Dupont
08:45 AM CephFS Bug #7503: mds start and oops after access to cephfs
MDS is getting an ENFILE (object lost) from the OSD while trying to read the OMAP from one of its stray directory obj... John Spray
07:18 AM CephFS Bug #7503 (Won't Fix): mds start and oops after access to cephfs
this is a follow up to http://tracker.ceph.com/issues/7367, which explain the scenario.
I now attach the mds.log
Yann Dupont
02:39 PM Messengers Bug #5508 (Can't reproduce): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
Sage Weil
02:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
Sage Weil
02:37 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
Sage Weil
02:37 PM Bug #6671 (Can't reproduce): FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
Sage Weil
02:36 PM Bug #6636: sockaddr_storage and uuid_t are not portable to other platforms
Sage Weil
02:35 PM Bug #6730 (Won't Fix): BUG: MAX_LOCKDEP_ENTRIES too low!
Sage Weil
02:35 PM Bug #6333 (Closed): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
See #6278 for teh snaptrimmer portion of this. the rest is somewhere between resolved, need more info, and can't repr... Sage Weil
02:33 PM Bug #6806: mon: audit cmd_getval() calls to make sure they handle failures correctly
this patch is still sitting in wip-6796-b Sage Weil
02:33 PM Bug #6633 (Resolved): osd: pgls vs osd restart/peering race misses objects
Samuel Just
02:32 PM Bug #6787: upstart is restarting daemons which we want to be dead
Sage Weil
02:30 PM Bug #7120 (Need More Info): osd: EEXIST on mkcoll on dumpling
Sage Weil
02:29 PM Bug #7170 (Can't reproduce): rados api test LibRadosMisc.CopyPP failed on next branch
Sage Weil
02:29 PM Bug #7172 (Resolved): osd: OSD failed to start with osd_leveldb_cache_size > 0
Samuel Just
02:29 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
Sage Weil
02:28 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
Samuel Just
02:28 PM Bug #7376 (In Progress): mon: >10s spent in remove_redundant_pg_temp
Sage Weil
02:28 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
Sage Weil
02:24 PM Bug #7068 (Need More Info): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.s...
Sage Weil
02:21 PM Bug #7072: logrotate not sending HUP signal
Sage Weil
02:20 PM Bug #7145 (Can't reproduce): PG::update_snap_map assert
Sage Weil
02:19 PM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
Sage Weil
02:18 PM Bug #7248: osd: bench set max size
Sage Weil
02:17 PM Support #7501: Firefly - monitor hangs when ceating EC pool with latest code in master/firefly br...
It looks like you've got an older ceph tool installed locally. Can you validate that the versions match? (i.e., on th... Greg Farnum
02:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
Sage Weil
02:13 PM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
Sage Weil
02:13 PM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
Sage Weil
02:12 PM Bug #7393 (Need More Info): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0...
Sage Weil
02:12 PM Bug #7458: osd: stray pg ref on shutdown
perhaps that pg work queue PGBackend implementation can use? Samuel Just
02:11 PM rbd Bug #7385 (In Progress): Objectcacher setting max object counts too low
Sage Weil
02:10 PM Bug #7398 (Need More Info): osd: ERANGE from clone
Sage Weil
02:09 PM Bug #7491 (In Progress): rados api crashes
Sage Weil
02:09 PM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
Sage Weil
09:36 AM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
wip-7506 Samuel Just
09:35 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
simple fix, ECTransaction needs to require hash_infos for deletions and stashes.
-6> 2014-02-20 22:47:44.48251...
Samuel Just
02:09 PM Bug #7494: EC filter read op bug
Sage Weil
02:08 PM Bug #7496 (Need More Info): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
Sage Weil
02:08 PM Bug #7498 (Need More Info): stuck in recovery
Sage Weil
02:08 PM Bug #7497 (Need More Info): timeout waiting to go clean
Sage Weil
02:08 PM Bug #7495 (Need More Info): ENOTEMPTY on collection remove
Sage Weil
01:58 PM Bug #7463: ceph-rest-api fails to start with no OSDs up
Dan fixed in db88e7f385f4464f5f4de517845607391c314ef5 Brian Andrus
01:08 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
This is pretty consistent in the rbd runs - 0 vs 1 dirty objects in each of these failures: http://pulpito.front.sepi... Josh Durgin
11:57 AM Bug #7508: 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burnupi09.front...
wip-7508 Samuel Just
11:57 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
Objecter doesn't take primary position into account.
2014-02-20T21:16:09.130 INFO:teuthology.task.rados.rados.0.ou...
Samuel Just
10:23 AM rbd Feature #7507 (New): krbd: Make device symlinks cluster aware
Currently when a device is mapped a udev script creates a symlink at /dev/rbd/<pool>/<imagename>
Would be nice if ...
Tyler Brekke
09:29 AM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
Ian Colle
07:22 AM Bug #7367: fail to run mds and mount rbd (v0.76)
OK, so see #7503, http://tracker.ceph.com/issues/7503.
Also see #7368, http://tracker.ceph.com/issues/7368 which...
Yann Dupont
09:02 AM Bug #7504 (Rejected): Ceph does not specify python2
Hi,
Ceph fails on archlinux because it uses python and not python2.
On Archlinux, python = python3 and to use pyt...
Alexandre BIQUE
08:30 AM CephFS Bug #7485 (Fix Under Review): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
John Spray
08:29 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)
https://github.com/ceph/ceph/pull/1283 John Spray
08:14 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)

MDS -1 gid 1 starts in BOOTING, sends a beacon
MON prepare_beacon records its existence and puts it into state STA...
John Spray
07:12 AM devops Bug #7486: python-backports needs fixing for rhel

Sheldon Mustard
04:18 AM Revision dadc9f7d (ceph): Do not spawn a parallel task if dictionary entry does not exist.
Fixes: 7397
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
01:04 AM Revision 6c207286 (ceph): Merge remote-tracking branch 'upstream/next'
Samuel Just
01:02 AM Revision 2bcddce8 (ceph): Merge remote-tracking branch 'upstream/wip-copyget' into next
Fixes: #7471
Reviewed-by: Greg Farnum <greg@inktank.com>
Samuel Just
12:48 AM rgw Bug #7502 (Rejected): S3 API - deleting object always returns 204 regardless of object is existin...
When using S3 API, deleting object always returns 204 regardless of object is existing or not. This is reproducible. ... Zhi Zhang
12:01 AM Revision ba5d12f4 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite into yuriw
Yuri Weinstein
12:00 AM Revision c6e6ced1 (ceph): PG::build_might_have_unfound: skip CRUSH_ITEM_NONE
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just

02/20/2014

11:51 PM Revision b92578e5 (ceph): Remove unused import
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision fdaaee57 (ceph): Source openrc before creating volume
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 11b60fef (ceph): Change usages of StringIO.read() to getvalue()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision f7b1d922 (ceph): Wait 30s for Keystone to start
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 830748a6 (ceph): Move external docs URLs
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision aecd98d7 (ceph): Fix incorrect exception name in docstring
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 741b4de3 (ceph): Add a retry to the rbd volume verification
This was running into an auth problem intermittently that Josh Durgin
said is likely not a real problem. Still, try t...
Zack Cerza
11:46 PM Revision b638dc41 (ceph): Don't run the exercise subtask by default
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 27bad445 (ceph): Move restart_apache() to after the reboot
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 021f84ac (ceph): Simplify create_if_vm's downburst config logic
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 3dcde65c (ceph): Add note about memory requirements
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1228ac88 (ceph): Add documentation to reboot()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 61e9ac4d (ceph): Move reboot() to teuthology.misc
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision e3f336d1 (ceph): Make reconnect() use Remote.reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 5c12d360 (ceph): Add devstack.exercise subtask
The subtask runs devstack/exercise.sh
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision 85e63dd9 (ceph): Allow using different devstack branches
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 7c571274 (ceph): Forget about saving the exercise.sh log, for now
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision f53028f9 (ceph): Add a new subtask: smoke()
Currently it creates a volume, then verifies that the volume exists in
Ceph - as opposed to some other place. This is...
Zack Cerza
11:46 PM Revision 69beebc9 (ceph): get_file() returns a str, not a StringIO...
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a2a5aed4 (ceph): Add Remote.hostname property
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1c71558e (ceph): Add Remote.is_online property
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 71b4bfe2 (ceph): Remote instances can now establish SSH connections
Previously, they required an active ssh connection object to be passed
to them. That behavior is still functional.
S...
Zack Cerza
11:46 PM Revision 8dfac438 (ceph): Make Remote.is_online more accurate
To really know if the connection is active, we need to read something
from the remote host.
Signed-off-by: Zack Cerz...
Zack Cerza
11:46 PM Revision 22894969 (ceph): Use new init parameters for Remote
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 297096b5 (ceph): Add Remote.reconnect()
Also rename Remote._connect() to Remote.connect() and change its
semantics to match Remote.reconnect()
Signed-off-by...
