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> - 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> - 10:59 PM Revision 8b77995f (ceph): Merge pull request #1494 from dachary/wip-gitmodule-mirrors
- build: add gf-complete/jerasure to gitmodule_mirrors
- 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... - 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... - 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... - 10:19 PM Revision 6252d28d (ceph): distros: add wheezy
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:19 PM Revision 0bfc365d (ceph): distros: add rhel 6.4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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
- 10:01 PM Revision 5679ae2a (ceph): Merge branch 'firefly'
- 10:00 PM Revision 8e748c0c (ceph): ceph.conf: tolerate 500ms of clock drift (up from 250)
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 09:28 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- 09:04 PM Revision 4221e0dd (ceph): build: add gf-complete/jerasure to gitmodule_mirrors
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:03 PM Revision a27ead67 (ceph): distros: add 14.04 to supported list
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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...
- 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. ...
- 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:...
- 08:55 PM Revision 8d4c4676 (ceph): distros: test rhel/centos 6.5 instead of 6.4
- 08:44 PM Revision 25d04fba (ceph): osd: dump priority queue state on dequeue at level 30
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 08:22 PM Revision 4a3464ce (ceph): common/PrioritizedQueue: include first item's cost in dump
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 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... - 08:16 PM Revision de576d5b (ceph): common/PrioritizedQueue: constify a few things
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:09 PM Revision f1e3bc9a (ceph): doc/dev/cache-pool: describe the tiering agent
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:07 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
- 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... - 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 ... - 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... - 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> - 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> - 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> - 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... - 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... - 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>
- 03:57 PM Bug #7776: client lockdep crash
- ubuntu@teuthology:/a/teuthology-2014-03-18_02:30:01-rados-firefly-distro-basic-plana/137408
- 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...
- 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... - 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> - 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... - 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> - 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.
- 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...
- 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...
- 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. - 01:54 PM Revision d7f3eb34 (ceph): knfs: make it a list
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:41 PM Bug #6633: osd: pgls vs osd restart/peering race misses objects
- backported to dumpling.
- 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...
- 12:34 PM Bug #7733: start_new_interval: always notify if !primary
- 12:30 PM Bug #7728: osd/ReplicatedPG.cc: 4999: FAILED assert(got)
- 12:30 PM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 11:40 AM Bug #7755: auth_log selection depends on the primary identity and can cause a loop
- 12:05 PM Feature #7767 (Fix Under Review): messenger:buffer reads
- 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...
- 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...
- 10:49 AM Bug #6806 (Pending Backport): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 09:42 AM Bug #6806 (Fix Under Review): mon: audit cmd_getval() calls to make sure they handle failures cor...
- 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... - 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.
- 01:45 AM Bug #7756: cannot get through configuration when configure.ac check xfs.h
- invalidate this bug report
- 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
- 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...
- 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... - 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... - 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 :...
- 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 :... - 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> - 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...
- 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....- 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 ...
- 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... - 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...- 05:25 AM CephFS Feature #7763 (Resolved): journal-tool: import
- Given a binary journal dump, insert it back into the metadata pool.
- 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...
- 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...
- 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.- 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.- 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.- 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-... - 03:56 AM Revision fb7b1f87 (ceph): Merge remote-tracking branch 'gh/firefly'
- 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> - 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> - 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...
- 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> - 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> - 01:26 AM Revision 29976607 (ceph): knfs: async export
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:08 AM Revision 1822a1cc (ceph): Merge pull request #229 from dachary/wip-ec-pool
- ceph_manager: update ec_pool creation parameters
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... - 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> - 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... - 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... - 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... - 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... - 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> - 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... - 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... - 11:23 PM Revision eac224a4 (ceph): doc: update the erasure-code dev documentation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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 ... - 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... - 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... - 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 ... - 11:19 PM Revision 1048763e (ceph): Merge remote-tracking branch 'gh/firefly'
- 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... - 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> - 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> - 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> - 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> - 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> - 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... - 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? - 08:52 PM Feature #7599 (Resolved): erasure-code : upgrade to jerasure-2
- 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...
- 07:15 PM Revision f0944003 (ceph): Add file to store mirror location of module's.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 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> - 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> - 06:42 PM Revision 7f177b3a (ceph): Merge pull request #226 from ceph/wip-7714
- prevent undefined values in finally block
- 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> - 04:33 PM Feature #7662 (Resolved): add a "ec profiles" map to OSDMap
- 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
- 04:22 PM Bug #7736 (Pending Backport): mon: can expose stale state
- 03:29 PM Bug #7736: mon: can expose stale state
- 04:45 AM Bug #7736: mon: can expose stale state
- 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... - 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... - 04:19 PM Revision 98e27d7b (ceph): Fix max_job_time timeout
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 04:12 PM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 10:48 AM Bug #7748 (Resolved): rados bench timeouts: reset timeout if recovery rate is non-zero
- 04:04 PM Bug #7738 (Pending Backport): osd: journal crash on startup on wheezy
- 04:04 PM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- 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...
- 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... - 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... - 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> - 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":... - 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... - 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 ... - 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... - 03:43 PM Bug #7713 (Duplicate): "Error: finished tid 3 when last_acked_tid was 4" in upgrade:dumpling-x:pa...
- 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.
- 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
- 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... - 03:37 PM rgw Bug #7741 (Resolved): sync.py: not enough arguments for format string
- commit:5e7a98911e6a6db525d65981034d28065a045e47
- 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... - 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... - 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... - 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> - 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> - 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 ... - 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... - 02:49 PM Revision 57c8fd96 (ceph): prevent undefined values in finally block
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 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> - 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... - 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... - 02:42 PM Revision 8f542dba (ceph): schedule_suite.sh: turn up journal log too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 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-... - 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> - 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... - 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...
- 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... - 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...
- 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 ... - 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.
- 01:00 PM rgw Bug #7749 (Resolved): radosgw-agent: worker.DataWorker.wait_for_object() should bail on requests....
- Fixed in teuthology commit:ef2edcd3a96a2118d793b7a102688f60fa100f52
- 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
- 11:23 AM rgw Bug #7749 (Fix Under Review): radosgw-agent: worker.DataWorker.wait_for_object() should bail on r...
- 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
- 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:...
- 10:40 AM Bug #7712 (Resolved): osd: ENOENT following copy-from
- 10:09 AM Bug #7715 (Resolved): Errors in cluster log "[ERR] mon.0" in in upgrade:dumpling-x:parallel-fire...
- whitelisted this
- 10:03 AM Feature #7717: Per CRUSH bucket used/available space
- 09:22 AM Fix #6780 (Closed): monitor errors when checking for quorum status
- 09:13 AM Fix #6780: monitor errors when checking for quorum status
- can no longer reproduce this on firefly. any objections on closing?
- 08:48 AM Revision d4d6ff07 (ceph): mon,osd,erasure-code: update copyright notices
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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 ... - 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... - 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@... - 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> - 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... - 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... - 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> - 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... - 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... - 08:48 AM Revision 3bc607ae (ceph): mon: crush_ruleset_create_erasure indent
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:48 AM Revision 9850ab27 (ceph): mon: crush_ruleset_create_erasure s/_map//
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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 ... - 08:48 AM Revision 32e122bd (ceph): mon: add pool name to prepare_pool_crush_ruleset
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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 ... - 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... - 08:19 AM Bug #7611 (Resolved): All mon nodes crash when running "ceph tell osd.X" and using the "version" ...
- 08:00 AM Bug #7611 (Fix Under Review): All mon nodes crash when running "ceph tell osd.X" and using the "v...
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> - 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> - 05:32 PM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 31a667918069ac72c70080dcacd6ff3b6d58f07b
- 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> - 03:26 PM Feature #7662 (In Progress): add a "ec profiles" map to OSDMap
- 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... - 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 ... - 12:11 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 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...
- 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... - 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...
- 09:36 AM Bug #7719 (Resolved): failed to become clean
- 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> - 04:42 AM Revision 1ae33147 (ceph): client: force getattr when inline data is missing
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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... - 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...
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> - 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> - 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...
- 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> - 07:39 PM CephFS Bug #7684 (Resolved): failed cfuse_workunit_kernel_untar_build.yaml test
- 06:12 PM Revision 2c875593 (ceph): multimds: fix misc -> fs/misc paths
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:39 PM Bug #7740 (Resolved): resurrected pgs have lb=hobject_t::min(), but we respond to queries on dele...
- 05:07 PM Bug #7736 (Fix Under Review): mon: can expose stale state
- 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 ...
- 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:... - 04:55 PM Revision 9e218402 (ceph): mds: include inline data in lock messages
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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... - 04:18 PM Revision 75971726 (ceph): upgrade/dumpling-x/stress-split: tolerate legacy crush tunables
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:17 PM rgw Bug #7730 (Rejected): Content-length should not required for initiate multipart upload
- 03:30 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 03:30 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 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... - 10:10 AM Bug #7738 (Resolved): osd: journal crash on startup on wheezy
- ubuntu@teuthology:/a/sage-wheezy/130813...
- 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...
- 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... - 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> - 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...
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... - 10:53 PM Revision 5322ecb2 (ceph): Merge branch 'master' of https://github.com/ceph/ceph
- 10:52 PM Revision ef1d7c91 (ceph): rados.py: Fixed docstring syntax warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 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> - 10:46 PM Revision 02b746d4 (ceph): doc: Fixed release notes syntax warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:46 PM Revision 752380dc (ceph): added print task
- 10:45 PM Revision 9cd67bb2 (ceph): doc: Fixed hyperlink.
- Fixes: #7558
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:26 PM Revision c6214f86 (ceph): Merge pull request #1463 from ceph/wip-7698
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 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> - 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>
- 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... - 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... - 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... - 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... - 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... - 08:26 PM Bug #7735: osd: priorityqueue debug dump crashes
- wip-pq
- 08:21 PM Bug #7735 (Resolved): osd: priorityqueue debug dump crashes
- discovered when doing backfill testing with wip-pq:...
- 08:23 PM Revision ab91b808 (ceph): mon/OSDMonitor: fix fall-thru case
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:21 PM Revision 0e0a9dbf (ceph): Merge remote-tracking branch 'gh/firefly'
- 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.
... - 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... - 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... - 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... - 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> - 08:11 PM Revision f2ac06bf (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140312'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 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... - 08:04 PM Revision 74ad3e30 (ceph): Merge remote-tracking branch 'gh/wip-coverity-20140409'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:42 PM Revision 5873b0f0 (ceph): Merge remote-tracking branch 'gh/wip-da-SCA-firefly-20140304'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 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:... - 06:28 PM Revision bb755167 (ceph): Merge pull request #1459 from ceph/wip-7696
- Wip 7696
Reviewed-by: Sage Weil <sage@inktank.com> - 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>
- 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> - 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> - 06:03 PM Bug #7732: stuck recovering with unfound -- build_might_have_unfound bug
- 05:58 PM Bug #7732 (Resolved): stuck recovering with unfound -- build_might_have_unfound bug
- 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... - 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> - 05:59 PM Bug #7733 (Resolved): start_new_interval: always notify if !primary
- 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... - 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> - 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>
- 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... - 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... - 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
... - 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...
- 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...
- 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... - 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... - 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... - 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 ...
- 04:36 PM Bug #7659 (In Progress): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing()....
- 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... - 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...
- 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.
- 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> - 03:30 PM Revision 5676d6e5 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:29 PM Revision ceac36b2 (ceph): doc/release-notes: 0.78 draft nodes; firefly draft notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:21 PM Revision 2e487d8a (ceph): knfs: test v3 and v4
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 03:10 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- 01:28 PM Bug #7720 (Duplicate): osd/ReplicatedPG.cc: 4991: FAILED assert(got)
- ...
- 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...- 02:47 PM Bug #7718: osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- 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.
- 12:58 PM Bug #7718 (Resolved): osd/PG.cc: 6062: FAILED assert(pg->want_acting.size())
- ...
- 02:37 PM Feature #7698: Add EC handling to ceph_filestore_dump
- Ready to go into either master or firefly branches.
- 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... - 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...
- 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/ - 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 ...
- 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...
- 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 ...
- 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...
- 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 ...
- 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... - 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...
- 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...
- 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:... - 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---...
- 11:51 AM Bug #7216 (Can't reproduce): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 09:43 AM Bug #7216 (New): ASSERT AuthMonitor::update_from_paxos on 0.72.2
- 11:35 AM Bug #7709 (Resolved): osd: RWORDERED does not order reads ack vs write commit
- 11:28 AM Bug #7696 (Resolved): osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 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---...
- 11:05 AM Bug #7692 (Resolved): mon: monitor fails to form quorum
- 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):...
- 10:51 AM Bug #7489 (Resolved): `ceph-mon` is silent after non-zero exit status
- 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, ...
- 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...
- 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 ...
- 10:09 AM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- 09:59 AM rbd Bug #7465 (Can't reproduce): krbd: size of disk read or set incorrectly
- 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...
- 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... - 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...
- 09:49 AM rgw Bug #7703 (Resolved): rgw: fail to copy object > 512k between buckets
- d0d21fae483cfaf5556b18b2f0e113c7d418e90c Landed to Firefly
- 09:44 AM Bug #7626: After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:44 AM Bug #7626 (New): After updating ceph from 0.75 to 0.77 one of the three monitors can't start
- 09:42 AM Bug #7497 (Can't reproduce): timeout waiting to go clean
- 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?
- 09:21 AM Bug #7710 (Fix Under Review): Multiple rados bench instance will overwrite the metadata object
- 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
- 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...
- 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... - 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 ... - 04:37 AM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- 02:12 AM Revision b125c95f (ceph): Merge pull request #18 from ceph/wip-knfs-fsstress
- knfs: add fsstress and kernel build
- 01:34 AM Revision 4773a277 (ceph): knfs: add fsstress and kernel build
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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> - 12:42 AM Revision e1694b4c (ceph): knfs: restructure a bit
- Separate cluster buildup from tasks.
