Activity
From 08/28/2013 to 09/26/2013
09/26/2013
- 11:23 PM Revision 60017e07 (ceph): Merge pull request #646 from liewegas/wip-6385
- qa/run_xfstests.sh: use old xfstests until we adapt to new org
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:21 PM Revision beb36630 (ceph): Revert "ceph: parse CEPH_ARGS environment variable"
- This reverts commit 67a95b9880c9bc6e858150352318d68d64ed74ad.
We now put CEPH_ARGS in the actual args we parse in py... - 11:20 PM Revision b475ff95 (ceph): Add CEPH_ARGS at the end of sys.argv
- This allows, for instance, to pass a different client name to ceph by
exporting CEPH_ARGS="--id client_id".
Signed-o... - 11:17 PM Revision 86cd7e92 (ceph): Merge pull request #647 from ceph/wip-ceph-cli-env
- improve ceph clie CEPH_ARGS handling
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 11:12 PM Bug #6422 (Fix Under Review): write_superblock() and write_version_stamp() not safe
- 02:08 PM Bug #6422 (Resolved): write_superblock() and write_version_stamp() not safe
- These function truncate the file before re-writing it. A crash could leave an empty file.
- 11:06 PM Revision 30abe324 (ceph): Add CEPH_ARGS at the end of sys.argv
- This allows, for instance, to pass a different client name to ceph by
exporting CEPH_ARGS="--id client_id".
Signed-o... - 11:06 PM Revision 97f462be (ceph): Revert "ceph: parse CEPH_ARGS environment variable"
- This reverts commit 67a95b9880c9bc6e858150352318d68d64ed74ad.
We now put CEPH_ARGS in the actual args we parse in py... - 10:17 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- With both those suggestions implemented, the output looks like this:...
- 03:53 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Yeah, it's not the best message. Maybe we should special case the 'saw 0 expected 1' case to something more intellig...
- 11:23 AM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Yeah, that would probably be good. It's clearly gotten to the point that it knows what command it's looking at, but w...
- 11:14 AM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- Not sure what you'd want to happen here; the "semantic reason for the failure of the command" is a bit of a stretch. ...
- 10:02 PM Revision cbf0ba22 (ceph): qa/run_xfstests.sh: use old xfstests until we adapt to new org
- Tests were rearranged upstream; use an old version for the time being
until we can refactor run_xfstests.sh to cope. ... - 09:26 PM Revision bab72ed3 (ceph): os: Simplify collection_list* funcs by removing dynamic_cast
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 09:07 PM Revision db5bbdd0 (ceph): rgw: quota utility class
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 08:37 PM Revision 2acceef6 (ceph): valgrind: suppress inet_ntop noise
- See #6240
Signed-off-by: Sage Weil <sage@inktank.com> - 08:12 PM Revision b5a39787 (ceph): Merge pull request #645 from liewegas/wip-6346
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 07:10 PM Revision a2f85115 (ceph): Merge pull request #114 from ceph/wip-linter
- Fix lots of linter errors
- 07:03 PM Revision 21765ce4 (ceph): Move 'import os' to inside main()
- This is necessary because of the monkey-patching.
- 07:02 PM Revision 962a9ae2 (ceph): Add '# noqa' to suppress a linter error
- Fixing this would require some more significant changes... and tempt me
with rewriting every module in the directory.... - 07:02 PM Revision 622ce111 (ceph): Don't redefine variable
- (cherry picked from commit 083717c1b4022289806030faf23ff7c4aa371f19)
- 07:01 PM Revision 8a11e4d0 (ceph): Remove unused variables
- (cherry picked from commit 581b6b3e977b99fc58fe25e66c933c65e38dc87c)
- 07:01 PM Revision 84974370 (ceph): Remove unused imports
- (cherry picked from commit 586817481119c4fc4a39f8804e7871a43491e01f)
- 07:01 PM Revision 97c56ef3 (ceph): Merge pull request #631 from ceph/wip-5857-8
- Wip 5857 8
Reviewed-by: Sage Weil <sage@inktank.com> - 07:01 PM Revision a2c9bdc7 (ceph): Fix undefined name errors
- (cherry picked from commit f59497ef2214f29d5995435d83766c7994e8f2cd)
- 07:00 PM Revision 62626b49 (ceph): Merge pull request #546 from ceph/wip-5862
- Wip 5862
Reviewed-by: Samuel Just <sam.just@inktank.com> - 07:00 PM Revision b301a741 (ceph): Make teuthology.locker a module
- 06:59 PM Revision cb3b563e (ceph): Add missing requirement: web.py
- (cherry picked from commit 1b3349525c361d4253f76729f8416ac6d9029289)
- 06:59 PM Revision fb5c3681 (ceph): add flake8 checks to teuthology
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
(cherry picked from commit 27c9eb8f81dc25c7b50bfb77d4d2d4ab4d1... - 06:35 PM Bug #6425 (Resolved): ceph cli: EntityAddr validation presumes presence of nonce; not required
- 06:07 PM Bug #6425 (Fix Under Review): ceph cli: EntityAddr validation presumes presence of nonce; not req...
- https://github.com/ceph/ceph/pull/648
- 04:51 PM Bug #6425 (Resolved): ceph cli: EntityAddr validation presumes presence of nonce; not required
- Mandell Degerness notices that ceph osd blacklist rm <ip> no longer works; the Python validator
is assuming that arg... - 06:29 PM Revision aba6efda (ceph): common, os, osd, test, tools: FileStore must work with ghobjects rather...
- Add ghobject_t to hboject.h header
Add constants NO_SHARD/NO_GEN and change gen_t/shard_t
Convert other headers from ... - 06:29 PM Revision 222f5aa6 (ceph): osd: Cleanup init()/read_superblock()
- Fix error handling in init()
Cleanup read_superblock() by moving unrelated code into init()
Move init() feature upgra... - 06:29 PM Revision 4a757eb8 (ceph): os/ObjectStore: Interim collection_list* functions in ObjectStore
- Handle ghobject_t to hobject_t conv of collection_list* funcs
Temporary code so that this branch doesn't break master... - 06:29 PM Revision 55f4aa19 (ceph): osd: Remove code for reading ancient unsupported logs
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:29 PM Revision 9750965f (ceph): os: Make write_version_stamp() private
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:29 PM Revision c6b83180 (ceph): os, osd, tools: Add backportable compatibility checking for sharded obj...
- OSD
New CEPH_OSD_FEATURE_INCOMPAT_SHARDS
FileStore
NEW CEPH_FS_FEATURE_INCOMPAT_SHARDS
Add FSSuperblock with fe... - 06:29 PM Revision 793ba9f1 (ceph): include, test: Add CompatSet::merge() operation
- New func merge() adds missing features from specified CompatSet
Add merge testing to unittest
Signed-off-by: David Z... - 06:24 PM Revision acc47d23 (ceph): include: Bug fixes for CompatSet
- FeatureSet insert/remove
Use 64-bit arithmetic to allow features past 31
Allow feature 63 by fixing assert in ins... - 06:24 PM Revision 4bc8f09f (ceph): test: Adding unittest for CompatSet
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:24 PM Revision bb195c24 (ceph): osd: read_superblock() not outputing unsupported features when incompat...
- Use working version of CompatSet::unsupported() to improve log output
Backport: dumpling, cuttlefish
Signed-off-by:... - 06:24 PM Revision 98b3cd3a (ceph): os: Fix version_stamp_is_valid() and write_version_stamp() error return
- Caused by 341fb208aa32117f58ed4ce623f4b152f64ac72e
Signed-off-by: David Zafman <david.zafman@inktank.com> - 06:24 PM Revision a1f6b14e (ceph): ReplicatedPG: take obc read lock prior to recovering an object to replicas
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision b06dce3b (ceph): ReplicatedPG/Backend: fix up recalc_subsets
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 02e5c1fc (ceph): ReplicatedPG: correctly handle backfill
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 039da62f (ceph): ReplicatedPG: don't proceed to backfill until recovering is empty
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 32900653 (ceph): OSD,ReplicatedPG: queue pushes in a op_tp workqueue
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision aeadecda (ceph): ReplicatedPG.h: remove temp_coll stub
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 2bc1e38c (ceph): ReplicatedPG: assert build_push_op succeeds on primary
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 07905af8 (ceph): ReplicatedPG: remove noop C_OSD_CompletedPull
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision b29ac2ad (ceph): ReplicatedBackend::handle_pull_response: use list<ObjectContextRef>
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 273ac2b4 (ceph): ReplicatedPG/Backend: shuffle over submit_push_*/build_push_op
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 4bc0eab1 (ceph): ReplicatedPG/Backend: split recover_missing out of prepare_pull
- Also, move prepare_pull to PGBackend.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:24 PM Revision 31c60422 (ceph): ReplicatedPG/Backend: handle down pull sources
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 3d6eb6ea (ceph): ReplicatedPG: remove pushing/pulling
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 9e8c3c3d (ceph): ReplicatedPG/Backend: move prep_push and friends to ReplicatedBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision e7a0b234 (ceph): ReplicatedBackend: remove priority from Pull/PushInfo
- Instead, we'll just nab the priority from the messages.
Signed-off-by: Samuel Just <sam.just@inktank.com> - 06:24 PM Revision 656d084d (ceph): ReplicatedBackend: track object contexts in Push/PullInfo
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision a287167c (ceph): ReplicatedBackend: handle stats properly
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 6cccef2d (ceph): ReplicatedBackend: wire in start_pushes
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision d53fc899 (ceph): ReplicatedPG/Backend: shuffle sub_op_push_reply
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 0e16230f (ceph): ReplicatedPG: make log_subop_stats static
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 8daaeba3 (ceph): ReplicatedPG/Backend: convert sub_op_pull
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 3e734722 (ceph): ReplicatedPG/Backend: move _do_push,_do_pull_response,do_push
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 666a316d (ceph): ReplicatedPG/Backend: shuffle do_pull/do_push_reply
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision f9810797 (ceph): ReplicatedPG/Backend: move handle_*
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision c1c2debd (ceph): ReplicatedPG/Backend: move over _failed_push
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision fea30f5b (ceph): ReplicatedPG/Backend: move over send_pushes/send_pulls/prep_push_op_blank
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 62a1eb6f (ceph): osd/: add PGBackend interfaces and stubs
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 138ccbee (ceph): OSD,ReplicatedPG: let PGBackend handle the temp collection
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 30ac934e (ceph): ReplicatedPG: pass on dump_recovery_info to PGBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 3148b121 (ceph): PG,ReplicatedPG: handle do_request in ReplicatedPG,PGBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 7da308bb (ceph): ReplicatedPG: extract PGBackend::Listener recovery callbacks
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 087f708b (ceph): osd/: allow dout for ReplicatedBackend methods to work in ReplicatedPG.cc
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision 8d447be1 (ceph): ReplicatedPG/Backend: shuffle sub_op_push over to ReplicatedBackend
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:24 PM Revision f94e6a30 (ceph): ReplicatedPG: Allow get_object_context caller to provide attributes
- This will be used by PGBackend implementers to get the SnapSet
and ObjectInfo for newly recovered objects on the prim... - 06:21 PM Revision de4cc871 (ceph): FileStore: ping tphandle between each operation within a transaction
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:21 PM Revision 5b7fa627 (ceph): ReplicatedPG: send_push is unused
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 06:21 PM Revision 5f44a949 (ceph): WorkQueue: add a workqueue which simply runs queued GenContexts
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 05:42 PM Revision 2b152e2b (ceph): Merge pull request #644 from ceph/wip-6345
- reverse the order of the mons in the init script when stopping
Reviewed-by: Sage Weil <sage@inktank.com> - 05:38 PM Revision 179001b4 (ceph): osd/ReplicatedPG: fix bl resize on write vs truncate race
- If we resize the write due to the funky truncate behavior, we need to
resize the bufferlist to match.
Fixes: #6346
S... - 05:30 PM Revision 881309db (ceph): Merge pull request #606 from ceph/wip-6332
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:27 PM Revision bd0f29a2 (ceph): mon: OSDMonitor: do not write full_latest during trim
- On commit 81983bab we patched OSDMonitor::update_from_paxos() such that we
write the latest full map version to 'full... - 05:23 PM Revision 6b435f5d (ceph): mon: don't list "--yes-i-really-mean-it" options as required
- By default options are required, and that leads to the Ceph CLI making
users add this to their commands before even s... - 05:21 PM Revision 89482cac (ceph): Merge remote-tracking branch 'gh/next'
- 05:10 PM Revision 9d5b724a (ceph): do not quote the variable to loop over
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 04:51 PM Revision f45675c2 (ceph): msg/msg_types: use proper NI_MAXSERV when formatting an IP address
- May as well be pedantic about it, even though we are leaving the port
in numeric form.
Signed-off-by: Sage Weil <sag... - 04:49 PM Revision 5584b371 (ceph): reverse the order of the mons in the init script when stopping
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 04:27 PM Revision ca97fae8 (ceph): qa: update snaps workunits for allow_new_snaps flag
- Test that it works in snaptest-0.sh, and set the flag in
all the snap workunits so they continue to function.
Signed... - 04:26 PM Revision 9771b1d5 (ceph): MDS: lock out snapshots until after a flag has been set in the MDSMap
- This way users can't put snapshots on their clusters unless they explicitly
ask for them and have seen a warning mess... - 04:14 PM Revision b1441705 (ceph): mds: properly return log replay error
- The only context that should see this is
C_MDS_BootStart, and it is prepared for failures,
so there's no reason to al... - 04:09 PM Revision 1d67aeba (ceph): common/crc32c_intel_fast: fix compile-time #ifdef
- This wasn't getting built in!
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.co... - 03:05 PM Bug #6424: ceph cli: -o failure to open gives backtrace, not error message
- 03:04 PM Bug #6424 (Resolved): ceph cli: -o failure to open gives backtrace, not error message
- Apparently the "can't open output file" path is not quite right:...
- 02:59 PM rbd Bug #6386: ceph-osd processes are having hang tasks
- I would try whatever kernel ubuntu has for precise that is > 3.8... not sure offhand what they have. If nothing else...
- 03:08 AM rbd Bug #6386: ceph-osd processes are having hang tasks
- Let me clarify the previous message. It happened once, but the hang tasks happened on many osds, not just on one. I'v...
- 03:05 AM rbd Bug #6386: ceph-osd processes are having hang tasks
- Sage,
I've seen this once on ceph 0.67.3. However, I've upgraded from 0.61.7 about 3 weeks ago and this happened o... - 02:47 PM Feature #6423 (Resolved): ceph-deploy should log command line args to logfile
- In order to help improve reading the log after the fact, ceph-deploy should log the command line args to the ./{clust...
- 02:06 PM Bug #6381: need apache-fastcgi packages built for fedora and debian
- we may need to rebuild apache-fastcgi packages for centos and rhel as well....
- 02:01 PM Subtask #5862 (Resolved): FileStore must work with ghobjects rather than hobjects
- Pull request #546
aba6efda13eb6ab4b96930e9cc2dbddebbe03f26 - 01:48 PM rgw Bug #6302 (Resolved): rgw: tasks/rgw_s3tests_multiregion.yaml tests hang
- 01:39 PM rgw Bug #6240 (Resolved): rgw: invalid read on addr in msgr via objecter
- pushed valgrind suppressions to all relevant teuthology.git branches
- 01:22 PM RADOS Feature #6421 (New): FileStore: Op unit tests
- I asked if zero-length writes to the FileStore actually worked, and Sage suggested adding some unit tests for that ki...
- 01:14 PM devops Feature #6310 (In Progress): Get Dumpling into CentOS Ceph repo
- 67.3 builds under mock on centos
- 01:13 PM Messengers Feature #6420 (New): buffer: make writemsg use splice where possible
- 01:13 PM Bug #6346 (Resolved): OSD: do not crash on bad client op input
- Merged commit:179001b42c142e0877e6c4991f88e7355c9b82ff into next via commit:b5a3978728d9435a543c00bb718f6e02438285c7
- 01:13 PM Feature #6419 (Resolved): buffer: make write_fd use splice where possible
- 01:13 PM Messengers Feature #6418 (New): buffer: make readmsg use raw_pipe where possible
- 01:12 PM Feature #6417 (Resolved): buffer: make read use raw_pipe() where possible
- 01:12 PM Feature #6416 (Resolved): buffer: create raw_pipe class; convert to buffer if inspected
- 01:11 PM Feature #6415 (Resolved): buffer: instrument c_ptr() calls
- 01:11 PM Feature #6414 (Rejected): filestore: make read() use a bufferlist method
- 01:10 PM devops Feature #6020: radosgw-apache opinionated package
- 01:09 PM Messengers Feature #6413 (New): msgr: move readmsg() into bufferlist; refactor read_message()
- 01:07 PM Messengers Feature #6412 (New): msgr: remove old rx_buffers functionality
- 01:02 PM Messengers Feature #6411 (New): msgr: move iov + sendmsg into bufferlist::sendmsg method
- ...
- 12:57 PM devops Bug #6410 (Resolved): support older version of ceph for mon_status commands
- All the `mon_status` commands that are currently implemented for dumpling versions of Ceph.
This can totally work ... - 12:56 PM Feature #6409 (Resolved): buffer: cache crc values
- 12:56 PM Feature #6408 (Resolved): crc: unit test demonstrating crc for concatenation of string
- 12:36 PM Revision fdf50dbc (ceph): Merge pull request #111 from ceph/wip-missing-packages
- If we're scheduling for non-ubuntu, look for rpms
- 12:02 PM Feature #5993 (Resolved): EC: [link] Refactor recovery to use PGBackend methods
- 12:02 PM Feature #5998 (Resolved): EC: [link] FileStore must work with ghobjects rather than hobjects
- 11:30 AM devops Bug #6345 (Resolved): order of init.d script shutdown sequence
- 10:44 AM Bug #6378 (Pending Backport): mon: osdmap crc mismatch during scrub
- 10:31 AM CephFS Bug #6399 (Resolved): snaptest-0.sh fails
- In master, commit:3cffff2a1abd266abbbc97effd73b79695d29682
- 09:34 AM CephFS Bug #6399 (Fix Under Review): snaptest-0.sh fails
- 09:47 AM Revision a65a8678 (ceph): autoconf: fix build out of tree
- so that the following works:
git clone git@github.com:ceph/ceph.git
cd ceph
./autogen.sh
mkdir ../build
cd ../build
... - 08:27 AM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- /a/teuthology-2013-09-20_23:01:15-fs-master-testing-basic-plana/8560
All these archive dirs we reference here are ... - 07:35 AM rgw Bug #6397 (Fix Under Review): rgw: valgrind issue
- 03:42 AM Revision 7147ef7f (ceph): Merge pull request #632 from ceph/wip-rworder
- fix up read vs write ordering flags; make ceph_test_rados use it
Reviewed-by: Greg Farnum <greg@inktank.com> - 03:08 AM Tasks #4321 (Resolved): unit tests for FileStore::_detect_fs
- A new ticket can be created when there is an incentive to keep working on this topic. When and if someone find the mo...
- 03:06 AM Documentation #5058 (Resolved): docs/master/dev/osd_internals updates
- This has been transformed into an ongoing update process with no designated issue to track progress.
- 03:02 AM Feature #6274 (Resolved): mon: MonCommand.h unit tests
- 02:18 AM Revision fde0f864 (ceph): Context: add GenContext templated on the callback argument
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 12:08 AM Revision 3cffff2a (ceph): mds/Server: fix LOOKUPSNAP
- The current LOOKUPSNAP code path was dereferencing mdr->dn[0] and getting
SEGV. Instead, set the do_lookup arg to fa...
09/25/2013
- 11:51 PM Revision fedbf353 (ceph): added v0.67.2 to upgrade-dumpling suite
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 11:49 PM Revision eda807e0 (ceph): common/bloom_filter: make mode match formatting
- 3 space tabs.. blech. Let's not change it now, though.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:49 PM Revision 8dcdeb2e (ceph): common/bloom_filter: make optimal parameter calculation static
- We pass the ctor our target behavior and calculate parameters based on
that. Avoid storing the target behavior, and ... - 11:49 PM Revision 9df9155c (ceph): common/bloom_filter: make bloom_filter encodable
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:49 PM Revision 12aa53cc (ceph): common/bloom_filter: move header from include/
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:43 PM CephFS Bug #6396: mds: recovery hits assert(!segment.empty()) when reissuing caps
- where to get the mds log? (I can access your lab now)
- 01:06 PM CephFS Bug #6396 (Resolved): mds: recovery hits assert(!segment.empty()) when reissuing caps
- ...
- 11:08 PM Revision 52c7f279 (ceph): Merge pull request #640 from ceph/wip-mon-pgmap
- fix mon crash when osdmap and pgmap aren't yet synced
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:47 PM Revision 4d8f78bc (ceph): mon/PGMonitor: fix segfault when osdmap and pgmap stats are out of sync
- The leader mon is responsible for propagating changes in the osdmap
into the pgmap (e.g., when a pool or osd goes awa... - 10:39 PM Revision aead63cf (ceph): Merge pull request #637 from dachary/master
- mailmap: add Matthew Roy, Matthew Wodrich
- 10:39 PM Revision 9a9e4ca2 (ceph): Merge pull request #639 from ceph/wip-gtest
- Makefile: don't use srcdir in TESTS
Reviewed-by: Roald J. van Loon <roaldvanloon@gmail.com> - 10:36 PM Revision 8de31437 (ceph): If we're scheduling for non-ubuntu, look for rpms
- 09:09 PM rgw Bug #6240: rgw: invalid read on addr in msgr via objecter
- valgrind shows ...
- 08:49 PM Revision e30f1fa7 (ceph): Merge pull request #110 from ceph/wip-nuke-import-os
- nuke: add missing import os
- 08:42 PM Revision 25bc62de (ceph): nuke: add missing import os
- $ teuthology-nuke -a . -r -u
Traceback (most recent call last):
File "/home/ubuntu/bin/teuthology-nuke", line 9, i... - 08:37 PM Revision 47993680 (ceph): Makefile: don't use srcdir in TESTS
- src/Makefile-env.am:31: error: using '$(srcdir)' in TESTS is currently broken: '$(srcdir)/unittest_bufferlist.sh'
src... - 05:46 PM Revision 7bbadf19 (ceph): mailmap: add Matthew Roy, Matthew Wodrich
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 05:25 PM Bug #6081: osd crashed during upgrade tests from dumpling to next in the nightlies
- ubuntu@teuthology:/a/teuthology-2013-09-25_01:35:02-upgrade-small-next-testing-basic-vps/17002
- 05:22 PM Bug #6400 (Duplicate): osd crashed in dumpling due to unexpected error (EEXIST?)
- logs: ubuntu@teuthology:/a/teuthology-2013-09-25_01:35:02-upgrade-small-next-testing-basic-vps/17000...
- 05:10 PM Revision c8cae87e (ceph): qa/workunits/mon/crush_ops.sh: fix test
- Fix root.
Fixes: #6392
Signed-off-by: Sage Weil <sage@inktank.com> - 04:53 PM CephFS Bug #6399 (Resolved): snaptest-0.sh fails
- MDS backtrace:...
- 04:31 PM Revision 60d541d3 (ceph): Merge pull request #615 from dachary/wip-jerasure-copy
- ErasureCode: get rid of extra copy when encoding
Reviewed-by: Sage Weil <sage@inktank.com> - 04:23 PM Revision cea343d0 (ceph): Merge pull request #634 from dachary/master
- git: consolidate mails in commit logs
Reviewed-by: Sage Weil <sage@inktank.com> - 04:23 PM Revision 81e571fb (ceph): Merge pull request #636 from dachary/wip-get_command_description
- autoconf: remove get_command_descriptions dependency to gtest
Reviewed-by: Sage Weil <sage@inktank.com> - 04:10 PM Bug #6384: ceph tool: incorrect pool delete line returns unintelligible failure message
- This is at least helped by commit:7e1c73538f44ad83db476ffa15d5121470b5154e in wip-6332 (pull request: https://github....
- 02:26 PM Revision 812234cb (ceph): ErasureCode: get rid of extra copy when encoding
- The substr_of bufferlist method is used to reduce the copies to the
strict minimum. It is both able to split bufferpt... - 01:50 PM Revision 661676f4 (ceph): Merge pull request #109 from ceph/wip-6388
- only use host_key if it is not None
- 01:25 PM Revision 80dcab7f (ceph): only use host_key if it is not None
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 01:12 PM rgw Bug #6397 (Resolved): rgw: valgrind issue
- ...
- 12:53 PM CephFS Bug #6394 (Resolved): teuthology: bad dereference in mds thrasher
- ...
- 12:24 PM Bug #6380: Monitor tries to bind on IPv6 address while not available yet after boot
- Sage Weil wrote:
> We've seen similar issues on fedora with ipv4; there it was just a problem with the init/systemd ... - 09:44 AM Bug #6380: Monitor tries to bind on IPv6 address while not available yet after boot
- We've seen similar issues on fedora with ipv4; there it was just a problem with the init/systemd ordering (networkman...
- 12:11 PM Revision 2422b2ae (ceph): autoconf: remove get_command_descriptions dependency to gtest
- It is not required and a leftover of the time when it was a unit test
which was a mistake to begin with. It has been ... - 11:19 AM Bug #6346: OSD: do not crash on bad client op input
- Well there's something weird going on then, because this is post-0.69 and appears to have passed those checks:...
- 10:25 AM Bug #6392 (Resolved): crush_ops.sh failure
- 09:44 AM Bug #6392 (Resolved): crush_ops.sh failure
- ubuntu@teuthology:/a/teuthology-2013-09-24_23:00:19-rados-next-testing-basic-plana/15648
time: 418s
log: htt... - 10:16 AM Bug #6378: mon: osdmap crc mismatch during scrub
- basically we're setting different values on 'full_latest' depending on the situation:
* during trim we set it to t... - 09:42 AM Subtask #6391: stuck incomplete
- overrides: ...
- 09:41 AM Subtask #6391 (Duplicate): stuck incomplete
- ubuntu@teuthology:/a/teuthology-2013-09-22_23:00:06-rados-master-testing-basic-plana/11735/
- 09:39 AM rbd Bug #6386 (Need More Info): ceph-osd processes are having hang tasks
- We used to see this periodicially but had no real clue. At some point we stopped seeing it. I suspect that it is ju...
- 02:46 AM rbd Bug #6386 (Can't reproduce): ceph-osd processes are having hang tasks
- I am having issues with ceph-osd processes showing hang tasks messages in dmesg output on both of my ceph-osd servers...
- 09:38 AM Bug #6390 (Can't reproduce): ENOTEMPTY on TEMP coll on replay
- ubuntu@teuthology:/a/teuthology-2013-09-22_23:00:06-rados-master-testing-basic-plana/11719/
2013-09-23 01:46:26.51... - 09:30 AM Documentation #6389 (Resolved): journal_aio is set to true by default
- Since Cuttlefish, journal_aio is set to true by default.
The documentation should be updated in doc/rados/configur... - 07:35 AM Bug #6348 (Resolved): ceph-deploy new.new needs to use same seperator as conf.write
- Merged into ceph-deploy master branch with hash: 36c4c71
- 06:07 AM Revision 04c7207a (ceph): git: consolidate mails in commit logs
- Map duplicate mails / names in commit logs to a single canonical names.