Zack Cerza
11:46 PM Revision fe0aedf7 (ceph): Set apache ServerName, reboot, restart devstack
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a1ed3d49 (ceph): Add logging calls to each helper function
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 1a0be5a0 (ceph): Tweaks to is_online and reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a4bf1f8f (ceph): Actually call Remote.reconnect()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision e73df9c8 (ceph): Make rejoin-stack.sh start screen in detached mode
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 74355e54 (ceph): Add optional 'owner' arg to sudo_write_file()
This gets passed directly to chown as 'sudo chown $owner $file'
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision b6740480 (ceph): Copy ceph auth keys over to devstack node
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision c6b5c01a (ceph): Split out devstack-ceph configuration
This is starting to get long, so create configure_devstack_and_ceph()
Signed-off-by: Zack Cerza <zack.cerza@inktank....
Zack Cerza
11:46 PM Revision b40f5f74 (ceph): Add set_libvirt_secret() and split out other steps
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 76588e97 (ceph): Add update_devstack_config_files()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision cedd1283 (ceph): Split out key generation
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision b33686f4 (ceph): Use get_file() and sudo_write_file()
... instead of copy_file()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
Zack Cerza
11:46 PM Revision f5006348 (ceph): Don't pass owner to copy_key()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision b474d282 (ceph): Fix typoed virsh call
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 119b438f (ceph): Call seek(0) on StringIO objects before reading
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision a55c22aa (ceph): Work around a bug in ConfigParser
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 375d7ddd (ceph): Use ConfigParser.set() instead of update()
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision dfe60526 (ceph): Add copy_file() to scp files between remotes
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:46 PM Revision 10e12c2d (ceph): Add skeleton devstack task
Currently only installs devstack on one node, and creates some pools on
the ceph cluster.
Signed-off-by: Zack Cerza ...
Zack Cerza
11:46 PM Revision ed512568 (ceph): Fix linter errors.
Signed-off-by: Zack Cerza <zack.cerza@inktank.com> Zack Cerza
11:01 PM Revision 1f30d1ab (ceph): ECBackend: deal with temp collection details in handle_sub_write
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:56 PM Revision a3f6d9a6 (ceph): Merge pull request #201 from ceph/wip-6531-wusui
Fix formatting and add docstrings to ceph_manager.py Zack Cerza
10:51 PM Revision 30f8938e (ceph): Fix formatting and add docstrings to ceph_manager.py
Fixes: 6531
Signed-off-by: Warren Usui <warren.usui@inktank.com>
Warren Usui
10:51 PM Revision b4ce61cc (ceph): Add back in print in ceph_manager that the last checkin accidentally re...
Warren Usui
10:42 PM Support #7501 (Closed): Firefly - monitor hangs when ceating EC pool with latest code in master/f...
We are so eager to test out the Firefly erasure coding features even before the RPM packages being released. Here we ... Zhi Zhang
09:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
pull request is #1280 for wip branch wip-7374-wusui Anonymous
09:22 PM rgw Bug #7374: s3_multipart_upload.pl fails
This has been pushed in its own branch to wip-7374-wusui Anonymous
09:28 PM rgw Bug #7375: s3_user_quota.pl fails
Pull request is #1279 for wip branch wip-7375-wusui Anonymous
09:21 PM rgw Bug #7375: s3_user_quota.pl fails
this has been pushed in its own branch to wip-7375-wusui
Anonymous
09:22 PM Revision c703a89d (ceph): ReplicatedPG::on_global_recover: requeue degraded, then unreadable
We need to requeue in reverse order since we are requeueing at the
front.
Signed-off-by: Samuel Just <sam.just@inkta...
Samuel Just
05:47 PM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
Dan Mick
05:30 PM Revision 4a802cd5 (ceph): Merge pull request #7 from ceph/wip-upgrade
upgrade: dumpling-next -> dumpling-x Zack Cerza
05:25 PM Revision 0ae33529 (ceph): rgw: multi object delete should be idempotent
Fixes: #7346
When doing a multi object delete, if an object does not exist then we
should return a success code for t...
Yehuda Sadeh
05:19 PM Revision 474d86ca (ceph): upgrade: dumpling-next -> dumpling-x
Make the final upgrade step unspecified so that it can be specified at
schedule time. This let us test dumpling -> f...
Sage Weil
05:19 PM Revision caf2edfc (ceph): rgw: minor cleanup
Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
05:05 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
05:01 PM Revision 1307ba9c (ceph): mds: Table read failure should log at error level
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision a4d0eb1b (ceph): mds: Remove some unused #defines
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision 2762ede7 (ceph): mds/CDir: Remove a few lines of cruft
Signed-off-by: John Spray <john.spray@inktank.com> John Spray
05:00 PM Revision 81bcf430 (ceph): mds: Don't create the /.ceph directory
This was entirely unused. On existing filesystems
it will live on, on new ones it will never be created.
Signed-off...
John Spray
04:59 PM Revision 5fb90a2f (ceph): Fix generate keystone token from credentials
Request to v2.0/tokens must be a POST request and the request
should specify JSON in the content-type header and fix ...
Mouad Ben
04:27 PM rgw Bug #7499 (Resolved): rgw: bucket unlink / link isn't working
bucket link doesn't work, as we're not able to specify the bucket instance to be linked. We need to think whether we ... Yehuda Sadeh
03:22 PM Revision 541beb87 (ceph): mds: Add encode/decode/dump for use with dencoder
This is for the MDSTable subclasses: AnchorServer,
SnapServer, InoTable. AnchorServer was partially there
but didn't...
John Spray
02:48 PM Bug #7498 (Resolved): stuck in recovery
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91241
- exec:
client.0:
...
Samuel Just
02:46 PM Bug #7497: timeout waiting to go clean
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/91236 Samuel Just
02:45 PM Bug #7497: timeout waiting to go clean
We might just increase the timeout for rados bench runs. Samuel Just
02:44 PM Bug #7497 (Can't reproduce): timeout waiting to go clean
2014-02-20T07:02:16.913 INFO:teuthology.task.radosbench.radosbench.0.err:[10.214.132.16]: 2014-02-20 07:02:16.911765 ... Samuel Just
02:40 PM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
-6> 2014-02-20 02:51:46.869695 7f9b5302e700 5 osd.0 pg_epoch: 152 pg[4.3( v 152'3174 (15'171,152'3174] local-les... Samuel Just
02:39 PM Bug #7495 (Resolved): ENOTEMPTY on collection remove
"can_rollback_to": 12}}]}
2014-02-20 06:28:11.741673 7fcba3c5c700 -1 os/FileStore.cc: In function 'uns...
Samuel Just
02:33 PM Bug #7494 (Resolved): EC filter read op bug
-4> 2014-02-20 00:12:48.296974 7f1623101700 5 -- op tracker -- , seq: 39278, time: 2014-02-20 00:12:48.295450, e... Samuel Just
02:24 PM Bug #7493 (Resolved): cephtool/pool_ops failure
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90946
{description: 'rados/si...
Samuel Just
02:18 PM Bug #7491 (Resolved): rados api crashes
ubuntu@teuthology:/a/teuthology-2014-02-19_23:00:21-rados-master-testing-basic-plana/90865
2014-02-19T23:44:36.621...
Samuel Just
02:18 PM Bug #7490 (Closed): [docs] adding monitor section doesn't specify the need for the admin keyring
The documentation to add monitors manually does not note that the admin keyring file needs to be present
when adding...
Alfredo Deza
01:42 PM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
While attempting to add a monitor that already was in the cluster with a specific IP, instead of
reporting the actu...
Alfredo Deza
10:52 AM Bug #7328 (Resolved): osd: reweight-by-utilization ended up with stuck remapped pgs
this came down to a crush flaw. there is a new tunable to address it in firefly, although it will remain off for the... Sage Weil
09:49 AM rgw Feature #7467: Make radosgw work with multiple hostnames
Yehuda Sadeh
09:20 AM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
Yehuda Sadeh
09:19 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
actually, seems that the original code is post dumpling. Yehuda Sadeh
09:13 AM rgw Bug #7453 (Pending Backport): Authentication to keystone using rgw_keystone_admin_* failed
Pushed, commit:5fb90a2f6dd5b31634efc748a977924dbdbebcb9 Yehuda Sadeh
08:11 AM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
New signed off patch Mouad Ben
08:48 AM rados-java Bug #7488: "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Yuri Weinstein wrote:
> Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing...
Yuri Weinstein
08:46 AM rados-java Bug #7488 (Rejected): "Error EAGAIN: osd.0 is not up" in rados-master-testing-basic-plana
Logs are in qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:00:22-rados-master-testing-basic-plana/88201
err...