Signed-off-by: Sage Weil <sage@inktank.com> - 12:39 AM Revision 7b0eda03 (ceph): nfs -> knfs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:38 AM Revision c5b557ee (ceph): qa/workunits: misc -> fs/misc
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:36 AM Revision adca6464 (ceph): workunits/misc -> fs/misc
- Signed-off-by: Sage Weil <sage@inktank.com>
03/13/2014
- 11:44 PM Revision 8c8b3e97 (ceph): PGLog: remove unused variable
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 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 ... - 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> - 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... - 11:24 PM Revision c452de17 (ceph): Merge pull request #1452 from ceph/wip-7706
- Wip 7706
Reviewed-by: Greg Farnum <greg@inktank.com> - 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> - 10:41 PM Bug #7709 (Fix Under Review): osd: RWORDERED does not order reads ack vs write commit
- 10:02 PM Bug #7709: osd: RWORDERED does not order reads ack vs write commit
- 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... - 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.... - 10:15 PM Revision 5ec49360 (ceph): Merge remote-tracking branch 'gh/firefly'
- 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... - 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... - 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... - 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... - 09:49 PM Revision dd946e0a (ceph): MOSDOp: include reassert_version in print
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:10 PM Bug #7498 (Resolved): stuck in recovery
- 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.
- 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... - 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... - 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> - 09:04 PM devops Bug #7641 (Resolved): packaging: ceph upgrade from cuttlefish to emperor is incomplete
- 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... - 09:01 PM CephFS Bug #7708 (Resolved): mds: null deref in issue_caps
- ...
- 08:28 PM CephFS Bug #7684: failed cfuse_workunit_kernel_untar_build.yaml test
- ...
- 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/... - 08:15 PM Revision d72335fe (ceph): Merge remote-tracking branch 'gh/firefly'
- 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... - 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... - 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.
... - 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... - 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... - 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... - 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... - 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... - 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... - 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".
... - 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 ... - 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)...
- 04:28 PM Bug #7706 (Pending Backport): osd: PrioritizedQueue can starve
- 01:58 PM Bug #7706 (Resolved): osd: PrioritizedQueue can starve
- starvation caused by pq max token limit
- 04:27 PM Bug #7704 (Resolved): "[ERR] scrub mismatch" in upgrade:dumpling-x:parallel-firefly---basic-pla...
- 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...
- 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---...
- 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---...
- 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... - 04:10 PM Bug #7635 (Duplicate): failed to recover before timeout expired
- 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> - 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> - 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
- 03:27 PM CephFS Bug #7565 (Resolved): Failed assert in check_rstats
- 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... - 02:59 PM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- 11:39 AM Bug #7705: ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong version")
- wip-7705
- 10:01 AM Bug #7705 (Resolved): ./test/osd/RadosModel.h: 837: FAILED assert(0 == "racing read got wrong ver...
- ...
- 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 ... - 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... - 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...
- 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...
- 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...
- 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... - 11:20 AM rgw Bug #7703 (Fix Under Review): rgw: fail to copy object > 512k between buckets
- 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... - 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... - 10:00 AM rgw Bug #7702 (Need More Info): osd thrashing + rgw = timeouts
- 09:41 AM Bug #7699 (Duplicate): "failed: thrashosds" in upgrade:dumpling-x:stress-split-firefly---basic-pl...
- 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
- 09:38 AM Bug #7259 (Resolved): ceph mon crash in master branch
- 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... - 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".... - 06:49 AM Revision fb4ca940 (ceph): mailmap: Danny Al-Gaaf name normalization
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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... - 04:32 AM Revision fb8ff445 (ceph): doc/release-notes: note that WATCH can get ENOENT now
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 01:33 AM Revision fce63aa8 (ceph): Merge pull request #1440 from ceph/wip-7649
- Wip 7649
Reviewed-by: Sage Weil <sage@inktank.com> - 12:09 AM Revision b5d2df4a (ceph): Merge pull request #1441 from ceph/wip-7671
- Wip 7671
Reviewed-by: Sage Weil <sage@inktank.com>
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>
- 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>
- 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> - 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> - 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... - 09:49 PM Revision 7fb5e146 (ceph): upgrade/dumpling-x: full librados tests after full upgrade
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 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... - 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.
- 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...
- 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... - 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 ... - 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... - 07:05 PM Revision f6b3a0b7 (ceph): Merge pull request #1423 from fractalcat/respect-python-env
- Update Python hashbang to respect environment
- 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> - 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> - 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... - 06:37 PM Bug #7696: osd/ECUtil.cc: 23: FAILED assert(i->second.length() == total_chunk_size)
- 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 ... - 06:32 PM Bug #7649 (Resolved): ec ceph_test_rados stuck recovering
- 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... - 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> - 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> - 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... - 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 ... - 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> - 05:32 PM Bug #7626 (Need More Info): After updating ceph from 0.75 to 0.77 one of the three monitors can't...
- 05:28 PM Revision dc00661d (ceph): osd_types: print lb if incomplete even if empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 05:09 PM Bug #7671 (Resolved): watch should return ENOENT if the object does not exist
- 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> - 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...
- 03:57 PM Revision 1ccabd80 (ceph): lock: allow -a with --brief
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:45 PM Bug #7682 (Resolved): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first ...
- 02:12 PM Bug #7682: osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->first == repop->v)
- 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.
...- 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...- 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...
- 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 ...
- 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... - 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... - 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... - 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 ...
- 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... - 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...
- 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... - 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...
- 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... - 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... - 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...
- 11:57 AM Bug #7695 (Resolved): ceph: ./admin/build-doc check for required tools fails for non debian envs
- 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...
- 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.
- 11:02 AM Feature #7698 (Resolved): Add EC handling to ceph_filestore_dump
- 10:46 AM Bug #7681 (Resolved): osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 10:45 AM Bug #7256 (Duplicate): ceph osd crashed at ReplicatedPG::trim_object on next
- 10:44 AM Bug #7650 (Resolved): rados bench seq tests not performed at correct IO sizes
- 10:06 AM Feature #7662: add a "ec profiles" map to OSDMap
- s/properties/ec profile/g
- 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... - 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... - 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:...
- 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> - 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> - 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> - 04:33 AM Revision 32fdca6d (ceph): Merge pull request #1411 from ceph/wip-7076-dumpling
- dumpling backport of watchers check for rbd_remove()
- 04:30 AM Revision e3f8dd03 (ceph): Merge pull request #1419 from ceph/wip-doc-prereq
- doc: update build prerequisites
- 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> - 04:25 AM Revision bd2defb9 (ceph): Merge pull request #1409 from enovance/wip-brag
- ceph-brag enhancements
Reviewed-by: Sage Weil <sage@inktank.com> - 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... - 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... - 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... - 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> - 02:20 AM Revision b70db7e7 (ceph): Merge remote-tracking branch 'gh/firefly'
- 02:16 AM Revision a18cd6dd (ceph): Merge remote-tracking branch 'gh/firefly'
- 02:16 AM Revision cfbbcf7c (ceph): upgrade/dumpling-x/stress-split: use dumpling workunits
- Signed-off-by: Sage Weil <sage@inktank.com>
- 02:04 AM Revision bfbfcf84 (ceph): Merge pull request #1422 from salehe/docfix-1
- rados.py: fix typo in Ioctx::read() docstring
- 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: ... - 01:48 AM Revision e5b65b45 (ceph): Merge pull request #222 from ceph/wip-trusty
- Handle newer btrfstools.
- 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> - 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 ... - 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: ... - 01:13 AM CephFS Bug #1318: directories disappear across multiple rsyncs
- please check if there was file recovery involved (MDCache::do_file_recover )
- 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> - 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> - 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...
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> - 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> - 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> - 11:02 PM Revision 64a6b26b (ceph): doc/release-notes: fill in some firefly history
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:00 PM Revision 1a9f6c32 (ceph): Merge pull request #17 from ceph/wip-final_load_fix
- fixed final_load problem
- 10:40 PM Revision 72094a85 (ceph): fixed final_load problem
- 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... - 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...
- 07:24 PM Bug #7689: librados: ENOENT on ioctx create
- downgrading thsi weirdness until i see it again
- 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.
- 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...
- 07:23 PM rgw Bug #6889 (Pending Backport): rgw: usage log: don't log system user operations
- 09:31 AM rgw Bug #6889 (Fix Under Review): rgw: usage log: don't log system user operations
- 07:15 PM Revision 24774a81 (ceph): osd/ReplicatedPG: fix typo
- This is the object count, not the dirty object count. Broken by
00bf3b56743830a4a9c5d6765946a4e68f530c57.
Reported-... - 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... - 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> - 06:22 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:14 PM rgw Bug #7687 (Fix Under Review): rgw: bucket creation time is not set
- 06:09 PM rgw Bug #7687: rgw: bucket creation time is not set
- actually it's set, but then it's overwritten.
- 03:09 PM rgw Bug #7687 (Resolved): rgw: bucket creation time is not set
- 06:20 PM Bug #7654 (Duplicate): "AssertionError: failed to recover before timeout expired" in teuthology-2...
- 7635
- 06:19 PM Bug #7631 (Resolved): command 'dump_ops_in_flight' not found
- fixed by teuthology commit:57259b54beb746b31b70bb3a92de18d604002b0a
- 06:15 PM Bug #7631 (In Progress): command 'dump_ops_in_flight' not found
- 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> - 06:10 PM Bug #7406 (Duplicate): Seg fault in find_object_context()in recent master rados run
- 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... - 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> - 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> - 05:17 PM Bug #7682 (In Progress): osd/ReplicatedPG.cc: 6268: FAILED assert(waiting_for_ondisk.begin()->fir...
- 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...
- 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> - 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> - 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> - 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> - 04:41 PM Revision a9a826ad (ceph): Merge pull request #220 from ceph/wip-print
- Add print task.
- 04:41 PM Bug #7688 (Won't Fix): warn at fs/btrfs/extent-tree.c:5748 __btrfs_free_extent+0x9ce/0xa20
- ...
- 04:38 PM Bug #7663 (Resolved): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10.214.134....
- 01:01 PM Bug #7663 (Fix Under Review): 2014-03-08T20:39:23.812 INFO:teuthology.task.rados.rados.1.err:[10....
- 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> - 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 ...
- 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... - 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... - 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...
- 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...
- 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...
- 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... - 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... - 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... - 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... - 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 ...
- 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... - 04:05 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
- 01:03 PM Bug #7658 (Fix Under Review): PGLog: _merge_object_divergent_entries: fix the case where prior_ve...
- 04:05 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
- 01:04 PM Bug #7657 (Fix Under Review): PGLog: fix proc_replica_log divergent entry selection
- 03:15 PM rgw Bug #7676 (Fix Under Review): rgw: multi-part upload incompatible with EC backend
- 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 ... - 03:02 PM Bug #7679 (Resolved): mds: stuck on TMAP2OMAP check incorrectly
- 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 ...
- 12:04 PM Bug #7679: mds: stuck on TMAP2OMAP check incorrectly
- ...
- 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... - 03:00 PM Bug #7686 (Duplicate): osd spinning in agent_work
- 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...
- 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.
- 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... - 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... - 02:40 PM Bug #7681: osd/SnapMapper.cc: 270: FAILED assert(check(oid))
- 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...- 02:21 PM rgw Bug #7661 (Resolved): rgw: s3_multipart_upload.pl and s3_user_quota.pl tests fail
- 02:21 PM rgw Bug #7375 (Resolved): s3_user_quota.pl fails
- 09:07 AM rgw Bug #7375: s3_user_quota.pl fails
- 02:20 PM rgw Bug #7374 (Resolved): s3_multipart_upload.pl fails
- 09:07 AM rgw Bug #7374: s3_multipart_upload.pl fails
- 02:01 PM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
- 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... - 01:59 PM Bug #7673 (Duplicate): "reached maximum tries" in /teuthology-2014-03-09_03:00:01-rados-firefly-t...
- 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.
- 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...
- 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... - 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... - 01:37 PM Bug #7093 (Resolved): osd: peering can send messages prior to auth
- Backported to Emperor and Dumpling
- 01:35 PM Bug #7468 (Duplicate): "scrub stat mismatch" error in rbd-master-testing-basic-plana suite
- 01:31 PM Bug #7653 (Duplicate): "FAILED assert(!old_value.has_contents())" in rados-firefly-testing-basic-...
- 01:24 PM Bug #5823 (Can't reproduce): cpu load on cluster node is very high, client can't get data on pg ...
- 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
- 01:20 PM Bug #7448 (Duplicate): os/FileJournal.cc: FAILED assert(fd >= 0)
- 01:11 PM Bug #7545 (Duplicate): rados: notify was not recieved in ceph_test_rados_watch_notify with thrash...
- 01:10 PM Bug #7611 (In Progress): All mon nodes crash when running "ceph tell osd.X" and using the "versio...
- 11:43 AM Bug #7674 (Resolved): Cache pool configuration stalls
- 11:00 AM Bug #7674 (Fix Under Review): Cache pool configuration stalls
- 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 ...
- 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?
- 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... - 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
- 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?
- 10:27 AM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 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 ... - 10:18 AM Bug #7592 (Resolved): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7592 (Fix Under Review): hit_set_trim() removal races with backfill
- 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...
- 09:51 AM Linux kernel client Bug #2759: libceph: crush tree algorithm is not understood
- We should be testing CRUSH with multiple algorithms
- 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... - 09:44 AM Linux kernel client Bug #2224 (Rejected): Oops in __cfh_to_dentry
- 09:44 AM Linux kernel client Bug #5244 (Rejected): btrfs hang on tree lock, 3.9 kernel
- 09:37 AM rbd Bug #4045 (Resolved): snap unprotect on a snapshot that is already unprotected throws inappropria...
- e91fb910653a672560867d4a81aa30f9d5dc0af8
- 09:35 AM rbd Bug #7582 (Resolved): "FAIL: test_rbd.TestImage.test_remove_with_watcher" in upgrade:dumpling-x-f...
- 09:34 AM rbd Bug #7583 (Resolved): "librbd::ImageCtx: error finding header" in upgrade:dumpling-x-firefly---ba...
- 09:33 AM rbd Bug #7625 (Resolved): ceph_test_rados_api_tier: not found
- 09:32 AM rbd Bug #6577 (Can't reproduce): arm testing: rbd test segfaults at FAILED assert((bool)_front == (bo...
- 09:21 AM rgw Bug #7543 (Resolved): rgw: off-by-one bug in rgw_trim_whitespace()
- 09:18 AM rgw Bug #6913 (Duplicate): valgrind issues when running rgw tests
- 09:17 AM rgw Bug #6802 (Rejected): ARM: rgw_swift failure (internal server error, 500)
- 09:17 AM rgw Bug #6696 (Can't reproduce): Upgrade rgw failure in nightly tests. (/home/ubuntu/cephtest/s3-test...