Useful to report to management with git short... - 05:42 AM devops Bug #6387 (Resolved): Handle HostNotFound for execnet connection errors
- Errors like the one below should be properly handled and displayed nicely
back to the user.... - 04:46 AM Revision 952b39d4 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
src/osd/ReplicatedPG.cc - 02:41 AM Fix #6278: osd: throttle snap trimming
- Wade, could you please share with us what kernel tuning you've done? I would like to try it as I am still having some...
09/24/2013
- 11:50 PM Revision 2870ec50 (ceph): rbd: move xfstest TESTDIR=... bit to front of command
- 2013-09-24T11:32:49.169 DEBUG:teuthology.orchestra.run:Running [10.214.132.4]: "/usr/bin/sudo adjust-ulimits ceph-cov...
- 10:39 PM Revision c9e7e2f7 (ceph): Merge pull request #633 from ceph/wip-repop-leaks
- fix a copule of leaks of RepGather structs
Reviewed-by: David Zafman <david.zafman@inktank.com> - 10:27 PM Revision 94548b4b (ceph): mon/OSDMonitor: fix 'ceph osd crush reweight ...'
- The adjust method returns a count of adjusted items.
Add a test.
Fixes: #6382
Backport: dumpling
Signed-off-by: Sag... - 10:27 PM Revision 00ff7f5c (ceph): qa: workunits: mon: crush_ops: test 'ceph osd crush move'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 3bc618b7b46496c5110edde0da9cae5d3... - 10:26 PM Revision ac0faaa3 (ceph): doc: Removed service ops language and added reference to operations.
- fixes: #6374
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 10:26 PM Revision 3de32562 (ceph): mon/OSDMonitor: fix 'ceph osd crush reweight ...'
- The adjust method returns a count of adjusted items.
Add a test.
Fixes: #6382
Backport: dumpling
Signed-off-by: Sag... - 10:22 PM Revision 0061363e (ceph): Merge pull request #477 from jpfrancois/patch-1
- Fix for Swift key command
- 09:45 PM Revision 073732cc (ceph): doc: Refactored diagram and text.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:44 PM Revision 99c10bcc (ceph): doc: Updated diagrams, refactored text.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:49 PM Revision 1c12eefc (ceph): osd/ReplicatedPG: fix leak of RepGather on watch timeout
- new_repop() gives us a ref; we need to release it, just as we do in
execute_ctx().
Backport: dumpling
Signed-off-by:... - 08:48 PM Revision 1d67e152 (ceph): osd/ReplicatedPG: fix leak of RepGather on large-object COPY_FROM
- new_repop() gives us a ref; we need to release it, just as we do in
execute_ctx().
Signed-off-by: Sage Weil <sage@in... - 08:04 PM Revision 3955666e (ceph): Add config option 'verify_host_keys'
- Defaults to True, meaning no change in behavior. If False, don't have
paramiko verify ssh host keys. - 08:04 PM Revision f1aac667 (ceph): ceph.conf: fix typo
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:04 PM Revision 218776b2 (ceph): Fix namespace collision
- 08:04 PM Revision f8bf53c4 (ceph): Fix namespace collision
- 07:48 PM Revision afa2468e (ceph): ceph_test_rados: order racing read wrt to the COPY_FROM
- The prevents:
- send COPY_FROM, blocks on recovering object
- send stat, procedes to return old object version
- ... - 07:48 PM Revision 3faf08f5 (ceph): librados: add OPERATION_ORDER_READS_WRITES flag
- This maps to the internal RWORDERED option, which indicates that a read
should be ordered the same way a write is.
S... - 07:37 PM Revision 9322305c (ceph): osd/ReplicatedPG: respect RWORDERED rados flag
- If this flag is set, we need to order reads as writes. In particular, this
means that reads will wait for degraded o... - 05:28 PM Revision 6f342872 (ceph): osd: change warn_interval_multiplier to uint32_t
- to prevent overflow in OpTracker::check_ops_in_flight when
multiplying warn_interval_multiplier *= 2
Backport: cuttl... - 05:27 PM Revision 0ff5b4a9 (ceph): osd: change warn_interval_multiplier to uint32_t
- to prevent overflow in OpTracker::check_ops_in_flight when
multiplying warn_interval_multiplier *= 2
Backport: cuttl... - 05:27 PM Revision f6510c76 (ceph): osd: change warn_interval_multiplier to uint32_t
- to prevent overflow in OpTracker::check_ops_in_flight when
multiplying warn_interval_multiplier *= 2
Backport: cuttl... - 05:27 PM Revision b0fee960 (ceph): Merge pull request #630 from dachary/master
- osd: change warn_interval_multiplier to uint32_t
Reviewed-by: Sage Weil <sage@inktank.com> - 05:18 PM Revision 84e1f096 (ceph): arch/intel: fix old comment
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:17 PM Revision 366b608f (ceph): arch/intel: use intel probe instructions for x86_64 only
- Not LP64, which includes ppc64 and clearly does not build.
Fixes: #6283
Signed-off-by: Sage Weil <sage@inktank.com>
... - 05:12 PM Revision 1bce1f00 (ceph): osd: change warn_interval_multiplier to uint32_t
- to prevent overflow in OpTracker::check_ops_in_flight when
multiplying warn_interval_multiplier *= 2
Backport: cuttl... - 04:49 PM rbd Bug #6385 (Resolved): run_xfstests.sh: doesn't work with newly-organized upstream tests
- upstream recently put tests into different groups; we currently call out specific tests that we run.
we should pro... - 04:41 PM Revision 6367868a (ceph): Merge pull request #107 from ceph/wip-fix-undefined-config
- fix an undefined name buy importing config
- 04:39 PM Revision 3e75cf3b (ceph): fix an undefined name buy importing config
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 04:30 PM Bug #6384 (Resolved): ceph tool: incorrect pool delete line returns unintelligible failure message
- ...
- 04:03 PM Revision fb15040b (ceph): crushtool: do not dump core with non-unique bucket IDs
- Return -EEXIST on duplicate ID
BUG FIX: crush_add_bucket() mixes error returns and IDs
Add optional argument to ret... - 04:02 PM Revision 410db3f3 (ceph): qa: workunits: cephtool: check if 'heap' commands are parseable
- Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
(cherry picked from commit b1eeaddd5f214c1b0883b44fc8cae07c649be... - 04:02 PM Revision 062060a3 (ceph): osd: OSD: add 'heap' command to known osd commands array
- Must have been forgotten during the cli rework.
Backport: dumpling
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.... - 04:02 PM Revision 3f32f57b (ceph): mds: MDS: pass only heap profiler commands instead of the whole cmd vector
- The heap profiler doesn't care, nor should it, what our command name is.
It only cares about the commands it handles.... - 04:02 PM Revision 46dcc466 (ceph): perfglue/heap_profiler.cc: expect args as first element on cmd vector
- We used to pass 'heap' as the first element of the cmd vector when
handling commands. We haven't been doing so for a... - 04:01 PM Revision 9dc5f15f (ceph): rgw: destroy get_obj handle in copy_obj()
- Fixes: #6176
Backport: dumpling
We take different code paths in copy_obj, make sure we close the handle
when we exit ... - 03:49 PM Revision ed6c2c08 (ceph): ceph.conf: reduce min pg per osd
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:42 PM Bug #6382 (Resolved): ceph osd crush reweight is broken; bad return code check
- 02:11 PM Bug #6382 (Resolved): ceph osd crush reweight is broken; bad return code check
- it calls newcrush.adjust_item_weightf, and expects 0, but adjust_item_weight* seem to return
a count of changed weig... - 03:42 PM Revision 2cbe93b8 (ceph): Merge pull request #628 from dachary/wip-erasure-fix-thread-test
- ErasureCode: fix plugin loading threaded test
Reviewed-by: Sage Weil <sage@inktank.com> - 03:30 PM Documentation #6374 (Resolved): Cephx Docs Reference Service Syntax
- Removed the service syntax and referred users back to the Operating a Cluster page.
- 03:17 PM Revision 8f4b1974 (ceph): Merge pull request #106 from ceph/wip-mirror
- Remove lots of ceph.com hardcoding; default to upstream sources
- 03:17 PM Revision db6efe3e (ceph): Merge pull request #106 from ceph/wip-mirror
- Remove lots of ceph.com hardcoding; default to upstream sources
- 03:09 PM Revision 4043c7d7 (ceph): Split test into two
- 02:38 PM Revision e1d7c32d (ceph): Merge pull request #627 from dachary/master
- rgw: fix rgw test to reflect usage change
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 02:07 PM Revision 4bc18189 (ceph): ErasureCode: fix plugin loading threaded test
- The TEST_F(ErasureCodePluginRegistryTest, factory_mutex) was bugous and
only succeeded by chance. The sleep was on th... - 01:59 PM Revision c19bd9ba (ceph): Merge pull request #105 from ceph/wip-missing-packages
- When scheduling fails, send an email.
- 01:26 PM Bug #5958 (Can't reproduce): os/DBObjectMap.cc: 393: FAILED assert(!valid || cur_iter->valid())
- 01:22 PM devops Bug #6369 (Resolved): catch the missing public_addr/public_network error for mons
- Merged into ceph-deploy master branch: e67c9d0
- 09:48 AM devops Bug #6369 (Fix Under Review): catch the missing public_addr/public_network error for mons
- Opened pull request https://github.com/ceph/ceph-deploy/pull/89
- 12:24 PM Bug #6381 (Resolved): need apache-fastcgi packages built for fedora and debian
- currently, we do not have apache-fastcgi packages built for fedora 19 and debian wheezy. So, the nightlies are failin...
- 12:24 PM devops Feature #6154 (Resolved): ceph-deploy should be able to use an argument "fs-type" to specify the ...
- Merged into ceph-deploy master branch with hash: 6fb89a6
- 11:55 AM Bug #6380 (Resolved): Monitor tries to bind on IPv6 address while not available yet after boot
- Not sure yet what the problem is, but creating a issue so it's documented.
When using IPv6 only and binding the mo... - 11:49 AM Bug #6348: ceph-deploy new.new needs to use same seperator as conf.write
- Resolved by https://github.com/ceph/ceph-deploy/pull/90
- 10:32 AM Bug #6283 (Resolved): ppc build fails
- 09:18 AM Bug #6283 (Fix Under Review): ppc build fails
- 10:32 AM Bug #6370 (Resolved): osd: slow request warning exponential backoff fails at 3840 seconds
- 09:59 AM Documentation #6379 (Closed): Better document impact of putting journals on different disks
- Questions such as the following are asked frequently on the mailing list and IRC:
- What happens if the journal is l... - 09:50 AM devops Bug #5944: ceph-deploy osd needs to be moved to use the new remote helpers
- 09:44 AM rbd Bug #6267: krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- Any update?
- 09:41 AM Bug #6333 (Need More Info): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Hey-
Here is what I think we need to fully understand what is happening:
- debug ms = 1, debug osd = 20 on the ... - 09:27 AM Bug #6377 (Resolved): pg_num warn cause teuthology to stall
- lowered threshold ing teuthology's ceph.conf.template
- 08:05 AM Bug #6377 (Resolved): pg_num warn cause teuthology to stall
- The "mon: warn when pg_num is too low or appears out of whack wrt the cluster size":https://github.com/ceph/ceph/pull...
- 09:24 AM Bug #6378 (Resolved): mon: osdmap crc mismatch during scrub
- teuthology-2013-09-23_19:00:20-rados-dumpling-testing-basic-plana
had a ~30 scrub mismatch failures. possibly the... - 09:16 AM Feature #6038 (Resolved): cachepool: filestore/osd: infrastructure for large object COPY atomic r...
- 09:06 AM RADOS Bug #6246 (Resolved): crushtool dumps core with non-unique bucket IDs
- 09:02 AM Bug #6361 (Resolved): mon: 'heap' commands not working
- 09:01 AM rgw Bug #6176 (Resolved): rgw: valgrind: leak in copy_obj
- 08:41 AM Fix #6278: osd: throttle snap trimming
- We seemed to hit this issue (not the sql herring) when deep scrubs kicked off. Disabling all scrubbing and some kerne...
- 06:05 AM Revision e50343e4 (ceph): rgw: fix rgw test to reflect usage change
- otherwise src/test/cli/radosgw-admin/help.t fails when running make
check when run after a configure --with-radosgw
... - 05:30 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Alright, I just tested it (the @wip-ceph-cli-env@ branch), and it works fine.
Thanks for having taken care of this... - 04:15 AM Feature #2666: rados tool: copy pool
- What's the command to copy a pool? Using "ceph -h" with latest dumpling doesn't show any command to copy pool?
- 01:14 AM Revision 058b1fab (ceph): When scheduling fails, send an email.
- Note that if no email is passed on the command line, no error email will
be sent. I did this to be polite.
09/23/2013
- 11:42 PM Revision 08c386f5 (ceph): Merge pull request #588 from dachary/wip-6274
- mon: unit tests to protect against some MonCommands.h typos
- 11:29 PM Revision 471233e9 (ceph): mon: MonCommands: expect a CephString as 1st arg for 'osd crush move'
- Fixes: #6230
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 7d3799fde19138f957f... - 11:24 PM Revision 29082250 (ceph): osd: revert 'osd max xattr size' limit
- Set it to 0 (unlimited) for now.
Backport: dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda... - 11:23 PM Revision abb88d70 (ceph): osd: revert 'osd max xattr size' limit
- Set it to 0 (unlimited) for now.
Backport: dumpling
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Yehuda... - 11:16 PM Revision 286a6991 (ceph): Merge pull request #566 from ceph/wip-purge-stray
- Fixes for purging stray
Reviewed-by: Sage Weil <sage@inktank.com> - 10:48 PM Revision 6200eeca (ceph): Merge pull request #591 from ceph/wip-misc
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 10:41 PM Revision 7741de0b (ceph): Merge branch 'master' of github.com:ceph/ceph
- 10:40 PM Revision 1425119b (ceph): Merge pull request #625 from ceph/wip-warn-pg
- mon: warn when pg_num is too low or appears out of whack wrt the cluster size
Reviewed-by: Greg Farnum <greg@inktank... - 10:34 PM Revision b3d3b374 (ceph): mds: be more careful about decoding LogEvents
- We need to wrap the full decode section or we can abort the process
if there's an issue (which we may want to just sk... - 10:31 PM Revision 73289b34 (ceph): mds: be more careful about decoding LogEvents
- We need to wrap the full decode section or we can abort the process
if there's an issue (which we may want to just sk... - 10:23 PM Documentation #6374 (Resolved): Cephx Docs Reference Service Syntax
- Replace sudo service ceph -a start | restart with a reference to the operations section. Syntax will differ based upo...
- 10:14 PM Revision 816cbbfe (ceph): Merge pull request #619 from dachary/wip-erasure-pad
- ErasureCode: optimize padding calculation
Reviewed-by: Sage Weil <sage@inktank.com> - 10:08 PM Revision c32c51a3 (ceph): ErasureCode: optimize padding calculation
- Andreas-Joachim Peters pointed out that the ErasureCodeJerasure method
pad_in_length is very inefficient for no reaso... - 09:57 PM Revision 60e9e854 (ceph): vstart: set 'mon pg min per osd'
- We need to tweak this since we create relatively few pgs per osd.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:57 PM Revision befdcfd6 (ceph): mon/PGMonitor: health warn if pool has relatively high objects/pg
- If there is a pool that has a high objects/pg relative to the rest of the
cluster, warn, as this suggests this partic... - 09:56 PM Revision a684ac82 (ceph): mon/PGMonitor: health warn if pg_num != pgp_num
- Users need to adjust pg_num *and* pgp_num for split but may forget to do
both.
Signed-off-by: Sage Weil <sage@inktan... - 09:56 PM Revision dc7114e0 (ceph): mon: warn if pg to osd ratio is too low
- If there are not enough PGs relative to the number of in osds, warn.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:52 PM Revision 97471e33 (ceph): ErasureCode: coding style conformance
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:46 PM Revision 1d54754c (ceph): pybind: ceph_argparse unit tests foundations
- The general idea is to have a series of commands, in the same order as
they show in mon/MonCommands.h, as if they wer... - 09:46 PM Revision d3bf39e7 (ceph): ceph_argparse: unit tests for validate_command pg
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision 253e53f4 (ceph): ceph_argparse: unit tests for validate_command auth
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision 00d15049 (ceph): ceph_argparse: unit tests for misc validate_command
- Contrary to all other classes, this series of command ( Monitor ) does
not have a common prefix.
http://tracker.ceph... - 09:46 PM Revision 0ff00306 (ceph): ceph_argparse: unit tests for validate_command mds
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision c09d01c2 (ceph): ceph_argparse: unit tests for validate_command mon
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision fa396d94 (ceph): ceph_argparse: unit tests for validate_command osd
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision bfd4db25 (ceph): ceph_argparse: unit tests for validate_command config-key
- http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Joao Eduard... - 09:46 PM Revision ee33ff81 (ceph): autotools: group test scripts in check_SCRIPTS
- The check_SCRIPTS is added in Makefile-env.am to list the tests that do
not require compilation. The scripts listed i... - 09:46 PM Revision 9c9d7e6a (ceph): autotools: set noinst_PROGRAMS
- to be used by unit test support programs that do not need to be installed
Signed-off-by: Loic Dachary <loic@dachary.... - 09:46 PM Revision e0b56973 (ceph): mon: convenience function to convert commands to json
- The get_command_descriptions is added to Monitor.h and contains
the code previously inlined in Monitor::handle_comman... - 09:46 PM Revision c16b54fd (ceph): mon: get_command_descriptions support program
- The get_command_descriptions function is not designed to be tested in
C++ because all the validation happens in pybin... - 09:46 PM Revision 96067e07 (ceph): .gitignore gtags(1) generated files
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:46 PM Revision 8f0bb2f0 (ceph): pybind: unit tests for ceph_argparse::parse_json_funcsigs
- Run parse_json_funcsigs against the builtin commands found
in mon/MonCommands.h. Although it does not provide for a f... - 09:46 PM Revision ccf22008 (ceph): mon: validate mon dump epoch as a positive integer
- All other epochs are validated in the same way
http://tracker.ceph.com/issues/6274 refs #6274
Reviewed-by: Joao Edu... - 09:46 PM Revision f9c7bc69 (ceph): pybind: catch EntityAddress missing /
- If the / is missing in an EntityAddress, an ArgumentValid exception must
be raised so that it can be caught in the sa... - 09:25 PM CephFS Feature #6373 (In Progress): kcephfs: qa: test fscache
- 09:25 PM Revision 0eb0c3e0 (ceph): Merge pull request #626 from ceph/wip-usage
- common/config: include --cluster in default usage message
- 09:19 PM Revision 06c58132 (ceph): mon: OSDMonitor: multiple rebuilt full maps per transaction
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
(cherry picked from commit 0d20cae0be701c5b6151a26ee5e4fe24d... - 09:19 PM Revision 65bbcaf4 (ceph): mon: OSDMonitor: update latest_full while rebuilding full maps
- Not doing so will make the monitor rebuild the osdmap full versions, even
though they may have been rebuilt before, e... - 09:19 PM Revision 9b9edb04 (ceph): mon: OSDMonitor: smaller transactions when rebuilding full versions
- Otherwise, for considerably sized rebuilds, the monitor will not only
consume vast amounts of memory, but it will als... - 09:16 PM Revision ed73e0aa (ceph): doc: Adding context to the federated configuration guide.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:16 PM Revision 298811f7 (ceph): mon: OSDMonitor: check if pool is on unmanaged snaps mode on mk/rmsnap
- Backport: dumpling
Fixes: #6047
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
(cherry picked from commit fab7... - 09:12 PM Revision da42355a (ceph): Merge pull request #599 from ceph/wip-6323
- mon: OSDMonitor: fix #6322 and #6323
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:11 PM Revision 104277c8 (ceph): Merge pull request #617 from dachary/wip-lfnindex
- os: fix TestLFNIndex test warnings
Reviewed-by: Sage Weil <sage@inktank.com> - 09:10 PM Revision 157754b3 (ceph): common/config: include --cluster in default usage message
- Clean it up a bit too.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:07 PM Revision 679f5207 (ceph): Merge pull request #624 from ceph/automake-fix-common
- make: build common/secret only on linux
Reviewed-by: Sage Weil <sage@inktank.com> - 08:12 PM Revision 362dba10 (ceph): os, ceph_osd: Rename on_disk_version to target_version
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 08:11 PM Revision 7b7e0046 (ceph): os: Prior version bump should have updated this
- Version available as argument, so use instead of constant
Caused by dab238b0fb76b76a8843f4e59319b0f0e4f966a2
Signed... - 08:07 PM Revision 27fb44b3 (ceph): make: build common/secret only on linux
- libkeyutils is only available on linux. before the automake refactoring
secret.c was compiled into rbd and ceph_mount... - 06:57 PM Revision c4bcb469 (ceph): common: Fix get_namespace() definition in hobject_t
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:57 PM Revision 0d47bf8a (ceph): os: Fix typo in comment
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:57 PM Revision 8407669e (ceph): os: Code conformance of os/LFNIndex.cc
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:57 PM Revision 0655cc15 (ceph): tools: Fix ceph_filestore_dump usage again
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 06:57 PM Revision 1c0aecbe (ceph): osd: Add assert() on collection_getattr() failure instead of later deco...
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 05:53 PM Revision 9adb73ae (ceph): Merge pull request #618 from dachary/wip-jerasure-minimum-to-decode
- ErasureCode: minimum_to_decode unit tests and optimization
Reviewed-by: Sage Weil <sage@inktank.com> - 05:27 PM Revision 5bc46108 (ceph): Merge pull request #605 from dachary/wip-erasure-code-plugin-test
- erasure code plugin test
- 05:26 PM Revision 10f29183 (ceph): Merge pull request #603 from dachary/wip-erasure-code-example
- erasure code example cleanup
- 05:24 PM Bug #6372: rados bench reports bad statistics when read --block-size > write --block-size
- I suspect the read is issued for > object size, but then just completes early, but the
stats tracking still uses th... - 05:21 PM Bug #6372 (Resolved): rados bench reports bad statistics when read --block-size > write --block-s...
- The current MB/s and average MB/s statistics for the rados read benchmark are off when the specified block size for t...
- 05:14 PM Revision b683005c (ceph): Merge pull request #607 from ceph/prctl-getname-test
- code_env: use feature test for PR_GET_NAME support
Reviewed-by: Sage Weil <sage@inktank.com> - 05:12 PM Revision 6b745c94 (ceph): Merge pull request #616 from ceph/automake-flags
- automake: fixup am_common_flags to avoid re-definitions
Reviewed-by: Roald J. van Loon <roaldvanloon@gmail.com> - 05:08 PM Bug #6371 (Duplicate): rados bench segfaults when read --block-size < write --block-size
- When setting the --block-size parameter for 'rados bench', if the --block-size for seq is less than the --block-size ...
- 04:55 PM Revision 2299c4db (ceph): Merge pull request #614 from ceph/wip-rados-model
- Prevent copy_from against yourself, and fix issues with the testing framework around it
Reviewed-by: Greg Farnum <gr... - 04:50 PM Revision 10363dad (ceph): Merge remote-tracking branch 'gh/next'
- 04:29 PM Bug #6230 (Resolved): ceph osd crush move appears to be broken
- 04:23 PM Bug #6336 (Resolved): xattrs limit breaks rgw large objects
- commit:abb88d70643c3a76435b7a9d5b04ff29f7502361
- 09:41 AM Bug #6336: xattrs limit breaks rgw large objects
- Yehuda, please confirm
- 09:38 AM Bug #6336: xattrs limit breaks rgw large objects
- please review
- 03:42 PM CephFS Bug #4221 (Resolved): MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events for DECO...
- Master commit:73289b34b0be5b6612e38944794d59b5e789f841
Dumpling commit:b3d3b3747c1eef695138dac828e5fcb435309c7b - 03:12 PM Bug #6370 (Resolved): osd: slow request warning exponential backoff fails at 3840 seconds
- on cuttlefish, user reports: The OSD keeps logging this as a "slow request". The back-off logic is funny; first it d...
- 02:20 PM Bug #6322 (Resolved): mon: osdmon: write 'latest_full' after rebuilding full version from increme...
- 02:12 PM Bug #6322 (Pending Backport): mon: osdmon: write 'latest_full' after rebuilding full version from...
- 02:20 PM Bug #6323 (Resolved): mon: osdmon: don't create a huge transaction on update_from_paxos(), when r...
- 02:13 PM Bug #6323 (Pending Backport): mon: osdmon: don't create a huge transaction on update_from_paxos()...
- 02:17 PM Bug #6047 (Resolved): mon: Assert and monitor-crash when attemting to create pool-snapshots while...
- 01:02 PM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Created #6369 to track (and warn about) the missing public_addr/public_network error
- 08:01 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Created (and resolved) #6314 that addresses the case where --initial and mon starts up but has rank -1 accordingly to...
- 01:01 PM devops Bug #6369 (Resolved): catch the missing public_addr/public_network error for mons
These are the logical scenarios where we should issue a warning so that a user can fix any potential mon issues:
...- 12:49 PM devops Bug #6367 (Resolved): ceph-deploy destroy broken
- Merged in ceph-deploy master branch with hash: f551755
The call to resolve the shortname of the host in the remo... - 08:48 AM devops Bug #6367 (Fix Under Review): ceph-deploy destroy broken
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/88
- 05:22 AM devops Bug #6367 (Resolved): ceph-deploy destroy broken
- Since the new hostname shortname refactoring was done into place, the remote function
that allows one to destroy a m... - 12:43 PM Bug #6366: long TAT - due too long residence time in Ceph code
- i picked a random write, client.4406.1:23924...
- 01:23 AM Bug #6366 (Closed): long TAT - due too long residence time in Ceph code
- In a default environment (repli=2) a 4k IO take approx. 2000 micro seconds for TAT / turn-around-time from start of a...
- 11:52 AM Revision 991139bc (ceph): doc: When bootstrapping mon set the correct caps for client.admin
- Otherwise client.admin will be privilege-less and the admin can't
access the cluster. - 10:31 AM Bug #6357 (Resolved): inverted test in osd pool create
- PR 608 landed 2d089e4644b623adb58ca8c0c924d2516efcac86
- 10:02 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Sage Weil wrote:
> Benoît Knecht wrote:
> > Do you want me to resubmit the patch with the revert of your fix includ... - 09:25 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Benoît Knecht wrote:
> Sage Weil wrote:
> > Ah, I see why. In this case we should probably revert my original fix ... - 09:19 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Sage Weil wrote:
> Ah, I see why. In this case we should probably revert my original fix too so that the options ar... - 09:03 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Benoît Knecht wrote:
> Please ignore the first patch, it didn't work if @CEPH_ARGS@ wasn't set.
Ah, I see why. I... - 07:28 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Please ignore the first patch, it didn't work if @CEPH_ARGS@ wasn't set.
- 07:09 AM Bug #6052: ceph cli doesn't respect CEPH_ARGS
- Well, this commit didn't solve the issue for me. Running @CEPH_ARGS="--id cinder" ceph -s@ doesn't change the client ...