Yuri Weinstein
07:20 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
See the thread "[ceph-users] ceph-mon segmentation fault"... Greg Farnum
06:48 AM devops Bug #7486 (Rejected): python-backports needs fixing for rhel
Getting warnings
/usr/lib/python2.6/site-packages/babel/__init__.py:33: UserWarning: Module backports was already ...
Sheldon Mustard
06:23 AM CephFS Bug #7485 (Resolved): Killing MDS during 'creating' breaks subsequent startup (no snaptable)

Pretty easy to reproduce: start MDS for first time on fresh cluster (I'm using vstart here), ctrl-c it promptly, tr...
John Spray
03:06 AM Revision c5c7f6c8 (ceph): Merge branch 'next'
Conflicts:
src/test/admin_socket.cc
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
Ken Dreyer
02:45 AM Bug #7367: fail to run mds and mount rbd (v0.76)
yes, please Zheng Yan
02:33 AM Bug #7367: fail to run mds and mount rbd (v0.76)
I think this bug can be closed as we're probably not in a supported scenario.
I've been able to backup all my RBD ...
Yann Dupont
02:41 AM Revision ebd43972 (ceph): RadosModel: copyfrom should result in a dirty object
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
02:22 AM Revision 68184d45 (ceph): PG: fix scrub feature check
acting[0] isn't necessarily the primary. Start at
0 and explicitely skip the primary.
Signed-off-by: Samuel Just <s...
Samuel Just
01:31 AM Revision 715cbd31 (ceph): ReplicatedPG: ensure that ec appends are aligned
When not writing out the last chunk, _write_copy_chunk
will trim the chunk to a stripe boundary for ec pools
and adju...
Samuel Just
01:31 AM Revision 44417927 (ceph): ECBackend: handle short reads
async reads may have a length past the end of the object.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
01:31 AM Revision 67d1f364 (ceph): ReplicatedPG: assert no omap for ec pool in _write_copy_chunk and skip
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
01:31 AM Revision c337f638 (ceph): ReplicatedPG: fix stat uses to use the correct shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
01:31 AM Revision 78d9c007 (ceph): ReplicatedPG::fill_in_copy_get, use getattr_maybe_cache
Also, add user_only flag to getattr_maybe_cache and cleanup
the other user.
Signed-off-by: Samuel Just <sam.just@ink...
Samuel Just
01:30 AM Revision aa110af9 (ceph): OSDMap::_apply_primary_affinity: skip CRUSH_ITEM_NONE in non-default check
Fixes: #7482
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: David Zafman <david.zafman@inktank.com>
Samuel Just
12:57 AM Revision b3bb9efe (ceph): doc/release-notes: v0.77
Also pending notes for v0.78
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
12:20 AM Revision fa96de9e (ceph): doc/release-notes: v0.67.7
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/19/2014

10:54 PM Revision 1bca9c5c (ceph): v0.77
Ken Dreyer
10:14 PM CephFS Bug #6608: samba teuthology dbench failure
We're still occasional samba test failures, but I haven't diagnosed them carefully enough to know if they're this fai... Greg Farnum
10:14 PM Revision 40bdcb88 (ceph): osd/,mon/: add (up|acting)_primary to pg_stat_t
We use pg_stat_t information to determine pg create targeting.
Fixes: #7481
Signed-off-by: Samuel Just <sam.just@ink...
Samuel Just
10:01 PM Revision d78b9b01 (ceph): jenkins: add debugging output to shell script
When we migrated the Jenkins commands into Git, the exact commands are
no longer visible unless we run with "-x".
Ad...
Ken Dreyer
09:44 PM Revision c0360077 (ceph): Merge pull request #195 from ceph/wip-7003-wusui
Add docstrings to the orchestra code. Also fix minor formatting issues Zack Cerza
09:40 PM Revision 31c27e13 (ceph): Merge pull request #186 from ceph/wip-7369
Fix #7369: "sed expression must be raw string" Alfredo Deza
09:40 PM Revision e5fe884e (ceph): Merge pull request #186 from ceph/wip-7369
Fix #7369: "sed expression must be raw string" Alfredo Deza
09:37 PM Revision f3ac7870 (ceph): Fix syntax error in first docstring added.
Warren Usui
09:34 PM Revision efd59a2a (ceph): Merge pull request #190 from kdreyer-inktank/jenkins
add jenkins-pull-requests-build script Zack Cerza
09:26 PM Revision a70e93fc (ceph): Merge pull request #199 from ceph/wip-6540-wusui
Add docstrings. Fix formatting issues for rgw.py Zack Cerza
09:26 PM Revision cc3d013e (ceph): Merge pull request #196 from ceph/wip-6541-wusui
Fix docstrings in radosgw-admin-rest.py Zack Cerza
09:26 PM Revision 8d85b21c (ceph): Merge pull request #197 from ceph/wip-6535-wusui
Fix docstrings for task/blktrace.py, peering_speed_test.py, proc_thrashe... Zack Cerza
09:25 PM Revision f18dcf5b (ceph): Merge pull request #198 from ceph/wip-6539-wusui
Fix docstrings and minor formatting in task/ssh_keys.py Zack Cerza
09:23 PM Revision 9f953d42 (ceph): Merge pull request #200 from ceph/wip-6532-wusui
Fixed task/args.py docstrings. Zack Cerza
07:23 PM CephFS Bug #7474: Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
are you using 3.8 kernel? if you are, please try 3.12 or 3.13 Zheng Yan
01:07 AM CephFS Bug #7474 (Won't Fix): Kernel oops with cephfs [ceph_write_begin -> *x8 -> wait_on_page_read]
I'm on Ubuntu 13.10 and I've installed the packages distributed with it (ceph-deploy 1.2.3-0ubuntu1 and `ceph` 0.67.4... Peter Waller
07:20 PM Revision 10fee0e3 (ceph): Revert "Show hostname instead of IP in errors"
This reverts commit eafeece243607eef8209eaa8c08eecc7d1098eb1.
I was having problems with my newly-created devstack t...
Zack Cerza
07:18 PM Revision 72f260e0 (ceph): Merge pull request #1256 from ceph/wip-librados-ops-and-rvals
librados c api for object operations and a few bug fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Reviewed-by...
Josh Durgin
07:07 PM Revision 0427f615 (ceph): rgw: fix swift range response
Fixes: #7099
Backport: dumpling
The range response header was broken in swift.
Reported-by: Julien Calvet <julien.ca...
Yehuda Sadeh
07:06 PM Revision 2b3e3c83 (ceph): rgw: fix etag in multipart complete
Fixes: #6830
The etag member variable was not set correctly.
Reported-by: Benjamin Gilbert <bgilbert@backtick.net>
S...
Yehuda Sadeh
07:06 PM Revision 859ed33e (ceph): rgw: reset objv tracker on bucket recreation
Fixes: #6951
If we cannot create a new bucket (as it already existed), we need to
read the old bucket's info. However...
Yehuda Sadeh
07:03 PM Revision 53de6412 (ceph): radosgw-admin: don't generate access key if user exists
Fixes: #6936
We want the user creation operation to be idempotent, so if user already
exists don't generate a new acc...
Yehuda Sadeh
06:09 PM Revision d7ab4244 (ceph): v0.67.7
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com> Ken Dreyer
05:56 PM Revision f0bfff11 (ceph): add jenkins-pull-requests-build script
Move our Jenkins pull requests build script out of Jenkins' database and
into Git so that we can have greater visibil...
Ken Dreyer
05:40 PM Revision 9e8882e0 (ceph): BackedUpObject::get_xattr() pass function parameter by reference
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:37 PM Revision 53b36898 (ceph): TestRados.cc: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:35 PM Revision 86b08796 (ceph): ErasureCodeBench: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:34 PM Revision 200ebb9b (ceph): ceph_erasure_code.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
aa110af991e6d637b30d740af46f3dc2168cde01 Samuel Just
03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
wip-copyget Samuel Just
11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
Samuel Just
05:32 PM Revision e6772c76 (ceph): RGWObjManifest: prefer prefix ++/--operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:30 PM Revision 42e6da7b (ceph): ReplicatedPG: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:26 PM Revision 29c4abd8 (ceph): OSD: use !empty() instead of size() > 0
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
Anonymous
05:20 PM rgw Bug #7375: s3_user_quota.pl fails
This is the same issue as 7374. Anonymous
02:16 PM rgw Bug #7375: s3_user_quota.pl fails
This appears to be a problem in the 7375 pl script. I am taking it. Anonymous
05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
I have pushed a change for this. Anonymous
02:15 PM rgw Bug #7374: s3_multipart_upload.pl fails
This appears to be two problems in the s3_multipart_upload.pl script.
I am taking this.
Anonymous
05:17 PM Revision be857274 (ceph): PG: use !empty() instead of size() > 0
[src/osd/PG.cc:543]: (performance) Possible inefficient checking
for 'actingbackfill' emptiness.