- 09:15 AM rgw Bug #6765 (Rejected): ARM: RGW s3 tests fail.
- 09:13 AM rgw Feature #7589: rgw: configurable chunk size
- Josh - please review wip-7589
- 09:12 AM rgw Feature #7589 (Fix Under Review): rgw: configurable chunk size
- 09:10 AM devops Bug #6453: libapache2-mod-fastcgi Packages for Debian Squeeze have incorrect dependencies
- 09:08 AM rgw Bug #6911: rgw test failure on the arm set up
- this sounds like a 32 bit int (size_t?) overflow
- 09:07 AM rgw Bug #7524 (Duplicate): "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- 09:06 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
- the mon assert is a dup
- 08:32 AM Revision fa30eb5d (ceph): rados.py: fix typo in Ioctx::read() docstring
- Signed-off-by: Mohammad Salehe <salehe+dev@gmail.com>
- 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...
- 07:17 AM CephFS Bug #6599 (Resolved): client: invalid iterator dereference in Client::trim_caps
- 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?
- 07:00 AM CephFS Bug #2187 (Can't reproduce): pjd chown/00.t failed test 97
- 06:59 AM CephFS Bug #2740 (Resolved): mds: crash in Objecter when shutting down too early
- 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... - 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... - 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... - 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)
- 02:53 AM Revision fbd9c154 (ceph): osd: Remove unused checkpoint code
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 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... - 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...
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 ... - 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> - 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... - 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... - 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 ... - 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>
- 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> - 10:45 PM Revision 7ac98b2a (ceph): doc: Updated sign-off by to sign-off-by
- sign-off-by: John Wilkins <john.wilkins@inktank.com>
- 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... - 09:14 PM Revision 52a2d692 (ceph): doc: fix reST formatting in release-process
- Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
- 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... - 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> - 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... - 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> - 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... - 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... - 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... - 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... - 06:58 PM Revision 0f7d954b (ceph): doc: Updated pull request with suggested changes.
- signed-off by: John Wilkins <john.wilkins@inktank.com>
- 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" ... - 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... - 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... - 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 ... - 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... - 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 ... - 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...
- 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... - 05:08 PM devops Bug #7677: Troubleshoot ceph-setup-nightly Jenkins failures
- Alfredo - please review.
- 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/...
- 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... - 05:07 PM Revision 7e43823f (ceph): doc: Fixed typo.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 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 ... - 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... - 04:38 PM Bug #7575 (Resolved): osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races ...
- 135c27ec74be352416d06a9d0ad78e63cf477433
- 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... - 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 ...
- 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...
- 03:44 PM devops Cleanup #7675 (In Progress): clean up Gary Lowell's WIP branches
- 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
- 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... - 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...
- 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... - 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 ... - 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...
- 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.
- 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, ... - 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...
- 02:15 PM Bug #7674 (Resolved): Cache pool configuration stalls
- In testing the following cache pool configuration:...
- 02:09 PM Bug #7672: PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 01:32 PM Bug #7672 (Resolved): PG::choose_acting: run recoverable_predicate without CRUSH_ITEM_NONE
- 02:09 PM Bug #7671: watch should return ENOENT if the object does not exist
- 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.
- 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'
- 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...
- 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...
- 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...
- 10:23 AM Bug #7592 (In Progress): hit_set_trim() removal races with backfill
- 10:09 AM Bug #7651 (Resolved): "HEALTH_WARN mds a is laggy" timed-out after 900 sec in -upgrade:dumpling-x...
- 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... - 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...
- 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 ... - 09:32 AM devops Bug #7669 (New): obscure traceback when a partition of type TOBE_UUID can't be mounted
- Steps to reproduce:...
- 07:29 AM Revision 4d3c1a19 (ceph): Adds radosgw-agent small file sync test
- Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com>
- 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... - 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> - 07:29 AM Revision 8ba02bfc (ceph): radosgw-agent: add logging to radosgw-admin task tests
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 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>
- 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>
- 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>
- 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> - 07:29 AM Revision dcad92eb (ceph): radosgw-admin: check that data deletions work as well
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 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-... - 07:24 AM Revision 26266045 (ceph): erasure-code: LARGEST_VECTOR_WORDSIZE is always 16
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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> - 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> - 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> - 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.
... - 06:35 AM Revision f92d3a56 (ceph): rgw: add data sync test
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 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... - 06:12 AM Revision c84f72ba (ceph): Merge branch 'master' of https://github.com/enovance/ceph-brag into fir...
- 06:11 AM Revision 18506ad6 (ceph): Removed all regular expression parsing and used '-f json' instead
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 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... - 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>
- 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) - 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...
- 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...
- 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...
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... - 09:27 PM Revision 2cf09089 (ceph): upgrade/dumpling-x: fix order
- Make it match the filename.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:58 PM Bug #7666 (Duplicate): librados: lock cycle on shutdown
- ...
- 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... - 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... - 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
- 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... - 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> - 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> - 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'.... - 05:29 PM Revision a4dfbc88 (ceph): workunit: change timeout 1h -> 3h
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:28 PM Revision 55c23a1a (ceph): qa: add script for testing rados allocation hint
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 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> - 12:22 PM Bug #7655 (Resolved): osd/ReplicatedPG.cc: 9293: FAILED assert(latest->is_update())
- 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?
- 10:32 AM Bug #7602 (Resolved): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (subsys lo...
- 10:10 AM Bug #7602 (Fix Under Review): 'ceph --admin-daemon *.asok config show' doesn't include debug_* (s...
- 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... - 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...
- 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.... - 10:56 AM Bug #7188 (Resolved): Admin socket files are lost on log rotation calling initctl reload (ubuntu ...
- 10:54 AM Bug #7496 (Duplicate): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
- looks like #7575
- 10:51 AM Bug #7587 (Duplicate): Failure of LibRadosTwoPoolsPP.PromoteSnap
- I'm pretty sure this is due to teh object_t SnapContext map. #7634
- 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-...
- 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 ... - 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-... - 12:02 AM Revision d1a888e0 (ceph): swift/containerops.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
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>
- 11:30 PM Revision 2223a372 (ceph): radosgw/config-ref.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:26 PM Revision 0b9d8936 (ceph): Add missing space in error message
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:19 PM Revision 87618d45 (ceph): session_authentication.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 11:07 PM Revision 682c6958 (ceph): release-process.rst: fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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> - 10:31 PM Revision e6660194 (ceph): doc/dev/logs.rst; fix some typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:25 PM Revision bbd1c4ba (ceph): filestore-filesystem-compat.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:22 PM Revision ae123a6d (ceph): corpus.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:16 PM Revision cf9f017d (ceph): config.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 10:11 PM Revision 5aaecc72 (ceph): cephx_protocol.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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... - 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. ... - 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... - 08:16 PM Revision eb667673 (ceph): Pass timeout to _spawn_on_all_clients()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 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... - 02:18 PM Revision 4e01884e (ceph): Log correct action in CephManager.remove_pool()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 02:01 PM Revision 72c63f13 (ceph): Log timeout value
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 01:58 PM Revision b4205cae (ceph): Iterate more sensibly over processes
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:27 AM Revision 2cbb0a40 (ceph): architecture.rst: fix typos
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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> - 10:13 AM Revision a4cbb192 (ceph): rados/operations/control.rst: fix typo
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:27 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Logs lines for *plana166726-98*...
- 09:16 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Crashing thread *7f991c37a700*...
- 08:56 AM Bug #7588 (In Progress): OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyge...
- ...
- 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
- 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/... - 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... - 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... - 12:53 AM Revision e830f9ff (ceph): TestPGLog: check on last_update in run_test_case
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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>
- 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> - 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...
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> - 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 ... - 11:23 PM Revision db0c3782 (ceph): Merge remote-tracking branch 'gh/wip-7210' into firefly
- Reviewed-by: Sage Weil <sage@inktank.com>
- 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... - 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... - 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... - 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> - 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> - 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... - 09:56 PM Revision c8b34f19 (ceph): mon/PGMonitor: improve debugging on PGMap updates slightly
- Chasing #7652
Signed-off-by: Sage Weil <sage@inktank.com> - 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: #... - 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... - 09:14 PM Revision 204b3ac7 (ceph): Change default workunit timeout to 1h
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 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> - 08:06 PM Bug #7587 (In Progress): Failure of LibRadosTwoPoolsPP.PromoteSnap
- 08:04 PM Revision ec38bd3c (ceph): Use safe_while's action arg
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 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... - 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... - 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.
... - 07:36 PM Revision 7604a1b6 (ceph): Update safe_while users to reflect new defaults
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:33 PM Revision 8258c847 (ceph): Change safe_while defaults to 6s 10x no increment
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 07:03 PM Revision 081a5c4b (ceph): Look for ready() in the right place
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 06:33 PM Bug #7636 (Duplicate): [ FAILED ] LibRadosTwoPoolsPP.EvictSnap
- this is due to the SnapContext object_t map key bug, see #7634
- 05:39 PM Revision ad04075b (ceph): Merge pull request #218 from ceph/wip-radosbench-timeout
- Introduce a timeout to radosbench's join phase
- 05:36 PM Revision 1778d358 (ceph): Use a timeout of config.get('time') * 2
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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> - 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
- 05:08 PM Bug #7659: osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_missing(soi...
- 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...- 05:08 PM Bug #7660 (Rejected): osd/ReplicatedPG.cc: 6751: FAILED assert(attrs || !pg_log.get_missing().is_...
- 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...- 04:53 PM Bug #7658 (Resolved): PGLog: _merge_object_divergent_entries: fix the case where prior_version ==...
- 04:52 PM Bug #7657 (Resolved): PGLog: fix proc_replica_log divergent entry selection
- 04:38 PM Revision aea501be (ceph): fs/basic: multimds
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:32 PM Revision 0815e4fa (ceph): rados/singleton-nomsgr: add allocation hint test
- Signed-off-by: Ilya Dryomov <ilya.dryomov@inktank.com>
- 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> - 04:19 PM Revision 0fd636c4 (ceph): Merge remote-tracking branch 'gh/firefly'
- Conflicts:
README - 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
- 03:33 PM Bug #7644 (In Progress): cephx: verify_reply couldn't decrypt with error: error decoding block fo...
- 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...
- 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... - 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,...- 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...
- 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...
- 03:24 PM Bug #7210 (Pending Backport): mon: does not validate snapshot removal commands
- 03:23 PM Bug #7210 (Resolved): mon: does not validate snapshot removal commands
- 03:05 PM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
- 01:30 PM Bug #7642 (Fix Under Review): osd: upgrade stress-split: bad state machine event
- 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.
- 10:22 AM Bug #7642 (Need More Info): osd: upgrade stress-split: bad state machine event
- 08:30 AM Bug #7642 (Resolved): osd: upgrade stress-split: bad state machine event
- ...
- 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...
- 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...
- 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
- 08:31 AM Bug #7643 (Resolved): librbd: upgrade stress-split: FAIL test_rbd.TestImage.test_remove_with_watcher
- ...
- 02:19 PM Bug #7652 (Resolved): mon not removing from creating_pgs
- 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....
- 12:49 PM Revision 3dd09e36 (ceph): Removed nw_info from sysinfo
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 12:42 PM Bug #7650: rados bench seq tests not performed at correct IO sizes
- 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...
- 12:42 PM Bug #7649: ec ceph_test_rados stuck recovering
- 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...
- 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---...
- 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... - 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...
- 09:10 AM Bug #7646 (Duplicate): osd/PGLog.cc: 291: FAILED assert(i->prior_version == last)
- ...
- 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... - 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...
- 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...
- 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>
- 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> - 05:11 AM Subtask #6586 (Resolved): ErasureCodeJerasure::decode does not use want_to_read
- "fixed":https://github.com/ceph/ceph/commit/3650da69
- 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> - 05:11 AM Revision e53aed28 (ceph): SubmittingPatches: clarify "github fork" in preference to "clone"
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 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... - 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> - 05:05 AM Cleanup #7388 (Closed): ceph osd find has no format argument
- The --format argument is implicit for all commands.
- 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 ... - 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>
- 05:03 AM Feature #6645 (Closed): EC: [link] BPC (basic pyramid code)
- 05:01 AM Feature #4929 (Resolved): Erasure encoded placement group
- 04:49 AM Subtask #5877 (Resolved): Plugable erasure code library
- 04:48 AM Subtask #5860 (Rejected): PG::calc_acting and friends should use PGBackend to select the acting s...
- Done elsewhere
- 04:42 AM Subtask #6888 (Resolved): EC/Tiering: Disallow omap writes on pools which are backed by EC pools
- In firefly
- 04:41 AM Subtask #5863 (Rejected): OSD internals must work in terms of cpg_t
- Done elsewhere
- 04:40 AM Subtask #5859 (Rejected): GetInfo should use PGBackend methods to determine when peering can cont...
- Done elsewhere
- 04:39 AM Subtask #5433 (Rejected): Factor out the ReplicatedPG object replication and client IO logic as a...
- Done elsewhere
- 04:32 AM Revision 20bfc978 (ceph): Give up on wait_until_healthy() after 15min
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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> - 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> - 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> - 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...
- 02:00 AM Revision ac6ebf87 (ceph): Merge pull request #217 from ceph/wip-fix-plus
- suite: fix + handling
- 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 ... - 01:51 AM Revision 136775b4 (ceph): Don't warn on legacy crush tunables
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 01:04 AM Revision 022a6a3e (ceph): Revert "The parallel task expects dicts here..."
- This reverts commit 79e348320f3695d085693b7ce0c538a9dfdd182b.
- 12:57 AM Revision 95d445da (ceph): Merge remote-tracking branch 'gh/firefly'
- 12:56 AM Revision 70de7d52 (ceph): Revert "Do not spawn a parallel task if dictionary entry does not exist."
- This reverts commit dadc9f7d0b6d9c13ccbc4edeb9f7875fc0ae0cac.