- 09:56 AM Bug #6364 (Resolved): osd: copy_from an object to itself does not return an error code
- Fixed in commit:59ee51aff71fc3fdba9562f19a9a7ce2263524b6 and merged to master in commit:2b75abbd850e6988539d79c3ab564...
- 09:34 AM Bug #6364 (Fix Under Review): osd: copy_from an object to itself does not return an error code
- 09:44 AM Bug #6301 (Closed): ceph-osd hung by XFS using linux 3.10
- 09:40 AM Bug #6346: OSD: do not crash on bad client op input
- ...
- 09:34 AM Bug #6359 (Resolved): FileStore::lfn_unlink: still need to check st_nlink
- 09:31 AM devops Feature #6362 (In Progress): move teuthology required stuff off download.ceph.com
- Work is ongoing in the wip-mirror branch:
https://github.com/ceph/teuthology/tree/wip-mirror
This doesn't current... - 08:00 AM devops Bug #6314 (Resolved): catch case where mon starts up but has rank -1 accordingly to mon_status.
- Merged into ceph-deploy master branch with hash: e66d751
- 07:58 AM devops Bug #6300 (Resolved): ceph-deploy: mon create prompts for password
- Merged into ceph-deploy master branch with hash: 1c3114a
- 07:06 AM rbd Bug #6368 (Resolved): rbd nosetests keep failing with AttributeError
- We keep seeing failures for tests against rbd, I think this has something to do with the use of globals
in the test... - 04:35 AM Bug #6361 (Pending Backport): mon: 'heap' commands not working
09/22/2013
- 09:02 AM Revision 9dfac9ed (ceph): ErasureCode: minimum_to_decode unit tests and optimization
- The minimum_to_decode function simply returns the available chunks if no
recovery is necessary.
Add unit tests cover... - 08:46 AM Revision 9442cfaa (ceph): os: fix TestLFNIndex test warnings
- Do not ignore system return value. Wrap emacs compile line to 80
characters.
Signed-off-by: Loic Dachary <loic@dacha... - 06:14 AM Revision 0f3ba297 (ceph): mds: remove unnecessary MDCache::maybe_eval_stray() calls
- Now we call MDCache::maybe_eval_stray() in MDSCacheObject::put().
So there is no need to call MDCache::maybe_eval_str... - 06:14 AM Revision 67386e45 (ceph): mds: don't trim stray inode from the cache.
- don't trim stray inode from the cache, purge it instead. This ensures
the stary directories at minimum size.
Signed-... - 06:14 AM Revision 7be9b92d (ceph): mds: avoid fetching backtrace when purging stray
- we save old data pools in both inode_backtrace_t::old_pools and
inode_t::old_pools. We have the inode in the cache wh... - 06:14 AM Revision 945eb3cb (ceph): mds: remove dirfrags when purging stray directory
- Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
- 06:14 AM Revision cbf1f3ca (ceph): mds: evaluate stray when releasing inode/dentry's reference
- Current method to purge stray inode is call MDCache::maybe_eval_stray()
after releasing a reference to the stray inod...
09/21/2013
- 05:41 PM Revision 0a439745 (ceph): automake: add per-target AM_CPPFLAGS
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:24 PM Revision 11d8d755 (ceph): makefile-env: separate cppflags and cflags usage
- AM_COMMON_FLAGS included both CPP and C[XX] flags. This can cause
re-definition errors like this:
make[4]: Nothing t... - 11:40 AM Revision 3c64784e (ceph): Merge pull request #612 from ceph/wip-6361
- perfglue/heapprofiler: expect cmd name when handling command instead of 'heap <cmd>'
This was broken by the cli rewo... - 04:06 AM Revision 2b75abbd (ceph): ceph_test_rados: fix COPY_FROM completion
- Fix the copy_from operation to not remove the objects from the in_use list
until after the entire operation is comple... - 03:49 AM Revision 935eb228 (ceph): ceph_test_rados: fix seq_num, improve error output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:44 AM Revision 4d0ee0b5 (ceph): ceph_test_rados: limit max_in_flight to objects/2
- In particular, we need to allow all in-flight ops to be COPY_FROM.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:43 AM Revision 303bc68e (ceph): ceph_test_rados: do not COPY_FROM self
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:43 AM Revision 59ee51af (ceph): osd/ReplicatedPG: handle COPY_FROM self
- Return EINVAL if we try to COPY_FROM ourselves.
Signed-off-by: Sage Weil <sage@inktank.com>
09/20/2013
- 10:44 PM Revision 08a97ae4 (ceph): Merge pull request #592 from ceph/wip-6287
- mon/OSDMonitor: make busy creating pgs message more explicit
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:41 PM Revision 2d089e46 (ceph): Merge pull request #608 from dachary/wip-6357
- mon: fix inverted test in osd pool create
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:27 PM Revision 5cb7b298 (ceph): mon: fix wrong arg to "instructed to" status message
- Fixes: #6293
Signed-off-by: Dan Mick <dan.mick@inktank.com>
(cherry picked from commit 16ebb25f7cdb8e92c618a333c505c1... - 09:46 PM devops Feature #6365 (Resolved): Package up newer version of Qemu for RHEL & EL6.3 and 6.4
- Looks like there is a newer version of Qemu from RHEL, which has some security fixes:
ftp://ftp.redhat.com/pub/red... - 09:07 PM Revision 9e98620e (ceph): rgw: destroy get_obj handle in copy_obj()
- Fixes: #6176
Backport: dumpling
We take different code paths in copy_obj, make sure we close the handle
when we exit ... - 08:53 PM Revision 0ce62787 (ceph): Don't hardcode the git://ceph.com/git/ mirror
- Default to https://github.com/ceph/ but add a ~/teuthology.yaml option
- 08:53 PM Revision 66555a40 (ceph): Don't hardcode the git://ceph.com/git/ mirror
- Default to https://github.com/ceph/ but add a ~/teuthology.yaml option
- 08:53 PM Revision e6040f78 (ceph): Don't hardcode ceph.com mirror for linux-firmware
- 08:50 PM Revision dc1c4250 (ceph): Merge pull request #103 from ceph/toxify
- Toxify teuthology
- 08:49 PM Revision 345bc47f (ceph): append .tox to avoid going in there
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:49 PM Revision 8d3cf9e1 (ceph): make sure we don't hard code the path for py.test
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:49 PM Revision cbda14f6 (ceph): just use python 2.7 for now
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:49 PM Revision b6842419 (ceph): tell tox to use site-packages
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:49 PM Revision feefe218 (ceph): tell py.test that we want teuthology stuff only
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:49 PM Revision b79343cc (ceph): move the sitepackages to testenv section
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:24 PM Revision d1deb6d5 (ceph): Don't hardcode teuthology's git repo URL
- 08:11 PM Revision 9de95d17 (ceph): Add a basic test for teuthology.config
- 08:08 PM Revision 556956f4 (ceph): Merge pull request #613 from ceph/wip-6356
- note that ceph-deploy should not be called with sudo on certain situations
- 08:06 PM Revision 50b55b6c (ceph): Merge pull request #104 from ceph/wip-copyfrom
- fix ceph_test_rados args
- 08:02 PM Revision c28dd12c (ceph): note that ceph-deploy should not be called with sudo on certain situations
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 08:01 PM Revision 2ade5b66 (ceph): doc: Updated graphic. Removed bullet points. Cleaned up RPM/YUM example.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:00 PM Revision c55d7ac7 (ceph): doc: Updated graphic to use same name as command line examples.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:00 PM Revision 10754438 (ceph): doc: Added Recommendations and Get Involved to Intro.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:00 PM Revision 5eb4db18 (ceph): doc: Removed Get Involved from Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:59 PM Revision af7ad1d7 (ceph): doc: Changed title, and removed recommendations sections.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:58 PM Revision dc19d242 (ceph): doc: Moved recommendations sections to Intro.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:56 PM Revision bfb27609 (ceph): rados: only pass --op copy_from if non-zero
- Among other things, this does not work with older ceph_test_rados binaries.
Backport: next
Signed-off-by: Sage Weil ... - 07:38 PM Revision 1600785d (ceph): Add config.ceph_git_base_url
- 07:34 PM Revision db1231b4 (ceph): Use config.lock_server
- 07:01 PM Revision 7153c2be (ceph): Add doc noting Inktank's lockserver URL
- Since I just removed it from lockstatus.py.
- 07:00 PM Revision e93c8ef2 (ceph): Use teuthology.config.
- Also use os.path.join()
- 04:51 PM Revision b1eeaddd (ceph): qa: workunits: cephtool: check if 'heap' commands are parseable
- Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
- 04:51 PM Revision 296f2d0d (ceph): osd: OSD: add 'heap' command to known osd commands array
- Must have been forgotten during the cli rework.
Backport: dumpling
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.... - 04:51 PM Revision 238fe272 (ceph): mds: MDS: pass only heap profiler commands instead of the whole cmd vector
- The heap profiler doesn't care, nor should it, what our command name is.
It only cares about the commands it handles.... - 04:51 PM Revision c98b910d (ceph): perfglue/heap_profiler.cc: expect args as first element on cmd vector
- We used to pass 'heap' as the first element of the cmd vector when
handling commands. We haven't been doing so for a... - 04:31 PM Bug #6364 (Resolved): osd: copy_from an object to itself does not return an error code
- I noticed this when a RadosModel run with a small number of total objects hung, and the last line was:...
- 04:30 PM Revision e112a834 (ceph): FileStore: only remove the omap entries if nlink == 1
- Fixes: #6359
Introduced in 17c5d765d7c7573f875f6b3ba66e3b6813110a06
Signed-off-by: Samuel Just <sam.just@inktank.com>... - 03:58 PM Revision a9926644 (ceph): lru_map: don't use list::size()
- replace list::size() with map::size(), which should have
a constant time complexity.
Reviewed-by: Sage Weil <sage@in... - 03:57 PM Revision 788546ea (ceph): common/lru_map: rename tokens to entries
- This code was originally used in a token cache, now
as a generic infrastructure rename token fields.
Reviewed-by: Sa... - 03:56 PM devops Feature #6362 (New): move teuthology required stuff off download.ceph.com
- We want to move stuff off ceph.com as only certain people have access to that and instead move it to a lab machine ev...
- 03:56 PM Revision 7c1d2ded (ceph): lru_map: don't use list::size()
- replace list::size() with map::size(), which should have
a constant time complexity.
Reviewed-by: Sage Weil <sage@in... - 03:55 PM Revision 532e41a9 (ceph): common/lru_map: rename tokens to entries
- This code was originally used in a token cache, now
as a generic infrastructure rename token fields.
Reviewed-by: Sa... - 03:55 PM Revision ca984e32 (ceph): bufferlist: don't use list::size()
- Reviewed-by: Sage Weil <sage@inktank.com>
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 03:46 PM Revision 04de6a83 (ceph): Merge pull request #590 from ceph/wip-6284
- osdc/ObjectCacher: finish contexts after dropping object reference
Tested: ubuntu@teuthology:/a/sage-2013-09-19_19:4... - 02:28 PM Revision eb18cbf4 (ceph): add .tox to gitignore
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:28 PM Revision cc4b9560 (ceph): add a tox file
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 02:05 PM rgw Bug #6360 (Fix Under Review): rgw: keystone token cache not working
- pushed a fix to wip-6360.
- 07:40 AM rgw Bug #6360 (Resolved): rgw: keystone token cache not working
- 02:05 PM rgw Bug #6176 (Pending Backport): rgw: valgrind: leak in copy_obj
- 02:01 PM Revision b14bdfbb (ceph): Merge pull request #102 from ceph/wip-tests
- Update all existing unit tests.
- 01:39 PM Revision eeb78b6b (ceph): Update test_connect() to reflect API changes
- Looks like paramiko changed a bit internally. All unit tests pass now!
- 01:37 PM Bug #6356 (Resolved): docs should warn against executing ceph-deploy as root
- Merged into ceph master branch with hash: 556956f449cef008c62352e0ae2c980156
- 01:04 PM Bug #6356: docs should warn against executing ceph-deploy as root
- Opened pull request: https://github.com/ceph/ceph/pull/613
- 12:56 PM devops Bug #6300 (Fix Under Review): ceph-deploy: mon create prompts for password
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/87
- 10:23 AM CephFS Feature #4354: mds: add an equivalent to the OSD OpTracker
- Got the OpTracker work rebased on master and pushed for review: wip-optracker, https://github.com/ceph/ceph/pull/610....
- 09:01 AM Bug #6361 (Fix Under Review): mon: 'heap' commands not working
- wip-6361, pull request 612
- 07:53 AM Bug #6361 (Resolved): mon: 'heap' commands not working
- reason is simple: ceph_heap_profiler_handle_command() in perfglue/heap_profiler.cc expects two args in the vector, t...
- 08:47 AM CephFS Bug #6284 (Resolved): client: failed xlist assert on put_inode()
- 05:46 AM Subtask #5862 (In Progress): FileStore must work with ghobjects rather than hobjects
- 05:44 AM Subtask #6113 (Resolved): add ceph osd pool create [name] [key=value]
- 04:03 AM Revision 0681971e (ceph): Makefile: add extra cls DENCODER_DEPS in the cls makefile, not rgw
- They belong next to the class. Also, if rgw isn't built, ceph-dencoder
will fail to link.
Fixes: #6352
Tested-by: H... - 01:15 AM Revision c2934655 (ceph): osd: change how we work around an interface limitation.
- If this had ever actually been triggered we would have hit an assert
in the OpRequest destructor that op->request is ... - 01:15 AM Revision ef1d62b4 (ceph): OpTracker: include a destructor for the TrackedOp base class.
- Our method of handling the OpRequest destructor is a little weird,
but we're about to get rid of the request member f... - 01:15 AM Revision e9bcd4c6 (ceph): osd: use TrackedOp::get_req() instead of direct access to the request.
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 01:15 AM Revision f7f30055 (ceph): OpTracker: provide a default implementation of TrackedOp::state_string
- We're moving towards dynamically-allocated states instead of the static
ones this started with, so the whole bitmask-... - 01:15 AM Revision a2d633bb (ceph): OpTracker: demand that a TrackedOp gets to own its Message for life.
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 01:15 AM Revision 9e0b5eae (ceph): OpTracker: get rid of TrackedOp::received_time for the Message
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 01:14 AM Revision 0678dcdd (ceph): OpRequest: remove obsolete comment about ref-counting (use OpRequestRef!)
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 01:14 AM Revision 24c33896 (ceph): OpTracker: start making the OpTracker into a generic
- We're starting by templating the create_request function and having
the OpTracker work in terms of TrackedOp[Ref]s in... - 01:14 AM Revision 5fdaccd2 (ceph): OpTracker: add an init_from_message() to the TrackedOp interface
- This can be used for the concrete implementations to gather any
extra data out of the message and do whatever extra s... - 01:14 AM Revision 3cb6abec (ceph): OpTracker: move the OpTracker and OpHistory into common/TrackedOp.[h|cc]
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 01:14 AM Revision a8bbb81b (ceph): OpTracker: remove the references to "osd" in config variables
- We may want to have daemon-specific settings in the future, but that
will be a small interface change and in the mean... - 01:14 AM Revision 06e1bcad (ceph): OpTracker: move OpTracker pointer and some init code into TrackedOp
- Clean up some member privacy issues while we're working on them.
Signed-off-by: Greg Farnum <greg@inktank.com> - 01:06 AM Revision 91dcdec1 (ceph): Merge pull request #609 from dmick/wip-6293
- mon: fix wrong arg to "instructed to" status message
Reviewed-by: David Zafman <david.zafman@inktank.com> - 12:29 AM Revision b993ecac (ceph): Update many unit tests to reflect 2yrs of changes
- These tests hadn't been updated in over two years. Only one is left
failing. - 12:20 AM Revision 53e17c2a (ceph): osd: move pow2_hist_t out of osd_types and into include/
- This has only been used for the OSD so far, but as with the rest
of the OpRequest stuff, it's actually pretty generic...
09/19/2013
- 11:14 PM Revision ffe7d80c (ceph): Add pytest.ini
- So far this just tells py.test not to recurse into directories
containing tests it doesn't need to run. - 11:05 PM Revision 16ebb25f (ceph): mon: fix wrong arg to "instructed to" status message
- Fixes: #6293
Signed-off-by: Dan Mick <dan.mick@inktank.com> - 11:04 PM Revision 5c46fc44 (ceph): doc: Made some changes and incorporated a draft diagram.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 11:03 PM Revision 5bb7417a (ceph): doc: Added draft of region/zone diagram.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:33 PM Revision bcc1680a (ceph): mon: fix inverted test in osd pool create
- When using the properties key=value only, the test was inverted
and an attempt to obtain a substring at index string:... - 10:00 PM Revision f3718c29 (ceph): code_env: use feature test for PR_GET_NAME support
- Function `get_process_name` has platform specific dependencies. Check
for Linux prctl function and correct command fl... - 09:07 PM Revision 60f5c305 (ceph): Merge pull request #101 from ceph/fix-adjust-ulimits-b
- Put helper scripts in /usr/bin
- 09:06 PM Revision 974aa6ae (ceph): Put helper scripts in /usr/bin
- 09:04 PM Bug #6352 (Resolved): Build from source failed
- 08:04 PM Bug #6352: Build from source failed
- make clean
./autogen.sh
./configure
make
problem still exists - 05:42 AM Bug #6352: Build from source failed
- can you try 'make distclean'? and/or a clean checkout? my guess is that automake isn't smart enough to handle the m...
- 08:57 PM Revision 136ef1cd (ceph): Merge pull request #100 from ceph/wip-tests
- Add test for teuthology.suite.build_email_body()
- 08:55 PM Revision 9ae29fa3 (ceph): Port to py.test
- 08:36 PM Revision 40907535 (ceph): Add test for teuthology.suite.build_email_body()
- 08:07 PM Revision babeb00c (ceph): rgw: use bufferlist::append() instead of bufferlist::push_back()
- push_back() expects char *, whereas append can append a single char.
Appending a NULL char to push_back is cast as a ... - 08:07 PM Revision daf85c45 (ceph): rgw: NULL terminate buffer before parsing it
- Fixes: #6175
Backport: dumpling
We get a buffer off the remote gateway which might
not be NULL terminated. The JSON p... - 08:03 PM Revision 08fe028b (ceph): rgw: use bufferlist::append() instead of bufferlist::push_back()
- push_back() expects char *, whereas append can append a single char.
Appending a NULL char to push_back is cast as a ... - 08:01 PM Bug #6359 (Resolved): FileStore::lfn_unlink: still need to check st_nlink
- 08:01 PM Revision 5216ed13 (ceph): Merge pull request #604 from ceph/wip-buck-centos-core
- Wip buck centos core
Reviewed-by: Gary Lowell <gary.lowell@inktank.com> - 07:52 PM Revision fd6646f2 (ceph): Makefile: fix unittest_arch
- Also broken by makefile refactor.
Signed-off-by: Sage Weil <sage@inktank.com> - 07:13 PM Revision c73040a5 (ceph): rgw: don't call list::size() in ObjectCache
- Fixes: #6286
Use an external counter instead of calling list::size()
Reviewed-by: Sage Weil <sage@inktank.com>
Signe... - 07:13 PM Revision be2907ef (ceph): rgw: don't call list::size() in ObjectCache
- Fixes: #6286
Use an external counter instead of calling list::size()
Reviewed-by: Sage Weil <sage@inktank.com>
Signe... - 07:12 PM Revision 14f6b749 (ceph): rgw: don't call list::size() in ObjectCache
- Fixes: #6286
Use an external counter instead of calling list::size()
Reviewed-by: Sage Weil <sage@inktank.com>
Signe... - 06:41 PM rbd Bug #6293 (Resolved): Using wildcard produces wrong output
- 06:21 PM Bug #5634 (In Progress): auth startup reports "ObjectNotFound" when keyring file is unreadable
- 06:18 PM Bug #6272 (Can't reproduce): ceph command usage missing setcrushmap
- Verified with David
- 04:39 PM Bug #6357: inverted test in osd pool create
- Musing: it might be nice to have a "key=value" validation type (CephKeyVal?) to catch things like this in the front e...
- 03:40 PM Bug #6357 (Fix Under Review): inverted test in osd pool create
- "proposed fix":https://github.com/ceph/ceph/pull/608
- 03:25 PM Bug #6357 (Resolved): inverted test in osd pool create
- Because "equal != string::npos":https://github.com/ceph/ceph/blob/5216ed134b99e7dfd9e936c632b3ad2d01acd481/src/mon/OS...
- 03:48 PM Revision 5421d6da (ceph): Makefile: fix unittest_crc32c
- This got dropped during the makefile refactor.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:08 PM Bug #5804 (Need More Info): mon: binds to 0.0.0.0:6800something port
- I did see this again on the mira045 etc. cluster, as I chatted with Joao about, and apparently mattt on IRC is experi...
- 01:37 PM CephFS Feature #6332 (Fix Under Review): mds: add config option disabling snapshots by default
- wip-6332; https://github.com/ceph/ceph/pull/606
- 01:22 PM rgw Feature #5170 (Fix Under Review): RGW: Object restriping tool to fix large objects from argonaut.
- Pushed implementation to wip-5170. It's built on top of bobtail. Adding the following commands to radosgw-admin:
<... - 11:11 AM rgw Feature #5170 (In Progress): RGW: Object restriping tool to fix large objects from argonaut.
- 01:06 PM rgw Bug #6340 (Resolved): rgw: segfault in copy_obj
- Pushed fix for both this and #6175).
- 01:05 PM rgw Bug #6175 (Resolved): rgw: valgrind: invalid reads in copy_obj
- pushed fix, backported to dumpling. Also needed to push a second fix (#6340).
- 12:23 PM Bug #6356 (Resolved): docs should warn against executing ceph-deploy as root
- This section of the docs: http://ceph.com/docs/master/start/quick-start-preflight/#configure-ssh talks about configur...
- 12:09 PM rgw Bug #6286 (Resolved): rgw: use of std::list::size() in ObjectCache
- Pushed into bobtail, cuttlefish, and dumpling.
- 11:10 AM devops Bug #6288 (Resolved): 'ceph-deploy mon create' with --cluster flag fails
- Merged to ceph-deploy master branch with hash: a4b6b6f
- 08:13 AM devops Bug #6288 (Fix Under Review): 'ceph-deploy mon create' with --cluster flag fails
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/86
- 09:25 AM Feature #6354 (Resolved): ObjectStore: allow xattrs as large as the underlying FS allows
- Right now our chained xattr implementation hard-codes a limit of 2K for each individual xattr. This is smaller than t...
- 07:47 AM Revision d8b55837 (ceph): ErasureCode: proofread abstract API documentation
- * Andreas-Joachim Peters suggests to reduce copies to the minimum. When
possible the output arguments will just poi... - 07:47 AM Revision def05f06 (ceph): ErasureCode: improve API implementation example
- * minimum_to_decode and minimum_to_decode_with_cost are replaced with
meaningfull examples instead of placeholders
... - 07:47 AM Revision 7324931d (ceph): ErasureCode: plugin loading in progress flag
- The bool loading data member of ErasureCodePluginRegistry is
set to true when a plugin is being loaded, to provide an... - 07:47 AM Revision 4c9497f9 (ceph): ErasureCode: complete plugin loader unit tests
- * TestErasureCodePluginExample.cc is renamed to TestErasureCodePlugin.cc
because it's not limited to the example wh... - 07:31 AM devops Bug #6289 (Resolved): new remote connection needs to be able to know about sudo
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/76
Merged into ceph-deploy master branch with hash: ... - 06:17 AM Bug #6336 (Fix Under Review): xattrs limit breaks rgw large objects
- wip-6336
- 06:01 AM Revision 862e0f12 (ceph): mds: fix MDCache::truncate_inode_finish() journal
- we should add projected parent directory's context to the journal
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 06:01 AM Revision e303b964 (ceph): mds: re-integrate stray when link count >= 1
- no reason not to rename inode out of the stray directory if the
inode's link count > 1
Signed-off-by: Yan, Zheng <zh... - 06:01 AM Revision 298c39f2 (ceph): mds: touch dentry bottom recursively
- Deleted directory inode's dirfrags may contain some null dentries.
When touch_dentry_bottom() is called, also move th... - 06:01 AM Revision c63b4edc (ceph): mds: allow delay in evaluating stray
- Add a new parameter 'delay' to MDCache::eval_stray(). If 'delay'
is true, MDCache::eval_stray() adds the stray dentry... - 05:59 AM rbd Bug #5876 (Pending Backport): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= i...
- the fixes just went upstream to linus's tree and are not in a released kernel yet. as soon as they appear there i wi...
- 01:25 AM rbd Bug #5876: Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_request->next_co...
- @Sage : in which kernel version can I found this fix please ?
- 03:57 AM Revision 1685de67 (ceph): Fix typo
- 03:38 AM Revision 96010924 (ceph): os/FileStore: fix uninitialized var
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:26 AM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- @Sage : does this fix present upstream ? in which kernel version ?
09/18/2013
- 11:21 PM Bug #6352 (Resolved): Build from source failed
- When pull from master branch and make failed:...
- 10:21 PM Bug #6336: xattrs limit breaks rgw large objects
- I don't think 1MB is ok, we should revert it for dumpling. I opened another two issues for revisiting the object mani...
- 08:05 PM Bug #6336: xattrs limit breaks rgw large objects
- Greg Farnum wrote:
> Huh, I'd forgotten about that. You're right of course. I'm not sure what issue Sage ran into th... - 01:55 PM Bug #6336: xattrs limit breaks rgw large objects
- Huh, I'd forgotten about that. You're right of course. I'm not sure what issue Sage ran into that he thought we neede...
- 12:23 PM Bug #6336: xattrs limit breaks rgw large objects
- 1. First of all, we already split xattrs into multiple xattrs when they get beyond a certain size in the osd. There a...
- 11:53 AM Bug #6336: xattrs limit breaks rgw large objects
- We should have a discussion with Sam and Sage before taking any action on this. Things I can tell you:
1) The limit ... - 08:26 PM Revision b66ac77f (ceph): osdc/ObjectCacher: finish contexts after dropping object reference
- The context to finish can be class C_Client_PutInode, which may drop
inode's last reference. So we should first drop ... - 07:31 PM Revision ce723b5a (ceph): doc/release-notes: v0.69
- Signed-off-by: Sage Weil <sage@inktank.com>
- 07:23 PM Revision af5ae2dd (ceph): Merge pull request #98 from ceph/time-fix
- If duration is missing from summary.yaml, use 0
- 07:08 PM Revision d83912e0 (ceph): If duration is missing from summary.yaml, use 0
- 06:41 PM Revision bbfbb097 (ceph): rgw: drain pending requests before completing write
- Fixes: #6268
When doing aio write of objects (either regular or multipart parts) we
need to drain pending aio request... - 06:40 PM Revision a855aba9 (ceph): rgw: drain pending requests before completing write
- Fixes: #6268
When doing aio write of objects (either regular or multipart parts) we
need to drain pending aio request... - 03:35 PM Revision db92bb91 (ceph): Merge pull request #97 from ceph/sentry
- Fix logs URL on Sentry pages.
- 03:30 PM Revision aaa3cf9b (ceph): Fix logs URL on Sentry pages.
- 02:38 PM CephFS Bug #6349 (Duplicate): MDS: failed assert !segments.empty() while rejoining after being standby-r...
- ...