[src/osd/PG.cc:148...
Danny Al-Gaaf
05:09 PM Revision f23ab4af (ceph): RPCRecPred: use !empty() instead of size() >= 1
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:05 PM Revision 0626df90 (ceph): KeyValueStore: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:03 PM Revision 76c17239 (ceph): KeyValueStore: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
05:02 PM Revision ede614a7 (ceph): FileStore: use !empty() instead of size()
[src/os/FileStore.cc:3635]: (performance) Possible inefficient checking
for 'omap_set' emptiness.
Signed-off-by: D...
Danny Al-Gaaf
04:59 PM Revision eaf66967 (ceph): DBObjectMap: use !empty() instead of size()
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:57 PM Revision 0bf0ec0f (ceph): OSDMonitor: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:55 PM Revision 31b4107a (ceph): OSDMonitor: use !empty() instead of size() > 0
[src/mon/OSDMonitor.cc:730]: (performance) Possible inefficient checking
for 'osd_weight' emptiness.
Signed-off-by...
Danny Al-Gaaf
04:53 PM Revision a1412bdf (ceph): MDCache: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
04:51 PM Revision 4a48d8ed (ceph): CrushWrapper::is_valid_crush_loc(): pass function parameter by reference
[src/crush/CrushWrapper.cc:1412]: (performance) Function parameter 'loc'
should be passed by reference.
Signed-off...
Danny Al-Gaaf
04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
The last call will end with abort()... Loïc Dachary
01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
... Loïc Dachary
10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
Loïc Dachary
06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
crashes on master as of today Loïc Dachary
03:41 PM Revision 3f68a5ca (ceph): CrushWrapper: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
03:38 PM Revision dd71051a (ceph): PGLog.h: prefer prefix ++operator for non-trivial iterator
[src/osd/PGLog.h:363]: (performance) Prefer prefix ++/-- operators for
non-primitive types.
[src/osd/PGLog.h:375]: ...
Danny Al-Gaaf
03:24 PM Revision 8488e710 (ceph): Client: remove a std::string::c_str() calls
[src/client/Client.cc:6821]: (performance) Passing the result of c_str() to a
function that takes std::string as ar...
Danny Al-Gaaf
03:17 PM Revision 1099e255 (ceph): common/config.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
03:13 PM Revision c7dfdfdc (ceph): str_map.cc: prefer prefix ++operator for non-trivial iterator
[src/common/str_map.cc:55]: (performance) Prefer prefix ++/-- operators
for non-primitive types.
Signed-off-by: Da...
Danny Al-Gaaf
03:10 PM Revision 7da714af (ceph): Client.cc: use !empty() instead of size()
[src/client/Client.cc:2275]: (performance) Possible inefficient
checking for 'cap_snaps' emptiness.
[src/client/Cli...
Danny Al-Gaaf
02:40 PM Bug #7471: ec pools copyfrom broken
wip-copyget Samuel Just
02:20 PM Revision fd08b09f (ceph): ceph_argparse.cc: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Samuel Just
11:41 AM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
Mon uses acting[0] to send create messages. More importantly, pg_stat_t does not include acting_primary or up_primar... Samuel Just
02:13 PM Revision 1d1392dd (ceph): Monitor: pass function parameter by reference
[src/mon/Monitor.h:619]: (performance) Function parameter 'param_str_map'
should be passed by reference.
Signed-of...
Danny Al-Gaaf
02:05 PM Revision ab45d44a (ceph): BarrierContext: prefer prefix ++operator for non-trivial iterator
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
02:02 PM Revision 4adcfa59 (ceph): BarrierContext: reduce scope of 'done' variable
Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de> Danny Al-Gaaf
01:54 PM Revision 19dad031 (ceph): MonClient: pass function parameter by reference
[src/mon/MonClient.h:412]: (performance) Function parameter 'mon_name'
should be passed by reference.
Changed also...
Danny Al-Gaaf
01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
This is already done (CORS). Yehuda Sadeh
01:34 PM Feature #7484 (New): better wording when authentication fails
After having a mismatch for the client.admin.keyring in a new host that I needed to get a monitor running I was getti... Alfredo Deza
01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
Yehuda Sadeh
01:33 PM rgw Tasks #5121 (Closed): bump up librados version
Closing this one. Yehuda Sadeh
01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7 Yehuda Sadeh
01:30 PM rgw Bug #6710 (Resolved): radosgw init script does not exit 1 and tell the user if the hostname does ...
This was fixed, commit:0c610918c4ebd6fc1376027cfe6425cfdcfa0245 Yehuda Sadeh
01:29 PM devops Bug #7483 (Rejected): ceph-deploy should fetch keyrings always
If keyring files exist in the cwd and they are dated/wrong ceph-deploy will say it has them and will not attempt to r... Alfredo Deza
01:28 PM rgw Feature #5136 (Closed): rgw: revise user stats
Yeah, I have no idea what this issue is about. Now, considering that user stats have actually been revised for the us... Yehuda Sadeh
01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
There's a good chance that this was #7030. Closing. Yehuda Sadeh
01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd Yehuda Sadeh
01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
Fix looks fine to me. Can you sign-off it? Yehuda Sadeh
10:29 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
subusers are only relevant for the swift case, and the regular access-key/secret combination does not apply to them. ... Yehuda Sadeh
10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
Yehuda Sadeh
10:19 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
So these packages were on the DVD (iso downloaded from https://rhn.redhat.com/rhn/software/channel/downloads/Download... Sandon Van Ness
10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
Yehuda Sadeh
09:35 AM rados-java Bug #7479 (Won't Fix): Test failed in rados-dumpling-testing-basic-plana
Logs are in - qa-proxy.ceph.com/teuthology/teuthology-2014-02-18_19:00:09-rados-dumpling-testing-basic-plana/89421
...
Yuri Weinstein
08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
Yehuda Sadeh
08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
Yehuda Sadeh
08:06 AM Bug #7451: updatedb will index /var/lib/ceph
This should also be reported to mlocate upstream (at Fedora) and to Red Hat for RHEL 7.
Here's the upstream update...
Ken Dreyer
07:53 AM rgw Bug #7426 (Resolved): Tests in rgw-dumpling-master-basic-plana fail, error "Couldn't init storage...
This was an issue with the osd, fixed by commit:2795339d3632df975486d51e69762f9f567fb43d. Yehuda Sadeh
06:20 AM Revision 314116e2 (ceph): PG: insert into stray set if !us_up() && !is_acting()
This is simpler than checking actingbackfill
since it may not yet be filled in.
Fixes: #7470
Signed-off-by: Samuel J...
Samuel Just
06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
crashes, investigating why Loïc Dachary
05:10 AM Revision a33874d0 (ceph): Merge pull request #1257 from ceph/wip-agent
osd: a few agent fixes
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
05:09 AM Bug #7445 (Rejected): missing feature bit ( next )
LD_LIBRARY_PATH was set to /usr/local/bin which contained an old version of the ceph libraries, causing the problem Loïc Dachary
05:05 AM Revision 0af73755 (ceph): osd/ReplicatedPG: strengthen agent_work assertions
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
05:05 AM Revision a40cd507 (ceph): osd/ReplicatedPG: load older HitSets into memory
If our evict_mode is non-idle, load older HitSets into memory in the agent
work thread.
Signed-off-by: Sage Weil <sa...
Sage Weil
05:05 AM Revision a5c5d924 (ceph): osd/ReplicatedPG: EOPNOTSUPP on hit_set_get on non-replicated pools
We need to use the async read stuff for this to work.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:24 AM rbd Bug #6480: librbd crashed qemu-system-x86_64
Just a note, bug itself is very unlikely to reproduce in a short times (one crash per 1k VM instances per month or so). Andrey Korolyov
03:46 AM Revision 1d907c60 (ceph): OSD: consider up/acting primary for new intervals
Both acting_up_affected and start_peering_interval need
to consider primary changes as well as acting/up changes.
Fi...
Samuel Just
02:42 AM Revision afbd58ea (ceph): rgw: don't try to read bucket's policy if it doesn't exist
It's going to fail anyway, just build a default policy.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
01:35 AM devops Feature #7475 (Rejected): ceph-disk: prepare should be idempotent
If the target device / directory is already prepared exactly as required, ceph-disk prepare should return true with a... Loïc Dachary
12:43 AM Revision 3ed68eb9 (ceph): rgw: return error if accessing object in non-existent bucket
Fixes: #7064
Instead of trying to access the object, which is impossible as we don't
even have a proper bucket info. ...
Yehuda Sadeh

02/18/2014

11:43 PM Revision b0dcc798 (ceph): radosgw-admin: gc list --include-all
A new option to the radosgw-admin gc list command that dumps *all* gc
entries, and not just the expired ones. This is...