- 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> - 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 ... - 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... - 12:04 AM Revision 487be437 (ceph): upgrade: fix indentation for final-workload
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
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> - 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> - 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... - 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> - 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> - 11:29 PM Revision 51461432 (ceph): upgrade/dumpling-x: more indentation
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:27 PM Revision 0bf78e6b (ceph): upgrade/dumpling-x: fix indentation
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:16 PM Revision d7892f12 (ceph): Merge remote-tracking branch 'gh/firefly'
- 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... - 10:53 PM Revision 7f5fcd7b (ceph): Merge pull request #14 from ceph/wip-final-workload-wusui
- Fix parallel workunit issues.
- 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.
... - 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... - 10:27 PM Revision 7d1e97f7 (ceph): Revert "Update rados_api_tests.yaml"
- This needs to reference dumpling now.
This reverts commit 8e88922581f80000784072e381867f0b5448cd7f. - 10:27 PM Revision 7b497e1f (ceph): get test-upgrade-firefly.sh from the dumpling branch
- it doesn't exist elsewhere
- 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... - 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... - 09:11 PM Bug #7610 (Resolved): Memory corruption during rados bench
- 11:28 AM Bug #7610: Memory corruption during rados bench
- 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... - 08:09 PM Bug #7637 (Resolved): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 03:39 PM Bug #7637 (In Progress): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 03:10 PM Bug #7637 (Fix Under Review): osd/OSD.cc: 518: FAILED assert(agent_queue.empty())
- 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 ... - 08:07 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
- 04:51 PM Bug #7640 (Resolved): teuthology: parallel refs to top level dict broken
- ...
- 08:06 PM Bug #7638 (Resolved): snap update rollback not working right
- 03:28 PM Bug #7638: snap update rollback not working right
- 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... - 08:05 PM Bug #7634 (Resolved): osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.len...
- 03:28 PM Bug #7634: osd/ReplicatedPG.cc: 7877: FAILED assert((data_included.empty() && data.length() == 0)...
- 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...- 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...- 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 ... - 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... - 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.... - 07:32 PM Revision c8c2f547 (ceph): Client: fix build issue (lost semicolon)
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 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... - 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> - 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> - 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> - 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> - 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 ?
- 06:14 PM devops Bug #7627: ceph-disk: does not start daemons properly under systemd
- ...
- 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...
- 05:57 PM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...
- 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 ... - 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
- 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...
- 10:12 AM Bug #7588: OSD Seg fault in string assign ObjectOperation::C_ObjectOperation_copyget::finish()
- Can I help ?
- 03:50 PM Bug #7072 (Resolved): logrotate not sending HUP signal
- 03:21 PM Bug #7072 (Fix Under Review): logrotate not sending HUP signal
- "work in progress":https://github.com/ceph/ceph/pull/1393
- 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
- 03:30 PM Bug #7393 (Resolved): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 white...
- 12:12 PM Bug #7393: osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0 whiteouts, 26738...
- 03:34 PM Bug #7632 (Resolved): os/FileStore.cc: 2538: FAILED assert(0 == "unexpected error")
- 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...
- 03:00 PM Bug #7633 (Resolved): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-firefl...
- 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... - 12:49 PM Bug #7633 (In Progress): "ceph_test_rados_api_tier: not found" in upgrade:dumpling-x:parallel-fir...
- 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
- 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?
- 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...
- 02:22 PM CephFS Feature #7324 (Resolved): qa: kcephfs + ACLs (new pjd tests?)
- 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...- 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... - 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.
- 11:30 AM Bug #7601: "command crashed with signal 6" in rados-firefly-testing-basic-plana suite - hung tests
- No logs, probably 7604.
- 11:01 AM Bug #7624 (Resolved): osd/ECBackend.cc: 1644: FAILED assert(r == 0)
- 10:59 AM Bug #7618 (Resolved): osd/ECBackend.cc: 475: FAILED assert(r == 0)
- 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
- 10:30 AM Bug #7487 (Resolved): mon: crashes when moving CRUSH items in zero-weighted tree?
- 10:29 AM Bug #7590 (Resolved): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap create <base>...
- 10:28 AM Bug #7630 (Duplicate): Simple tiering test produces OSD assert
- #7604
- 10:28 AM Bug #7630 (Resolved): Simple tiering test produces OSD assert
- 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... - 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...
- 09:46 AM Feature #7058: osd primary affinity
- https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity
- 09:24 AM rbd Feature #7455: krbd,kcephfs: support primary-affinity
- https://wiki.ceph.com/Planning/Blueprints/Firefly/osdmap%3A_primary_role_affinity
- 09:17 AM rbd Feature #7455 (In Progress): krbd,kcephfs: support primary-affinity
- 09:10 AM Feature #7619 (In Progress): objecter: replace client_lock with fine grained read-write locks
- 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 ...
- 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...
- 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... - 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> - 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... - 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?
- 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... - 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> - 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... - 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>
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... - 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> - 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> - 11:18 PM Revision 16e3d4d3 (ceph): Merge pull request #1382 from ceph/wip-7616
- Wip 7616
Reviewed-by: Sage Weil <sage@inktank.com> - 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> - 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, ... - 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> - 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... - 10:21 PM Revision 10f66072 (ceph): Merge pull request #1372 from ceph/wip-7607
- wip 7607
Reviewed-by: Sage Weil <sage@inktank.com> - 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
- 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
- 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> - 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... - 09:17 PM Revision 240446e7 (ceph): test: merge unittest_crushwrapper and unittest_crush_wrapper
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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-... - 08:53 PM Revision 8b3934fc (ceph): PGBackend::rollback_stash: remove the correct shard
- Fixes: #7616
Signed-off-by: Samuel Just <sam.just@inktank.com> - 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... - 08:52 PM Revision ca12e0d9 (ceph): qa/workunits/mon/crush_ops: use expect_false
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 08:39 PM Revision 9a8bf66d (ceph): ceph.conf.template: add in sensible erasure coding defaults
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 08:38 PM Revision e6698af8 (ceph): ceph_manager: fix erasure coding m, k values
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 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> - 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> - 08:13 PM Revision e69da0a5 (ceph): Log job PID
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 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> - 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... - 06:14 PM Revision c5f0e718 (ceph): Merge pull request #216 from ceph/wip-workunit-timeout
- Add a 6h timeout to workunits
- 05:50 PM Revision dab02408 (ceph): Merge pull request #9 from ceph/wip-upgrade-dumpling
- upgrade/dumpling: two fixes
- 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... - 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...
- 05:46 PM Revision 66ea0710 (ceph): Merge pull request #13 from ceph/wip-upgrade
- a few upgrade fixes
- 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.... - 05:40 PM Bug #7623 (Resolved): local 'best' uninitialized in Objecter
- 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... - 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... - 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... - 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 ... - 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... - 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> - 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
- 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...
- 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... - 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:
... - 03:18 PM Bug #7621 (Resolved): ceph_test_rados_api_c_read_operations core dumped
- 3f59f02913f4277f419052d546bb7448f74aec4d
- 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.
- 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...
- 03:32 PM Bug #7618: osd/ECBackend.cc: 475: FAILED assert(r == 0)
- Merged 1 fix, found another problem.
- 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... - 03:31 PM Bug #7616 (Resolved): broken rollback_stash
- 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 ... - 03:27 PM Bug #7590 (Fix Under Review): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap creat...
- 02:47 PM Fix #7562 (Fix Under Review): mon: pretty-print of mon status should keep monitor ranks and names...
- 02:24 PM Feature #7442 (Resolved): mon: health warn on pg "full"
- 02:21 PM Bug #7607 (Resolved): ReplicatedPG::fill_in_copy_get: omap doesn't get filled in correctly for sm...
- 02:19 PM Bug #6820 (Resolved): Bad commandline usage crashed my monitor
- 02:18 PM Bug #7248 (Resolved): osd: bench set max size
- 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... - 02:12 PM Feature #7619 (Resolved): objecter: replace client_lock with fine grained read-write locks
- 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... - 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...
- 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... - 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...
- 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...
- 12:41 PM Bug #7608 (Resolved): test/librados/tier.cc multiple -ENOTEMPTY failures
- 12:30 PM Bug #7608 (Fix Under Review): test/librados/tier.cc multiple -ENOTEMPTY failures
- 09:37 AM Bug #7608 (In Progress): test/librados/tier.cc multiple -ENOTEMPTY failures
- 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... - 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... - 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...
- 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...
- 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.
- 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 ...
- 08:48 AM CephFS Bug #7613 (Can't reproduce): mds/MDCache.cc: 216: FAILED assert(inode_map.count(in->vino()) == 0)
- ...
- 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.
- 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... - 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
... - 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...
- 07:55 AM Revision 60a329f8 (ceph): Merge pull request #1338 from dachary/wip-mailmap
- mailmap updates
Reviewed-by: Christophe Courtaut <christophe.courtaut@gmail.com> - 07:47 AM Revision d4950a1d (ceph): mailmap: Danny Al-Gaaf affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision a85d0ef6 (ceph): mailmap: Steve Stock affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision fdb644a2 (ceph): mailmap: Ron Allred affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 07:47 AM Revision 0eac1ba0 (ceph): mailmap: Bjørnar Ness affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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> - 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... - 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...
- 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
- 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... - 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> - 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... - 03:22 AM Revision 4bf28df2 (ceph): Merge remote-tracking branch 'upstream/wip-7447' into firefly
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 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 <... - 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> - 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> - 12:09 AM Revision fb510c29 (ceph): Merge pull request #12 from ceph/wip-final-workload-wusui
- Fix dumpling-x upgrade suite.
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... - 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>
- 11:29 PM Revision f2a4eec1 (ceph): PGBackend/ECBackend: handle temp objects correctly
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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... - 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.
- 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> - 09:24 PM Revision a7057e10 (ceph): doc: Improve CloudStack RBD documentation
- 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... - 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....- 07:33 PM Bug #7601: "command crashed with signal 6" in rados-firefly-testing-basic-plana suite - hung tests
- nvm
- 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 ... - 07:27 PM Bug #7447 (Resolved): osd: copy_from temp objects interact awkwardly with backfill
- 07:27 PM Bug #7604 (Resolved): osd/ReplicatedPG.cc: 5460: FAILED assert(cop->rval >= 0)
- 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... - 06:50 PM Revision c2cc1789 (ceph): ECBackend.cc: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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... - 05:02 PM Bug #7607 (Resolved): ReplicatedPG::fill_in_copy_get: omap doesn't get filled in correctly for sm...
- 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>
- 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...
- 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="$... - 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> - 03:21 PM Bug #7595 (Resolved): osd/ReplicatedPG.cc: 2236: FAILED assert(snapset.seq)
- 07:14 AM Bug #7595 (Fix Under Review): osd/ReplicatedPG.cc: 2236: FAILED assert(snapset.seq)
- 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... - 03:21 PM Bug #7563 (Resolved): osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_up...
- 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 = ... - 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>
- 02:43 PM Revision 39fc1db3 (ceph): KeyValueStore: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 02:43 PM Revision c2f3f2b5 (ceph): close file descriptor in error case
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 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>
- 02:43 PM Revision e4c4aaed (ceph): ErasureCodePlugin.cc: reduce scope of local variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 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>
- 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... - 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... - 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... - 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...
- 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> - 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... - 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...
- 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...
- 10:45 AM rgw Bug #7597: hang in rados/test.sh
- I was wrong, it's not a network problem.
From vpm104:... - 08:47 AM rgw Bug #7597 (Duplicate): hang in rados/test.sh
- Looking into a particular hung job:...
- 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... - 08:46 AM Revision 46b9f655 (ceph): Merge remote-tracking branch 'brag/master' into firefly
- Signed-off-by: Babu Shanmugam <anbu@enovance.com>
- 07:01 AM Revision 6d323c04 (ceph): mailmap: Mike Lundy affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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> - 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> - 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> - 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> - 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> - 05:16 AM Revision 0e5fd0e3 (ceph): osd: make default bloom hit set fpp configurable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 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)... - 05:16 AM Revision 241b9e81 (ceph): mon/OSDMonitor: fix some whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:16 AM Revision 49e54aba (ceph): mon/OSDMonitor: fix race in 'osd tier remove ...'
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 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 ... - 03:26 AM Subtask #7548 (Fix Under Review): Basic docs for Erasure Coding
- 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> - 01:05 AM Revision 198b0aa2 (ceph): Merge pull request #1354 from ceph/wip-7563
- Wip 7563
Reviewed-by: Greg Farnum <greg@inktank.com> - 12:59 AM Revision adb04f81 (ceph): Removed branch ref to fix http://tracker.ceph.com/issues/7584
- 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> - 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... - 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...
- 12:07 AM Revision 8e889225 (ceph): Update rados_api_tests.yaml
- Removed branch ref to fix http://tracker.ceph.com/issues/7584
- 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> - 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>
- 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... - 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... - 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... - 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... - 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... - 12:05 AM Revision 3cc9e226 (ceph): TestPGLog: not worth maintaining tests of assert behavior
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 12:05 AM Revision ff329ac5 (ceph): TestPGLog:rewind_divergent_log: set prior_version for delete
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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>
03/03/2014
- 10:48 PM CephFS Bug #2679 (Can't reproduce): POSIX file lock not released on process termination
- 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> - 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>
- 09:43 PM Bug #7578 (Resolved): end of options ( -- ) disables CEPH_ARGS
- 09:24 AM Bug #7578 (Fix Under Review): end of options ( -- ) disables CEPH_ARGS
- 09:37 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
- 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!
- 06:31 PM CephFS Bug #2288 (Resolved): libcephfs: setxattr returns EEXIST following removexattr
- 08:47 PM Revision 963fb881 (ceph): Merge pull request #215 from dachary/wip-ec-pool
- ceph-manager: fix ec_pool parameters
- 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> - 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... - 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... - 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...- 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 ... - 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> - 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... - 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(). ... - 06:33 PM Revision 1f5b796f (ceph): FileStore: introduce XfsFileStoreBackend class
- Introduce XfsFileStoreBackend class, currently the only filestore
backend implementing SETALLOCHINT op. This commit ... - 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... - 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_... - 06:17 PM CephFS Bug #2445 (Can't reproduce): crash when removing a non-empty directory
- 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
- 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... - 05:07 PM Revision 28c29c1d (ceph): Revert "ObjectCacher: remove unused target/max setters"
- This reverts commit e1a49e5386c3ed4a6bc4870f01630349cb04d749.