- 02:38 PM Bug #6348 (Resolved): ceph-deploy new.new needs to use same seperator as conf.write
- currently ceph-deploy new creates space seperated variable names such as:
(./{cluster}.conf)
osd journal size =... - 02:27 PM Bug #6347 (Can't reproduce): ObjectCacher: generated request with differing data and data length ...
- /a/teuthology-2013-09-17_23:01:16-fs-next-testing-basic-plana/1237
Unfortunately we don't have any ObjectCacher lo... - 02:19 PM Bug #6346 (Resolved): OSD: do not crash on bad client op input
- ...
- 01:39 PM devops Bug #6345 (Resolved): order of init.d script shutdown sequence
- The init.d shutdown sequence first stops the monitors, then the osds and then the mds. I think this sequence should ...
- 01:15 PM devops Feature #6154: ceph-deploy should be able to use an argument "fs-type" to specify the filesystem ...
- Sure, done. See https://github.com/ceph/ceph-deploy/pull/85.
- 07:08 AM devops Feature #6154: ceph-deploy should be able to use an argument "fs-type" to specify the filesystem ...
- Benoit, the patch looks good. Could you ammend the commit to have a `signed-by` signature? This is done with the `-s`...
- 01:05 PM devops Feature #6017 (Resolved): ceph-deploy mon create: create on all mons in ceph.conf + then do gathe...
- Merged into ceph-deploy master branch with hash: e66d751
\o/ - 09:54 AM devops Feature #6017 (Fix Under Review): ceph-deploy mon create: create on all mons in ceph.conf + then ...
- Opened pull request https://github.com/ceph/ceph-deploy/pull/82
- 11:38 AM rgw Bug #6268 (Resolved): rgw: RGWPutObj calls processor->complete() before all inflight data is drained
- backported to bobtail, cuttlefish, dumpling.
- 11:32 AM rgw Feature #6341 (New): rgw: stress failure testing
- So that we can detect issues like #6368
- 10:35 AM rgw Bug #6340: rgw: segfault in copy_obj
- The fix to #6175 actually broke it. Pushed a fix to wip-6340. We'll need to squash this one with wip-6175 when we bac...
- 10:12 AM rgw Bug #6340 (Resolved): rgw: segfault in copy_obj
- This occurred on the next branch:
http://qa-proxy.ceph.com/teuthology/teuthology-2013-09-17_23:01:11-rgw-next-test... - 10:09 AM Feature #5035: rados: smarter localized reads
- Blueprint: http://wiki.ceph.com/01Planning/02Blueprints/Emperor/librados%2F%2Fobjecter%3A_smarter_localized_reads
- 09:58 AM rgw Feature #6339 (Resolved): rgw: compact manifest data
- manifest data includes lots of duplicate strings, we can probably omit most of these (e.g., add a prefix field).
- 09:57 AM rgw Feature #6338 (Resolved): rgw: better manifest scaling
- 09:12 AM devops Bug #6335 (Resolved): ceph-deploy may *still* hang with pushy
- We moved the conn.close() call as early as possible in all `mon create` calls.
Pull request: https://github.com/ce... - 09:11 AM Revision 33671f35 (ceph): Merge branch 'next'
- 08:57 AM rgw Bug #3896 (New): rest-bench common/WorkQueue.cc: 54: FAILED assert(_threads.empty())
- 08:56 AM devops Bug #6337 (Resolved): Closed connection causes import errors for Debian mon create commands
- 08:56 AM devops Bug #6337: Closed connection causes import errors for Debian mon create commands
- Merged into ceph-deploy master branch: b67281e
- 07:35 AM devops Bug #6337 (Fix Under Review): Closed connection causes import errors for Debian mon create commands
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/84
- 07:22 AM devops Bug #6337 (Resolved): Closed connection causes import errors for Debian mon create commands
- Because of a last minute fix to prevent connections hanging on `mon create` that meant closing the pushy connection
... - 08:30 AM devops Bug #6330 (Closed): ceph-deploy does not use /etc/hosts entry making functional DNS a dependency
- 01:40 AM Revision 6ca6f2f9 (ceph): v0.69
09/17/2013
- 11:13 PM Revision b923152e (ceph): Merge pull request #96 from ceph/wip-fix-sudoers
- Make sed expressions safe to run multiple times
- 11:04 PM Revision bbda7522 (ceph): Make sed expressions safe to run multiple times
- Also, make them ignore commented lines.
- 09:04 PM Revision 5541a1df (ceph): doc: Updated link to Storage Cluster Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:04 PM Revision 6af8e3c8 (ceph): doc: Updated link to Storage Cluster Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:03 PM Revision b1d58fac (ceph): doc: Updated link to Storage Cluster Quick Start.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:03 PM Revision a39de7b1 (ceph): doc: Made sysvinit and service sections parallel to upstart for clarity.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:02 PM Revision 0fed6ab0 (ceph): doc: Updated for 3-node deployment. Leaner discussion. More use cases.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:02 PM Revision 3a3ef336 (ceph): doc: Removed introductory material. Renamed the page.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:01 PM Revision c054469f (ceph): doc: Updated for 3-node deployment and multiple Linux distributions.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:22 PM Revision 31fff93b (ceph): doc: Added Intro to Ceph to Index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:22 PM Revision fcd749ff (ceph): doc: Excised content from "Getting Started" and created Intro to Ceph.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:04 PM devops Bug #6330: ceph-deploy does not use /etc/hosts entry making functional DNS a dependency
- Thanks Alfredo. I tried to recreate the error I encountered as a test case but have failed to make it re-occur. I now...
- 01:24 PM devops Bug #6330: ceph-deploy does not use /etc/hosts entry making functional DNS a dependency
- Can you give me an example on where does ceph-deploy fails to use something that is defined in `/etc/hosts` ?
All ... - 07:10 PM Revision c4a47ffd (ceph): Add dummy suite.
- 06:47 PM Revision 61ddeb6a (ceph): Revert "suite: don't schedule follow-on summary job for an empty run"
- This reverts commit a2b7c728964fb0064ba2a69818289caf723f09fc.
- 06:21 PM Bug #6336 (Resolved): xattrs limit breaks rgw large objects
- a 64k attrs limit was introduced in dumpling, however, that completely breaks rgw when trying to upload large objects...
- 06:14 PM Revision b37f88c9 (ceph): Merge pull request #586 from ceph/wip-copyfrom-big
- Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com> - 06:06 PM Revision 045b9029 (ceph): osd: allow a copy_from without knowing the src_version
- If we don't specify the version up front, learn the version after the first
chunk and enforce it thereafter to ensure... - 06:06 PM Revision 3a001878 (ceph): librados: test copy_from without src_version specified
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:06 PM Revision a80f831b (ceph): ceph_test_rados: identify write seq_num in output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:06 PM Revision 4e29e362 (ceph): osd/ReplicatedPG: stage object chunks to replicas during COPY_FROM
- As we get each chunk of data during the COPY_FROM operation, write it out
to a temporary object on the replicas. Whe... - 06:06 PM Revision 5921703e (ceph): ceph_test_rados: more readable output
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:06 PM Revision df7c36ac (ceph): osd/ReplicatedPG: factor some bits into finish_copy
- This is a bit cleaner and hopefully more usable for osd-driven cache
promotion.
Signed-off-by: Sage Weil <sage@inkta... - 06:06 PM Revision f97277cc (ceph): osd: add infrastructure to block io on an obc
- Add an is_blocked() method for the obc, and add infrastructure to block
any operations if it returns true. Clean up ... - 06:06 PM Revision cdc637f0 (ceph): osd: block requests on object during COPY_FROM
- Block any request on an object (read or write) during the COPY_FROM
operation.
This could potentially be broken down... - 06:06 PM Revision d050596a (ceph): ceph_test_rados: use get_version64() throughout
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:06 PM Revision 83f12e46 (ceph): ceph_test_rados: submit a racing read with every COPY_FROM
- Verify that the racing read completes after the COPY_FROM does (i.e., is
blocked by it).
Signed-off-by: Sage Weil <s... - 05:39 PM Revision 1f80d632 (ceph): doc: Replaced code-block with inline literal to fix auto numbering.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 05:34 PM Revision 7d5dfa2b (ceph): doc: Made s3gw.fcgi paths consistent.
- fixes: #6182
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 05:26 PM devops Bug #6335 (Resolved): ceph-deploy may *still* hang with pushy
- We need to close the connection as early as possible in an attempt to mitigate probably hanging issues....
- 04:58 PM Revision 0d20cae0 (ceph): mon: OSDMonitor: multiple rebuilt full maps per transaction
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 03:19 PM rgw Bug #6176: rgw: valgrind: leak in copy_obj
- 03:18 PM rgw Bug #3896: rest-bench common/WorkQueue.cc: 54: FAILED assert(_threads.empty())
- I'm seeing this for every rest-bench I run (seq, write and cleanup) on both Cuttlefish and Dumpling.
@cephdrop@cep... - 02:42 PM rgw Bug #6334 (Resolved): RGW admin socket doesn't appear to exist by default
- it should. Testing wip-6286 based on 0.67.3.
- 01:47 PM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- We had an osd process die unexpectedly a few days ago. I run a cronjob that 'service ceph start's on all nodes for th...
- 12:04 PM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Added a graph of the same time period from last night / this morning for a comparison of what the graphs should look ...
- 11:57 AM Bug #6333: Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- In the attached image you'll see graphs of a set of nine Windows guests running video surveillance over the duration ...
- 11:47 AM Bug #6333 (Closed): Recovery and/or Backfill Cause QEMU/RBD Reads to Hang
- Some (but not all) of our qemu instances booted from rbd copy on write clones experience i/o outages during recovery ...
- 01:31 PM Revision 59147be9 (ceph): osd: compute full ratio from kb_avail
- On btrfs, kb_used + kb_avail can be much smaller than total kb, and
what really matters to avoid filling up the disk ... - 12:43 PM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- And for a successful run for two nodes, it looks like this:...
- 12:42 PM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- This is how it looks for monitors that never reach quorum, it loops for 5 times per monitor with incremental wait tim...
- 12:19 PM RADOS Feature #6325: mon: mon_status should make it clear when the mon has connection issues
- Hmmm. The issue with doing this in the Messenger is that all those errors are expected to occur at some point — failu...
- 02:12 AM RADOS Feature #6325: mon: mon_status should make it clear when the mon has connection issues
- possible approach:
Considering the class Monitor is a dispatcher of the messenger, add a new courtesy function to ... - 11:09 AM Bug #6207: Found incorrect object contents
- The comments from me and Sage about wip-copyfrom-big sadly refer to a different issue that would not have been presen...
- 10:57 AM Bug #6207: Found incorrect object contents
- pushed what it hink is a fix to wip-copyfrom-big. should get squashed down once we verify.
- 10:39 AM rgw Documentation #6182 (Resolved): Conflicting locations for s3gw.fcgi
- See http://ceph.com/docs/master/install/rpm/#installing-ceph-object-storage
- 10:33 AM rgw Documentation #6182 (In Progress): Conflicting locations for s3gw.fcgi
- 09:56 AM CephFS Feature #6332 (Resolved): mds: add config option disabling snapshots by default
- Right now snapshots are even more broken than they used to be (see #5250). Add a config option that controls whether ...
- 09:45 AM Bug #6301: ceph-osd hung by XFS using linux 3.10
- It woudl probably be best ot send the xfs info to the xfs@oss.sgi.com list.
Also--you probably don't want to use '... - 09:31 AM Bug #6331 (Rejected): Disk partition and replicas
- jordi - these types of questions would be more appropriately resolved in #ceph on IRC or by sending an e-mail to ceph...
- 04:00 AM Bug #6331 (Rejected): Disk partition and replicas
- Hi!
I've a remote server with one unit where is installed Ubuntu. I can't create another partition on the disk to in... - 08:58 AM Revision 3966e6ea (ceph): ErasureCode: proofread abstract API documentation
- * Andreas-Joachim Peters suggests to reduce copies to the minimum. When
possible the output arguments will just poi... - 08:58 AM Revision 89e8b8be (ceph): ErasureCode: improve API implementation example
- * minimum_to_decode and minimum_to_decode_with_cost are replaced with
meaningfull examples instead of placeholders
... - 07:56 AM Subtask #5879 (Resolved): jerasure plugin
- 07:42 AM devops Bug #6300: ceph-deploy: mon create prompts for password
- This is now fixed in the library handling ceph-deploy connections: https://github.com/alfredodeza/remoto/commit/ed273...
- 07:11 AM devops Bug #6300: ceph-deploy: mon create prompts for password
- 06:57 AM devops Bug #6300: ceph-deploy: mon create prompts for password
- Actually, this is kind of valid (my initial take on it was that keys where missing).
This is caused by how ceph-de... - 05:07 AM Revision 971bf60b (ceph): Remove unneeded junit4 check
- We refactored the java tests to not use
the ExternalResource class, so this test
is no longer necessary.
Signed-off-... - 05:03 AM Revision e38bd8d5 (ceph): Removing extraneous code
- The ExternalResource code was unnecessary and caused
issues on CentOS. Removing it.
Update Makefile.am to reflect the... - 05:02 AM Revision cd6f4bcd (ceph): Use a loop for testing jdk paths
- Loop through a list of sensible default
locations for a JDK, stopping if a
workable JDK is found.
Also, add support f... - 04:06 AM Revision 109cd50c (ceph): Merge pull request #601 from pipul/feature/develop_130917
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 03:22 AM Revision 4520c5f6 (ceph): suite: do not calculate product on an empty list (take 2)
- The original attempt to fix this with dda7954090ccc9ffd8ecd961d6b530a0e6d24964
failed because I screwed up the indent... - 02:34 AM Revision 3cef7554 (ceph): fix some comments
- Signed-off-by: fangdong <yp.fangdong@gmail.com>
- 02:08 AM devops Feature #6154: ceph-deploy should be able to use an argument "fs-type" to specify the filesystem ...
- Here's a patch to add the proposed option. Let me know if it needs adjustments.
- 02:00 AM Revision ae7912f5 (ceph): doc: Added conf example.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:57 AM Revision e55d59f8 (ceph): doc: Updated usage.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 01:40 AM Revision 0be2c87a (ceph): doc: Removed --fs-type option and text.
- fixes: #6326
Signed-off-by: John Wilkins <john.wilkins@inktank.com> - 01:40 AM Fix #6278: osd: throttle snap trimming
- Wade,
I think this issue is not related to the SQL locking. At least not in my case. I've done as suggested by Mik... - 01:38 AM Revision 874186ba (ceph): doc: Updated the usage scenario and made a few syntax edits.
- fixes: #6308
Signed-off-by: John Wilkins <john.wilkins@inktank.com>
09/16/2013
- 11:33 PM Revision e65d6e2a (ceph): Revert "suite: do not calculate product on an empty list"
- This reverts commit dda7954090ccc9ffd8ecd961d6b530a0e6d24964.
This commit was causing the number of jobs scheduled p... - 10:49 PM Bug #6207: Found incorrect object contents
- /a/sage-bug-6207-c/1
- 10:44 PM Bug #6207: Found incorrect object contents
- which run are these notes referring to?
- 05:30 PM Bug #6207: Found incorrect object contents
- http://fpaste.org/39993/79377326/ contains the output on osd.0 during backfill that concerns me if you don't want to ...
- 05:18 PM Bug #6207: Found incorrect object contents
- I looked through that failure more and gathered up some notes that I suspect will lead one of you to know what's goin...
- 04:21 PM Bug #6207: Found incorrect object contents
- [ From here to comment 11 do not apply to any instances of this bug on master or dumpling. Please disregard. ]
Sam... - 09:14 PM Revision c9c710c1 (ceph): Merge pull request #600 from dachary/fix-erasure-warning
- ErasureCode: fix uninitialized variable warning
Reviewed-by: Greg Farnum <greg@inktank.com> - 09:04 PM Revision abd2fcd5 (ceph): ErasureCode: fix uninitialized variable warning
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:57 PM Revision 4930ccb8 (ceph): Merge pull request #597 from ceph/remove-hadoop-shim
- This branch built fine on the gitbuilders and the list of removed files looks good to me.
Reviewed-by: Greg Farnum <... - 08:50 PM devops Bug #6330 (Closed): ceph-deploy does not use /etc/hosts entry making functional DNS a dependency
- This is to avoid what I consider to be a bug in Linux where some tools do not respect the /etc/nsswitch.conf settings...
- 08:49 PM Revision a8e77738 (ceph): Merge pull request #94 from ceph/wip-fix-sudoers
- Use teuthology-specific backup for /etc/sudoers
- 08:25 PM Revision 8b63396e (ceph): Use teuthology-specific backup for /etc/sudoers
- 06:51 PM Bug #6326 (Resolved): docs: ceph-deploy does not have a `--fs-type`
- See http://ceph.com/docs/master/rados/deployment/ceph-deploy-osd/
- 05:35 PM Bug #6326 (In Progress): docs: ceph-deploy does not have a `--fs-type`
- 10:41 AM Bug #6326 (Resolved): docs: ceph-deploy does not have a `--fs-type`
- I've gone through a few people asking why the feature to alter the filesystem type from ceph-deploy doesn't work, the...
- 06:50 PM Revision 5ca6bc39 (ceph): Merge pull request #93 from ceph/wip-runfix
- Make run_job merge job_config['config'] if needed
- 06:49 PM RADOS Documentation #6308 (Resolved): crushtool examples are confusing/outofdate..
- See http://ceph.com/docs/master/man/8/crushtool/
- 06:15 PM RADOS Documentation #6308 (In Progress): crushtool examples are confusing/outofdate..
- 06:14 PM Revision 4d2e3c27 (ceph): Make run_job merge job_config['config'] if needed
- 05:37 PM Revision c36da3df (ceph): Merge pull request #92 from ceph/sentry
- Be less picky about trailing slashes.
- 05:35 PM Revision fad71073 (ceph): Be less picky about trailing slashes.
- 04:34 PM rgw Bug #6176 (Fix Under Review): rgw: valgrind: leak in copy_obj
- 03:21 PM rgw Bug #6176: rgw: valgrind: leak in copy_obj
- hmm.. found an issue with my fix, redoing.
- 02:59 PM rgw Bug #6176 (Fix Under Review): rgw: valgrind: leak in copy_obj
- pushed a fix to wip-6176.
- 11:08 AM rgw Bug #6176: rgw: valgrind: leak in copy_obj
- just to clarify: teuthology run was against this commit, not when the bug was introduced.
- 11:07 AM rgw Bug #6176: rgw: valgrind: leak in copy_obj
- happened in commit:56ff4101a12e190caea9805dd5fb250ab5fa8e8c
- 03:01 PM Bug #5700: very high memory usage after update
- So after 5 days of having latest dumpling running, memory usage is still quite high:...
- 12:47 PM Documentation #6327 (Closed): Update CloudStack docs for 4.2
- Need to update CloudStack docs for 4.2.
- 12:36 PM devops Bug #6324 (Resolved): add a timeout flag for commands that may hang
- 10:33 AM devops Bug #6324: add a timeout flag for commands that may hang
- Fixed and merged into ceph-deploy master branch with hash: ab46733
- 09:45 AM devops Bug #6324 (Fix Under Review): add a timeout flag for commands that may hang
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/77
- 07:18 AM devops Bug #6324 (Resolved): add a timeout flag for commands that may hang
- There are certain commands that can cause a remote process to hang if we are capturing both stderr and stdout and som...
- 09:55 AM devops Bug #6314: catch case where mon starts up but has rank -1 accordingly to mon_status.
- Greg, yes, you are correct. The idea here is that we will implement a command to deploy all monitors defined initiall...
- 09:53 AM devops Bug #6314 (In Progress): catch case where mon starts up but has rank -1 accordingly to mon_status.
- Created issue #6324 to prevent this command from hanging.
- 08:48 AM Fix #6278: osd: throttle snap trimming
- Its possible, that sql type workflows and ceph have an issue. I am going to investigate that on my own pre-production...
- 08:17 AM Fix #6278: osd: throttle snap trimming
- It seems to me that I am also effected by this issue with 3-5 virtual machines crashing on a daily basis with a lot o...
- 08:39 AM Bug #6323 (Fix Under Review): mon: osdmon: don't create a huge transaction on update_from_paxos()...
- 08:39 AM Bug #6322 (Fix Under Review): mon: osdmon: write 'latest_full' after rebuilding full version from...
- 08:14 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- Just created issue #6325 to clearly tell when there is a connection problem, which (currently) it is impossible to te...
- 08:12 AM RADOS Feature #6325 (New): mon: mon_status should make it clear when the mon has connection issues
- If `mon_status` is called when having network connection issues it will not state anything that can alert a user/syst...
- 03:56 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- I have just managed to deploy 3 ceph nodes successfully in Ubuntu Raring using Dumpling 0.67.3. The above issue looks...
09/15/2013
- 11:33 PM Revision 81983bab (ceph): mon: OSDMonitor: update latest_full while rebuilding full maps
- Not doing so will make the monitor rebuild the osdmap full versions, even
though they may have been rebuilt before, e... - 11:32 PM Revision 4ac1570c (ceph): mon: OSDMonitor: smaller transactions when rebuilding full versions
- Otherwise, for considerably sized rebuilds, the monitor will not only
consume vast amounts of memory, but it will als... - 09:43 PM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Hi All,
I am still hitting this in RHEL 6.4 with latest dumpling release (ceph-0.67.3-0.el6.x86_64).
For my setup,... - 01:13 PM Bug #6323: mon: osdmon: don't create a huge transaction on update_from_paxos(), when rebuilding f...
- 12:43 PM Bug #6323 (Resolved): mon: osdmon: don't create a huge transaction on update_from_paxos(), when r...
- If we have thousands of missing full versions (see #6322), our memory consumption can skyrocket. And we may end up b...
- 01:12 PM Bug #6322: mon: osdmon: write 'latest_full' after rebuilding full version from incrementals on up...
- 12:41 PM Bug #6322: mon: osdmon: write 'latest_full' after rebuilding full version from incrementals on up...
- Given monitor on dumpling has
fc: 505 ; lc: 168872; latest_full: 505 ; diff: 168367
This leads to a significant... - 12:34 PM Bug #6322 (Resolved): mon: osdmon: write 'latest_full' after rebuilding full version from increme...
09/14/2013
- 01:09 AM Revision 01ec6a3f (ceph): Merge pull request #538 from dachary/wip-5879
- jerasure-1.2A plugin
Reviewed-by: Samuel Just <sam.just@inktank.com>
09/13/2013
- 10:35 PM Revision 4216eac0 (ceph): rgw: try to create log pool if doesn't exist
- When using replica log, if the log pool doesn't exist all operations are
going to fail. Try to create it if doesn't e... - 08:59 PM Revision 7b908b41 (ceph): modified rgw tests and fs tests to get it going in the nightlies
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 08:40 PM Revision 0d37a334 (ceph): added rgw task
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 08:39 PM Revision b86c0686 (ceph): hadoop: remove hadoop shim
- The in-tree Hadoop shim was a combination of libcephfs wrapper, and the
bits to support Hadoop. This has been replace... - 06:52 PM Feature #6001 (Resolved): EC: [link] jerasure plugin
- 01ec6a3fdf9da8b35cc034788ab306957d5fd969 landed
- 05:02 PM Revision e7f74831 (ceph): rgw: NULL terminate buffer before parsing it
- Fixes: #6175
Backport: dumpling
We get a buffer off the remote gateway which might
not be NULL terminated. The JSON p... - 03:57 PM Revision 40e0cabc (ceph): Merge pull request #594 from ceph/fix-no-tcmalloc-build
- make: add tmalloc lib dep in tcmalloc guard
Reviewed-by: Sage Weil <sage@inktank.com> - 03:54 PM rgw Bug #6302: rgw: tasks/rgw_s3tests_multiregion.yaml tests hang
- Pushed a fix to next (commit:4216eac0f59af60f60d4ce909b9ace87a7b64ccc). Still need to validate that this was the actu...
- 02:06 PM rgw Bug #6302: rgw: tasks/rgw_s3tests_multiregion.yaml tests hang
- I see this when trying to set worker bound:...
- 08:09 AM rgw Bug #6302 (Resolved): rgw: tasks/rgw_s3tests_multiregion.yaml tests hang
- > [30666] rgw/verify/{clusters/fixed-2.yaml fs/btrfs.yaml msgr-failures/few.yaml tasks/rgw_s3tests_multiregion.yaml v...
- 03:41 PM Revision 568eccf8 (ceph): Merge pull request #91 from ceph/wip-suite
- suite: do not calculate product on an empty list
- 03:39 PM Revision a2b7c728 (ceph): suite: don't schedule follow-on summary job for an empty run
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:39 PM Revision 5a083894 (ceph): suite: be verbose about how many jobs we generate
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:29 PM Revision 3f8c9690 (ceph): make: add tmalloc lib dep in tcmalloc guard
- Fixes --without-tcmalloc on boxes without libtcmalloc.
Signed-off-by: Noah Watkins <noahwatkins@gmail.com> - 03:22 PM Revision dda79540 (ceph): suite: do not calculate product on an empty list
- This fixes a bug where a directory with just % generates a
bogus job item with no actual content. (e.g.,
$ find bas... - 02:46 PM rgw Feature #6317 (New): rgw: replace pool creation
- New api to create more than 8 pgs per generated pool exists now, switch to using it.
- 01:55 PM Fix #6059: osd: block reads while repgather is writing across replicas
- Note, just extending the obc->write_lock() region doesn't really work since it can cause the op_tp to be blocked prev...
- 01:40 PM Feature #6147 (Fix Under Review): mon: calculate, expose per-pool pg stat deltas
- wip-6147 ; pull request 596
- 01:27 PM rbd Documentation #5009 (In Progress): doc: explain how to get qemu packages for each distro
- 01:24 PM rbd Feature #4013: rbd: openstack: extend nova boot api to support going from image to volume
- https://review.openstack.org/#/c/42474/
- 01:21 PM rbd Feature #4013 (Resolved): rbd: openstack: extend nova boot api to support going from image to volume
- 01:23 PM rbd Subtask #4016 (Resolved): rbd: openstack: extend nova boot api: modify libvirt driver to support ...
- 01:21 PM rbd Feature #4211 (Rejected): get good qemu, libvirt versions+patches in CentOS+
- 01:17 PM rgw Feature #6195: rgw: test full sync (with large object)
- 01:11 PM rgw Feature #4342 (Duplicate): rgw: dr: data sync agent: update sync processing state
- 01:04 PM rgw Feature #4342 (In Progress): rgw: dr: data sync agent: update sync processing state
- 01:10 PM rgw Documentation #5119 (Resolved): rgw: document which pools allowed to collide
- Added commentary to the ceph configuration reference.
- 01:09 PM rgw Documentation #5651 (Resolved): rgw: secret features need documentation
- Community fix provided.
- 01:09 PM rgw Feature #6191 (Fix Under Review): rgw: DR: per bucket replica_log handling
- 01:04 PM rgw Feature #6191 (In Progress): rgw: DR: per bucket replica_log handling
- 01:09 PM rgw Feature #6190 (Fix Under Review): rgw: DR: read list of buckets to do full sync on
- 01:04 PM rgw Feature #6190 (In Progress): rgw: DR: read list of buckets to do full sync on
- 01:07 PM devops Bug #6314: catch case where mon starts up but has rank -1 accordingly to mon_status.