Yehuda Sadeh
11:38 PM Revision 1ff0eefe (ceph): Merge pull request #1259 from ceph/wip-6677
rgw: add compatibility for MultipartUpload
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:37 PM Revision a2c195d8 (ceph): Merge pull request #1258 from ceph/wip-rgw-gc
radosgw-admin: gc list --include-all
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
11:07 PM CephFS Bug #6608: samba teuthology dbench failure
still see the issue ? Zheng Yan
10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
Samuel Just
04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
wip-strays Samuel Just
09:49 PM Revision b9e1341f (ceph): rados/thrash: add ec-radosbench workload
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:45 PM Revision 386650d9 (ceph): rados/thrash: add ec workloads
Adds ec workloads for snaps, small objects, read-write.
copy-from is not yet enabled.
Signed-off-by: Samuel Just <s...
Samuel Just
09:41 PM Revision 82cf9795 (ceph): Merge pull request #1261 from ceph/wip-7463
ceph_rest_api.py: don't fail if no up OSDs found on startup
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
09:25 PM Revision 609f4c56 (ceph): Throw a Timeout exception on timeout.
Signed-off-by: Mike Lundy <mike@fluffypenguin.org>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Mike Lundy
09:19 PM Revision e3715652 (ceph): task/: add ec_pool and append to rados.py
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:19 PM Revision 2718dbc3 (ceph): radosbench: simplify pool creation and add ec_pool support
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
09:11 PM Revision 3fb6e258 (ceph): test/rgw: manifest unitest
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:11 PM Revision b3ce1889 (ceph): cls/rgw: fix debug output
print the correct error value
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
Yehuda Sadeh
09:11 PM Revision 19754413 (ceph): dencoder: fix for new rgw manifest code
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> Yehuda Sadeh
09:11 PM Revision da64bf70 (ceph): rgw: scalable manifest object
Define a new manifest structure. The idea is that the manifest defines a
set of rules for structuring the object part...
Yehuda Sadeh
09:07 PM Revision c5d3bdf7 (ceph): Merge pull request #1214 from ceph/wip-rgw-manifest-2
Wip rgw manifest 2
Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
09:07 PM Revision db88e7f3 (ceph): ceph_rest_api.py: don't fail if no up OSDs found on startup
allow find_up_osd() to return None, and have caller check for it
Fixes: #7463
Signed-off-by: Dan Mick <dan.mick@inkt...
Dan Mick
08:34 PM Revision 0dc4309b (ceph): librados: add read to c object operation api
Do the usual bufferlist to buffer conversion in a callback from the
objecter before the librados user gets called.
S...
Josh Durgin
08:34 PM Revision 2543cde7 (ceph): librados: add exec to the c object operations api
Add two versions: one that allocates a buffer of the appropriate
length for the user, but relies on the user to free ...
Josh Durgin
08:34 PM Revision f68b706e (ceph): Objecter: add a way to chain callbacks
The librados C api needs to do extra things like converting c++ data
structures or setting lengths, but some objecter...
Josh Durgin
08:34 PM Revision 242a6c85 (ceph): librados: add read xattr functions for c object operations
Only implement string xattr comparison by since integer xattr
comparison assumes ceph-encoded integers in little-endi...
Josh Durgin
08:34 PM Revision 995fea9a (ceph): librados: add omap object operations to the c api
Create an iterator type similar to XattrIter for returning results.
It just wraps the std::map to preserve sorting.
...
Josh Durgin
08:34 PM Revision bac7bb64 (ceph): librados: bump version number
This covers the many recent changes leading up to the firefly release,
including the c object operations api.
Signed...
Josh Durgin
08:34 PM Revision 7a760337 (ceph): packaging: add test programs for librados c object operations
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision 4b229f71 (ceph): qa: add librados c object operations tests to librados test script
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision e550ad79 (ceph): ReplicatedPG: avoid undefined behavior in xattr comparison
Reading past the end of a pointer returned by string.data() in c++98
is undefined. While we're fixing this, also allo...
Josh Durgin
08:34 PM Revision 77436989 (ceph): ReplicatedPG: don't copy the ops vector into OpContext
There's no need to copy it, and if we refer to the same vector from
the original MOSDOp, we can modify rvals for indi...
Josh Durgin
08:34 PM Revision 1d661ca9 (ceph): ReplicatedPG: set individual osd op rvals
This takes care of things that can fail before transaction is
executed, like omap comparison. Getting individual rval...
Josh Durgin
08:34 PM Revision 18f08cd9 (ceph): ReplicatedPG: clear osd op reply output for writes
Since the vector of OSDOps used by the reply is the same
as the one processed by do_osd_ops() now, any output data
ne...
Josh Durgin
08:34 PM Revision bfbfcd6e (ceph): ReplicatedPG: fix successful write condition
ctx->modify no longer implies that the operation is a write,
if it ever did. These days op->may_write() is checked re...
Josh Durgin
08:34 PM Revision 7a019b38 (ceph): test/librados: remove unused lines and fix return code for cmp guards
Now that return values are actually set by the osd and client, fix up
the tests that were checking the old behavior.
...
Josh Durgin
08:34 PM Revision 9630f2f0 (ceph): test/librados: create general test case classes
Using a test case allows us to remove a boatload of boilerplate code
in all the tests, and focus them more on what th...
Josh Durgin
08:34 PM Revision 8d4a5fd5 (ceph): test/librados: add a connect_cluster() helper
This mirrors the c++ version, connect_cluster_pp(), and removes the
same code from create_one_pool().
Signed-off-by:...
Josh Durgin
08:34 PM Revision d3c6f171 (ceph): test/librados: use connect_cluster_pp() instead of duplicating it
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision c6d8d0ef (ceph): test/librados/cmd: remove unnecessary pool creation
Several tests here don't use the pool at all.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
Josh Durgin
08:34 PM Revision 5497e1cb (ceph): test/librados: use a test case instead of duplicating code everywhere
These tests don't have any special requirements on their ioctx and
pools, so they can also run much faster by using d...
Josh Durgin
08:34 PM Revision ae072ac2 (ceph): test/librados: use standard rados test case for snapshot tests
Split these into two categories, self-managed and pool snapshots,
since they are mutually exclusive for a single pool...
Josh Durgin
08:34 PM Revision 5276e3cc (ceph): test/librados: refactor setup/teardown in tiering tests
These tests can either use the standard RadosTest, with one pool, or a
new test case with two pools.
The new test ca...
Josh Durgin
08:34 PM Revision c61ba410 (ceph): test/librados: add ObjectReadOperation tests
These will help prevent regressions and demonstrate what should be
expected by the c api.
Signed-off-by: Josh Durgin...
Josh Durgin
08:34 PM Revision e255bf58 (ceph): librados: add section docs for object operations
The doxygen end section of watch notify was accidentally moved when
these were added, so fix that at the same time.
...
Josh Durgin
08:34 PM Revision 50ca88a1 (ceph): librados: add some comments about constants in librados.h
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> Josh Durgin
08:34 PM Revision 7f1f0b55 (ceph): librados: remove constant for CMPXATTR_NOP
This constant was just added in the public header to match the
operations in rados.h, and was not included in a stabl...
Josh Durgin
08:34 PM Revision 4f4121ae (ceph): librados: add global op flags to the c api
The c++ api did not include these in the sync versions of the calls,
so add a flags argument to the IoCtxImpl functio...
Josh Durgin
08:34 PM Revision bc03fbb4 (ceph): librados: add individual op flags for c write operations
Move flag validation to a static function so it can be shared with the
c++ api. Refer to the new C constants from the...
Josh Durgin
08:34 PM Revision 770942aa (ceph): librados: add exec to the c write operations api
Nothing special needed here, just copying the input buffer and passing
things through. Don't allow output data since ...
Josh Durgin
08:34 PM Revision 6094e437 (ceph): librados: add simple atomic read operations to c api
stat, assert_exists, and set_flags are simple and need no extra
infrastrucutre.
Signed-off-by: Josh Durgin <josh.dur...
Josh Durgin
08:34 PM Revision 6503f21a (ceph): Objecter: add a context argument to ObjectOperation::read()
The c api will need this to be able to set the output buffer length
and potentially copy from bufferlist to buffer.
...
Josh Durgin
08:34 PM Revision abca34aa (ceph): Objecter: keep ObjectOperation rval pointers for writes
Just before sending an op, prepare_mutate_op() is called, creating a
new Op. prepare_read_op() already copied over al...
Josh Durgin
08:34 PM Revision 6273ba4a (ceph): test/librados: move test.cc into its own library
This way it doesn't have to be compiled many times, and it's easier
to add new general functionality to new files wit...