- 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... - 05:01 PM Bug #7590 (Resolved): mon: ceph osd tier add ..., ceph osd rm <tier>, ceph osd snap create <base>...
- ...
- 04:57 PM rgw Feature #7589 (Resolved): rgw: configurable chunk size
- 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... - 04:24 PM Revision b7274170 (ceph): Merge pull request #11 from ceph/wip-7581
- increase verbosity for OSDs for ceph-deploy tests
- 04:24 PM Revision 3006f231 (ceph): Merge pull request #207 from ceph/wip-7356
- helper for bombing out of infinite loops
- 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.
- 03:35 PM Bug #7563: osd/ReplicatedPG.cc: 8425: FAILED assert(info.last_complete == info.last_update)
- 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.
- 03:34 PM Bug #6313 (In Progress): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- 03:34 PM Bug #6313 (Fix Under Review): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- 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- 04:11 PM Cleanup #7586: deprecate rados_pool_create
- ...
- 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...
- 04:04 PM Revision 2bf27024 (ceph): increase verbosity for OSDs for ceph-deploy tests
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 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... - 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>
- 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... - 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>
- 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>
- 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...- 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...
- 03:35 PM Bug #7447: osd: copy_from temp objects interact awkwardly with backfill
- 03:28 PM Revision aca6ac34 (ceph): qa: workunits: cephtool: test 'osd bench' limits
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:08 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
- 123ff9e18a27c6517a291aab1e0613b27d70d711
- 12:42 PM Bug #7458 (Fix Under Review): osd: stray pg ref on shutdown
- 03:08 PM Feature #7438: EC: adapt watch/notify stress test for EC and add to nightly
- 12:42 PM Feature #7438 (In Progress): EC: adapt watch/notify stress test for EC and add to nightly
- 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.... - 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> - 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 ... - 01:58 PM devops Bug #7585 (Resolved): ceph-deploy should handle requiretty failures
- This is unacceptable:...
- 12:43 PM Bug #7406 (New): Seg fault in find_object_context()in recent master rados run
- 10:23 AM Bug #7406 (In Progress): Seg fault in find_object_context()in recent master rados run
- 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... - 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... - 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 - 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...
- 09:53 AM Feature #7442 (Fix Under Review): mon: health warn on pg "full"
- 09:52 AM Linux kernel client Feature #6163 (Resolved): support caching pool and redirects
- 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...
- 09:34 AM Bug #7575: osd/ReplicatedPG.cc: 10600: FAILED assert(r >= 0): hit_set_persist() races with agent_...
- 09:19 AM Bug #7448 (In Progress): os/FileJournal.cc: FAILED assert(fd >= 0)
- 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...
- 08:46 AM rgw Bug #7543 (Pending Backport): rgw: off-by-one bug in rgw_trim_whitespace()
- 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... - 08:28 AM Revision cababd92 (ceph): mon: add mon-test-helpers.sh to EXTRA_DIST
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:28 AM Revision eb21bc80 (ceph): osd: helper to create an OSD for functional tests
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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: ... - 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... - 07:56 AM Revision 9dd6e34c (ceph): mailmap: Mouad Benchchaoui affiliation
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 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> - 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... - 06:59 AM Bug #7423 (Resolved): erasure code: ./rados get retrieves a larger object
- 06:55 AM CephFS Bug #1874 (Can't reproduce): Running `git gc` on a bare git repository hosted by ceph results in ...
- 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... - 06:51 AM Feature #7571 (Fix Under Review): erasure code: implicit ruleset creation when a pool is created
- 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... - 05:06 AM Revision 10f87fc6 (ceph): Merge pull request #1344 from ceph/wip-7539
- Wip 7539
Reviewed-by: Sage Weil <sage@inktank.com> - 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...
- 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...
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> - 10:51 PM Revision 855edc6e (ceph): Fix typo ceph-disk
- Fix typo
Signed-off-by: Sébastien Han <sebastien.han@enovance.com> - 09:05 PM Bug #7539 (Resolved): Firefly EC pool massive memory leak during writes
- 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> - 12:55 PM Bug #7538 (Resolved): librados: rados ls crashes on firefly due to segfault in ObjectIterator::op...
- 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- 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... - 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> - 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... - 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> - 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>
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... - 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... - 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> - 10:54 PM Revision d4118e15 (ceph): MOSDECSubOpWrite: drop transaction, log_entries in clear_buffers
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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... - 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> - 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 ...
- 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> - 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...- 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... - 03:58 PM Bug #6736 (Resolved): Bugs in per pool IOPs/recovery statistics
- 03:56 PM Subtask #5487 (Closed): Factor out ObjectContext / ReplicatedPG::object_contexts
- Obsoleted.
- 03:55 PM Subtask #6895 (Rejected): omap needs to be disablable on a per-pool basis, this needs to be requi...
- Not needed.
- 03:10 PM Bug #7542 (Resolved): ec misdirected op
- 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... - 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... - 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... - 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... - 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... - 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 ... - 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()... - 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... - 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
... - 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>
- 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 ?
- 09:05 AM Bug #7572 (Fix Under Review): Bad 'acting' array in JSON 'pg dump' output
- https://github.com/ceph/ceph/pull/1339
- 08:58 AM Bug #7572 (Resolved): Bad 'acting' array in JSON 'pg dump' output
Example:...- 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...- 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> - 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... - 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> - 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> - 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 <... - 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>
- 05:08 AM Revision 63e34639 (ceph): Merge pull request #1326 from ceph/wip-7542
- Wip 7542
Reviewed-by: Greg Farnum <greg@inktank.com> - 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>
- 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... - 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... - 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> - 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... - 05:04 AM Revision 214977ab (ceph): client: choose hash function according to dir layout
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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>
- 01:46 AM Feature #7457 (Fix Under Review): mon: prevent addition of non-empty pools as a tier
- 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(...
02/28/2014
- 11:32 PM Revision a01d3ca8 (ceph): Merge pull request #213 from ceph/wip-kdb-except
- Allow setting kdb to fail.
- 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... - 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... - 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.
... - 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> - 07:27 PM Revision fbb1ec88 (ceph): ECBackend: don't leak transactions
- Fixes: #7539
Signed-off-by: Samuel Just <sam.just@inktank.com> - 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... - 07:13 PM Revision 4f31eb01 (ceph): Merge pull request #212 from ceph/wip-limit
- Added --limit option to teuthology-suite.
- 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... - 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... - 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> - 05:04 PM Revision 4b5338fa (ceph): Merge pull request #211 from ceph/wip-7554
- mds_thrash #7554
- 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... - 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> - 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... - 04:11 PM Revision a850a387 (ceph): doc/dev/cache-pool: fix notes
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 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... - 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...
- 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 ... - 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...
- 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 ...
- 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...
- 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... - 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 ...
- 05:07 AM Bug #7423 (Fix Under Review): erasure code: ./rados get retrieves a larger object
- 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...
02/27/2014
- 09:29 PM CephFS Cleanup #3742 (Resolved): Remove old Hadoop wrappers and configuration options
- 09:27 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
- Actually, yeh I'll look at this.
- 03:30 PM CephFS Bug #3318: java: lock access to CephStat, CephStatVFS from native
- Is this still an issue, Noah?
- 09:23 PM CephFS Bug #4861 (Rejected): Alter Java components to build against Java 1.6 (or 1.7)
- 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...
- 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...
- 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...
- 04:03 PM CephFS Bug #4023: kclient: d_revalidate is abusing d_parent
- Is this still a problem?
- 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 ... - 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... - 05:14 PM CephFS Bug #4722: kernel BUG at fs/ceph/caps.c:1006 invalid opcode: 0000
- who cares 3.5 kernel?
- 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!
- 05:13 PM CephFS Bug #7565: Failed assert in check_rstats
- it's CDir::check_rstats() bug, not rstat corruption.
- 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...- 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. - 04:50 PM CephFS Bug #926: mds: fix rename between snaprealms
- Snapshots
- 04:50 PM CephFS Bug #1552 (Duplicate): qa: file locking test fails
- #7326
- 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.
- 04:45 PM CephFS Bug #3596: ceph-fuse: crash in mds rejoin
- Snapshots
- 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.
- 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, ... - 04:42 PM CephFS Bug #2288: libcephfs: setxattr returns EEXIST following removexattr
- Confirmed MDS bug!
- 04:41 PM Bug #7458: osd: stray pg ref on shutdown
- 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.
- 04:38 PM CephFS Bug #1666: hadoop: time-related meta-data problems
- Also see #7564
But low priority, for this is Hadoop - 04:36 PM CephFS Bug #4212: mds: open_snap_parents isn't called all the times it needs to be
- Snapshots
- 04:36 PM CephFS Bug #4213: mds: old_parents is never cleaned up
- Snapshots
- 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
- 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...
- 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.
- 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... - 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...
- 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...
- 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...
- 03:53 PM CephFS Bug #4134: mds: request locking hang under snaptests
- snapshots = low
- 03:52 PM CephFS Bug #3719 (Can't reproduce): pjd test 145 failed in the nightly runs
- These logs are gone.
- 03:45 PM CephFS Bug #4280: mds: crash on lookupsnap
- Snapshots = low priority
- 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...
- 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...
- 03:30 PM CephFS Bug #4738: libceph: unlink vs. readdir (and other dir orders)
- Need more info, samba, uclient, etc.
- 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...
- 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.
- 03:25 PM CephFS Bug #4920: client: does not respect O_NOFOLLOW
- uclient = low priority, for now.
- 03:25 PM Bug #7542: ec misdirected op
- wip-7542
- 03:25 PM Bug #7539: Firefly EC pool massive memory leak during writes
- testing wip-7542
- 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... - 03:25 PM CephFS Bug #4188: mds crashes when cow-ing entries in formerly snapshotted dir
- Snapshots = low priority. *sigh*
- 03:21 PM CephFS Bug #5360: ceph-fuse: failing smbtorture tests
- Samba against ceph-fuse (not even using libcephfs) = low priority.
- 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...
- 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!
- 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.
- 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.
- 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.
- 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... - 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...
- 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?
- 01:24 PM CephFS Bug #6741: failed snaptest-2.sh; got ENOTEMPTY on should-be empty dir
- Downgrading: ceph-fuse and snapshots.
- 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.
- 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...
- 01:20 PM CephFS Bug #7206 (Need More Info): Ceph MDS Hang on hadoop workloads
- 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...
- 12:42 PM Fix #7562 (Resolved): mon: pretty-print of mon status should keep monitor ranks and names aligned
- ...
- 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.
- 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...
- 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... - 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 ... - 07:57 AM Bug #7248 (Fix Under Review): osd: bench set max size
- https://github.com/ceph/ceph/pull/1324
- 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...
- 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/...
- 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> - 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... - 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,... - 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... - 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... - 03:59 AM Revision 30aa2d65 (ceph): client: clear migrate seq when MDS restarts
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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...
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... - 11:02 PM Bug #7387: Malformed JSON command output when non-ASCII strings are present
- 10:41 PM Revision 0dcf3f4d (ceph): --dead implies --refresh
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 10:22 PM Revision d42f31e5 (ceph): Symlink worker log after child starts
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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>
- 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> - 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... - 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... - 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... - 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 ... - 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... - 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> - 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... - 06:09 PM Revision f8a2a53c (ceph): Push complete info when reporting jobs as dead
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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. ...- 05:47 PM Revision 0db35b95 (ceph): Merge pull request #210 from ceph/wip-queue
- Add teuthology-queue command for beanstalk Managmeent.
- 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> - 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 - 05:01 PM CephFS Bug #4746: client: invalidate callback can deadlock
- Demoted due to ceph-fuse and FUSE interface work.
- 05:00 PM CephFS Bug #4829: client: handling part of MClientForward incorrectly?
- Demoting due to uclient and multi-mds.
- 04:58 PM CephFS Bug #5787: client/Client.cc: 2081: FAILED assert(!unclean) in put_inode
- Demoting due to uclient and Need More Info.
- 04:57 PM CephFS Bug #6473: multimds + ceph-fuse: fsstress gets ENOTEMPTY on final rm -r
- Demoting due to multi-mds.
- 04:57 PM CephFS Bug #5765: kclient: High CPU due to raw_spin_lock in ceph_cap_string
- Demoting due to performance, not correctness.
- 04:56 PM CephFS Bug #5021: ceph-fuse: crash on traceless reply
- Demoting due to uclient.
- 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....
- 04:48 PM CephFS Bug #6608: samba teuthology dbench failure
- Demoting priority on samba.
- 04:47 PM CephFS Bug #7011: ENOTEMPTY on ceph-fuse + snaptest-? test
- Demoting priority on ceph-fuse and snapshots.
- 04:47 PM CephFS Bug #6613: samba is crashing in teuthology
- Demoting priority on samba.
- 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?
- 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...
- 04:29 PM CephFS Feature #4001 (Resolved): Implement the migration path from using the AnchorTable to using lookup...
- Again, Zheng got this done.
- 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...
- 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)?
- 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...
- 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...
- 03:33 PM Bug #7549: Mon deadlock
I did add a -d to the vstart.sh invocation in the test/vstart_wrapper.sh script.- 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...- 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.... - 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> - 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
- 01:17 PM Revision 6ba89851 (ceph): fix docstring typo
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 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... - 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.
- 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.
- 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.... - 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 ...
- 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...
- 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 ...
- 07:15 AM CephFS Bug #7530: mds: failed anchor assert on replay
- commit:7ba3200f1e91d803cdf84f96777641f7d18d3c01
- 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 ... - 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> - 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. - 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".
- 04:42 AM Revision 5a6cb3da (ceph): Merge pull request #1317 from ceph/wip-7537
- Wip 7537
Reviewed-by: David Zafman <david.zafman@inktank.com> - 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 ... - 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> - 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> - 01:08 AM CephFS Feature #7531 (Closed): MDS: support required feature sets like the OSD and monitor
- MDS map contains CompatSet::FeatureSet
- 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> - 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... - 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 <...