- But...it *should* have rank -1 before it gets the chance to join the quorum, shouldn't it?
Or have I forgotten how r... - 01:00 PM devops Bug #6314 (Resolved): catch case where mon starts up but has rank -1 accordingly to mon_status.
- Now that `mon_status` is implemented we need some glue-code to check make it a bit more robust and ensure that the ra...
- 01:06 PM rgw Feature #6193 (In Progress): rgw: DR: per bucket sync
- 01:06 PM rgw Feature #6192 (In Progress): rgw: DR: per object sync
- 12:24 PM devops Feature #6020: radosgw-apache opinionated package
- The package should have the following
- depend on our mod_fastcgi
- enable fastcgi module
- enable rewrite mo... - 12:11 PM Bug #6313: dumpling: FAILED assert(latest->is_update()) from recover_primary()
- We restarted osd.4 and osd.1 to fix the issue.
- 12:08 PM Bug #6313 (Duplicate): dumpling: FAILED assert(latest->is_update()) from recover_primary()
- restarting the backfill target for the osd fixed the issue
- 11:51 AM devops Feature #6310: Get Dumpling into CentOS Ceph repo
- 11:50 AM devops Feature #6310 (Closed): Get Dumpling into CentOS Ceph repo
- 11:51 AM Bug #6311 (Resolved): Some scripts assume the location of python
- The following scripts' shebang strings all hardcode python's location to /usr/bin/python. They don't work on FreeBSD...
- 11:41 AM devops Feature #5956: Implement a radosgw command in ceph-deploy
- Is this a dup with 4408?
- 11:40 AM devops Feature #6067 (In Progress): ceph-deploy: make mon create catch common errors
- 11:39 AM Bug #5492: scripts installing into /usr/usr/sbin (with --prefix=/usr)
- Danny's fix does not resolve the original problem in either Ubuntu 12.04 or FreeBSD 9.1. I think that the real probl...
- 10:05 AM RADOS Documentation #6308 (Resolved): crushtool examples are confusing/outofdate..
- this example:
crushtool --build 128 shelf uniform 4 rack straw 8 root straw 0 -o map
does not work
this does wo... - 09:59 AM rgw Bug #6175 (Pending Backport): rgw: valgrind: invalid reads in copy_obj
- 09:36 AM rgw Bug #6268 (Pending Backport): rgw: RGWPutObj calls processor->complete() before all inflight data...
- 04:59 AM Bug #6301 (Need More Info): ceph-osd hung by XFS using linux 3.10
- 02:39 AM Bug #6301 (Closed): ceph-osd hung by XFS using linux 3.10
- The kernel configuration ( 3.10.11 sources ) is here : attachment:config.gz
The general ceph setup is described here...
09/12/2013
- 10:56 PM Revision 42c2b704 (ceph): Merge pull request #90 from ceph/sentry
- Fix get_http_log_path(), update callers, add tests
- 10:28 PM Revision 31f0f7ad (ceph): Fix get_http_log_path(), update callers, add tests
- 10:07 PM Revision 9de651a9 (ceph): Merge branch 'master' of github.com:ceph/teuthology
- 10:03 PM Revision eb4c575f (ceph): made help more readable
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 09:42 PM Revision 2db2ba78 (ceph): Fix TypeError
- (cherry picked from commit c4591a16e1781f8da3502b38e3dc72f629478312)
- 06:24 PM Revision 1901a145 (ceph): removed basic dir as it was empty
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:17 PM CephFS Bug #5418: kceph: crash in remove_session_caps
- 06:16 PM CephFS Bug #5927 (Resolved): kcephfs: ENOTEMPTY on rm -r
- 06:13 PM Revision 388dd1e2 (ceph): Merge branch 'wip-6226'
- 06:12 PM Revision daf417f9 (ceph): osd/ReplicatedPG.cc: Verify that recovery is truly complete
- Backportable change to insure that even if no new ops started or
are running that indeed recovery is complete. Preve... - 06:11 PM Revision 139a714e (ceph): osd/OSD.cc: Use MIN() so that we don't exceed osd_recovery_max_active
- Caused by 944f3b73531af791c90f0f061280160003545c63
Fixes: #6291
Backport: dumpling
Signed-off-by: David Zafman <da... - 05:38 PM Revision a41aa946 (ceph): Merge pull request #589 from ceph/wip-6279
- mon/MDSMonitor: don't reset incarnation when creating newfs
Reviewed-by: Greg Farnum <greg@inktank.com> - 05:17 PM Revision 6552f5a5 (ceph): Merge pull request #88 from ceph/wip-fix-clones
- Use check_output() and log.exception()
- 04:42 PM devops Bug #6300 (Resolved): ceph-deploy: mon create prompts for password
- ceph-deploy version: 1.2.3
ceph version: dumpling [v0.67.3]
on a single node setup, "mon create" command prompt... - 04:14 PM Revision e83b5def (ceph): Use check_output() and log.exception()
- This should help us figure out why our checkouts keep getting deleted.
- 03:28 PM Cleanup #6287 (Resolved): OSDmonitor.c message "still creating pgs, wait" should be explicit abou...
- 07:20 AM Cleanup #6287 (Fix Under Review): OSDmonitor.c message "still creating pgs, wait" should be expli...
- https://github.com/ceph/ceph/pull/592
- 03:18 PM rbd Bug #6299: Dumpling Creates Extra Log Files
- I have this exact same behavior since updating to dumpling. It only seems to affect dumpling. Cuttlefish and earlier ...
- 03:11 PM rbd Bug #6299 (Resolved): Dumpling Creates Extra Log Files
- Created my cluster with mkcephfs, and distribute a common ceph.conf to all nodes with monitors and osd stanzas define...
- 02:34 PM RADOS Bug #6297 (In Progress): ceph osd tell * will break when FD limit reached, messenger should close...
- In environments with a large number of OSD's (approaching or exceeding the file descriptor limit set), ceph osd tell ...
- 02:20 PM Revision 46337296 (ceph): mon/OSDMonitor: make busy creating pgs message more explicit
- Fixes: #6287
Signed-off-by: Sage Weil <sage@inktank.com> - 02:18 PM Bug #6296 (Won't Fix): osd_scrub_load_threshold Should Take Core Count Into Consideration
- osd_scrub_load_threshold defaults to 0.5 which prevents scrub starting on relatively un-loaded multi-core systems. Th...
- 01:26 PM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- Pull request to implement the new mon_status : https://github.com/ceph/ceph-deploy/pull/71
Was merged into ceph-de... - 01:24 PM devops Feature #6017 (In Progress): ceph-deploy mon create: create on all mons in ceph.conf + then do ga...
- 01:25 PM devops Bug #6288: 'ceph-deploy mon create' with --cluster flag fails
- 01:25 PM devops Bug #6288: 'ceph-deploy mon create' with --cluster flag fails
- What happens here is that the call to start the daemon in `ceph_deploy/hosts/debian/mon/create.py` does not pass the ...
- 08:27 AM devops Bug #6288 (Resolved): 'ceph-deploy mon create' with --cluster flag fails
- The command:
$ ceph-deploy --cluster ceph0 mon create cephgs-{0,1,2}
runs without error yet it fails to do anyt... - 12:32 PM Fix #6278: osd: throttle snap trimming
- For a few weeks, I've had to run with noscrub and nodeep-scrub, because both can cause 100% spindle contention result...
- 11:40 AM Fix #6278: osd: throttle snap trimming
- The fix for bug 6291 resolves an issue with recovery using more resources than it should.
A workaround is to disab... - 11:56 AM Bug #6294 (Rejected): avoid using std::list::size()
- It's O(N) and might have performance implications.
- 11:44 AM rbd Bug #6293 (Resolved): Using wildcard produces wrong output
Using a wildcard should output "osds ..... instructed to deep-scrub"
$ ceph osd deep-scrub '*'
osds 0,1,2,3 instr...- 11:20 AM Bug #6292 (Pending Backport): Verify that recovery is truly complete
- daf417f9ccc9181c549ad2d4a19b16b0c3caf85f
- 11:20 AM Bug #6292 (Resolved): Verify that recovery is truly complete
- This came out of the analysis of bug 6226. Even though that bug was actually fixed by changes that prevented a negat...
- 11:16 AM Bug #6291 (Pending Backport): Recovery can take more resources than it should
- 139a714e13aa3c7f42091270b55dde8a17b3c4b8
- 11:07 AM Bug #6291: Recovery can take more resources than it should
- Caused by 944f3b73 "OSD: only start osd_recovery_max_single_start at once"
- 11:01 AM Bug #6291 (Resolved): Recovery can take more resources than it should
The code in do_recovery() uses MAX() instead of MIN() so is can exceed osd_recovery_max_active.- 10:58 AM Feature #6189 (In Progress): cachepool: osd: promote on read
- I'm starting on this now.
- 10:50 AM Bug #6226 (Resolved): after editing crushmap and adding new hosts, injecting it, several existing...
This was already fixed by backport commit 1ea6b561 in v0.61.8 release. See previous comment.- 10:40 AM CephFS Bug #6279 (Pending Backport): creating a new fs on pools from an old fs can lead to lost MDS Tables
- 10:39 AM CephFS Bug #6279 (Resolved): creating a new fs on pools from an old fs can lead to lost MDS Tables
- Merged in commit:a41aa9468f4c8dd92604c20e015904ac75f1e746.
Thanks! - 10:07 AM Feature #6033 (Resolved): cachepool: osd: basic io decision: read/write from/to cache pool or EAG...
- This got merged into master a couple days ago; commit:383d8a199ea70578bb418cf36812963b04c42873
- 10:03 AM CephFS Feature #6290 (Resolved): Journaler: warn and shut down if we hit end of journal too early
- If a gap gets created in the journal, the Journaler shuts down replay but doesn't warn that it hit ENOENT unexpectedl...
- 09:02 AM devops Bug #6289 (Resolved): new remote connection needs to be able to know about sudo
- The new execnet library needs to know about the need to insert `sudo` to remote commands (something that was already ...
- 08:30 AM devops Feature #4954 (Resolved): ceph-deploy: help and document need to be updated for osd create
- Merged into ceph-deploy master branch with hash: 26a41b6
- 08:21 AM devops Feature #4954 (In Progress): ceph-deploy: help and document need to be updated for osd create
- pull request opened https://github.com/ceph/ceph-deploy/pull/74
- 08:23 AM devops Bug #5975 (Resolved): Find a real fix for the pushy issue of hanging/deadlocking during long-runn...
- Merged into ceph-deploy master with hash: 5a87cb8
We have now started the migration away from pushy which fixes ... - 07:26 AM devops Bug #5975 (In Progress): Find a real fix for the pushy issue of hanging/deadlocking during long-r...
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/71
- 07:33 AM Bug #5700: very high memory usage after update
- I just upgraded to dumpling: adjusted ceph.conf, restarted all mons, restarted all osds
After the restart, the osd... - 07:23 AM Revision 40613b70 (ceph): mon/MDSMonitor: don't reset incarnation when creating newfs
- Fixes: #6279
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com> - 05:51 AM Revision 31e3a51e (ceph): rgw: don't call list::size() in ObjectCache
- Fixes: #6286
Use an external counter instead of calling list::size()
Reviewed-by: Sage Weil <sage@inktank.com>
Signe... - 05:30 AM Revision 91375d09 (ceph): common: fix Mutex, Cond no-copy declarations
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:54 AM Revision 626669af (ceph): rgw: drain pending requests before completing write
- Fixes: #6268
When doing aio write of objects (either regular or multipart parts) we
need to drain pending aio request... - 01:42 AM Revision 131124d7 (ceph): rgw: drain pending requests before completing write
- Fixes: #6268
When doing aio write of objects (either regular or multipart parts) we
need to drain pending aio request... - 12:13 AM Revision 40d6c60f (ceph): feature # 5942. Added examples to teuthology binaries help page
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
09/11/2013
- 11:43 PM Cleanup #6287 (Resolved): OSDmonitor.c message "still creating pgs, wait" should be explicit abou...
- In the case where the cluster is still busy creating PGs after a 'pool set pg_num' and a 'pool set pgp_num' is done, ...
- 11:00 PM rgw Bug #6286 (Pending Backport): rgw: use of std::list::size() in ObjectCache
- 10:26 PM rgw Bug #6286 (Resolved): rgw: use of std::list::size() in ObjectCache
- We shouldn't call list::size() it's O(n).
- 10:56 PM Revision 155cdd29 (ceph): osd: flag new/old temp objects in MOSDSubOp
- Allow us to mark when we start and stop using a temporary object in a
sub_op. If we start to use it, make sure the c... - 10:56 PM Revision 25a608cd (ceph): osd/ReplicatedPG: allow RepGathers with no version
- If the repop has no version set, skip the updates to last_update and
last_update_{applied,ondisk} and last_complete_o... - 10:45 PM Bug #6226 (Fix Under Review): after editing crushmap and adding new hosts, injecting it, several ...
- 04:01 PM Bug #6226: after editing crushmap and adding new hosts, injecting it, several existing OSD crashed
There is a race already fixed in a later release by (01d3e094) which could allow start_recovery_ops() to be called ...- 12:10 AM Bug #6226: after editing crushmap and adding new hosts, injecting it, several existing OSD crashed
- I was wrong - we are indeed on 0.61.7
root@ineri ~$ ndo all_nodes ceph --version
h0 ceph version 0.61.7... - 10:19 PM Revision 17c5d765 (ceph): os/FileStore: implement collection_move_rename
- This is similar to a collection_add + collection_move sequence in that we
apply the same replay guards. The differen... - 10:19 PM Revision 6cecd0db (ceph): osd/osd_types: move coll_t::META_COLL definition
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:19 PM Revision c9885e74 (ceph): osd/ReplicatedPG: generate one-off unique temp object names
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:19 PM Revision 27ca5d2e (ceph): osd/ReplicatedPG: drop dead code from parallelexec issue_repop
- This is unused and references otherwise unused variables we can remove!
Signed-off-by: Sage Weil <sage@inktank.com> - 10:19 PM Revision c4260fad (ceph): osd/ReplicatedPG: drop unused issue_repop() arguments
- These are cruft from the old parallelexec mode and can be removed.
Signed-off-by: Sage Weil <sage@inktank.com> - 10:09 PM Revision ef7cffc3 (ceph): os/ObjectStore: add collection_move_rename
- Add method to move an object between collections *and* change its name.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:06 PM Revision 06be66b3 (ceph): Merge pull request #87 from ceph/sentry
- Add logs URL to sentry reports
- 08:45 PM Revision 1228d8cb (ceph): Add teuthology branch to sentry report tags
- 08:40 PM Revision 0ad9c875 (ceph): Ensure teuthology_branch is stored in job_config
- 08:31 PM Revision 5b3ce845 (ceph): Add ctx.config to sentry info.
- 08:14 PM Revision fe51db6f (ceph): Merge job_config and ctx.config
- 07:51 PM CephFS Bug #6284 (Fix Under Review): client: failed xlist assert on put_inode()
- https://github.com/ceph/ceph/pull/590
- 02:05 PM CephFS Bug #6284 (Resolved): client: failed xlist assert on put_inode()
- teuthology archives: /a/teuthology-2013-09-11_01:30:26-upgrade-fs-next-testing-basic-plana/29583/remote/ubuntu@plana3...
- 07:51 PM CephFS Bug #6279 (Fix Under Review): creating a new fs on pools from an old fs can lead to lost MDS Tables
- 06:55 PM CephFS Bug #6279: creating a new fs on pools from an old fs can lead to lost MDS Tables
- https://github.com/ceph/ceph/pull/589
- 12:39 PM CephFS Bug #6279 (Resolved): creating a new fs on pools from an old fs can lead to lost MDS Tables
- See the thread at http://www.mail-archive.com/ceph-users@lists.ceph.com/msg03918.html
If you delete your FS (but n... - 07:49 PM Revision 725ba83c (ceph): Add test for misc.get_http_log_path()
- 07:00 PM Revision 38a1a6dd (ceph): Use sentry.get_ident() again
- 06:58 PM Revision 4e9c5378 (ceph): Don't fail if there's no job_id
- 06:47 PM Revision df492570 (ceph): Passing job_id to get_http_log_path() is optional
- 06:44 PM Revision 713fa524 (ceph): Add job id and actual archive dir to job config
- Also add job id to info.yaml
- 06:44 PM Revision f7537f9c (ceph): Add logs URL to sentry reports
- 05:03 PM rbd Bug #6257: rbd: cp on sparse image allocates objects in dest
- Same goes for "rbd flatten", which also seems to allocate every block in the resulting image, even if large parts are...
- 04:47 PM Revision 670db7e8 (ceph): rgw: fix get cors, delete cors
- Remove a couple of variables that overrode class member. Not
really clear how it was working before, might have been ... - 04:47 PM Revision a304016f (ceph): Merge branch 'wip-6078-dumpling' into dumpling
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 04:47 PM CephFS Bug #4221 (Fix Under Review): MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events ...
- 04:46 PM CephFS Bug #4221: MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events for DECODE macros
- A corrupt object might lead to asserts getting thrown as part of DECODE_START or DECODE_FINISH. These macros are not ...
- 04:45 PM Revision a5fdd44e (ceph): rgw: remove use of s->bucket_cors
- Some old code still tried to use s->bucket_cors, which was
abandoned in a cleanup work.
Signed-off-by: Yehuda Sadeh ... - 04:45 PM Revision c3385d8a (ceph): rgw: OPTIONS request doesn't need to read object info
- This is a bucket-only operation, so we shouldn't look at the
object. Object may not exist and we might respond with N... - 04:45 PM Revision 94e7b594 (ceph): rgw: add a generic CORS response handling
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:45 PM Revision 71873aba (ceph): rgw: tie CORS header response to all relevant operations
- Have the CORS responses on all relevant operations. Also add headers
on failure cases.
Signed-off-by: Yehuda Sadeh <... - 04:45 PM Revision 986fa92a (ceph): rgw: don't handle CORS if rule not found (is NULL)
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:45 PM Revision d45c87ea (ceph): rgw: fix CORS rule check
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 04:45 PM Revision 13b28cc3 (ceph): rgw: add COPY method to be handled by CORS
- Was missing this http method.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:45 PM Revision ac0a30fe (ceph): rgw: fix certain return status cases in CORS
- Change return values in certain cases, reorder
checks, etc.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 04:01 PM Revision 73e626cc (ceph): Merge pull request #587 from kri5/master
- rgw-admin: Adds --metadata-key option to help
Reviwed-by: Yehuda Sadeh <yehuda@inktank.com> - 03:50 PM Revision c1ba2763 (ceph): Move get_http_log_path
- 03:50 PM Revision 4699ad1c (ceph): Don't "import misc as teuthology"
- 03:49 PM Revision 288bef33 (ceph): rgw-admin: Adds --metadata-key option to help
- Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com>
- 03:03 PM Revision c9db15e6 (ceph): s/jobid/job_id/
- 01:47 PM rgw Bug #6175 (Fix Under Review): rgw: valgrind: invalid reads in copy_obj
- 01:27 PM Bug #6283 (Resolved): ppc build fails
- josef reports: http://kojipkgs.fedoraproject.org//work/tasks/4881/5924881/build.log
- 01:20 PM devops Bug #6281 (Closed): ceph-deploy config.py write_conf throws away old config just because they are...
- in example
ceph-deploy new node-1:10.20.0.2
echo [global] >> /etc/ceph/ceph.conf
echo public address = 10.20.0.0... - 12:37 PM Fix #6278: osd: throttle snap trimming
- We are collecting perf dump metrics from all OSD and RBD admin sockets. What metrics would be the most useful to grap...
- 12:33 PM Fix #6278 (Resolved): osd: throttle snap trimming
- Qemu guests on our cluster experience high I/O latency, stalls or complete halts when spindle contention is created b...
- 12:25 PM rbd Bug #5955 (Resolved): qemu deadlock when librbd caching enabled (writethru or writeback).
- 11:34 AM rbd Bug #5955: qemu deadlock when librbd caching enabled (writethru or writeback).
- Sage,
This issue should be closed, as it seems to be resolved by upgrading qemu to include joshd's async flush pat... - 10:39 AM rgw Bug #6078 (Resolved): rgw: CORS not working
- Done. Backported to dumpling, merged at commit:a304016fa01b02efd500135c00b9bf3407a9999c. Also, commit:670db7e80ddc9c2...
- 10:01 AM rbd Bug #5428 (Can't reproduce): libceph: null deref in ceph_auth_reset
- 10:01 AM Feature #6274 (Fix Under Review): mon: MonCommand.h unit tests
- 01:16 AM Feature #6274 (Resolved): mon: MonCommand.h unit tests
- "work in progress":https://github.com/ceph/ceph/pull/588
unit tests to validate the syntax of the strings : syntax... - 10:00 AM rbd Bug #5876 (Resolved): Assertion failure in rbd_img_obj_callback() : rbd_assert(which >= img_reque...
- 09:59 AM Linux kernel client Bug #5429 (Duplicate): libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
- i think/hope this is a duplicate of the async notify racing with shutdown
- 09:59 AM rbd Bug #5647 (Resolved): krbd: EBlACKLIST osd reply resulting in an oops on 3.9
- 09:58 AM rbd Bug #5636 (Resolved): krbd: crash in image refresh
- 09:57 AM rbd Bug #5454 (Resolved): krbd: assertion failure in rbd_img_obj_callback()
- 09:57 AM rbd Bug #5760 (Resolved): libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front....
- 09:36 AM rgw Bug #6268 (Fix Under Review): rgw: RGWPutObj calls processor->complete() before all inflight data...
- 08:34 AM Feature #6227 (New): make osd crush placement on startup handle multiple trees (e.g., ssd + sas)
- 12:11 AM Feature #6227: make osd crush placement on startup handle multiple trees (e.g., ssd + sas)
- ok - that works nicely as a workaround for us.
Looking forward to better management tools for hierarchies ;)
/jc - 07:59 AM devops Bug #6269 (Resolved): ceph-deploy needs to use the equivalent of `hostname -s`
- Merged to ceph-deploy master branch with hash: c7756f8
- 07:58 AM devops Bug #6269: ceph-deploy needs to use the equivalent of `hostname -s`
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/72
- 03:10 AM Revision 0499948a (ceph): rgw: when failing read from client, return correct error
- Fixes: #6214
When getting a failed read from client when putting an object
we returned the wrong value (always 0), wh...
09/10/2013
- 11:53 PM Revision 89df90f6 (ceph): rados: add --op copy_from ... support
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:15 PM Revision 558d9fc9 (ceph): osd: bind objecter messenger to cluster address
- We don't want it binding to whatever willy-nilly, and as an OSD even
its "client" traffic should go on the cluster ad... - 11:15 PM Revision 1d1bf41e (ceph): osd: name the objecter's messenger "ms_objecter" instead of "hbclient"
- Bad copypasta on initial create?
Signed-off-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.... - 11:15 PM Revision 14c71ea3 (ceph): Objecter: rename cancel_op -> cancel_linger_op
- This makes it possible to converse about op_cancel and cancel_linger_op
without getting too confused.
Signed-off-by:... - 10:49 PM Revision 383d8a19 (ceph): Merge pull request #580 from ceph/wip-6033-redirects
- Reviewed-by: Sage Weil <sage@inktank.com>
- 10:33 PM Revision 76c343ba (ceph): osd: implement basic caching policies in ReplicatedPG
- Right now these are very basic and aren't as sophisticated as we
want them to end up, but we have a skeleton for wher... - 10:33 PM Revision ab2506db (ceph): test: update cache test since OSDs support redirects
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 10:33 PM Revision ac1c9217 (ceph): MOSDOpReply: add a redirect member
- When present, clients must send the request to the location specified
by the redirect (by using the combine_with_loca... - 10:33 PM Revision 29133fda (ceph): Objecter: write a helper function to clean up ops that need to be retried
- We have a little block to clean them up if we get back EAGAIN, but it's
actually leaking map references; we will also... - 10:33 PM Revision fbbe3ad1 (ceph): Objecter: follow redirect replies from the OSD
- If we get back a redirect reply, we clean up the Op's external references
and re-send using the target_oloc and targe... - 10:33 PM Revision aeec0c64 (ceph): osd: create a new request_redirect_t
- We'll use this so that the OSD can tell the Objecter to redirect a
request to a different object somewhere else.
Sig... - 10:33 PM Revision 79f02d6b (ceph): Objecter: rename Op::oid -> Op::base_oid
- Analagous to the oloc->base_oloc rename we did in
e2fcad09d94d965867147627b73e99da9454436f, we may specify a differen... - 10:33 PM Revision a45612c2 (ceph): Objecter: add an Op::target_oid, and use it when submitting Ops
- For now it's just a copy of base_oid, but soon we will allow it
to be overwritten for OSD-driven redirects.
Signed-o... - 10:04 PM Revision e3ca59c3 (ceph): Merge pull request #585 from ceph/wip-osd-pool-create-syntax
- fix ceph tool (syntax error in command specification prevents anything from working)
Reviewed-by: Sage Weil <sage@in... - 09:47 PM Revision c24e1706 (ceph): mon: fix syntax error in osd pool create args
- Just missing a space between pgp_num and properties specification.
Signed-off-by: Josh Durgin <josh.durgin@inktank.com> - 08:08 PM rgw Bug #6214 (Resolved): rgw: PUT object with chunked upload doesn't propagate client side errors
- 08:08 PM rgw Bug #6214: rgw: PUT object with chunked upload doesn't propagate client side errors
- No need for backporting this one. It is clear that this wasn't the cuprit for the original issue (seems like it was a...
- 08:04 PM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
- Was already merged into dumpling (commit:9b953aa4100eca5de2319b3c17c54bc2f6b03064).
- 07:20 PM Revision 748fa5e5 (ceph): Merge pull request #85 from ceph/wip-testdir
- remove basedir/testdir distinction
- 05:53 PM Revision 5acc57f5 (ceph): remove basedir/testdir distinction
- We should never run with a conflicting testdir in the basedir, and the
code to do this is confusing and buggy. Go ba... - 05:17 PM Bug #6272 (Need More Info): ceph command usage missing setcrushmap
- ...
- 03:56 PM Bug #6272 (Closed): ceph command usage missing setcrushmap
This documented feature does not show up in ceph --help output
ceph osd setcrushmap -i {compiled-crushmap-filen...- 04:42 PM devops Cleanup #6273 (New): Doxygen Renderer
- Sphinx has been upgraded to 1.1.3, fixing the index problem. However, we do have an outstanding issue with Doxygen. ...