Josh Durgin
08:34 PM Revision 393a2021 (ceph): Merge pull request #1227 from ceph/wip-7394
Improve the OSD and generic monitor timeout mechanisms
Reviewed-by: Sage Weil <sage@inktank.com>
Gregory Farnum
07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
1d907c60d7628429292917fbabf61d09ef8dfa6f Samuel Just
04:15 PM Bug #7469: ENXIO on ec pool write
Samuel Just
04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
testing wip-primary Samuel Just
07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
Stopping the teuthology run and running the commands manually reveals the following:... Anonymous
06:56 PM Revision 43b5cf97 (ceph): Merge remote-tracking branch 'upstream/wip-ecbackend-for-review'
Reviewed-by: Sage Weil <sage@inktank.com> Samuel Just
06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
Yehuda Sadeh
05:09 PM rbd Bug #6480 (Need More Info): librbd crashed qemu-system-x86_64
...and now there's a new similar instance, this time on rhel:... Josh Durgin
12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
Ian Colle
04:22 PM Revision 45a782ff (ceph): Merge pull request #1255 from ceph/wip-cache-perf
osd: add perfcounters for new cache and agent events
Reviewed-by: Haomai Wang <haomaiwang@gmail.com>
Sage Weil
04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
Samuel Just
03:46 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Moving to the ceph project since any scrub errors are general rados problems. Josh Durgin
03:33 PM Bug #7468: "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
Yuri Weinstein wrote:
Logs - qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-master-testing-basic-...
Yuri Weinstein
03:30 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
There are several of those.
Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-02-17_23:02:00-rbd-maste...
Yuri Weinstein
03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d Yehuda Sadeh
03:10 PM rgw Feature #7467 (Resolved): Make radosgw work with multiple hostnames
A ceph user has a situation in which they would like to switch to a new hostname for accessing the gateways. At the t... Brian Andrus
02:47 PM Revision 4c930a0a (ceph): Revert "Capture stderr and include in CommandFailedError"
This reverts commit d0a434923100dd16548e5f76eaffa5462c4b91d4. Alfredo Deza
02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
Yehuda Sadeh
09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
Yehuda Sadeh
02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
commit:609f4c56718d8279895b02b8163bbe1976c02bfb Josh Durgin
02:21 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
The recently added timeouts for librados should result in a specific exception type in the python bindings. Josh Durgin
01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41 Yehuda Sadeh
01:07 PM Bug #7463 (Fix Under Review): ceph-rest-api fails to start with no OSDs up
No reason not to start. This appears to fix it:... Dan Mick
11:26 AM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
ceph-rest-api fails to start id it can find no up OSDs:
osdid = find_up_osd(app)
File "/usr/lib/python2.6/sit...
Brian Andrus
12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
Ian Colle
12:54 PM Revision c93f14f2 (ceph): filestore_idempotent: filestore -> objectstore path change
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
Ian Colle
12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
Ian Colle
12:51 PM Revision 150e87a1 (ceph): osd: l_osd_tier_whiteout
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision dbec1096 (ceph): osd: l_osd_tier_[dirty|clean]
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision d1a185bd (ceph): osd: l_osd_agent_{wake,skip,flush,evict}
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 4bee6ff1 (ceph): osd/ReplicatedPG: clean up agent skip debug output
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 4b0a0a10 (ceph): osd: l_osd_copyfrom
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision c45a477e (ceph): osd: l_osd_tier_[try_]flush[_fail]
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:51 PM Revision 2d5371dd (ceph): osd: l_osd_tier_evict
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
12:45 PM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
This was observed on a 3.11 ubuntu kernel:... Josh Durgin
12:40 PM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
backported in commit:4e47a003bb3adcee690067d4037c248a93023c20 a while ago Josh Durgin
12:37 PM Feature #7464 (Rejected): Backport appropriate pieces of #7394, #7395
We put some fixes for OSDs overwhelming the monitor into master; now they need to get backported to Dumpling. Greg Farnum
12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e Greg Farnum
11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
Samuel Just
11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
Samuel Just
11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
Samuel Just
11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7366 (Resolved): EC: scrubbing
Samuel Just
11:01 AM Feature #7366: EC: scrubbing
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:01 AM Feature #7361 (Rejected): EC: arrange for chunks to have some padding where we can later add chec...
Not desirable for final design Samuel Just
11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
43b5cf977cd93bd5ee811491c4728701fa1a3ae2 Samuel Just
09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b Yehuda Sadeh
09:29 AM rgw Bug #7346 (Pending Backport): An unfound object as part of multi-object delete should return dele...
A fix was pushed, commit:8ca3d95bf633ea9616852cec74f02285a03071d5. Yehuda Sadeh
08:54 AM Bug #7451: updatedb will index /var/lib/ceph
Sage Weil wrote:
> I'm not sure the init script is the place to do it.. maybe the package postinst?
postinst is n...
Dietmar Maurer
04:12 AM Revision 11f288e5 (ceph): Objecter: track primary explicitly to detect changing primaries
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5e727bfe (ceph): RadosModel: only output if missing header is actually a problem
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 7772014a (ceph): OSD,PG: pass through EC messages
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision ae827cfe (ceph): osd_types: add swap, claim_append to ObjectModDesc
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 258af5eb (ceph): buffer: allow caller to initialize bufferhash state
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 7731a949 (ceph): ObjectStore: add bufferlist/string getattr
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 33c38301 (ceph): osd/ECUtil: add ec encode/decode util helpers
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 45b6c59e (ceph): osd/ECTransaction: add type encapsulating EC transaction
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 792f0a85 (ceph): ECBackend: flesh out ECBackend implementation
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision b90584a8 (ceph): osd/: instantiate the right backend based on pool
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision bc31c4b3 (ceph): ReplicatedPG: add some debugging if waiting_for_commit is non-empty
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision f0b69b38 (ceph): osd/: replace bufferptr with bufferlist for attrs in recovery
Now we won't have to keep converting back and forth!
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:12 AM Revision 1835c29f (ceph): ReplicatedBackend: factor out be_deep-scrub
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 26745ca8 (ceph): PGBackend/ReplicatedBackend: move the backend agnostic code into PGBack...
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 510585b7 (ceph): PGBackend/ReplicatedBackend: factor out logical to ondisk size mapping
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision ca323ff6 (ceph): ReplicatedPG: fix size checking for ECBackend pools
Allow the backend to adjust the logical object size before
checking against the ondisk size.
Signed-off-by: Samuel J...
Samuel Just
04:12 AM Revision 0661d802 (ceph): PGBackend: make getattrs virtual
This way, the backend can choose to filter private attrs.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:12 AM Revision e8820ac4 (ceph): src/osd/: add ECBackend stubs
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 6cd64a50 (ceph): messages,osd: add EC messages and associated types
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5db3b2dc (ceph): osd/: extend pg_interval_t to include primary
Otherwise, we cannot correctly determine up_from/up_thru for
old intervals. Also, we need this information to determ...
Samuel Just
04:12 AM Revision 2d3205ff (ceph): PG: skip CRUSH_ITEM_NONE in acting set in various places
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 5a8c0bb9 (ceph): os/: allow objects with NO_GEN but non-NO_SHARD shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 74b8a0c0 (ceph): PG,PGBackend: expose acting and backfill_targets
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision facec765 (ceph): PGBackend: add some additional helpers.
ECBackend's primary specific logic mostly won't treat the
primary shard specially, so it'll be handy to have primary
...
Samuel Just
04:12 AM Revision 8b33d60f (ceph): PG: allow PGBackend to set criteria for PG up-ness
ECBackend needs to be able to require that a readable
set of the most recent interval to write be available
in order ...
Samuel Just
04:12 AM Revision 84e2f39c (ceph): PG,ReplicatedPG: Generalize missing_loc for ECBackend
Prior to EC pools, unfound => missing. Now, unfound (unreadable,
really) is dependent on the PGBackend requirements ...
Samuel Just
04:12 AM Revision 0b180e6a (ceph): PG::discover_all_missing: request a FULLLOG
Otherwise, we cannot correct for divergent objects in the missing
set.
Signed-off-by: Samuel Just <sam.just@inktank....
Samuel Just
04:12 AM Revision 41e19453 (ceph): PG: refactor calc_acting to handle pg_shard_t changes
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 285cf772 (ceph): PG: introduce calc_ec_acting
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 109b3c9e (ceph): OSDMap: fill in get_primary_shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 904704ac (ceph): OSDMap: handle CRUSH_ITEM_NONE in acting sets
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:12 AM Revision 9d8be1b0 (ceph): Objecter: handle primary other than acting[0]
EC pool particularly might have CRUSH_ITEM_NONE as acting[0] which
is not a valid osd.
Signed-off-by: Samuel Just <s...
Samuel Just
04:12 AM Revision 035d6cc2 (ceph): osd/: refer to pg by spg_t and replica by pg_shard_t
We may have multiple pg shards on the same osd for an
ec pool. Thus, replicas must be referred to by <osd, shard>
an...