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> - 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> - 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> - 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> - 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, ... - 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... - 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... - 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... - 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... - 08:42 PM Bug #7537 (Resolved): OSDMonitor thrash produces invalid EC pool mappings
- 5a6cb3da201ce503b4aef1744c3dc15511d15a13
- 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]
... - 07:55 PM Bug #7406: Seg fault in find_object_context()in recent master rados run
- 07:52 PM Bug #7535 (Duplicate): Switching to classic scrub unnecessarily
- 12:55 PM Bug #7535: Switching to classic scrub unnecessarily
This was primarily fixed by 7357b6ed4bbc6ef44a80640ffb7e1ddacab10b5e for tracker #7517.- 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 ...- 07:51 PM Revision 9e55f6f2 (ceph): Add missing fedora yamls.
- Running a git add first would have been helpfull...
- 07:51 PM Revision 67ed25f1 (ceph): Run ceph-deploy on fedora19 not old fedora18.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 07:50 PM Revision d741cd99 (ceph): Add missing fedora yamls.
- Running a git add first would have been helpfull...
- 07:42 PM Revision 9fb8231f (ceph): Run ceph-deploy on fedora19 not old fedora18.
- Signed-off-by: Sandon Van Ness <sandon@inktank.com>
- 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... - 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... - 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 ... - 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... - 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... - 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... - 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... - 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 ... - 07:34 PM devops Feature #7435 (Resolved): RHEL 6.5 and CentOS 6.5 Gitbuilders
- Created and on the index page.
- 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... - 06:27 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
- 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...
- 09:09 AM CephFS Bug #7530: mds: failed anchor assert on replay
- Crashed on first try, log at debug-mds=10 attached
- 07:04 AM CephFS Bug #7530 (In Progress): mds: failed anchor assert on replay
- 03:47 PM Bug #6922 (Resolved): mon: do not allow unreasonable PG splitting
- Sam merged this.
- 01:40 PM Bug #6922: mon: do not allow unreasonable PG splitting
- PR: https://github.com/ceph/ceph/pull/1316
- 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...
- 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...
- 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...
- 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/...
- 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...
- 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:...
- 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.
- 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...
- 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...
- 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.
- 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> - 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.
- 07:02 AM CephFS Feature #3863 (In Progress): implement a tool to lookup inode numbers without holding their path
- 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... - 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... - 03:56 AM Revision 9f7f4eda (ceph): Revert "osd/PG: fix assert when deep repair finds no errors"
- This reverts commit e3e3328ec8a57f1ae2a2fd9893c51068798720a0.
- 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>
- 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...
- 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...
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...
- 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 ...
- 10:11 PM CephFS Bug #7530 (Resolved): mds: failed anchor assert on replay
- ...
- 09:22 PM Revision 25919351 (ceph): use itertools for seconds sum
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 09:21 PM Revision 60892ca9 (ceph): tests for the new while helper
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 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.... - 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 ...
- 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...
- 08:22 PM devops Feature #6986: Build packages containing RBD and CephFS kernel modules for installation on RHEL7-...
- 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.
... - 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...
- 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 ... - 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...
- 08:09 PM Revision 171a5e1a (ceph): add a helper for while loops
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 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>
- 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> - 05:10 PM CephFS Feature #4000 (Resolved): Design a migration path from using the AnchorTable to using lookup-by-ino
- 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?
- 05:10 PM CephFS Feature #7323 (Resolved): mds: fix and merge pending libcephfs changes
- 05:09 PM CephFS Feature #3999 (Resolved): update CDir encoding
- this was revved as part of zheng's omap stuff
- 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> - 04:15 PM Linux kernel client Cleanup #2847 (Resolved): libceph: osdmap definition is out of date
- 04:15 PM Linux kernel client Feature #6991 (Resolved): support CEPH_FEATURE_OSDMAP_ENC
- 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...
- 12:14 PM Revision 69082a69 (ceph): mds: add mds_kill_create_at for testing
- Signed-off-by: John Spray <john.spray@inktank.com>
- 11:24 AM rgw Bug #7524: "scrub stat mismatch" error in rgw-firefly-distro-basic-plana suite
- Seems related to #7468
- 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... - 10:20 AM rgw Bug #6936 (Resolved): radosgw-admin allows same user to be created multiple times
- Fixed for firefly, commit:53de64122b206d11aa42fd401f88f02f2908e942
- 10:20 AM rgw Bug #6951 (Resolved): rgw: bucket re-create fails when cache is disabled
- Fixed for firefly, commit:859ed33ed7f9a96f4783dfb3e130d5eb60c622dd
- 10:16 AM rgw Bug #6830 (Resolved): S3 CompleteMultipartUploadResult has empty ETag element
- Fixed, commit:2b3e3c834cd0e8b890296fa2b92ebb5de01a1bc1
- 10:15 AM rgw Bug #7064 (Resolved): S3 request to non-existent object in non-existent bucket results in 30 seco...
- Fixed, commit:3ed68eb9fac9b3d0bf9111867d609f9ea08fb202
- 09:58 AM devops Bug #7356 (In Progress): Kill all while loops that will never end....
- 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...
- 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... - 07:28 AM Bug #7504 (Rejected): Ceph does not specify python2
- 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... - 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> - 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... - 03:49 AM Revision 5f53cf13 (ceph): Merge pull request #1307 from ceph/wip-7517
- Wip 7517
- 03:12 AM Revision 0243d29c (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:11 AM Revision 87ebe461 (ceph): upgrade/dumpling: add recent dumpling point releases
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:10 AM Revision bad8e609 (ceph): upgrade/dumpling: upgrade to latest dumpling, not emperor
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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 ... - 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....
- 12:58 AM CephFS Feature #7315 (Closed): review and merge zheng's dirfrag series
- 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...
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> - 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...
- 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>
- 10:48 PM Revision dcb9946b (ceph): Merge pull request #1306 from ceph/wip-7512
- wip-7512
Reviewed-by: Sage Weil <sage@inktank.com> - 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... - 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> - 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> - 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... - 08:15 PM Revision df3ba724 (ceph): mon/PGMap: add unit test for min_last_epoch_clean
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 08:14 PM Revision 8913ab4b (ceph): ECBackend: skip canceled xattr reads as well
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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
- 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...
- 07:49 PM Bug #7517 (Resolved): osd/PG.cc: 3673: FAILED assert(pool.info.type == pg_pool_t::TYPE_REPLICATED)
- 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... - 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... - 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...
- 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...
- 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 ... - 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... - 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> - 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> - 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> - 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::... - 05:00 PM Revision 9651b18b (ceph): os/ObjectStore: fix rebase errors
- These were goofed by d74f1282cd268b4b04cfd9e90ddeac6d1dc6be7e.
Signed-off-by: Sage Weil <sage@inktank.com> - 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...
- 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> - 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> - 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 - 03:38 PM Revision 0e50f7a0 (ceph): Merge remote-tracking branch 'gh/firefly'
- 03:37 PM Revision 57eeebee (ceph): Merge pull request #1290 from ceph/wip-os-doc
- os/ObjectStore: document interface
- 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> - 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> - 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... - 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> - 02:48 PM Bug #7512 (Resolved): osd/PG.cc: 5279: FAILED assert(0 == "we got a bad state machine event")
- 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...
- 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 ...
- 12:21 PM Bug #7493 (Resolved): cephtool/pool_ops failure
- commit:70d23b9a0ad9af5ca35a627a7f93c7e610e17549
- 08:23 AM Feature #7360 (Resolved): When EC ready add back test.sh test case for "mon: OSDMonitor: do not a...
- 07:54 AM Bug #7494 (Resolved): EC filter read op bug
- 07:54 AM Bug #7506 (Resolved): osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- 07:53 AM Bug #7508 (Resolved): 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burn...
- 07:25 AM Bug #7491 (Resolved): rados api crashes
- 07:21 AM Feature #7441 (Resolved): osd: perfcounters for cache events and agent events
- 07:21 AM Feature #7514 (Resolved): qa: add ceph_test_objectstore to rados test suite
- 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... - 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 - 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... - 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> - 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... - 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>
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> - 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... - 08:37 PM Revision 8b4cf1c0 (ceph): OSDMap: make calc_pg_rank/role const for acting
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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>
- 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> - 08:37 PM Revision 9da4d40e (ceph): PGLog: test for missing using the correct shard value
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 08:37 PM Revision 005b4fad (ceph): Objecter: resend op if primary role changed
- Fixes: #7508
Signed-off-by: Samuel Just <sam.just@inktank.com> - 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> - 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>
- 08:35 PM Revision ab4c9a67 (ceph): ECUtil: clear() should reset hashes to -1, not 0
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 05:35 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
- 05:27 PM Bug #7513: PGLog::activate_not_complete: log.complete_to decrement typo
- https://github.com/ceph/ceph/pull/1300
- 05:25 PM Bug #7513 (Resolved): PGLog::activate_not_complete: log.complete_to decrement typo
- 05:19 PM Bug #7511 (Resolved): "set noup; set down <n>; unset noup" doesn't bring <n> back up
- merged
- 01:48 PM Bug #7511 (Fix Under Review): "set noup; set down <n>; unset noup" doesn't bring <n> back up
- 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... - 03:57 PM Revision 90ebdcc4 (ceph): Rename keyvaluestore_check_backend to keyvaluestore_debug_check_backend
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 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> - 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... - 01:05 PM Revision 9543664b (ceph): Remove filestore_inject_stall
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:05 PM Revision 697411c8 (ceph): Add backend check option to KeyValueStore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:05 PM Revision 8c4d8659 (ceph): Add config tracker to KeyValueStore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:05 PM Revision 62c1631f (ceph): Remove eio inject codes in KeyValueStore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:05 PM Revision a52d7cd0 (ceph): Add KeyValueStore op thread options
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:05 PM Revision 3e6a1fc6 (ceph): Add read/write operation to store_test.cc
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 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>
- 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... - 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... - 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... - 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... - 01:05 PM Revision ec8a4193 (ceph): Implement collection_rename interface in KeyValueStore
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 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... - 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... - 01:04 PM Revision c9fdceee (ceph): Add test for omap interface
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 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... - 01:04 PM Revision 024a1204 (ceph): Use rename operation to make colection_move atomic
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:04 PM Revision 4e7f1de9 (ceph): Adjust some interfaces to optimize caller codes
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 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... - 03:28 AM Revision a715c7f2 (ceph): Merge branch 'wip-6685-firefly' into firefly
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 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> - 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>
- 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.
... - 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>
- 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> - 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 ... - 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...
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> - 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 - 10:46 PM Revision 78b65ace (ceph): Merge remote-tracking branch 'origin/port/updates' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 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.... - 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> - 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... - 09:51 PM Revision 6e284806 (ceph): schedule_suite: debug filestore = 20 too
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:15 PM Bug #7511: "set noup; set down <n>; unset noup" doesn't bring <n> back up
- ...
- 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... - 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... - 09:10 PM Revision 68f62660 (ceph): Merge remote-tracking branch 'origin/wip-6936' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:09 PM Revision 8ebc2a26 (ceph): Merge remote-tracking branch 'origin/wip-7099' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:08 PM Revision 731d483b (ceph): Merge remote-tracking branch 'origin/wip-6830' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:07 PM Revision a19b460a (ceph): Merge remote-tracking branch 'origin/wip-6951' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:06 PM Revision 0aac04a2 (ceph): Merge remote-tracking branch 'origin/wip-7064' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:05 PM Revision d509e53d (ceph): Merge remote-tracking branch 'origin/wip-7271' into firefly
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 09:01 PM Revision ae61abf0 (ceph): Merge pull request #205 from kdreyer-inktank/jenkins
- jenkins: fail fast during job execution
- 09:00 PM Revision 76046cf3 (ceph): dencoder: check for radosgw build option
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 09:00 PM Revision 5373ee24 (ceph): osd: use ceph scoped shared_ptr
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 08:59 PM Revision a4f091cd (ceph): Merge pull request #8 from ceph/yuriw
- Added new dumpling-emperor-x upgrade suite
- 08:10 PM Revision f9d8c10c (ceph): removed leftover dirs again
- 07:32 PM Bug #6685 (Resolved): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- a9677e136ee4753b86ed1151ca6ff08e4b63473d
- 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...- 02:15 PM Bug #6685 (In Progress): osd/ReplicatedPG.cc: 8345: FAILED assert(0 == "erroneously present object")
- 07:31 PM Revision fee57a48 (ceph): removed one upgrade-sequence step and re-named the rest of steps
- 07:25 PM Revision 7e625d27 (ceph): Merge pull request #206 from ceph/wip-osd-debug
- schedule_suite: debug osd = 20 for the time being
- 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> - 06:20 PM Revision 084c6aed (ceph): Merge pull request #203 from ceph/wip-devstack
- Add devstack task
- 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... - 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.
- 05:40 PM Revision fd6f61d6 (ceph): removed unfinished stress-split suite from
- 05:30 PM Revision 8ba6a2b0 (ceph): removed obsolete suite from upgrades dir and added dumpling-emperor-x p...
- 05:23 PM Revision ca600a2e (ceph): Add unit test for task.devstack.parse_os_table()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 04:18 PM Revision 54116135 (ceph): Add debug output for reconnect() failures
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:57 PM Revision 05842e9f (ceph): Add explanations to asserts
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 03:43 PM Revision cfb7b948 (ceph): Guard against ctx.config being unset or None
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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...
- 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...
- 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
- 02:39 PM Messengers Bug #5508 (Can't reproduce): msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
- 02:38 PM Bug #6441 (Can't reproduce): msgr: leak of tls from delay thread
- 02:37 PM Bug #6575 (Can't reproduce): messenger: failed assert(pipes.count(p)) in reaper
- 02:37 PM Bug #6671 (Can't reproduce): FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
- 02:36 PM Bug #6636: sockaddr_storage and uuid_t are not portable to other platforms
- 02:35 PM Bug #6730 (Won't Fix): BUG: MAX_LOCKDEP_ENTRIES too low!
- 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...
- 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
- 02:33 PM Bug #6633 (Resolved): osd: pgls vs osd restart/peering race misses objects
- 02:32 PM Bug #6787: upstart is restarting daemons which we want to be dead
- 02:30 PM Bug #7120 (Need More Info): osd: EEXIST on mkcoll on dumpling
- 02:29 PM Bug #7170 (Can't reproduce): rados api test LibRadosMisc.CopyPP failed on next branch
- 02:29 PM Bug #7172 (Resolved): osd: OSD failed to start with osd_leveldb_cache_size > 0
- 02:29 PM Bug #7306 (Resolved): mon: bad boost::get: key val is not type std::string from HitSet* tests
- 02:28 PM Bug #7250 (Resolved): osd: string xattr comparison can have undefined behavior
- 02:28 PM Bug #7376 (In Progress): mon: >10s spent in remove_redundant_pg_temp
- 02:28 PM Bug #7345 (Can't reproduce): LibRadosTier.Evict failed in rados suite
- 02:24 PM Bug #7068 (Need More Info): os/FileStore.cc: 4035: FAILED assert(omap_attrs.size() == omap_aset.s...