- 04:17 PM Revision dedfccd9 (ceph): Merge pull request #584 from dachary/master
- autoconf: use $(UNITTEST_CXXFLAGS) in tests
Reviewed-by: Sage Weil <sage@inktank.com> - 04:15 PM Revision 277d2667 (ceph): Merge pull request #578 from dachary/wip-6113
- mon: add key[=value] ... to osd pool create
Reviewed-by: Sage Weil <sage@inktank.com> - 03:16 PM Bug #5922 (Duplicate): osd: unfound objects on next
- 03:00 PM Revision 780954e2 (ceph): autoconf: use $(UNITTEST_CXXFLAGS) in tests
- As suggested by Roald van Loon
https://github.com/ceph/ceph/pull/538/files#r6260751
Signed-off-by: Loic Dachary <loi... - 02:46 PM Revision 647188c4 (ceph): ErasureCodeJerasure: plugin
- Create the class matching the string found in the
erasure-code-technique parameter, using the same strings are the
or... - 02:46 PM Revision 65f1970a (ceph): ErasureCodeJerasure: define technique ReedSolomonVandermonde
- technique == reed_sol_van
parse : default to K=7, M=3 and W=8 . If W is not 8, 16 or 32, it
reverts to 8.
pad_in_le... - 02:46 PM Revision b70cb93a (ceph): ErasureCodeJerasure: define technique ReedSolomonRAID6
- technique == reed_sol_r6_op
parse : default to K=7 and W=8 . If W is not 8, 16 or 32, it
reverts to 8.
pad_in_lengt... - 02:46 PM Revision 530fb8a5 (ceph): ErasureCodeJerasure: define techniques CauchyOrig and CauchyGood
- The technique Cauchy has two variants:
ErasureCodeInterface (abstract)
|
-> ErasureCodeJerasure... - 02:46 PM Revision 9a820105 (ceph): ErasureCodeJerasure: define technique Liberation
- technique == "liberation"
parse : default to K=7, M=2 and W=7 and packetsize = 8.
If any of the following constraint... - 02:46 PM Revision 63867e94 (ceph): ErasureCodeJerasure: define technique BlaumRoth
- technique == "blaum_roth"
ErasureCodeInterface (abstract)
|
-> ErasureCodeJerasure (abstract)
... - 02:46 PM Revision e9e53912 (ceph): ErasureCodeJerasure: define technique Liber8tion
- technique == "liber8tion"
ErasureCodeInterface (abstract)
|
-> ErasureCodeJerasure (abstract)
... - 02:46 PM Revision c8def860 (ceph): ErasureCodeJerasure: unit test common to all techniques
- A typed unit test is defined and must run regardless of the technique.
When a new technique is derived from ErasureCo... - 02:27 PM Fix #6116: osd: incomplete pg from thrashing on next
- Ok, there are enough logs to confirm that this is the primary-thinks-it's-clean vs backfill-peer-thinks-it's-clean race.
- 02:18 PM Fix #6116: osd: incomplete pg from thrashing on next
- 1.3f does appear to be incomplete in the osd log
- 02:16 PM Fix #6116: osd: incomplete pg from thrashing on next
- From the mon logs, last reported seems to be
2013-09-09 22:31:28.047555 7f56db94d700 15 mon.a@0(leader).pg v1614 go... - 02:13 PM Fix #6116: osd: incomplete pg from thrashing on next
- There appear to be no pgs in incomplete state according to the osd log. Issue notifying the mon?
- 02:12 PM Fix #6116: osd: incomplete pg from thrashing on next
- The task was in process of letting the cluster recover with osd.2 down.
- 02:10 PM Fix #6116: osd: incomplete pg from thrashing on next
- Hmm, the last osd log entry indicates that the pg in question may have gone clean?
2013-09-09 22:27:19.022997 7f1724... - 02:09 PM Fix #6116: osd: incomplete pg from thrashing on next
- time: 2717s
log: http://qa-proxy.ceph.com/teuthology/teuthology-2013-09-09_20:00:20-rados-dumpling-testing-basi... - 02:11 PM CephFS Bug #4221: MDS: LogEvent::decode needs to respect mds_log_skip_corrupt_events for DECODE macros
- Actually, I think the details here are incorrect. mds_log_skip_corrupt_events behavior is broken, but it's not the re...
- 01:50 PM Bug #6118: failed to recover before timeout expired on radosbench, rados api tests
- http://qa-proxy.ceph.com/teuthology/teuthology-2013-09-04_20:00:07-rados-dumpling-testing-basic-plana/21637/
Seems... - 11:53 AM Revision 454c116d (ceph): mon: add key[=value] ... to osd pool create
- With the introduction of the erasure code pool, arguments to be
interpreted depending on the pool type must be introd... - 10:51 AM devops Bug #6269 (Resolved): ceph-deploy needs to use the equivalent of `hostname -s`
- It currently uses:...
- 10:17 AM Bug #6226: after editing crushmap and adding new hosts, injecting it, several existing OSD crashed
- The bug description claims that cluster is running v0.61.5 but attached log says v0.61.7. Could there be a mix of no...
- 09:58 AM devops Feature #4954: ceph-deploy: help and document need to be updated for osd create
- ...
- 09:19 AM rgw Bug #6268 (Resolved): rgw: RGWPutObj calls processor->complete() before all inflight data is drained
- This is problematic because we have ordering issue here. We end up updating the head before flushing all data is done...
- 05:27 AM Revision a786ad77 (ceph): ceph-disk: make initial journal files 0 bytes
- The ceph-osd will resize journal files up and properly fallocate() them
so that the blocks are preallocated and (hope... - 04:50 AM Revision 8c76f3a0 (ceph): crushtool: do not dump core with non-unique bucket IDs
- Return -EEXIST on duplicate ID
BUG FIX: crush_add_bucket() mixes error returns and IDs
Add optional argument to ret... - 04:47 AM Revision bde2772b (ceph): doc/release-notes: v0.67.3
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:24 AM Revision ccbd9b0c (ceph): upgrade/rgw*: use correct branch for s3tests
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:16 AM Revision c56e039c (ceph): buffer: uninline, constify crc32c()
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:12 AM Revision 397b4c20 (ceph): osd: add empty() function to object_locator_t
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:49 AM Bug #5823: cpu load on cluster node is very high, client can't get data on pg from primary node ...
- The slow request increase frequently ...
see the attached file for more detail - 12:21 AM Revision 82e40a7d (ceph): ReplicatedPG: do not meaninglessly fill in the reqid on make_writeable(...
- This reqid is used to fill in a map that is used for giving clients
the correct version on replayed ops, unless the r... - 12:21 AM Revision 0b24be28 (ceph): MOSDOpReply: more const-correctness
- get_map_epoch() is a non-reference getter -- mark it as const!
Signed-off-by: Greg Farnum <greg@inktank.com> - 12:01 AM Revision 8ab29e95 (ceph): ErasureCodeJerasure: import jerasure-1.2A
- The files are copied verbatim from
http://web.eecs.utk.edu/~plank/plank/papers/Jerasure-1.2A.tar and a
section is add... - 12:01 AM Revision 9b4048aa (ceph): ErasureCodeJerasure: fix jerasure compilation
- Add the imported jerasure-1.2A to the Makefile.am and fix the
compilation warnings.
https://github.com/dachary/ceph/... - 12:01 AM Revision e4354687 (ceph): ErasureCodeJerasure: base class for jerasure ErasureCodeInterface
- The ErasureCodeJerasure class is derived from ErasureCodeInterface and
is meant to be derived to implement each jeras...
09/09/2013
- 11:55 PM Revision 661b377c (ceph): os/FileStore: pass old + new object name to lfn_link
- For now, the only caller leaves the name the same.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:42 PM Revision 7281354f (ceph): Merge pull request #569 from ceph/wip-osd-stat
- osd: expose bytes used/avail via perf / asok
- 11:36 PM Revision deea63f7 (ceph): osd: expose bytes used/avail via perf / asok
- This values are already sent to the monitor. Expose them via the admin
socket too so collectd/diamond/whatever can p... - 11:31 PM Revision 63901a4f (ceph): Merge pull request #583 from ceph/wip-6230-workunit
- qa: workunits: mon: crush_ops: test 'ceph osd crush move'
Reviewed-by: Sage Weil <sage@inktank.com> - 11:29 PM Revision 3bc618b7 (ceph): qa: workunits: mon: crush_ops: test 'ceph osd crush move'
- Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com>
- 11:01 PM Revision a5a3510e (ceph): Merge pull request #582 from ceph/wip-6230
- mon: MonCommands: expect a CephString as 1st arg for 'osd crush move'
Reviewed-by: Sage Weil <sage@inktank.com> - 10:44 PM Revision 7d3799fd (ceph): mon: MonCommands: expect a CephString as 1st arg for 'osd crush move'
- Fixes: #6230
Signed-off-by: Joao Eduardo Luis <joao.luis@inktank.com> - 10:40 PM rbd Bug #6267: krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- Sage Weil wrote:
> can you try a 3.10 kernel? there was at least one locking fix during that interval that could ex... - 10:33 PM rbd Bug #6267 (Need More Info): krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- can you try a 3.10 kernel? there was at least one locking fix during that interval that could explain this. (also, ...
- 10:24 PM rbd Bug #6267 (Resolved): krbd: null deref in __kick_osd_requests+0x15e/0x1b0
- [639680.982539] BUG: unable to handle kernel NULL pointer dereference at 0000000000000498
[639680.986988] IP: [<ffff... - 10:39 PM Revision 04120360 (ceph): Merge pull request #581 from dachary/master
- autoconf: use $(LIBOSD) $(LIBCOMMON) instead of libosd.a libcommon.la
Reviewed-by: Sage Weil <sage@inktank.com> - 10:30 PM Revision 132e4039 (ceph): autoconf: use $(LIBOSD) $(LIBCOMMON) instead of libosd.a libcommon.la
- hardcoded library names in unit test dependencies break compilation
Signed-off-by: Loic Dachary <loic@dachary.org> - 10:30 PM Revision 4c5b3c7b (ceph): doc: Syntax fix to suppress gitbuilder errors.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:29 PM Revision 8bf858f2 (ceph): doc: Removed mkcephfs reference.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:27 PM Revision 494aff6b (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:27 PM Revision 95c0c6c9 (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:27 PM Revision 1e54d835 (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:26 PM Revision 68659a65 (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:23 PM Revision 1bb72255 (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:22 PM Revision a6a71406 (ceph): doc: Syntax fixes to suppress gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 10:22 PM Revision ac609a4f (ceph): doc: Syntax fixes to remove gitbuilder errors.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:54 PM Revision 07ff0215 (ceph): Merge pull request #518 from dachary/wip-5878
- erasure plugin mechanism and abstract API
Reviewed-by: Samuel Just <sam.just@inktank.com> - 09:51 PM RADOS Bug #6246 (Pending Backport): crushtool dumps core with non-unique bucket IDs
- 01:09 PM RADOS Bug #6246 (Fix Under Review): crushtool dumps core with non-unique bucket IDs
- 09:34 PM Revision 39217947 (ceph): ErasureCodePlugin: plugin registry tests and example
- libec_example.la is a fully functional plugin based on
ErasureCodeExample to test the ErasureCodePlugin abstract
inte... - 09:32 PM Revision 916901f9 (ceph): ErasureCodePlugin: plugin registry
- A ErasureCodePluginRegistry singleton holds all erasure plugin objects
derived from ErasureCodePlugin and dlopen(2) h... - 09:28 PM Revision b61369c8 (ceph): ErasureCodePlugin: plugin interface
- When dynamically loaded, a plugin is expected to define
int __erasure_code_init(char *plugin_name);
When called... - 09:26 PM Revision 640f2f21 (ceph): ErasureCode: example implementation : K=2 M=1
- An erasure code implementation designed for tests. Although it is fully
functional and could be used on actual data, ... - 09:15 PM Revision 03f083ce (ceph): rbd/singleton: fix path
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:10 PM Revision 95d61c1a (ceph): Fix usage to include export and import --type options
- Signed-off-by: David Zafman <david.zafman@inktank.com>
- 07:50 PM Revision 408cd615 (ceph): v0.67.3
- 07:45 PM Revision 9f989c7f (ceph): Merge pull request #84 from ceph/wip-buck-daemon-helper
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 07:37 PM Revision d47ae37e (ceph): Adding in erroneously removed args
- The 'kill' argument was accidentially removed
as part of patch
53b8e27da996f2efdcc4eb687f3bda0791a8d947
Signed-off-b... - 07:23 PM Revision dde21bdf (ceph): ErasureCode: abstract interface
- The erasure coded pool relies on this abstract interface to encode and
decode the chunks stored in the OSD. It has be... - 06:34 PM Revision f3d507e0 (ceph): Merge pull request #579 from ceph/wip-doc-warn-fix
- make sure we use a version of sphinx that we can handle
- 06:19 PM Revision ff9beb2c (ceph): doc: Syntax fixes to stop gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:19 PM Revision 9c097016 (ceph): doc: Syntax fixes to stop gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:19 PM Revision 5900b43a (ceph): doc: Syntax fixes to stop gitbuilder warnings.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 06:00 PM Revision 99c42e13 (ceph): make sure we use a version of sphinx that we can handle
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 05:55 PM devops Bug #6266 (Resolved): ceph-deploy new command broken
- 04:49 PM devops Bug #6266: ceph-deploy new command broken
- wip-6266 works fine!
- 04:44 PM devops Bug #6266 (Fix Under Review): ceph-deploy new command broken
- wip-6266
- 04:32 PM devops Bug #6266 (Resolved): ceph-deploy new command broken
- on mira016, that has the latest version of ceph-deploy [v1.2.3], new command is broken and so am not able to proceed ...
- 04:37 PM devops Bug #6255 (Resolved): ceph-deploy: fail to parse json from mon_status
- commit:f957f89
- 06:04 AM devops Bug #6255 (Fix Under Review): ceph-deploy: fail to parse json from mon_status
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/69
- 04:22 PM rbd Bug #6265 (Resolved): krbd: blockdev --setr{o,w} claims success but has no effect
- From http://permalink.gmane.org/gmane.comp.file-systems.ceph.user/3957...
- 04:18 PM rbd Feature #6264 (Resolved): rbd: expose all options available to rbd map
- These include ro/rw, share/noshare for osd_clients, crc/nocrc, and osd client timeouts.
These are mainly useful for ... - 04:15 PM Bug #6254 (In Progress): ceph_test_rados: rollback then delete gets ENOENT
- 04:12 PM Feature #6038 (Fix Under Review): cachepool: filestore/osd: infrastructure for large object COPY ...
- 04:12 PM Feature #6147 (In Progress): mon: calculate, expose per-pool pg stat deltas
- 04:02 PM Revision 583ffaf4 (ceph): Merge pull request #577 from roaldvanloon/wip-automake
- automake cleanup: implementing non-recursive make
Reviewed-by: Sage Weil <sage@inktank.com> - 04:01 PM Bug #6230 (Pending Backport): ceph osd crush move appears to be broken
- 09:41 AM Bug #6230: ceph osd crush move appears to be broken
- Joao - please take a look.
- 08:56 AM Bug #6230: ceph osd crush move appears to be broken
- nope, looks like this is supposed to work (and did in 0.61). from ML:...
- 03:01 PM Feature #6000 (Resolved): EC: [link] erasure plugin mechanism and abstract API
- 03:00 PM Subtask #5878 (Resolved): erasure plugin mechanism and abstract API
- 01:58 PM RADOS Fix #6262 (New): toofull osd prevents backfilling of other pg replicas
- Say a pg is to be 4-way replicated across osds [0,1,2,3].
AFAICT, if any of the osds 0, 1 or 2 hit the toofull thr... - 01:48 PM Feature #6261 (Resolved): ceph-filestore-dump use cases for disaster recovery
- Context: I often take cluster snapshots and compare file hashes and replication factors of all osds in my cluster, to...
- 01:24 PM Feature #6033 (Fix Under Review): cachepool: osd: basic io decision: read/write from/to cache poo...
- The OSD is slightly less stupid now, and it looks like making it smarter is going to be part of future tickets (the c...
- 12:09 PM rbd Bug #5426: librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::complete()
- ubuntu@teuthology:/a/teuthology-2013-09-09_01:36:24-upgrade-small-next-testing-basic-vps/27433
- 09:47 AM Bug #6040 (Resolved): Significant slowdown of osds since v0.67 Dumpling
- 09:45 AM RADOS Fix #6250: OSD: handle ENODEV on reads
- This was a mailing list report about when the OSD gets back ENODEV from the underlying filesystem.
- 09:39 AM RADOS Fix #6250: OSD: handle ENODEV on reads
- do you have a log? i see no instance of ENODEV in the code..
- 09:38 AM Feature #6258: ceph-disk: zap should wipefs
- Waiting for feedback from list.
- 09:07 AM Feature #6258 (Rejected): ceph-disk: zap should wipefs
- see
http://thread.gmane.org/gmane.comp.file-systems.ceph.user/3726/focus=3774 - 09:17 AM rgw Bug #6240: rgw: invalid read on addr in msgr via objecter
- What I see in the failed case is this:...
- 08:51 AM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- And I just made this work with execnet.
... and it doesn't hang *at all*... - 06:57 AM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- And now we have to back out of this change because once again, the infamous pushy bug (#5975) that cannot be fixed.
... - 08:17 AM Bug #5175: leveldb: LOG and MANIFEST file grow without bound (LOG being _text_ log !)
- Here's how leveldb works in respect to the log:
- setting it to /dev/null will only make the info messages to be w... - 08:03 AM Bug #5804 (Can't reproduce): mon: binds to 0.0.0.0:6800something port
- Have inspected the code and haven't found a reason for this to happen yet, nor was I able to reproduce this at all.
... - 04:52 AM Revision a4e476ba (ceph): Merge remote-tracking branch 'gh/wip-valgrind'
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 04:40 AM Revision 726fe73d (ceph): rados: fix typo
- cct is a member of the ObjBencher parent that we are trying to
initialize; need to pass in cct_ here.
Broken in 5dd0... - 02:12 AM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
- Has anyone else experienced this issue? It seems to be affecting a few others - http://lists.ceph.com/pipermail/ceph-...
- 01:53 AM Subtask #6113 (In Progress): add ceph osd pool create [name] [key=value]
09/08/2013
- 10:21 PM rgw Bug #6240: rgw: invalid read on addr in msgr via objecter
- the first difference i see between a passing and failing run is that the passing run gets ENOENT when reading default...
- 10:12 PM Revision 922aa09b (ceph): fix a few missing adjust-ulimits users
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:45 PM rbd Bug #6257 (Resolved): rbd: cp on sparse image allocates objects in dest
- ...
- 09:41 PM Bug #6256 (Resolved): rados bench: segfault in ceph_clock_now
- 04:14 PM Bug #6256 (Resolved): rados bench: segfault in ceph_clock_now
- ...
- 07:04 PM Support #6238: About the data migration in Ceph
- You can find all the information on signing up for the mailing lists here:
http://ceph.com/resources/mailing-list-... - 03:43 AM Support #6238: About the data migration in Ceph
- Greg Farnum wrote:
> These sorts of questions are appropriate for the ceph-users list. Please send them there. :)
... - 04:52 PM Revision 2946dd85 (ceph): upgrade: set dumpling branch for rest.yaml
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:17 PM Bug #6207: Found incorrect object contents
- ubuntu@teuthology:/a/teuthology-2013-09-08_01:00:04-rados-master-testing-basic-plana/25850
- 09:59 AM Bug #6118: failed to recover before timeout expired on radosbench, rados api tests
- another one with full logs: ubuntu@teuthology:/a/teuthology-2013-09-07_13:39:47-rados-dumpling-testing-basic-plana/25183
- 09:56 AM devops Bug #6255 (Resolved): ceph-deploy: fail to parse json from mon_status
- ...
- 09:22 AM Bug #6254 (Resolved): ceph_test_rados: rollback then delete gets ENOENT
- ubuntu@teuthology:/a/teuthology-2013-09-07_01:00:04-rados-next-testing-basic-plana/24495
ubuntu@teuthology:/a/teutho...
09/07/2013
- 10:11 PM Revision 6949d221 (ceph): automake cleanup: implementing non-recursive make
- - Enabling subdir objects
- Created a Makefile-env.am with basic automake init
- Created .am files per subdir, includ... - 09:11 PM Revision b2caa799 (ceph): Merge remote-tracking branch 'gh/next'
- 09:10 PM Revision 49dfb6ce (ceph): Merge pull request #575 from roaldvanloon/wip-automake-prepare
- Wip automake prepare
Reviewed-by: Sage Weil <sage@inktank.com> - 09:09 PM Revision bc552647 (ceph): Merge pull request #576 from ceph/wip-6078-2
- rgw: fix get cors, delete cors
Reviewed-by: Sage Weil <sage@inktank.com> - 08:44 PM Revision 99c6be2f (ceph): automake cleanup: renaming buildtest
- The previous name could cause confusion (it's not only used to test
build libcommon anymore).
Signed-off-by: Roald J... - 08:41 PM Revision 09b42c03 (ceph): automake cleanup: renamed inttypes.h
- - In "includes", inttypes.h was cluttering the system's one. This caused
random build errors on some systems/in som... - 08:41 PM Revision bb312b68 (ceph): automake cleanup: moving hobject from os to common
- This file is used by libcommon, so lets put it in src/common instead of
src/os.
Signed-off-by: Roald J. van Loon <ro... - 08:41 PM Revision bf6341fd (ceph): automake cleanup: moving code away from include to common
- Includes should only be includes. Moving C code to libcommon.
Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com> - 08:41 PM Revision 0b267b30 (ceph): automake cleanup: moving tests to test subdir
- This are tests and should be in the src/test subdir.
Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com> - 08:41 PM Revision 3daf6ea9 (ceph): automake cleanup: moving misc tools to tools subdir
- Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com>
- 08:41 PM Revision 417f1f2a (ceph): automake cleanup: moving rados tool to tools subdir
- Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com>
- 08:41 PM Revision 7845115f (ceph): automake cleanup: adding vta support to configure
- Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com>
- 08:34 PM Revision 17a7342b (ceph): Merge pull request #574 from dalgaaf/fix/da-dumpling-cherry-picks
- init-radosgw*: fix status return value if radosgw isn't running
Reviewed-by: Sage Weil <sage@inktank.com> - 08:32 PM Revision b16f8123 (ceph): Merge pull request #573 from dalgaaf/fix/da-cuttlefish-fixes-and-cherry...
- Cherry-pick some smaller changes from master to cuttlefish
Reviewed-by: Sage Weil <sage@inktank.com> - 08:31 PM Revision 624e084a (ceph): Merge pull request #572 from roaldvanloon/wip-fix-buildtests
- fix: build tests need libcrc.la
Reviewed-by: Sage Weil <sage@inktank.com> - 06:32 PM Revision 5f16ea62 (ceph): tools/ceph.cc: add missig 'ceph osd lspools' command to help
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 05:32 PM Revision 10433bbe (ceph): init-radosgw*: fix status return value if radosgw isn't running
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit b5137baf651eaaa9f67e3864509e437f9d5... - 05:31 PM Revision 59f02ecf (ceph): init-radosgw*: fix status return value if radosgw isn't running
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit b5137baf651eaaa9f67e3864509e437f9d5... - 05:31 PM Revision c25770c3 (ceph): init-radosgw*: add all sections to usage output
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit a0c5095be3640e98d5541920c19387bf376... - 05:30 PM Revision 1a8347e0 (ceph): init-radosgw*: add status
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit 385457f8d871238a896229d0c2cbb256469... - 05:30 PM Revision b1c2aa2c (ceph): fix init-radosgw* to use the same indentation
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
(cherry picked from commit b4d4e92ed2deae435a24b36d086c1a73e59... - 05:30 PM Revision 794ed1fa (ceph): ceph_authtool.cc: update help/usage text
- Added implemented but not listed commands to the help/usage text:
* -g shortcut for --gen-key
* -a shortcut for --a... - 05:25 PM Revision c17d1349 (ceph): fix: build tests need libcrc.la
- Build tests are failing because the need crc32c.cc's functions, so we
need to link them against libcrc.la
Signed-off... - 04:33 PM rgw Bug #6240: rgw: invalid read on addr in msgr via objecter
- ...
- 03:45 PM Revision 13e42447 (ceph): Merge pull request #570 from roaldvanloon/wip-cleanup-globals
- cleanup: state_name in NamedState init list
Reviewed-by: Sage Weil <sage@inktank.com> - 03:42 PM Revision d5a85d92 (ceph): Merge pull request #571 from dalgaaf/fix-da-init-radosgw
- init-radosgw*: fix status return value if radosgw isn't running
Backport: dumpling
Reviewed-by: Sage Weil <sage@inkt... - 03:31 PM devops Feature #1668: collectd: push ceph plugin upstream
- I've issued a pull request with some updates: https://github.com/ceph/collectd/pull/1
I'll rebase against the mast... - 09:30 AM Revision b5137baf (ceph): init-radosgw*: fix status return value if radosgw isn't running
- Signed-off-by: Danny Al-Gaaf <danny.al-gaaf@bisect.de>
- 09:15 AM Revision 55a52714 (ceph): cleanup: state_name in NamedState init list
- Added const char *state_name to the NamedState initializer list. This
correctly enforces a state name.
Signed-off-by... - 09:02 AM Bug #6128 (Rejected): glance image-create with rbd --location fails to create image in rdb
- Closing in the ceph tracker as it's not ceph-specific, but a general bug in glance.
- 05:33 AM Revision 13872785 (ceph): rgw: fix get cors, delete cors
- Remove a couple of variables that overrode class member. Not
really clear how it was working before, might have been ... - 12:38 AM Revision 6b401445 (ceph): rgw: fix valgrind when no valgrind
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Josh Durgin <josh.durgin@inktank.com> - 12:34 AM Revision a5c33a3d (ceph): rgw: fix valgrind when no valgrind
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:20 AM Revision 3a24579b (ceph): mini upgrade suite to run across all distros
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
09/06/2013
- 11:20 PM Revision 037ef818 (ceph): Merge pull request #82 from ceph/wip-valgrind
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 11:09 PM Revision 19324c63 (ceph): misc: valgrind: fix valgrind.supp path
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:09 PM Revision 9e03c737 (ceph): misc: valgrind: fix cd behavior
- The cd needs to happen at the beginning of the command, not at the end, or
else the funky wrapper scripts don't work ... - 11:08 PM Revision b4252bff (ceph): FileStore: add config option to disable the wbthrottle
- Backport: dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherr... - 11:08 PM Revision 699324e0 (ceph): WBThrottle: use fdatasync instead of fsync
- Backport: dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com>
(cherr... - 11:06 PM Revision 074717b4 (ceph): PGLog: initialize writeout_from in PGLog constructor
- Fixes: 6151
Backport: dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com>
Introduced: f808c205c503f7d32518c916... - 11:06 PM Revision c22d980c (ceph): PGLog: maintain writeout_from and trimmed
- This way, we can avoid omap_rmkeyrange in the common append
and trim cases.
Fixes: #6040
Backport: Dumpling
Signed-o... - 11:06 PM Revision 53c7ab4d (ceph): PGLog: don't maintain log_keys_debug if the config is disabled
- Fixes: #6040
Backport: Dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com>
(cherry picked from commit 1c0d75db... - 11:05 PM Revision 40dc4893 (ceph): PGLog: move the log size check after the early return
- There really are stl implementations (like the one on my ubuntu 12.04
machine) which have a list::size() which is lin... - 11:00 PM Revision 4261eb5e (ceph): rbd.cc: relicense as LGPL2
- All past authors for rbd.cc have consented to relicensing from GPL to
LGPL2 via email:
---
Date: Sat, 27 Jul 2013 0... - 10:13 PM Revision 766bd05f (ceph): Merge pull request #81 from ceph/wip-runfix
- Get rid of chdir-coredump.
- 10:11 PM Revision 82cfa848 (ceph): Get rid of chdir-coredump.