Samuel Just
04:11 AM Revision 5d01f88c (ceph): ReplicatedBackend/PGBackend: move objects_* methods into PGBackend
These also are unchanged in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:11 AM Revision 761f0b1e (ceph): PGBackend: use whoami_shard().shard in rollback*, objects*
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 31b7937b (ceph): PGBackend/ReplicatedBackend: move temp handling into PGBackend
Temp handling is also the same in ReplicatedBackend as in ECBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:11 AM Revision fa980644 (ceph): ReplicatedBackend: excise OSDService*
This should eventually make it easier to mock out a PGBackend::Listener.
Signed-off-by: Samuel Just <sam.just@inktan...
Samuel Just
04:11 AM Revision 8b46dd1d (ceph): messages/: include shard information in various pg messages
We can no longer use the messenger source information to determine
the origin of the message since an osd might have ...
Samuel Just
04:11 AM Revision f678aefd (ceph): TestPGLog: remove test with DELETE op with prior_version = eversion_t()
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 1c93e03f (ceph): osd/: Add a shard parameter to SnapMapper to handle multiple pg shards
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision f2826fa2 (ceph): src/osd: pass in version to recover to recover_object
Otherwise we need to do some annoying contortions to
get it out of the missing sets.
Signed-off-by: Samuel Just <sam...
Samuel Just
04:11 AM Revision 44b43df4 (ceph): ObjectStore: use ghobject_t for setattrs
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 4a259516 (ceph): osd_types: introduce spg_t, pg_shard_t
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
04:11 AM Revision 8ca875b6 (ceph): PGBackend/ReplicatedBackend: move rollback methods into PGBackend
These will end up essentially unchanged in ECBackend as it turns out.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
04:10 AM Revision 09d611d2 (ceph): PGLog::merge_old_entry: simplify the oe.version > ne.version case
If ne.version < oe.version, the correct answer is to rollback oe.version
if possible regardless of what the entries a...
Samuel Just
12:41 AM Revision 5f8eedf0 (ceph): rados/thrash: test rados against cache pool with agents
Run rados model against a pool with target_max_objects set so that the
tiering agent is working against us.
Signed-o...
Sage Weil
12:26 AM Revision e6a1122b (ceph): osd: l_osd_tier_promote
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil

02/17/2014

11:56 PM RADOS Bug #7460 (New): librados: no test for c api's global ops flags
This could be tested by creating a binary just for testing that enables logging, sets some global op flags, and grepp... Josh Durgin
11:15 PM Revision 5bc92ece (ceph): Merge pull request #1128 from ceph/wip-dirfrags
Fixes for mds cluster + directory fragments Zheng Yan
10:25 PM Revision d116e55f (ceph): PG: just ignore rollbacks on objects we have already failed to rollback
The relevant changes to missing and/or the filestore will have
already been made.
Signed-off-by: Samuel Just <sam.ju...
Samuel Just
10:25 PM Revision fd9da00e (ceph): ReplicatedPG: take snapset_obc write lock where appropriate
Otherwise, we might read it for backfill before it's fully created
on a peer.
Signed-off-by: Samuel Just <sam.just@i...
Samuel Just
10:25 PM Revision 0e7b10ac (ceph): PG::remove_snap_mapped_object: use pg_whoami.shard
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 3650da69 (ceph): ErasureCodeJerasure: fill in decoded if all shards are included
This causes it to match minimum_to_decode.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 13a41e14 (ceph): FileStore: permit NULL onreadable callback
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision d8b6d4c1 (ceph): ReplicatedPG: release_op_ctx_locks in all-applied, not all-committed
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision b3b2bab4 (ceph): ReplicatedPG: handle xattr cache on rollback and delete_head
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 17e6ecc8 (ceph): ReplicatedPG: find_object_context debugging: output oi
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision f020ce90 (ceph): ReplicatedPG:: remove_snap_mapped_object already removes the object
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 643b6a50 (ceph): ReplicatedPG,osd_types: seperate require_rollback from ec_pool
It's handy to allow a pool to answer false to ec_pool() and
true to require_rollback() in order to allow a replicated...
Samuel Just
10:24 PM Revision d687ed96 (ceph): ReplicatedPG: take clone write lock as well in make_writeable
Otherwise, we might start backfilling the clone before the op is
complete.
Signed-off-by: Samuel Just <sam.just@inkt...
Samuel Just
10:24 PM Revision da4652c9 (ceph): ReplicatedPG: release backfill state on_global_recover not peer recover
There may now be multiple backfill peers.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 4c1338f4 (ceph): SimpleMessenger: init_local_connection whenever my_inst changes
This is necessary to correctly handle messages to self.
Signed-off-by: Samuel Just <sam.just@inktank.com>
Samuel Just
10:24 PM Revision 211fc4e1 (ceph): librados: add calls to expose required write alignment
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision e0b05085 (ceph): ReplicatedPG: reject unaligned writes on ec pools
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 541a7e27 (ceph): TestRados: send aligned appends on erasure pools
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 06ec9bd4 (ceph): ObjectStore: fix OP_COLL_ADD dump output
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:24 PM Revision 44f5d4de (ceph): ErasureCodeJerasure: fix alignement issues in encode/decode
Signed-off-by: Samuel Just <sam.just@inktank.com> Samuel Just
10:14 PM Revision 093128a8 (ceph): Merge pull request #1139 from ceph/wip-agent
osd: basic cache tier agent
Reviewed-by: Samuel Just <sam.just@inktank.com>
Sage Weil
10:04 PM Revision 749bf40f (ceph): iozone: kill empty suite
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:18 PM Revision 66ffaa65 (ceph): kcephfs, krbd: do not thrash primary-affinity
Kenrel doesn't yet support it. See #7455
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
09:16 PM Revision 3d0ce693 (ceph): thrashosds: allow primary-affinity thrashing to be disabled
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision bd8fcd25 (ceph): osd: improve whiteout debug prints
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision 79976466 (ceph): ReplicatedBackend: print char ack_type as int
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
09:07 PM Revision 63f5a799 (ceph): osd/ReplicatedPG: make agent skip blocked obcs
Among other things, this can interfere with an in-flight copy-from and
corrupt the pg stats.
Signed-off-by: Sage Wei...
Sage Weil
07:09 PM Revision 62532fb0 (ceph): Merge pull request #1254 from ceph/wip-barrier
libcephfs: disable barriers for now Sage Weil
07:07 PM Revision a4ca4a73 (ceph): Merge remote-tracking branch 'gh/wip-7212-sage-b'
We should carefully backport some or all of this.
Backport: emperor, dumpling
Reviewed-by: Joao Eduardo Luis <joao.l...
Sage Weil
06:27 PM Revision a71d829e (ceph): client: disable barrier support
The boost interval_set class is not available on centos6/rhel6. Until that
dependency is sorted out, fix the build.
...
Sage Weil
06:23 PM Revision 747002c6 (ceph): client: fix barrier interval
(start, end) not (start, length)
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
06:16 PM Revision d7457f73 (ceph): client/barrier: drop unused active_commit_interval
Signed-off-by: Sage Weil <sage@inktank.com> Sage Weil
06:15 PM Revision ce643e00 (ceph): client: don't populate Client::barriers from read accesses
If the entry doesn't exist, no need to create it.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
04:28 PM Feature #7459 (Closed): ceph-rest-api: sysvinit and upstart scripts
enumerate daemon by directory in /var/lib/ceph/rest, using the same structure as the osd, mon, and other daemons.
...
Sage Weil
03:44 PM Bug #7458: osd: stray pg ref on shutdown
Sage Weil
03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
... Sage Weil
03:34 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
http://pulpito.ceph.com/teuthology-2014-02-14_23:00:16-rados-master-testing-basic-plana/84322
http://pulpito.ceph.co...
Sage Weil
02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
Sage Weil
02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
Sage Weil
02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
Sage Weil
02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
Sage Weil
02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
Sage Weil
02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
Sage Weil
01:39 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
Simplest thing seems to be to unconditionally send temp object ops to the backfill targets. Then the final completio... Sage Weil
01:37 PM CephFS Bug #7422 (In Progress): client/barrier.h uses boost's interval set library, which is not availab...
The barrier code has been disabled to fix the build. Matt said he will follow up. http://marc.info/?l=ceph-devel&m=... Sage Weil
01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
Sage Weil
01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
Sage Weil
01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
reopened #7385 Sage Weil
01:33 PM rbd Bug #7385 (Pending Backport): Objectcacher setting max object counts too low
This now leaks memory.. presumably stray Object's the cache that never get cleaned up.
Let's just increase the obj...
Sage Weil
01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
Sage Weil
01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
when this is complete, be sure to fix ceph-qa-suite.git Sage Weil
11:08 AM Bug #7212 (Pending Backport): monitor fails to start
Sage Weil
10:34 AM rgw Bug #7450: "radosgw-admin key create" ignores specified access key when subuser specified
The problem is in rgw_user.h:void set_subuser(..) sets 'gen_access = true;'. I can't understand why it's doing that, ... Robin Johnson
08:44 AM CephFS Bug #7424 (Rejected): Cannot read from zero-length file
Pavel Veretennikov wrote:
> * Strange that it worked without permission. Where had it stored the data?