- 02:21 PM Bug #7072: logrotate not sending HUP signal
- 02:20 PM Bug #7145 (Can't reproduce): PG::update_snap_map assert
- 02:19 PM Bug #7203 (Can't reproduce): osd/ReplicatedPG.cc: 9551: FAILED assert(r >= 0) in scan_range
- 02:18 PM Bug #7248: osd: bench set max size
- 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...
- 02:14 PM Bug #6003 (Need More Info): journal Unable to read past sequence 406 ...
- 02:13 PM Bug #7281 (Can't reproduce): osd: ... tried to pull ... but got ENOENT
- 02:13 PM Bug #7354 (Can't reproduce): osd: LibRadosTier.PromoteSnap failure
- 02:12 PM Bug #7393 (Need More Info): osd: scrub stat mismatch, got 9/9 objects, 0/0 clones, 9/4 dirty, 0/0...
- 02:12 PM Bug #7458: osd: stray pg ref on shutdown
- perhaps that pg work queue PGBackend implementation can use?
- 02:11 PM rbd Bug #7385 (In Progress): Objectcacher setting max object counts too low
- 02:10 PM Bug #7398 (Need More Info): osd: ERANGE from clone
- 02:09 PM Bug #7491 (In Progress): rados api crashes
- 02:09 PM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- 09:36 AM Bug #7506: osd/ECUtil.h: 117: FAILED assert(old_size == total_chunk_size)
- wip-7506
- 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... - 02:09 PM Bug #7494: EC filter read op bug
- 02:08 PM Bug #7496 (Need More Info): agent hit set crash: osd/ReplicatedPG.cc: 10579: FAILED assert(r >= 0)
- 02:08 PM Bug #7498 (Need More Info): stuck in recovery
- 02:08 PM Bug #7497 (Need More Info): timeout waiting to go clean
- 02:08 PM Bug #7495 (Need More Info): ENOTEMPTY on collection remove
- 01:58 PM Bug #7463: ceph-rest-api fails to start with no OSDs up
- Dan fixed in db88e7f385f4464f5f4de517845607391c314ef5
- 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...
- 11:57 AM Bug #7508: 2014-02-20T21:16:18.808 INFO:teuthology.task.rados.rados.0.err:[ubuntu@burnupi09.front...
- wip-7508
- 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... - 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 ... - 09:29 AM Bug #7367 (Closed): fail to run mds and mount rbd (v0.76)
- 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... - 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... - 08:30 AM CephFS Bug #7485 (Fix Under Review): Killing MDS during 'creating' breaks subsequent startup (no snaptable)
- 08:29 AM CephFS Bug #7485: Killing MDS during 'creating' breaks subsequent startup (no snaptable)
- https://github.com/ceph/ceph/pull/1283
- 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...- 07:12 AM devops Bug #7486: python-backports needs fixing for rhel
- 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> - 01:04 AM Revision 6c207286 (ceph): Merge remote-tracking branch 'upstream/next'
- 01:02 AM Revision 2bcddce8 (ceph): Merge remote-tracking branch 'upstream/wip-copyget' into next
- Fixes: #7471
Reviewed-by: Greg Farnum <greg@inktank.com> - 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. ...
- 12:01 AM Revision ba5d12f4 (ceph): Merge branch 'master' of github.com:ceph/ceph-qa-suite into yuriw
- 12:00 AM Revision c6e6ced1 (ceph): PG::build_might_have_unfound: skip CRUSH_ITEM_NONE
- Signed-off-by: Samuel Just <sam.just@inktank.com>
02/20/2014
- 11:51 PM Revision b92578e5 (ceph): Remove unused import
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision fdaaee57 (ceph): Source openrc before creating volume
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 11b60fef (ceph): Change usages of StringIO.read() to getvalue()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision f7b1d922 (ceph): Wait 30s for Keystone to start
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 830748a6 (ceph): Move external docs URLs
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision aecd98d7 (ceph): Fix incorrect exception name in docstring
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 11:46 PM Revision b638dc41 (ceph): Don't run the exercise subtask by default
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 27bad445 (ceph): Move restart_apache() to after the reboot
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 021f84ac (ceph): Simplify create_if_vm's downburst config logic
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 3dcde65c (ceph): Add note about memory requirements
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 1228ac88 (ceph): Add documentation to reboot()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 61e9ac4d (ceph): Move reboot() to teuthology.misc
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision e3f336d1 (ceph): Make reconnect() use Remote.reconnect()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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> - 11:46 PM Revision 85e63dd9 (ceph): Allow using different devstack branches
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 7c571274 (ceph): Forget about saving the exercise.sh log, for now
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 11:46 PM Revision 69beebc9 (ceph): get_file() returns a str, not a StringIO...
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision a2a5aed4 (ceph): Add Remote.hostname property
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 1c71558e (ceph): Add Remote.is_online property
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 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... - 11:46 PM Revision 22894969 (ceph): Use new init parameters for Remote
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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... - 11:46 PM Revision fe0aedf7 (ceph): Set apache ServerName, reboot, restart devstack
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision a1ed3d49 (ceph): Add logging calls to each helper function
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 1a0be5a0 (ceph): Tweaks to is_online and reconnect()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision a4bf1f8f (ceph): Actually call Remote.reconnect()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision e73df9c8 (ceph): Make rejoin-stack.sh start screen in detached mode
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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> - 11:46 PM Revision b6740480 (ceph): Copy ceph auth keys over to devstack node
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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.... - 11:46 PM Revision b40f5f74 (ceph): Add set_libvirt_secret() and split out other steps
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 76588e97 (ceph): Add update_devstack_config_files()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision cedd1283 (ceph): Split out key generation
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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> - 11:46 PM Revision f5006348 (ceph): Don't pass owner to copy_key()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision b474d282 (ceph): Fix typoed virsh call
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 119b438f (ceph): Call seek(0) on StringIO objects before reading
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision a55c22aa (ceph): Work around a bug in ConfigParser
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision 375d7ddd (ceph): Use ConfigParser.set() instead of update()
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 11:46 PM Revision dfe60526 (ceph): Add copy_file() to scp files between remotes
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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 ... - 11:46 PM Revision ed512568 (ceph): Fix linter errors.
- Signed-off-by: Zack Cerza <zack.cerza@inktank.com>
- 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>
- 10:56 PM Revision a3f6d9a6 (ceph): Merge pull request #201 from ceph/wip-6531-wusui
- Fix formatting and add docstrings to ceph_manager.py
- 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> - 10:51 PM Revision b4ce61cc (ceph): Add back in print in ceph_manager that the last checkin accidentally re...
- 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 ...
- 09:29 PM rgw Bug #7374: s3_multipart_upload.pl fails
- pull request is #1280 for wip branch wip-7374-wusui
- 09:22 PM rgw Bug #7374: s3_multipart_upload.pl fails
- This has been pushed in its own branch to wip-7374-wusui
- 09:28 PM rgw Bug #7375: s3_user_quota.pl fails
- Pull request is #1279 for wip branch wip-7375-wusui
- 09:21 PM rgw Bug #7375: s3_user_quota.pl fails
- this has been pushed in its own branch to wip-7375-wusui
- 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... - 05:47 PM Bug #7463 (Resolved): ceph-rest-api fails to start with no OSDs up
- 05:30 PM Revision 4a802cd5 (ceph): Merge pull request #7 from ceph/wip-upgrade
- upgrade: dumpling-next -> dumpling-x
- 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... - 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... - 05:19 PM Revision caf2edfc (ceph): rgw: minor cleanup
- Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 05:05 PM Bug #7471 (Resolved): ec pools copyfrom broken
- 05:01 PM Revision 1307ba9c (ceph): mds: Table read failure should log at error level
- Signed-off-by: John Spray <john.spray@inktank.com>
- 05:00 PM Revision a4d0eb1b (ceph): mds: Remove some unused #defines
- Signed-off-by: John Spray <john.spray@inktank.com>
- 05:00 PM Revision 2762ede7 (ceph): mds/CDir: Remove a few lines of cruft
- Signed-off-by: John Spray <john.spray@inktank.com>
- 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... - 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 ... - 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 ...
- 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... - 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:
... - 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
- 02:45 PM Bug #7497: timeout waiting to go clean
- We might just increase the timeout for rados bench runs.
- 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 ...
- 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...
- 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... - 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...
- 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... - 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... - 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... - 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... - 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...
- 09:49 AM rgw Feature #7467: Make radosgw work with multiple hostnames
- 09:20 AM rgw Bug #7346 (Resolved): An unfound object as part of multi-object delete should return deleted inst...
- 09:19 AM rgw Bug #7453 (Resolved): Authentication to keystone using rgw_keystone_admin_* failed
- actually, seems that the original code is post dumpling.
- 09:13 AM rgw Bug #7453 (Pending Backport): Authentication to keystone using rgw_keystone_admin_* failed
- Pushed, commit:5fb90a2f6dd5b31634efc748a977924dbdbebcb9
- 08:11 AM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
- New signed off patch
- 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... - 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... - 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"...
- 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 ... - 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...- 03:06 AM Revision c5c7f6c8 (ceph): Merge branch 'next'
- Conflicts:
src/test/admin_socket.cc
Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com> - 02:45 AM Bug #7367: fail to run mds and mount rbd (v0.76)
- yes, please
- 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 ... - 02:41 AM Revision ebd43972 (ceph): RadosModel: copyfrom should result in a dirty object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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... - 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> - 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>
- 01:31 AM Revision c337f638 (ceph): ReplicatedPG: fix stat uses to use the correct shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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> - 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> - 12:20 AM Revision fa96de9e (ceph): doc/release-notes: v0.67.7
- Signed-off-by: Sage Weil <sage@inktank.com>
02/19/2014
- 10:54 PM Revision 1bca9c5c (ceph): v0.77
- 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...
- 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... - 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... - 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
- 09:40 PM Revision 31c27e13 (ceph): Merge pull request #186 from ceph/wip-7369
- Fix #7369: "sed expression must be raw string"
- 09:40 PM Revision e5fe884e (ceph): Merge pull request #186 from ceph/wip-7369
- Fix #7369: "sed expression must be raw string"
- 09:37 PM Revision f3ac7870 (ceph): Fix syntax error in first docstring added.
- 09:34 PM Revision efd59a2a (ceph): Merge pull request #190 from kdreyer-inktank/jenkins
- add jenkins-pull-requests-build script
- 09:26 PM Revision a70e93fc (ceph): Merge pull request #199 from ceph/wip-6540-wusui
- Add docstrings. Fix formatting issues for rgw.py
- 09:26 PM Revision cc3d013e (ceph): Merge pull request #196 from ceph/wip-6541-wusui
- Fix docstrings in radosgw-admin-rest.py
- 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...
- 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
- 09:23 PM Revision 9f953d42 (ceph): Merge pull request #200 from ceph/wip-6532-wusui
- Fixed task/args.py docstrings.
- 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
- 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...
- 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... - 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... - 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... - 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... - 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... - 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... - 06:09 PM Revision d7ab4244 (ceph): v0.67.7
- Signed-off-by: Ken Dreyer <ken.dreyer@inktank.com>
- 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... - 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>
- 05:37 PM Revision 53b36898 (ceph): TestRados.cc: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 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>
- 05:32 PM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- aa110af991e6d637b30d740af46f3dc2168cde01
- 03:19 PM Bug #7482: primary affinity crash in OSDMap on osd
- wip-copyget
- 11:42 AM Bug #7482 (Resolved): primary affinity crash in OSDMap on osd
- 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>
- 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>
- 05:26 PM Revision 29c4abd8 (ceph): OSD: use !empty() instead of size() > 0
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:21 PM rgw Bug #7375 (Fix Under Review): s3_user_quota.pl fails
- 05:20 PM rgw Bug #7375: s3_user_quota.pl fails
- This is the same issue as 7374.
- 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.
- 05:21 PM rgw Bug #7374 (Fix Under Review): s3_multipart_upload.pl fails
- I have pushed a change for this.
- 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. - 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... - 05:09 PM Revision f23ab4af (ceph): RPCRecPred: use !empty() instead of size() >= 1
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 05:03 PM Revision 76c17239 (ceph): KeyValueStore: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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... - 04:59 PM Revision eaf66967 (ceph): DBObjectMap: use !empty() instead of size()
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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>
- 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... - 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>
- 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... - 04:07 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- The last call will end with abort()...
- 01:02 PM Bug #7423: erasure code: ./rados get retrieves a larger object
- ...
- 10:24 AM Bug #7423 (In Progress): erasure code: ./rados get retrieves a larger object
- 06:00 AM Bug #7423: erasure code: ./rados get retrieves a larger object
- crashes on master as of today
- 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>
- 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]: ... - 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... - 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>
- 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... - 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... - 02:40 PM Bug #7471: ec pools copyfrom broken
- wip-copyget
- 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>
- 02:15 PM Bug #7481 (Resolved): stuck creating, ec pool, primary affinity
- 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...
- 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... - 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>
- 02:02 PM Revision 4adcfa59 (ceph): BarrierContext: reduce scope of 'done' variable
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 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... - 01:40 PM rgw Feature #4715 (Resolved): rgw: Add support for OPTIONS HTTP method
- This is already done (CORS).
- 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...
- 01:34 PM rgw Bug #5843 (Won't Fix): swift api: x-container-meta-{key} should not be allowed on an object
- 01:33 PM rgw Tasks #5121 (Closed): bump up librados version
- Closing this one.
- 01:33 PM rgw Feature #5506 (Resolved): rgw: use Keystone to authenticate S3 requests
- Done by Roald van Loon, commit:a200e184b15a03a4ca382e94caf01efb41cb9db7
- 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
- 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...
- 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...
- 01:26 PM rgw Bug #6733 (Closed): rgw readwrite test fails on next branch
- There's a good chance that this was #7030. Closing.