- 09:56 PM Revision f8e15040 (ceph): Merge pull request #80 from ceph/wip-runfix
- ceph: fix daemon-helper typo
- 09:49 PM Revision a60e84d4 (ceph): ceph: fix daemon-helper typo
- Broken in edc5ef8860b2917c14ee648f15ac7751535d411a
Signed-off-by: Sage Weil <sage@inktank.com> - 09:10 PM Revision feb204bf (ceph): Merge pull request #79 from ceph/wip-valgrind
- misc: valgrind --num-callers=50
- 09:05 PM Revision 2214fe18 (ceph): misc: valgrind --num-callers=50
- Default is 12, which isn't quite enough.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:02 PM Revision 712b7a95 (ceph): Merge pull request #568 from roaldvanloon/wip-cleanup-globals
- Wip cleanup globals
Reviewed-by: Sage Weil <sage@inktank.com> - 08:24 PM Revision c6d7ae0f (ceph): Merge pull request #78 from ceph/wip-6247
- Move helper scripts to /usr/local/bin to clean up logs.
- 08:24 PM Revision 611733c8 (ceph): Merge pull request #78 from ceph/wip-6247
- Move helper scripts to /usr/local/bin to clean up logs.
- 08:10 PM Revision 53b8e27d (ceph): Helper scripts live in /usr/local/bin now!
- 08:10 PM Revision 6e8a3807 (ceph): Helper scripts live in /usr/local/bin now!
- 08:09 PM Revision edc5ef88 (ceph): Move helper scripts to /usr/local/bin
- 04:50 PM Revision be889fa9 (ceph): Merge remote-tracking branch 'gh/next'
- 04:40 PM Revision bbdfa147 (ceph): Merge pull request #77 from ceph/wip-start
- queue: fix stderr redirect
- 04:39 PM Revision 1a05f9d0 (ceph): queue: fix stderr redirect
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:31 PM Revision 39c89dcf (ceph): common/crc32c_intel_fast: avoid reading partial trailing word
- The optimized intel code reads in word-sized chunks, knowing that the
allocator will only hand out memory in word-siz... - 04:27 PM Revision a4f0551f (ceph): Merge pull request #75 from ceph/wip-tube
- queue: include tube name in worker logs
- 04:23 PM Revision 1a03b175 (ceph): Merge pull request #76 from ceph/wip-5954
- Be polite and restore /etc/sudoers when done
- 04:19 PM Revision 5cd2f081 (ceph): queue: include tube name in worker logs
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:18 PM Revision f0eabc97 (ceph): Be polite and restore /etc/sudoers when done
- 02:53 PM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- Added a helper to check the mon_status in the remote host, it will be used to make sure it is actually running correc...
- 12:32 PM Bug #6249: daemon mon_status should report a daemon is not running
- Something along those lines would totally work for me :)
- 10:00 AM Bug #6249: daemon mon_status should report a daemon is not running
- The path could just be the wrong path as well (eg, got changed in config but daemon wasn't restarted). To be accurate...
- 08:48 AM Bug #6249 (Resolved): daemon mon_status should report a daemon is not running
- The current behavior is that it will return a generic exception log with a `No such file or directory` which is confu...
- 10:34 AM Bug #5823: cpu load on cluster node is very high, client can't get data on pg from primary node ...
- I'm using Ubuntu 12.10 (GNU/Linux 3.5.0-25-generic x86_64) kernel for all cluster nodes.
sometimes, i saw the osd ... - 10:11 AM RADOS Fix #6250 (New): OSD: handle ENODEV on reads
- Apparently the OSD translates a read error response of ENODEV into ENOENT and returns that to the client. That respon...
- 09:31 AM Bug #6235 (Resolved): fast intel crc code reads trailing words
- oops, he already did.. i'll merge this in!
- 09:29 AM Bug #6235: fast intel crc code reads trailing words
- Greg - please review.
- 09:04 AM devops Feature #5282 (In Progress): Get Dumpling into EPEL
- I've pinged both the epel/fedora and centos maintainers about including 0.67.3 when it's released.
- 09:02 AM devops Feature #5847 (Resolved): Build own versions of most recent leveldb for all supported platforms.
- Removing the Basho fix appears to fix the problem with centos/rhel6.3 platforms, so going with that solution.
Note... - 08:53 AM rgw Bug #5702 (Resolved): Radosgw RPM unnecessarily requires mod_fcgid
- Resolved with:
commit 8df504c157fc9de526657e5787c8fb532b678320
Author: Gary Lowell <gary.lowell@inktank.com>
Dat... - 08:51 AM Bug #6083 (Resolved): fedora18 rpm packages for ceph should be built with proper naming conventio...
- Resolved with the following commit:
commit 22e26a694da98da29a3fb3aa63e1627140831f39
Author: Gary Lowell <gary.low... - 08:45 AM rbd Feature #4917 (Resolved): iSCSI: Package tgt
- Pushed to ceph-extras repo.
- 08:37 AM Bug #6223 (Resolved): error generating keys
- 03:47 AM Bug #6223: error generating keys
- Hi!!
I've reinstalled Ceph with the new hostname and it's working fine now!! :)
Thanks a lot! - 08:36 AM Revision c3529ed0 (ceph): cleanup: passing context to NamedState for ceph_clock
- This makes the constructor call on the subclasses explicit, and passes
the cct to the NamedState constructor. This cc... - 08:24 AM devops Bug #6104 (Resolved): ceph-deploy should workaround pseudo-tty in SSH
- Merged into ceph-deploy master branch, with hash: 8eee1a3
- 07:22 AM devops Bug #6104 (Fix Under Review): ceph-deploy should workaround pseudo-tty in SSH
- This is not fixable with `pushy` (see ticket thread). So we are now falling back to disabling sudo if you are connect...
- 08:11 AM Revision 159693de (ceph): cleanup: globals from libosd
- There are some new globals introduced in libosd lately. This patch
cleans them.
Signed-off-by: Roald J. van Loon <ro... - 05:19 AM RADOS Bug #6246 (Resolved): crushtool dumps core with non-unique bucket IDs
- Any crushmap with duplicate bucket IDs will cause crushtool to dump core on compile. It would be much better of crush...
09/05/2013
- 10:42 PM Bug #6233: OSD crash during repair
- Was missing xattrs:
2013-09-06 09:30:19.813811 7f0ae8cbc700 0 log [INF] : applying configuration change: internal... - 07:46 PM Bug #6233: OSD crash during repair
- The pg being repaired at the time is 2.12, which 'ceph pg dump' tells me lives on [6,7]. Attached log is the output a...
- 10:16 PM Revision 4857a2a0 (ceph): Merge pull request #74 from ceph/wip-5954
- Wip 5954
- 10:15 PM Revision 7db9311a (ceph): Merge pull request #73 from ceph/wip-5954-alt
- Via automagic, only call ulimit -n if running as root.
- 09:56 PM Revision d6e8b233 (ceph): Add internal.sudo subtask.
- 09:55 PM Revision 6d1ed573 (ceph): Let execute() accept a string for args.
- 09:55 PM Revision 90f9a6ad (ceph): Add get_archive_dir()
- 09:55 PM Revision 8f2fb9da (ceph): Use misc.get_archive_dir()
- 09:55 PM Revision 6406a1ec (ceph): Add Cluster.write_file()
- 09:41 PM Revision 91fd0413 (ceph): Put sudo in front of adjust-ulimits if it's used
- 09:30 PM Revision 8e37361b (ceph): Via automagic, only call ulimit -n if running as root.
- Also, add comments because comments are cool.
- 08:29 PM Revision bb980c85 (ceph): Merge pull request #567 from roaldvanloon/wip-cleanup-globals
- Reviewed-by: Sage Weil <sage@inktank.com>
- 08:15 PM Revision 258396d5 (ceph): doc: Added entry for federated configuration to the index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:15 PM Revision da5ccf7a (ceph): doc: Added draft of configuration guide for federated gateways.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:02 PM Revision cf93c838 (ceph): cleanup: removing refs to globals from libosd
- Removed almost all references to globals, apart from two;
- In OSD.cc: reference to g_lockdep
- In PG.h: NamedState ... - 07:02 PM Revision 5dd0a83f (ceph): cleanup: removing globals from common/obj_bencher
- This file is in common/ but cant be included in libcommon.la because of
this reference. Removing it, making the binar... - 07:02 PM Revision 8d0a1dbc (ceph): cleanup: reduced number of pointer indirection in osd
- Signed-off-by: Roald J. van Loon <roaldvanloon@gmail.com>
- 07:01 PM Revision 9c4e6266 (ceph): cleanup: removed last references to globals from client
- - There were some refs in SyntheticClient to g_(ceph_context|conf), I
replaced them with client->cct and client->cc... - 06:58 PM Revision d34ba164 (ceph): Run yum clean all after installing new ceph-release.
- In order to get around the issue of repomd.xml being older than
the previously installed one depending on when the gi... - 05:23 PM devops Bug #6245 (Resolved): ceph-deploy: install command broken
- Fix merged to ceph-deploy master branch, with hash 225b7fbbab3ab9880484e2b814a4443986765849
After going back from ... - 05:21 PM devops Bug #6245 (Fix Under Review): ceph-deploy: install command broken
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/64
- 04:32 PM devops Bug #6245 (Resolved): ceph-deploy: install command broken
- ceph deploy version: 1.2.3
when trying to install ceph using ceph-deploy, it always installs the default ubuntu ... - 03:51 PM Revision d33853d3 (ceph): Merge pull request #555 from dachary/master
- minor documentation fixes
- 12:17 PM rgw Bug #6214 (Pending Backport): rgw: PUT object with chunked upload doesn't propagate client side e...
- Looks good to me.
- 12:17 PM devops Bug #6035 (Closed): ceph-deploy: ceph-create-keys stuck on fedora 18 VMs
- Closing as I cannot replicate this any more.
- 12:16 PM devops Bug #6160 (Resolved): allow installation of packages only
- merge on ceph-deploy's master branch with hash: 73b920a
- 07:03 AM devops Bug #6160: allow installation of packages only
- pull request opened https://github.com/ceph/ceph-deploy/pull/62
- 12:12 PM devops Feature #6017: ceph-deploy mon create: create on all mons in ceph.conf + then do gatherkeys if no...
- currently blocked as I cannot implement correctly the mon_status on remote hosts because I get output like:...
- 10:05 AM Feature #6033: cachepool: osd: basic io decision: read/write from/to cache pool or EAGAIN; make o...
- wip-6033-redirects
The Objecter half of this is done and seems to be working correctly. The OSD portion is a bit mor... - 09:41 AM Bug #6223: error generating keys
- jordi arcas wrote:
> HI Sage,
> It doesn't works...
> I've changed the hostname wich really is NCSL007.
> I atta... - 09:36 AM Bug #6223: error generating keys
- HI Sage,
It doesn't works...
I've changed the hostname wich really is NCSL007.
I attach you all logs with the new... - 08:15 AM Bug #6223: error generating keys
- jordi arcas wrote:
> Hi! I attach you all the logs I found
>
> Thanks!!
Heh, it was actually the IPs and hostn... - 01:25 AM Bug #6223: error generating keys
- Hi! I attach you all the logs I found
Thanks!! - 09:41 AM Fix #6242 (Resolved): ceph CLI should honor `--help` and not return log lines back
- I wanted to have access to the help menu in the `ceph` CLI, but for some reason it just returns a few log lines
with... - 09:40 AM Support #6238 (Rejected): About the data migration in Ceph
- These sorts of questions are appropriate for the ceph-users list. Please send them there. :)
- 06:15 AM Support #6238 (Rejected): About the data migration in Ceph
- Hi all,
recently i read the source code and paper, and i have some questions about the data movement:
1. when... - 09:39 AM Bug #6230: ceph osd crush move appears to be broken
- iirc move is only for leaf items.. there is link and unlink for buckets?
- 09:31 AM devops Bug #6237 (Resolved): osd create fails because key is not in remote function
- Merged into ceph-deploy master branch with hash: 3b49407cdc5d3cfe2a55fd843f7e8c8723a4c7db
- 07:05 AM devops Bug #6237: osd create fails because key is not in remote function
- Pull request opened: https://github.com/ceph/ceph-deploy/pull/63
- 06:02 AM devops Bug #6237 (Resolved): osd create fails because key is not in remote function
- ...
- 08:26 AM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/teuthology-2013-09-04_17:24:00-rados-master-testing-basic-plana/21102
- 08:20 AM rbd Bug #5426: librbd: mutex assert in perfcounters::tinc in librbd::AioCompletion::complete()
- ubuntu@teuthology:/a/teuthology-2013-09-05_01:00:58-rbd-next-testing-basic-plana/22153
- 08:05 AM Bug #6118: failed to recover before timeout expired on radosbench, rados api tests
- http://qa-proxy.ceph.com/teuthology/teuthology-2013-09-04_20:00:07-rados-dumpling-testing-basic-plana/21637/
- 08:04 AM rgw Bug #6240 (Resolved): rgw: invalid read on addr in msgr via objecter
- ...
- 12:35 AM Revision dfcee0cb (ceph): osd/ReplicatedPG: set reply versions for pg ops (PGLS)
- Returning the current version for the pgid and last_user_version makes
some sense here.
Signed-off-by: Sage Weil <sa... - 12:35 AM Revision c4414a34 (ceph): osd/ReplicatedPG: set reply versions on dup op ACK
- All other MOSDOpReply creators do this, with the exception of the pg
op.
Fixes: #6222
Signed-off-by: Sage Weil <sage...
09/04/2013
- 11:49 PM Revision 211c5f13 (ceph): rgw: flush pending data when completing multipart part upload
- Fixes: #6111
Backport: dumpling
When completing the part upload we need to flush any data that we
aggregated and didn... - 11:41 PM Revision 9a551296 (ceph): rgw: flush pending data when completing multipart part upload
- Fixes: #6111
Backport: dumpling
When completing the part upload we need to flush any data that we
aggregated and didn... - 11:39 PM Revision 16b24f10 (ceph): librados: make note of which calls steal the bufferlist contents
- This is an unfortunate feature of the API, but it can't be changed without
potentially breaking users.
Fixes: #5989
... - 11:28 PM Bug #6236 (Won't Fix): ceph pg dump columns sometimes out of alignment
We should pad columns so that even when multiple states are present for a pg the column headers are in the right po...- 11:28 PM Revision 616d4cb5 (ceph): rgw: check object name after rebuilding it in S3 POST
- Fixes: #6088
Backport: bobtail, cuttlefish, dumpling
When posting an object it is possible to provide a key
name tha... - 11:27 PM Revision 97a97c3c (ceph): rgw: check object name after rebuilding it in S3 POST
- Fixes: #6088
Backport: bobtail, cuttlefish, dumpling
When posting an object it is possible to provide a key
name tha... - 11:27 PM Revision 1a965101 (ceph): rgw: check object name after rebuilding it in S3 POST
- Fixes: #6088
Backport: bobtail, cuttlefish, dumpling
When posting an object it is possible to provide a key
name tha... - 11:26 PM Revision c8ec532f (ceph): rgw: check object name after rebuilding it in S3 POST
- Fixes: #6088
Backport: bobtail, cuttlefish, dumpling
When posting an object it is possible to provide a key
name tha... - 11:18 PM Revision ea412c05 (ceph): Merge branch 'wip-6078' into next
- Reviewed-by: Josh Durgin <josh.durgin@inktank.com>
- 11:11 PM Revision 8203b9b0 (ceph): rgw: fix CORS rule check
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:11 PM Revision 6ae4049a (ceph): rgw: add COPY method to be handled by CORS
- Was missing this http method.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:11 PM Revision 6af5a537 (ceph): rgw: fix certain return status cases in CORS
- Change return values in certain cases, reorder
checks, etc.
Signed-off-by: Yehuda Sadeh <yehuda@inktank.com> - 11:11 PM Revision 77c2a331 (ceph): rgw: remove use of s->bucket_cors
- Some old code still tried to use s->bucket_cors, which was
abandoned in a cleanup work.
Signed-off-by: Yehuda Sadeh ... - 11:11 PM Revision df4f712f (ceph): rgw: OPTIONS request doesn't need to read object info
- This is a bucket-only operation, so we shouldn't look at the
object. Object may not exist and we might respond with N... - 11:11 PM Revision 83eb5d67 (ceph): rgw: add a generic CORS response handling
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:11 PM Revision c5407983 (ceph): rgw: tie CORS header response to all relevant operations
- Have the CORS responses on all relevant operations. Also add headers
on failure cases.
Signed-off-by: Yehuda Sadeh <... - 11:11 PM Revision b564db89 (ceph): rgw: don't handle CORS if rule not found (is NULL)
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 11:05 PM Revision 3e90c2ab (ceph): common: unit test for crc32c
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 11:05 PM Revision 3233336c (ceph): common/crc32c_intel_fast: fix compile-time #ifdef
- This wasn't getting built in!
Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 11:05 PM Revision cfb07f14 (ceph): arch: add NEON cpu feature detection
- Signed-off-by: Sage Weil <sage@inktank.com>
Reviewed-by: Dan Mick <dan.mick@inktank.com> - 10:37 PM Revision 83a4848e (ceph): doc: Updated usage for --infile syntax. Added zone name for zone syntax.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:44 PM Revision df112473 (ceph): mon/OSDMonitor: fix POOL_OP_DELETE_SNAP early return
- Cut&paste goof in 0e85074402cd02b292daadcb5b8e73ac1207d571.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:31 PM Bug #6235 (Resolved): fast intel crc code reads trailing words
- ...
- 09:24 PM Revision 0f63cedd (ceph): Merge pull request #71 from ceph/wip-no-pythonpath
- drop obsolete PYTHONPATH settings
- 09:21 PM Revision c155dce1 (ceph): drop obsolete PYTHONPATH settings
- These are left over from when we were extracting a tarball in the test dir.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:04 PM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/teuthology-2013-09-04_17:24:00-rados-master-testing-basic-plana/21102
- 08:28 PM Revision e95e7073 (ceph): doc: Organized into sections. Added zone/region and pool details.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 08:16 PM Revision 89f1139d (ceph): Append '/' to the end of the log directory path
- 08:01 PM Revision 1bd74a02 (ceph): mon/MonClient: release pending outgoing messages on shutdown
- This fixes a small memory leak when we have messages queued for the mon
when we shut down. It is harmless except for... - 06:48 PM Documentation #6234 (Resolved): all our new-user paths need to document name-resolution restrictions
- yet another new user was confused about needing a non-127/8 address for the hostname today.
http://ceph.com/docs/m... - 06:25 PM Revision 9f44de5c (ceph): doc/release-notes: v0.68
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:46 PM Revision 4e7db958 (ceph): rbd: add rbd_snaps_ops.sh test
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:43 PM Revision 6a4f4f0d (ceph): Merge remote-tracking branch 'gh/wip-6047'
- Reviewed-by: Sage Weil <sage@inktank.com>
- 05:25 PM Revision b05f7ea5 (ceph): osd/ReplicatedPG: set reply versions for pg ops (PGLS)
- Returning the current version for the pgid and last_user_version makes
some sense here.
Signed-off-by: Sage Weil <sa... - 05:25 PM Revision 5148aac7 (ceph): osd/ReplicatedPG: set reply versions on dup op ACK
- All other MOSDOpReply creators do this, with the exception of the pg
op.
Fixes: #6222
Signed-off-by: Sage Weil <sage... - 05:11 PM Bug #6233 (Closed): OSD crash during repair
- On 0.56.7-1~bpo70+1, whilst trying to repair an OSD:
2013-09-05 09:19:33.020619 7f540a12d700 0 log [ERR] : 2.12 r... - 05:10 PM Revision f566102c (ceph): doc: remove 'Unexpected indentation' from versions doc.
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 04:47 PM rgw Bug #6111 (Resolved): rgw: multipart upload fails when last chunk < 512k
- Fixed, commit:9a551296e0811f2b65972377b25bb28dbb42f575.
- 03:45 PM rgw Bug #6111: rgw: multipart upload fails when last chunk < 512k
- The fix looks good to me. It looks like the s3-tests branch (wip-6111) has a couple extra lines left over from debugg...
- 04:39 PM Fix #5989 (Resolved): librados: document that bufferlist usage model is inconsistent
- 04:28 PM Revision b56af552 (ceph): Merge pull request #564 from ljagiello/swift_doc_fix
- Correct syntax for generate swift key
Signed-off-by: Lukasz Jagiello <jagiello.lukasz@gmail.com> - 04:26 PM rgw Bug #6088 (Resolved): rgw: When uploading via POST specifying text instead of file formdata input...
- Fixed, commit:c8ec532fadc0df36e4b265fe20a2ff3e35319744. Also cherry-picked to bobtail, cuttlefish, and dumpling.
- 04:22 PM rgw Bug #6088: rgw: When uploading via POST specifying text instead of file formdata input field, a s...
- The bug reproduction was manual, not sure how easy it'd be creating a boto based test for that.
- 03:01 PM rgw Bug #6088: rgw: When uploading via POST specifying text instead of file formdata input field, a s...
- Looks good to me, is there an associated s3-tests branch as well?
- 04:18 PM rgw Bug #6078 (Pending Backport): rgw: CORS not working
- 02:52 PM rgw Bug #6078: rgw: CORS not working
- Left a couple comments on github. It'd be nice to try to break up some of the changes and explicitly explain why chan...
- 04:16 PM Revision a26c8313 (ceph): Merge pull request #64 from ceph/wip-nuke-info
- nuke: get pid, owner from info.yaml (if present)
- 04:13 PM Revision 7dee3a13 (ceph): Merge pull request #65 from ceph/wip-schedule
- schedule: strip out targets
- 04:02 PM rgw Feature #6232 (New): rgw: create unitest for is_string_in_set()
- Recommended in code review for issue #6078
- 02:33 PM Revision a9a516a2 (ceph): Correct syntax for generate swift key
- 02:04 PM Revision f24e42bb (ceph): Merge pull request #68 from alfredodeza/6224
- add the missing for fedora links in install task
- 01:46 PM rbd Feature #4017 (Resolved): rbd: openstack: simplify volume booting with new api
- 01:41 PM rbd Feature #4017: rbd: openstack: simplify volume booting with new api
- Implemented by https://review.openstack.org/#/c/41728/
- 01:42 PM devops Bug #6160 (In Progress): allow installation of packages only
- 01:34 PM Feature #6231 (Resolved): buffer: cache crc in buffer::raw (or similar) to avoid recalculation fo...
- 01:32 PM rbd Subtask #4020 (Resolved): rbd: openstack: simplify volume booting with new api: make image boot b...
- superceded by modified boot panel interface: https://review.openstack.org/#/c/41728/
- 01:31 PM rbd Subtask #4019 (Resolved): rbd: openstack: simplify volume booting with new api: add boot option t...
- superceded by modified boot panel interface: https://review.openstack.org/#/c/41728/
- 01:30 PM rbd Subtask #4018 (Resolved): rbd: openstack: simplify volume booting with new api: modify boot panel...
- superceded by modified boot panel interface: https://review.openstack.org/#/c/41728/
- 01:26 PM rbd Subtask #4015 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-...
- https://review.openstack.org/#/c/38815/
- 01:23 PM rbd Subtask #4014 (Resolved): rbd: openstack: extend nova boot api: add block_dev_mapping_v2 to nova-api
- https://review.openstack.org/#/c/32568/
- 01:14 PM rbd Subtask #4016 (Fix Under Review): rbd: openstack: extend nova boot api: modify libvirt driver to ...
- https://review.openstack.org/#/c/42474/
- 01:03 PM Revision a9522ae2 (ceph): add the missing for fedora links in install task
- Signed-off-by: Alfredo Deza <alfredo.deza@inktank.com>
- 12:41 PM Bug #6230 (Resolved): ceph osd crush move appears to be broken
Per documentation at: http://ceph.com/docs/master/rados/operations/crush-map/
ceph osd crush move {bucket-name} ...- 10:53 AM Bug #6207: Found incorrect object contents
- The problem offset appears not to have changed since the prior successful read, and kern.log had:
2013-09-04T08:57... - 09:44 AM Bug #6207: Found incorrect object contents
- full logs here: ubuntu@teuthology:/var/lib/teuthworker/archive/sage-bug-6222-b/20456
- 10:41 AM devops Bug #4924 (Resolved): ceph-deploy: gatherkeys fails on raring (cuttlefish)
- 10:34 AM Revision ab69d993 (ceph): mon: fix typo and remove redundant sentence
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:33 AM Revision 3c9f8498 (ceph): doc: erasure code ghobject is made of gen_t + shard_t
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:33 AM Revision 7c09ede7 (ceph): mon: fix typo in comment
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:30 AM Bug #6222 (Resolved): ceph_test_rados failure; user_version 0 after a write
- Merged into master. :)
- 09:41 AM Bug #6223 (Need More Info): error generating keys
- can you attach your ceph.conf, /etc/hosts from the host where the mon is, and the output from 'ceph daemon mon.`hostn...
- 04:17 AM Bug #6223 (Resolved): error generating keys
- Hi!
I'm trying to prepare an admin and server node with ceph-deploy.
I've configured SHH, hostnames and I've instal... - 09:24 AM rgw Bug #6214: rgw: PUT object with chunked upload doesn't propagate client side errors
- Josh - can you please review?
- 09:21 AM devops Feature #6017 (In Progress): ceph-deploy mon create: create on all mons in ceph.conf + then do ga...
- Issue #6132 has been resolved and that adds a big warning message when the provided hostname does not match that of t...
- 09:15 AM Feature #6227: make osd crush placement on startup handle multiple trees (e.g., ssd + sas)
- The simplest solution is to set 'osd crush update on start = false' in your ceph.conf. We don't have a mechanism rig...
- 08:02 AM Feature #6227 (New): make osd crush placement on startup handle multiple trees (e.g., ssd + sas)
- See our crush map for layout: basically, we have 64 OSD SATA drives in one hierarchy and 6 SSD drives in a 'ssd' root...
- 09:07 AM devops Bug #6132 (Resolved): ceph-deploy to detect and warn when host != hostname
- Merged to ceph-deploy master branch with hash: 124e53e3513e80b306c68af7db1f4fe13e5d9d58
- 08:59 AM devops Bug #6132 (Fix Under Review): ceph-deploy to detect and warn when host != hostname
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/60
- 08:37 AM Revision d9187a73 (ceph): Merge branch 'next'
- 08:06 AM rbd Feature #6228 (Resolved): image name metavariable
- h3. User description
Symptoms:
* When a VM has two RBD volumes attached, the admin socket only access one of th... - 07:39 AM Bug #6226 (Resolved): after editing crushmap and adding new hosts, injecting it, several existing...
- I have edited the crushmap on our 70 OSD, 10 server, 0.61.5 ceph cluster (see attached file) and injected it.
I ha... - 06:50 AM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- Same thing here : I cherry-picked your commit (a9fb92762883e2522fc4d1dcd403c5d888264746 : rbd: fix buffer size for wr...
- 06:36 AM devops Bug #5944: ceph-deploy osd needs to be moved to use the new remote helpers
- This is a **massive** effort because `osd` is huge. Will update as I make progress on this.
`prepare` and `activat... - 04:56 AM Revision d5e265dc (ceph): schedule_suite.sh: turn up osd logging a little
- We have a collectin of bugs that we haven't been able to
reproduce but crop up regularly in the nightlies. Sam's bes...