It was onl...
Sage Weil
07:32 AM CephFS Bug #7424: Cannot read from zero-length file
* Strange that it worked without permission. Where had it stored the data? Pavel Veretennikov
07:31 AM CephFS Bug #7424: Cannot read from zero-length file
Yes, the problem resolved after I gave client access to default data pool
rwx pool=data
Strange that it work...
Pavel Veretennikov
06:52 AM CephFS Bug #7424: Cannot read from zero-length file
does client have permission permission to access the data pool? try using admin's keyring to mount the fs. Zheng Yan
01:19 AM CephFS Bug #7424: Cannot read from zero-length file
Ubuntu doesn't use SELinux as I know. /selinux lib is empty, only one related selinux package is present - libselinux... Pavel Veretennikov
06:25 AM Revision a1dbc9ce (ceph): qa/workunits/suites/pjd: use test suite with acl tweak
Test 45 in xacl/00.t fails on ext4 and cephfs. Just disable it.
Everything else passes.
Signed-off-by: Sage Weil <s...
Sage Weil
05:53 AM Revision c1f42770 (ceph): radosgw-admin: fix object policy read op
Fixes: #7083
This was broken when we fixed #6940. We use the same function to both
read the bucket policy and the obj...
Yehuda Sadeh
05:43 AM devops Feature #7454 (Resolved): ceph-disk: support osd removal / ceph-disk remove
There should be a *ceph-disk remove* to cleanup an OSD and the associated device / directory. This is not something a... Loïc Dachary
05:35 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
If you supply rgw_keystone_admin_user and rgw_keystone_admin_password ... instead of supplying "rgw_keystone_admin_to... Mouad Ben
05:23 AM Revision 623748e5 (ceph): mds: bump the protocol version
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
04:53 AM Revision 2a19a1be (ceph): osd/ReplicatedPG: allow is_degraded_object() to be called outside of ba...
The agent does this.
Signed-off-by: Sage Weil <sage@inktank.com>
Sage Weil
01:37 AM Revision e5457dfb (ceph): mds: open sessions for rejoin imported caps
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 6e013cd6 (ceph): mds: properly set COMPLETE flag when merging dirfrags
don't keep the COMPLETE flag when merging dirfrags during journal
replay, because it's inconvenience to check if the ...
Yan, Zheng
01:37 AM Revision 0eb311d3 (ceph): mds: fix open undef dirfrags
Undef inode may contain a undef dirfrag (*). When undef inode is
opened, we should force fragment the undef dirfrag (...
Yan, Zheng
01:37 AM Revision 305d16f3 (ceph): mds: handle frag mismatch for cache rejoin weak
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 80799395 (ceph): mds: handle frag mismatch for cache expire
When sending MDSFragmentNotify to peers, also replicate the new
dirfrags. This guarantees peers get new replica nonce...
Yan, Zheng
01:37 AM Revision 9a47913d (ceph): mds: improve freeze tree deadlock detection
Current code uses the start time of freezing tree to detect deadlock.
It is better to check how long the auth pin cou...
Yan, Zheng
01:37 AM Revision 9df6861b (ceph): mds: freeze dir deadlock detection
freezing dir and freezing tree have the same deadlock cases.
This patch adds freeze dir deadlock detection, which imi...
Yan, Zheng
01:37 AM Revision 3dc51dea (ceph): mds: minor cleanup for EFragment and MMDSFragmentNotify
pass dirfrag_t to their constructors, instead of passing inode_t
and frag_t separately.
Signed-off-by: Yan, Zheng <z...
Yan, Zheng
01:37 AM Revision 98105b24 (ceph): mds: preserve dir_auth when spliting/merging dirfrags
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision ee7ac6fc (ceph): mds: allow fragmenting subtree dirfrags
We can't wait until object becomes auth pinnable after freezing a
dirfrag/subtree, because it can cause deadlock. Cur...
Yan, Zheng
01:37 AM Revision f3666ede (ceph): mds: journal dirfragtree change
Introduce new flag DIRTYDFT to CDir and EMetaBlob::dirlump, the new
flag indicates the dirfrag is newly fragmented an...
Yan, Zheng
01:37 AM Revision 4d5ceba5 (ceph): mds: fix 'force dirfrags' during journal replay
For rename operation, null dentry is first replayed, it detaches
the inode from the FS hierarchy. Then primary dentry...
Yan, Zheng
01:37 AM Revision 5b1de69a (ceph): mds: force fragment subtree bounds when replaying ESubtreeMap
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> Yan, Zheng
01:37 AM Revision 3b90c785 (ceph): mds: fixes for thrash fragment
This patch contains 3 changes:
- limit the number of in progress fragmenting processes.
- reduce the probability of s...
Yan, Zheng
01:37 AM Revision cc77ef2d (ceph): mds: fix scattered wrlock rejoin
If unstable scatter lock is encountered when handling weak cache
rejoin, don't remove the recovering MDS from the sca...
Yan, Zheng
01:37 AM Revision 22535340 (ceph): mds: avoid race between cache expire and pushing replicas
MDentryLink and MMDSFragmentNotify push replica inode/dirfrags
to other MDS. They both are racy because, when the tar...
Yan, Zheng
01:37 AM Revision 74ef370b (ceph): mds: fix negative rstat assertion
when gathering rstat for directory inode that is fragmented to
several dirfrags, inode's rstat may temporarily become...
Yan, Zheng
01:37 AM Revision 21d209d0 (ceph): mds: wake up dentry waiters when handling cache rejoin ack
Cache rejoin ack message may fragment dirfrag, we should set the
'replay' parameter of adjust_dir_fragments() to fals...
Yan, Zheng
01:37 AM Revision 9e8dbf9e (ceph): mds: remove failed MDS from export bystanders list
make sure the importer does not wait for MExportDirNotifyAck from
the failed MDS
Signed-off-by: Yan, Zheng <zheng.z....
Yan, Zheng
01:37 AM Revision c54b3cea (ceph): mds: fix slave rename rollback
use rollback bufferlist to decide if the inode is being exported.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Yan, Zheng
01:37 AM Revision d0df8413 (ceph): mds: allow acquiring wrlock and remote wrlock at the same time
Rename may move file from one dirfrag to another dirfrag of the same
directory inode. If two dirfrags belong to diffe...
Yan, Zheng
01:37 AM Revision 3fb408ee (ceph): mds: introduce nonlocking auth pin
Add a parameter to Locker::acquire_locks() to enabled nonblocking
auth pin. If nonblocking mode is enabled and an obj...
Yan, Zheng
01:37 AM Revision 3154ee84 (ceph): mds: acquire locks required by exporting dir
Start internal MDS request to acquire locks required by exporting dir.
It's more reliable than using Locker::rdlock_t...
Yan, Zheng
01:37 AM Revision 5faa3134 (ceph): mds: acquire scatter locks when exporting dir
If auth MDS of the subtree root inode is neither the exporter MDS
nor the importer MDS and it gathers subtree root's ...
Yan, Zheng
01:37 AM Revision 2c909cda (ceph): mds: revert commit 15a5d37a
commit 15a5d37a (mds: fix race between scatter gather and dirfrag export)
is incomplete, it doesn't handles the race ...
Yan, Zheng
01:37 AM Revision 1ff77666 (ceph): mds: introduce fine-grained discover dirfrag wait queue
Current discover dirfrag code only allows discover one dirfrag at
a time. This can cause deadlock if there are direct...
Yan, Zheng
01:37 AM Revision b88034ee (ceph): mds: use discover_path to open remote inode
MDCache::discover_ino() doesn't work well for directories that are
fragmented to several dirfrags. Because MDCache::h...
Yan, Zheng
01:37 AM Revision ffe71516 (ceph): mds: handle frag mismatch for discover
When handle discover dirfrag message, choose an approximate frag if
the requested dirfrag doesn't exist. When handlin...
Yan, Zheng
01:37 AM Revision e0e25658 (ceph): mds: fix MDCache::get_force_dirfrag_bound_set()
don't force dir fragments according to the subtree bounds in resolve
message. The resolve message was not sent by the...
Yan, Zheng
01:37 AM Revision 1080fa45 (ceph): mds: fix MDCache::adjust_subtree_after_rename()
process subtree dirfrags first, then process nested dirfrags. because
the code that processes nested dirfrags treats ...
Yan, Zheng
01:37 AM Revision ee0ab2b7 (ceph): mds: fix CInode::get_dirfrags_under()
make the function work when opened dirfrags don't match the
dirfragtree.
Signed-off-by: Yan, Zheng <zheng.z.yan@inte...
Yan, Zheng
 

Also available in: Atom