- 01:24 PM rgw Feature #4365 (Resolved): rgw: allow setting wildcard keystone role
- This was merged long ago, commit:8078e9684e7200db582cab02e0bf5ead557133dd
- 01:05 PM rgw Bug #7453: Authentication to keystone using rgw_keystone_admin_* failed
- Fix looks fine to me. Can you sign-off it?
- 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. ...
- 10:21 AM rgw Bug #6936 (Fix Under Review): radosgw-admin allows same user to be created multiple times
- 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...
- 10:11 AM rgw Bug #7099 (Fix Under Review): Strange Comportments with media files
- 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
... - 08:27 AM rgw Bug #6830 (Fix Under Review): S3 CompleteMultipartUploadResult has empty ETag element
- 08:08 AM rgw Bug #6951 (Fix Under Review): rgw: bucket re-create fails when cache is disabled
- 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... - 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.
- 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... - 06:11 AM Feature #7360: When EC ready add back test.sh test case for "mon: OSDMonitor: do not allow changi...
- crashes, investigating why
- 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> - 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
- 05:05 AM Revision 0af73755 (ceph): osd/ReplicatedPG: strengthen agent_work assertions
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 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> - 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).
- 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... - 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> - 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...
- 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. ...
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... - 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> - 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> - 11:07 PM CephFS Bug #6608: samba teuthology dbench failure
- still see the issue ?
- 10:21 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:15 PM Bug #7470: ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- 04:13 PM Bug #7470 (Resolved): ReplicatedPG:2110 assert(!is_actingbackfill(*p));
- wip-strays
- 09:49 PM Revision b9e1341f (ceph): rados/thrash: add ec-radosbench workload
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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> - 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> - 09:19 PM Revision e3715652 (ceph): task/: add ec_pool and append to rados.py
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:19 PM Revision 2718dbc3 (ceph): radosbench: simplify pool creation and add ec_pool support
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 09:11 PM Revision 3fb6e258 (ceph): test/rgw: manifest unitest
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 09:11 PM Revision b3ce1889 (ceph): cls/rgw: fix debug output
- print the correct error value
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 09:11 PM Revision 19754413 (ceph): dencoder: fix for new rgw manifest code
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 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... - 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> - 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... - 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... - 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 ... - 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... - 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... - 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.
... - 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... - 08:34 PM Revision 7a760337 (ceph): packaging: add test programs for librados c object operations
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 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>
- 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... - 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... - 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... - 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... - 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... - 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.
... - 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... - 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:... - 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>
- 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> - 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... - 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... - 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... - 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... - 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.
... - 08:34 PM Revision 50ca88a1 (ceph): librados: add some comments about constants in librados.h
- Signed-off-by: Josh Durgin <josh.durgin@inktank.com>
- 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... - 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... - 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... - 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 ... - 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... - 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.
... - 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... - 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... - 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> - 07:48 PM Bug #7469 (Resolved): ENXIO on ec pool write
- 1d907c60d7628429292917fbabf61d09ef8dfa6f
- 04:15 PM Bug #7469: ENXIO on ec pool write
- 04:12 PM Bug #7469 (Resolved): ENXIO on ec pool write
- testing wip-primary
- 07:45 PM rgw Bug #7374: s3_multipart_upload.pl fails
- Stopping the teuthology run and running the commands manually reveals the following:...
- 06:56 PM Revision 43b5cf97 (ceph): Merge remote-tracking branch 'upstream/wip-ecbackend-for-review'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 06:40 PM rgw Bug #7064 (Fix Under Review): S3 request to non-existent object in non-existent bucket results in...
- 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:...
- 12:54 PM rbd Bug #6480 (Can't reproduce): librbd crashed qemu-system-x86_64
- 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> - 04:18 PM Bug #7471 (Resolved): ec pools copyfrom broken
- 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.
- 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-... - 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... - 03:46 PM rgw Feature #6677 (Resolved): rgw: add compatibility for MultipartUpload
- Fixed, commit:5a44e178e4e5503c9edf0da15a6b4ec968d1184d
- 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...
- 02:47 PM Revision 4c930a0a (ceph): Revert "Capture stderr and include in CommandFailedError"
- This reverts commit d0a434923100dd16548e5f76eaffa5462c4b91d4.
- 02:39 PM rgw Bug #7271 (Fix Under Review): container create via swift doesn't register ACL
- 09:32 AM rgw Bug #7271: container create via swift doesn't register ACL
- 02:30 PM rbd Bug #7466 (Resolved): rbd: timeout error not exposed in python bindings
- commit:609f4c56718d8279895b02b8163bbe1976c02bfb
- 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.
- 01:18 PM rgw Feature #6339 (Resolved): rgw: compact manifest data
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 01:17 PM rgw Feature #6338 (Resolved): rgw: better manifest scaling
- Merged, commit:c5d3bdf7fa23990171024cc0a4480d50a3951f41
- 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:...
- 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... - 12:55 PM rbd Bug #5488 (Need More Info): librbd: deadlock in image refresh
- 12:54 PM Revision c93f14f2 (ceph): filestore_idempotent: filestore -> objectstore path change
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:53 PM rbd Bug #5876 (New): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->n...
- 12:52 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 12:51 PM Revision 150e87a1 (ceph): osd: l_osd_tier_whiteout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision dbec1096 (ceph): osd: l_osd_tier_[dirty|clean]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision d1a185bd (ceph): osd: l_osd_agent_{wake,skip,flush,evict}
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 4bee6ff1 (ceph): osd/ReplicatedPG: clean up agent skip debug output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 4b0a0a10 (ceph): osd: l_osd_copyfrom
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision c45a477e (ceph): osd: l_osd_tier_[try_]flush[_fail]
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:51 PM Revision 2d5371dd (ceph): osd: l_osd_tier_evict
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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:...
- 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
- 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.
- 12:36 PM Fix #7394 (Resolved): OSD: relax monitor ping requirements while connecting
- Merged into master in commit:393a202198fbe67e7c4456d18c19fdef29305b5e
- 11:02 AM Feature #7149 (Resolved): EC: missing_loc should be maintained until the object is no longer degr...
- 11:01 AM Feature #7149 (Closed): EC: missing_loc should be maintained until the object is no longer degraded
- 11:00 AM Feature #7149: EC: missing_loc should be maintained until the object is no longer degraded
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7246 (Resolved): EC: maintain missing_loc for objects missing anywhere in acting set
- 11:00 AM Feature #7246: EC: maintain missing_loc for objects missing anywhere in acting set
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:01 AM Feature #7366 (Resolved): EC: scrubbing
- 11:01 AM Feature #7366: EC: scrubbing
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 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
- 11:00 AM Feature #7247 (Resolved): EC: distinguish is_missing from is_readable
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5995 (Resolved): EC: [link] Getinfo should use PGBackend methods to determine when peeri...
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #5999 (Resolved): EC: [link] OSD internals must work in terms of cpg_t
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6438 (Resolved): EC: implement EC client IO
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 11:00 AM Feature #6437 (Resolved): EC: implement ECBackend recovery
- 43b5cf977cd93bd5ee811491c4728701fa1a3ae2
- 09:31 AM rgw Bug #7336 (Resolved): rgw: limit on list buckets broken
- Fixed, commit:04b1ae466e280568656f8effb031b01505077c6b
- 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.
- 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... - 04:12 AM Revision 11f288e5 (ceph): Objecter: track primary explicitly to detect changing primaries
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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>
- 04:12 AM Revision 7772014a (ceph): OSD,PG: pass through EC messages
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision ae827cfe (ceph): osd_types: add swap, claim_append to ObjectModDesc
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 258af5eb (ceph): buffer: allow caller to initialize bufferhash state
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 7731a949 (ceph): ObjectStore: add bufferlist/string getattr
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 33c38301 (ceph): osd/ECUtil: add ec encode/decode util helpers
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 45b6c59e (ceph): osd/ECTransaction: add type encapsulating EC transaction
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 792f0a85 (ceph): ECBackend: flesh out ECBackend implementation
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision b90584a8 (ceph): osd/: instantiate the right backend based on pool
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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>
- 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> - 04:12 AM Revision 1835c29f (ceph): ReplicatedBackend: factor out be_deep-scrub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 26745ca8 (ceph): PGBackend/ReplicatedBackend: move the backend agnostic code into PGBack...
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 510585b7 (ceph): PGBackend/ReplicatedBackend: factor out logical to ondisk size mapping
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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> - 04:12 AM Revision e8820ac4 (ceph): src/osd/: add ECBackend stubs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 6cd64a50 (ceph): messages,osd: add EC messages and associated types
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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>
- 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>
- 04:12 AM Revision 74b8a0c0 (ceph): PG,PGBackend: expose acting and backfill_targets
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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
... - 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 ... - 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 ... - 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.... - 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>
- 04:12 AM Revision 285cf772 (ceph): PG: introduce calc_ec_acting
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 109b3c9e (ceph): OSDMap: fill in get_primary_shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:12 AM Revision 904704ac (ceph): OSDMap: handle CRUSH_ITEM_NONE in acting sets
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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... - 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> - 04:11 AM Revision 761f0b1e (ceph): PGBackend: use whoami_shard().shard in rollback*, objects*
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 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... - 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 ... - 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>
- 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>
- 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... - 04:11 AM Revision 44b43df4 (ceph): ObjectStore: use ghobject_t for setattrs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 04:11 AM Revision 4a259516 (ceph): osd_types: introduce spg_t, pg_shard_t
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 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... - 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... - 12:26 AM Revision e6a1122b (ceph): osd: l_osd_tier_promote
- Signed-off-by: Sage Weil <sage@inktank.com>
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...
- 11:15 PM Revision 5bc92ece (ceph): Merge pull request #1128 from ceph/wip-dirfrags
- Fixes for mds cluster + directory fragments
- 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... - 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... - 10:25 PM Revision 0e7b10ac (ceph): PG::remove_snap_mapped_object: use pg_whoami.shard
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 10:24 PM Revision 13a41e14 (ceph): FileStore: permit NULL onreadable callback
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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>
- 10:24 PM Revision b3b2bab4 (ceph): ReplicatedPG: handle xattr cache on rollback and delete_head
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 17e6ecc8 (ceph): ReplicatedPG: find_object_context debugging: output oi
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision f020ce90 (ceph): ReplicatedPG:: remove_snap_mapped_object already removes the object
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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... - 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... - 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> - 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> - 10:24 PM Revision 211fc4e1 (ceph): librados: add calls to expose required write alignment
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision e0b05085 (ceph): ReplicatedPG: reject unaligned writes on ec pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 541a7e27 (ceph): TestRados: send aligned appends on erasure pools
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 06ec9bd4 (ceph): ObjectStore: fix OP_COLL_ADD dump output
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 10:24 PM Revision 44f5d4de (ceph): ErasureCodeJerasure: fix alignement issues in encode/decode
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 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> - 10:04 PM Revision 749bf40f (ceph): iozone: kill empty suite
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 09:16 PM Revision 3d0ce693 (ceph): thrashosds: allow primary-affinity thrashing to be disabled
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:07 PM Revision bd8fcd25 (ceph): osd: improve whiteout debug prints
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:07 PM Revision 79976466 (ceph): ReplicatedBackend: print char ack_type as int
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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... - 07:09 PM Revision 62532fb0 (ceph): Merge pull request #1254 from ceph/wip-barrier
- libcephfs: disable barriers for now
- 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... - 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.
... - 06:23 PM Revision 747002c6 (ceph): client: fix barrier interval
- (start, end) not (start, length)
Signed-off-by: Sage Weil <sage@inktank.com> - 06:16 PM Revision d7457f73 (ceph): client/barrier: drop unused active_commit_interval
- Signed-off-by: Sage Weil <sage@inktank.com>
- 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> - 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.
... - 03:44 PM Bug #7458: osd: stray pg ref on shutdown
- 03:42 PM Bug #7458 (Resolved): osd: stray pg ref on shutdown
- ...
- 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... - 02:39 PM Feature #7457 (Resolved): mon: prevent addition of non-empty pools as a tier
- 02:15 PM RADOS Feature #7456 (New): osd: agent: measure temperature
- 02:14 PM Feature #7035 (Resolved): cachepool: agent: blocking eviction (when cache pool is 'full')
- 02:14 PM Feature #7033 (Resolved): cachepool: agent: trivial flushing
- 02:14 PM Feature #7034 (Resolved): cachepool: agent: basic eviction
- 02:13 PM Feature #7441 (Fix Under Review): osd: perfcounters for cache events and agent events
- 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...
- 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=...
- 01:35 PM Bug #6313 (Can't reproduce): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- 01:34 PM CephFS Bug #7373 (Resolved): kcephfs nfs file create failes with EOPNOTSUPP
- 01:33 PM rbd Bug #7418 (Duplicate): f7cf25f2 is causing KVM processes to use excessive memory
- reopened #7385
- 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... - 01:32 PM rbd Bug #7385: Objectcacher setting max object counts too low
- 01:17 PM rbd Feature #7455 (Resolved): krbd,kcephfs: support primary-affinity
- when this is complete, be sure to fix ceph-qa-suite.git
- 11:08 AM Bug #7212 (Pending Backport): monitor fails to start
- 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, ...
- 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... - 07:32 AM CephFS Bug #7424: Cannot read from zero-length file
- * Strange that it worked without permission. Where had it stored the data?
- 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... - 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.
- 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...
- 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... - 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... - 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...
- 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...
- 05:23 AM Revision 623748e5 (ceph): mds: bump the protocol version
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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> - 01:37 AM Revision e5457dfb (ceph): mds: open sessions for rejoin imported caps
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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 ... - 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 (... - 01:37 AM Revision 305d16f3 (ceph): mds: handle frag mismatch for cache rejoin weak
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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... - 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... - 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... - 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... - 01:37 AM Revision 98105b24 (ceph): mds: preserve dir_auth when spliting/merging dirfrags
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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... - 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... - 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... - 01:37 AM Revision 5b1de69a (ceph): mds: force fragment subtree bounds when replaying ESubtreeMap
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 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... - 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... - 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... - 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... - 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... - 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.... - 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> - 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... - 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... - 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... - 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 ... - 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 ... - 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... - 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... - 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... - 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... - 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 ... - 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...
Also available in: Atom