09/03/2013
- 11:10 PM Revision b4cf0f25 (ceph): v0.68
- 11:00 PM Revision 2b2f296e (ceph): Merge branch 'wip-copyfrom'
- Reviewed-by: Samuel Just <sam.just@inktank.com>
- 10:56 PM Revision dcbdeaf6 (ceph): doc: Fix repo URL for Ceph cloning (dev/generatedocs)
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
- 10:48 PM Revision 3a8adf53 (ceph): objecter, librados: add COPY_FROM operation
- This operation will copy an entire object (data, attrs, omap)
atomically. If the src_version does not match the sour... - 10:48 PM Revision ed680791 (ceph): osd: initial COPY_FROM (not viable for large objects)
- Initial pass at COPY_FROM implementation. This uses COPY_GET to read an
object from another OSD and write it locally... - 10:48 PM Revision 996af2d8 (ceph): ceph_test_rados: test COPY_FROM
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:42 PM Bug #6222 (Fix Under Review): ceph_test_rados failure; user_version 0 after a write
- 08:56 PM Bug #6222 (Resolved): ceph_test_rados failure; user_version 0 after a write
- ...
- 09:35 PM Revision a455b16f (ceph): Add missing sudo from command.
- Fixes: #6218
- 09:20 PM Revision 746e78c6 (ceph): doc: Updated manual install to include sync agent, ARM packages, and DN...
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 09:10 PM Revision c367d6fe (ceph): ceph_test_rados: add missing kick for rollback
- This was broken by the refactor in 96aaa5e3a371ade8b91ad9ab991d996eaef2cea5
and can make us hang.
Signed-off-by: Sag... - 09:07 PM Revision 2d7054d1 (ceph): Merge pull request #67 from ceph/wip-3791
- Wip 3791
- 09:05 PM Revision 5985c9d5 (ceph): Add note about public teuthology logs.
- 09:02 PM Revision 51640632 (ceph): Wrap paragraphs.
- 08:53 PM Bug #6179 (Resolved): ceph_test_rados user_version checks fail during thrashing
- 09:36 AM Bug #6179 (Fix Under Review): ceph_test_rados user_version checks fail during thrashing
- 09:35 AM Bug #6179: ceph_test_rados user_version checks fail during thrashing
- Looks like maybe he found the bug (wip-6179).
- 08:34 PM Revision 24f26697 (ceph): rgw: change watch init ordering, don't distribute if can't
- Backport: dumpling
Moving back the watch initialization after the zone init,
as the zone info holds the control pool... - 08:33 PM Revision 1d1f7f18 (ceph): rgw: change watch init ordering, don't distribute if can't
- Backport: dumpling
Moving back the watch initialization after the zone init,
as the zone info holds the control pool... - 08:24 PM Revision 21b5dbd4 (ceph): Merge pull request #66 from ceph/wip-specific-exceptions
- Catch CommandFailedError and print debug info
- 07:40 PM Revision f744c4ce (ceph): Catch CommandFailedError and print debug info
- 07:05 PM Revision f3db12f0 (ceph): schedule: strip out targets
- If the user feeds in a yaml with targets, the worker will launch the job
but fail with
2013-09-03T11:18:34.333 CRITI... - 06:46 PM Revision f36f16a6 (ceph): Logs and Sentry links are public now.
- 06:13 PM Revision 7a0bd5bc (ceph): ceph.spec.in: remove trailing paren in previous commit
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 06:13 PM Revision f1507d23 (ceph): ceph.spec.in: Don't invoke debug_package macro on centos.
- If the redhat-rpm-config package is installed, the debuginfo rpms will
be built by default. The build will fail whe... - 06:09 PM Revision 4ba3d520 (ceph): Revert "Use install -d for /var/log/ceph."
- This reverts commit 8f29b3f9f1f294c449bb5215767cad67fdf7cde6.
Reviewed-by: Warren Usui <warren.usui@inktank.com> - 05:54 PM Revision 087800ee (ceph): osd: provide better version bounds for cls_current_version and ENOENT r...
- Following the changes to when we set or increase the user_version, we
want to continue to return the best lower bound... - 05:07 PM Revision d71cd549 (ceph): Merge remote-tracking branch 'gh/wip-6179'
- Reviewed-by: Greg Farnum <greg@inktank.com>
- 04:26 PM Feature #6221 (New): Objecter,OSD: make it easy to determine when the network is misbehaving
- This probably takes the form of:
1) perf counter for Pipe reconnects
2) maybe an average for the period from sendin... - 04:01 PM Feature #6038 (In Progress): cachepool: filestore/osd: infrastructure for large object COPY atomi...
- 04:01 PM Feature #6031 (Resolved): cachepool: osd: COPY from another pool; small objects only
- 12:33 PM Feature #6031 (In Progress): cachepool: osd: COPY from another pool; small objects only
- 11:13 AM Feature #6031 (Resolved): cachepool: osd: COPY from another pool; small objects only
- 03:49 PM Revision 8078e968 (ceph): Merge pull request #562 from kri5/wip-4365
- rgw: Allow wildcard in supported keystone roles.
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 02:20 PM Bug #6196 (Resolved): unittest_lfnindex testing older HASH_INDEX_TAG
- 7ec0b4fb780b91b44427ed94eee82c3c6b6fff9f
- 09:36 AM Bug #6196 (In Progress): unittest_lfnindex testing older HASH_INDEX_TAG
- 02:08 PM rgw Documentation #6217 (Closed): rgw: update man pages
- for radosgw, radosgw-admin
- 01:47 PM devops Bug #6216 (Resolved): rpm missing package when junit not installed
- Either need to not faile if libcepfs_java is not built, or configure needs to fail if the required package is not fou...
- 01:33 PM rgw Bug #6161 (Resolved): radosgw 0.67.2 update -> "ERROR: failed to initialize watch"
- Pushed a fix, commit:1d1f7f18dfbdc46fdb09a96ef973475cd29feef5.
- 01:29 PM rgw Cleanup #6215 (New): rgw: get rid / rename base op class ret value
- This is a reminiscent of the ancient original gateway architecture, and should probably die now. Issues like #6214 ca...
- 01:27 PM rgw Bug #6214 (Fix Under Review): rgw: PUT object with chunked upload doesn't propagate client side e...
- 01:23 PM rgw Bug #6214 (Resolved): rgw: PUT object with chunked upload doesn't propagate client side errors
- E.g., client disconnected in the middle of upload. This affects also multi-part upload (when uploading part data).
- 01:07 PM Bug #5700: very high memory usage after update
- Ah ok, that increase might explain the increased memory usage, We'll know for sure in a few days :)
But anyway, is... - 09:33 AM Bug #5700: very high memory usage after update
- Ah, sorry, I missed that.
And yeah, the massif output confirms that ~80% of the heap is consumed by the pg logs. ... - 08:54 AM Bug #5700: very high memory usage after update
- Great! There are no other show stoppers and upgrade should be smooth, right? :)
I uploaded my binary and the massi... - 08:28 AM Bug #5700: very high memory usage after update
- Corin Langosch wrote:
> For testing I'd like to wait for for the next dumpling release (hopefully with fixed http://... - 08:12 AM Bug #5700: very high memory usage after update
- For testing I'd like to wait for for the next dumpling release (hopefully with fixed http://tracker.ceph.com/issues/6...
- 07:39 AM Bug #5700: very high memory usage after update
- Also, massif should have generated a report file that indicates which callers are allocating all of the memory. Can ...
- 07:38 AM Bug #5700: very high memory usage after update
- Corin Langosch wrote:
> Do these settings affect data safety in any way? The cluster is an important production one,... - 12:57 PM devops Bug #5763 (Resolved): ceph-deploy new [IP] should error out
- Merged to ceph-deploy master branch with hash: 77438b522c82e79fdb0f9b0c5963ba5a61f07f10
The validator was updated ... - 08:09 AM devops Bug #5763 (Fix Under Review): ceph-deploy new [IP] should error out
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/58
- 11:31 AM rgw Bug #6208: rgw: md5 checksum failed on readwrite during upgrade-next tests
- There's a bunch of these in the apache logs:...
- 08:16 AM rgw Bug #6208 (Can't reproduce): rgw: md5 checksum failed on readwrite during upgrade-next tests
- ...
- 11:02 AM devops Feature #6018 (In Progress): Build ceph via jenkins
- 10:59 AM Bug #6177 (Can't reproduce): osd/ReplicatedPG.cc: 3852: FAILED assert(ctx->user_at_version > ctx-...
- We believe we fixed this up in the fix chain for #6179. My guess is on the pg_log_event_t changes to only specify new...
- 10:39 AM rbd Feature #4917 (In Progress): iSCSI: Package tgt
- Package build is set up except for opensuse12.2 and sles11sp2. It looks like for SuSE the IB devel libraries come fr...
- 10:21 AM Feature #5984: mon: probe monitors to check on their status regardless of quorum
- After a bit more thought I think we should make the mon_command() more robust and put this there. the fact that mon_...
- 10:18 AM devops Bug #5944 (In Progress): ceph-deploy osd needs to be moved to use the new remote helpers
- 10:15 AM Bug #6209 (Resolved): Objecter::recalc_op_target() breaks on non-existent pool target
- N/m, Sage got this already in commit:1610768d4a5373e57a0bde62e1a3365c2f5b0073
- 10:11 AM Bug #6209 (Resolved): Objecter::recalc_op_target() breaks on non-existent pool target
- I busted it with my tiering changes and will need to refactor in order to deal with unknown pools.
- 10:07 AM rgw Documentation #5669 (Resolved): Default site in Apache interferes with Gateway
- Not sure why this was opened. It has actually been in the documentation for quite some time.
- 10:06 AM rgw Documentation #5165: rgw: multisite: regions and global namespace documentation
- Wrote a "conceptual" document that failed Tamil's ease-of-use test, and rewrote in a quick-install procedure style. W...
- 09:31 AM Revision 60195581 (ceph): rgw: Allow wildcard in supported keystone roles.
- http://tracker.ceph.com/issues/4365 fixes #4365
Signed-off-by: Christophe Courtaut <christophe.courtaut@gmail.com> - 08:13 AM Bug #6118: failed to recover before timeout expired on radosbench, rados api tests
- 4 objects degraded, 1 pg stuck in recovery_wait...
- 07:48 AM Linux kernel client Bug #5429: libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
- ...
- 12:08 AM Revision f79b3799 (ceph): osd/ReplicatedPG: set user_version in waiting_for_commit replies
- Signed-off-by: Sage Weil <sage@inktank.com>
09/02/2013
- 09:32 PM Bug #6043: upstart does not reflect running ceph-osd daemons (ubuntu 13.04 only)
I seem to be running into a similar issue. Running 13.04 and 0.67.2 but it was also happening with 0.61.7, it seems...- 12:39 PM Bug #5700: very high memory usage after update
- BTW, would be nice if this issue would be re-opened. I cannot do this.. :(
- 09:52 AM Bug #6207 (Resolved): Found incorrect object contents
- ...
09/01/2013
- 11:06 PM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- more than 20GB later, still no bug so for my part it's solved. Thanks! :)
- 04:32 PM rbd Bug #5760: libceph: osdc_build_request(): BUG_ON(p > msg->front.iov_base + msg->front.iov_len);
- git cherry-pick 103673bf04c8207c92c3286005dfaa2d259ac9b6 68d253bc92e5fd780869b1fb31dd8e49267b8d4e
from v3.10.9 (0a4b... - 03:48 PM Revision 38169979 (ceph): schedule_suite.sh: default email to ceph-qa@ceph.com
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:42 PM Revision cc8e9011 (ceph): osd/ReplicatedPG: do not log user_version on deletion events
- Or snap trim events where we are adjusting the head's snapdir attr.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:42 PM Revision 72c6c302 (ceph): osd/ReplicatedPG: log previous user_version on clone
- Nothing relies on this, but it makes sense to me.
Signed-off-by: Sage Weil <sage@inktank.com> - 03:42 PM Revision 99793d97 (ceph): osd/ReplicatedPG: do not log a user_version on the snapdir object
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:42 PM Revision e8506b5a (ceph): osd/ReplicatedPG: do not set ctx->user_at_version unless ctx->user_modify
- Leave ctx->user_at_version set to the previous oi.user_version unless/until
we find that ctx->user_modify is true.
S... - 03:42 PM Revision 1610768d (ceph): osd: debug user_versions a bit
- Signed-off-by: Sage Weil <sage@inktank.com>
- 03:42 PM Revision 7d72e559 (ceph): osd/PG: only raise PG's last_user_version if entry is >
- We may have pg entries that do not increase the user_version at all (i.e.,
they may be 0). Do not update the last_us... - 03:42 PM Revision 1c5e58a8 (ceph): osdc/Objecter: fix dereference of NULL pg_pool_t
- Make sure we don't dereference a NULL pointer. Note that we check a
bit further down if the target pool does not exi... - 11:59 AM Bug #6177: osd/ReplicatedPG.cc: 3852: FAILED assert(ctx->user_at_version > ctx->new_obs.oi.user_v...
- http://teuthology.front.sepia.ceph.com/archive/teuthology-2013-09-01_01:01:33-krbd-master-testing-basic-plana/16054
- 12:43 AM Revision a200e184 (ceph): Validate S3 tokens against Keystone
- - Added config option to allow S3 to use Keystone auth
- Implemented JSONDecoder for KeystoneToken
- RGW_Auth_S3::aut...
08/31/2013
- 11:46 PM Revision 9636722a (ceph): Merge pull request #561 from ceph/wip-6178
- os: LevelDBStore: ignore ENOENT files when estimating store size
Reviewed-by: Sage Weil <sage@inktank.com> - 05:31 PM Revision c7f2def8 (ceph): Merge branch 'next'
- 05:30 PM Revision e48d6cb4 (ceph): mon: fix uninitialized Op field
- - Uninitialized field in MonitorLevelDB::Op causes random build errors.
Signed-off-by: Roald J. van Loon <roaldvanlo... - 05:28 PM Revision a5d815d2 (ceph): automake cleanup: uninitialized version_t
- This sometimes gives a completely random uint64_t value, because it is
potentially used uninitialized.
Signed-off-by... - 04:47 PM Bug #6179: ceph_test_rados user_version checks fail during thrashing
- 04:47 PM Bug #6178 (Resolved): mon/DataHealthService.cc: 131: FAILED assert(store_size > 0)
- 12:35 PM Bug #6178 (Fix Under Review): mon/DataHealthService.cc: 131: FAILED assert(store_size > 0)
- wip-6178 ; pull request 561
- 11:16 AM Bug #5700: very high memory usage after update
- Do these settings affect data safety in any way? The cluster is an important production one, so I cannot really play ...
- 10:18 AM Bug #5700: very high memory usage after update
- Corin Langosch wrote:
> I jus thought recreating the journal would help, but I didn't help at all.
>
> kill osd.1... - 03:07 AM Bug #5700: very high memory usage after update
- I jus thought recreating the journal would help, but I didn't help at all.
kill osd.12
/usr/bin/ceph-osd -i 12 --... - 02:00 AM Bug #5700: very high memory usage after update
- !http://s21.postimg.org/lzotzs1on/massif.jpg!
Looks like ceph is reading the whole log file (1GB) in memory and no... - 01:59 AM Bug #5700: very high memory usage after update
- !http://postimg.org/image/8vj9n39mr/!
Looks like ceph is reading the whole log file (1GB) in memory and not freein... - 01:45 AM Bug #5700: very high memory usage after update
- Here we go:
** restart with valgrind **
valgrind --tool=massif /usr/bin/ceph-osd -i 12 --pid-file /var/run/ceph... - 12:59 AM Bug #5700: very high memory usage after update
- > It's the pgs per osd that matters. But yeah, I'm not happy with my answer either, but I don't have much else to go ...
- 06:22 AM Revision 3d64322c (ceph): Revert "get_scratch_devices(): catch CommandFailedError, log "dev in use""
- This reverts commit 416508de9c628c5cae1b3a7f05bb3ec0e3639bdb.
NameError: global name 'CommandFailedError' is not def... - 05:19 AM rbd Feature #4231 (Closed): librbd: Java bindings
- Yes!
I'll close this one. - 12:35 AM Revision 80b61406 (ceph): README: add deps
- Reported-by: Loic Dachary <loic@dachary.org>
Signed-off-by: Sage Weil <sage@inktank.com> - 12:35 AM Revision 35b9beab (ceph): s/ceph-debug/ceph-debuginfo for rpms
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 12:02 AM Revision 46279327 (ceph): Merge pull request #541 from ceph/wip-6036
- osd objecter; copy-get
Reviewed-by: Greg Farnum <greg@inktank.com>
Reviewed-by: Samuel Just <sam.just@inktank.com>
08/30/2013
- 11:57 PM Revision 8d74f417 (ceph): osd/ReplicatedPG: factor {execute,reply}_ctx() out of do_op()
- Separate the processing of an OpContext from the preamble and
allocation, so that we can delay the execution for some... - 11:57 PM Revision b0a30a55 (ceph): osd: COPY_GET operation
- Add new rados operation to copy all user-visible content for an object
in a simple, safe way. Use a new object_copy_... - 11:57 PM Revision 4f6c6b2d (ceph): osd/ReplicatedPG: do not requeue if not primary
- This saves us a bit of work, since we will discard the op anyway if
we aren't primary (or even if we become primary a... - 11:54 PM Revision a6b04c5d (ceph): osd: discriminate based on connection messenger, not peer type
- Replace ->get_source().is_osd() checks and instead see if it is the
cluster_messenger so that we do not confuse ourse... - 11:54 PM Revision 34709447 (ceph): osd: add an Objecter instance
- It gets its own lock, timer, and osdmap.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:54 PM Revision bc99437e (ceph): osd: feed OSDMaps to the Objecter
- Feed every map message we see (that isn't discarded for some other
reason) to the Objecter. It has the same continui... - 11:54 PM Revision 20b25c6f (ceph): ceph-osd: rename msgr vars
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:54 PM Revision 8ba50c0e (ceph): osd/ReplicatedPG: drop src_obc.clear() calls
- These are all about to go out of scope; no need to clear them
explicitly.
Signed-off-by: Sage Weil <sage@inktank.com> - 11:54 PM Revision c6d0b10e (ceph): osd, objecter: clean up assert_ver()
- Create a separate union in the args and clean up the code a bit so that
this doesn't reuse the (unrelated) watch help... - 11:54 PM Revision 42b3d55d (ceph): osdc/Objecter: only request map on startup if epoch == 0
- Normal clients have no map and need one to get started. If we are the
OSD, we will already have one and will get fed... - 11:54 PM Revision 36d6e6fa (ceph): osdc/Objecter: allow ops to be canceled
- This is useful in general, and specifically will be useful for the
rados COPY operation.
Signed-off-by: Sage Weil <s... - 11:54 PM Revision 0712d958 (ceph): osd: less whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:54 PM Revision ea61abad (ceph): osd/ReplicatedPG: add whitespace
- Signed-off-by: Sage Weil <sage@inktank.com>
- 11:54 PM Revision a1dd98d7 (ceph): osd: add a separate messenger for the Objecter
- We will give the OSD's Objecter its own messenger so that it does not
interfere with the OSD when it marks things up ... - 11:54 PM Revision 6473060e (ceph): os/ObjectStore: add bufferlist variant of setattrs
- And hopefully we can kill the bufferptr ones someday!
Signed-off-by: Sage Weil <sage@inktank.com> - 11:53 PM Bug #6206 (Won't Fix): OSD::do_convertfs() doesn't transfer attributes
If we bump the FileStore::on_disk_version (renaming to FileStore::target_version), after the convertfs we can't mou...- 11:18 PM Revision 7ec0b4fb (ceph): unittest_lfnindex testing older HASH_INDEX_TAG
- Switch to work with new HOBJECT_WITH_POOL
fixes: #6196
Signed-off-by: David Zafman <david.zafman@inktank.com>
Revie... - 10:42 PM Revision 416508de (ceph): get_scratch_devices(): catch CommandFailedError, log "dev in use"
- Signed-off-by: Dan Mick <dan.mick@inktank.com>
Reviewed-by: Sage Weil <sage@inktank.com> - 10:41 PM Revision 8a65ae8e (ceph): doc/rados/operations/pools: remove experimental note about pg splitting
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:24 PM Revision b882aa2a (ceph): Merge pull request #560 from ceph/wip-6032-cache-objecter
- Wip 6032 cache objecter
Reviewed-by: Sage Weil <sage@inktank.com> - 09:13 PM Revision b30a1b28 (ceph): Merge pull request #554 from ceph/wip-tier-interface
- Specify a user and pg_pool_t interface for tiering/caching specifications
Reviewed-by: Samuel Just <sam.just@inktank... - 09:06 PM Revision e2fcad09 (ceph): Objecter: rename Op::oloc -> Op::base_oloc
- We want to be able to target other pools for caching and tiering, so
we need to take an oloc from the client and tran... - 09:06 PM Revision 665acc11 (ceph): Objecter: add an Op::target_oloc and use it instead of base_oloc in sen...
- For now we simply set target_oloc = base_oloc in recalc_op_target(), but
we will shortly be doing more interesting th... - 09:06 PM Revision b76953c6 (ceph): Objecter: be careful about precalculated pgids
- The only current user of the precalc_pgid field is list_objects. That's
fine, but we don't want new users to inadvert... - 09:06 PM Revision 4e439857 (ceph): mon/OSDMonitor: 'osd tier cache-mode <pool> <mode>'
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:06 PM Revision e3fb9121 (ceph): Objecter: respect read_tier & write_tier for initial op submission
- We overwrite target_oloc.pool with the appropriate [read|write]_tier.
write_tier wins if it matches both.
We don't ha... - 09:06 PM Revision efb7ab2a (ceph): qa/workunits/cephtool/test.sh: test osd tier CLI
- Signed-off-by: Sage Weil <sage@inktank.com>
- 09:06 PM Revision dae9a34b (ceph): osd_types: note that write_tier wins if read_tier is different
- For pg_pool_t.
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:06 PM Revision 3516996b (ceph): mon/OSDMonitor: 'osd tier {set,remove}-overlay <pool> [tierpool]'
- Also prevent 'osd tier remove ...' if the tierpool is the current overlay.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:06 PM Revision 13aac48f (ceph): workunits: add a test for caching redirects
- This may need to change since it exploits some of the loose
consistency we currently have with caching pools, but for... - 06:53 PM Revision df55c3e7 (ceph): added point releases of dumpling to upgrade-dumpling suite
- Signed-off-by: tamil <tamil.muthamizhan@inktank.com>
- 06:15 PM Feature #6198 (New): packaging, admin_socket: create ceph group, make socket be group writable
- admin_socket consumers must be root today (because the daemons run as root and create the socket without manipulating...
- 05:36 PM Revision 12c8850a (ceph): Merge pull request #530 from ceph/wip-monc-leak
- mon/MonClient: release pending outgoing messages on shutdown
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 05:05 PM Revision 64774e57 (ceph): os: LevelDBStore: ignore ENOENT files when estimating store size
- While iterating over the store files we race against leveldb, which may
be shuffling data around thus removing some f... - 05:03 PM Feature #6036 (Resolved): cachepool: osd: add objecter
- 05:02 PM Revision dcbf50b8 (ceph): nuke: get pid, owner from info.yaml (if present)
- Fall back to the old files if info.yaml is missing.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:42 PM Revision a708c8ab (ceph): ceph-post-file: use mktemp instead of tempfile
- tempfile is a debian thing, apparently; mktemp is present everywhere.
Signed-off-by: Sage Weil <sage@inktank.com>
(c... - 04:42 PM Revision 625f13ee (ceph): mon: discover mon addrs, names during election state too
- Currently we only detect new mon addrs and names during the probing phase.
For non-trivial clusters, this means we ca... - 04:41 PM Revision e60d4e09 (ceph): ceph-post-file: use mktemp instead of tempfile
- tempfile is a debian thing, apparently; mktemp is present everywhere.
Signed-off-by: Sage Weil <sage@inktank.com> - 04:31 PM rgw Feature #5842 (Resolved): rgw: integrate multi-region s3tests into teuthology task
- These tests have run successfully in the nightlies (they had valgrind issues that are being tracked on other tickets)...
- 12:30 PM rgw Feature #5842 (In Progress): rgw: integrate multi-region s3tests into teuthology task
- teuthology was updated to generate the necessary S3TEST_CONF input to trigger multi-region tests in the s3tests. This...
- 04:30 PM Bug #6179: ceph_test_rados user_version checks fail during thrashing
- Unfortunately I didn't set up any debug output for user versions because...well, because I didn't want to confuse thi...
- 10:19 AM Bug #6179: ceph_test_rados user_version checks fail during thrashing
- flab:teuthology 10:17 AM $ teuthology-schedule a.yaml --name sage-bug-6179-a -n 1
Job scheduled with ID 13732
sho... - 09:25 AM Bug #6179: ceph_test_rados user_version checks fail during thrashing
- 09:22 AM Bug #6179 (Resolved): ceph_test_rados user_version checks fail during thrashing
- 2013-08-30T01:33:42.532 INFO:teuthology.task.rados.rados.0.out:[10.214.132.15]: Writing 44 current snap is 201
...
... - 04:28 PM Revision 57cb25c8 (ceph): upstart: handle upper case in cluster name and id
- Signed-off-by: Alexandre Marangone <alexandre.marangone@inktank.com>
(cherry picked from commit 851619ab6645967e5d765... - 04:15 PM Revision e0d42c82 (ceph): Merge pull request #63 from ceph/wip-logger
- Never use 'except:' without specifying an Exception.
- 04:10 PM Revision 3981a8f1 (ceph): Never use 'except:' without specifying an Exception.
- 04:06 PM Bug #6196 (Resolved): unittest_lfnindex testing older HASH_INDEX_TAG
This unit test should test newer HOBJECT_WITH_POOL index_version.- 03:35 PM Bug #5700: very high memory usage after update
- Corin Langosch wrote:
> Hi Sage,
>
> to be honest I'm a little disappointed by your answer. 8192 isn't a lot of ... - 02:06 PM Bug #5700: very high memory usage after update
- Hi Sage,
to be honest I'm a little disappointed by your answer. 8192 isn't a lot of pgs? The docs say 50-100 pgs ... - 03:31 PM rgw Feature #6195 (Resolved): rgw: test full sync (with large object)
- Create a large object (greater than 5GB), test full sync that includes that object.
- 03:27 PM Feature #6032 (Resolved): cachepool: objecter: send requests to cache pool
- Thanks Sage!
merged to master in commit:b882aa2ace54099a1b5c2ce5b25ac29e29b9ec14 - 03:09 PM Feature #6032: cachepool: objecter: send requests to cache pool
- https://github.com/ceph/ceph/pull/560, branch wip-6032-cache-objecter
- 02:49 PM Feature #6032 (Fix Under Review): cachepool: objecter: send requests to cache pool
- 03:24 PM rgw Feature #6193 (Resolved): rgw: DR: per bucket sync
- Per bucket sync. Get the bucket sync position (name of objects that are currently in sync). For each such object, do ...
- 03:23 PM rgw Feature #6192 (Resolved): rgw: DR: per object sync
- Single object sync
Need to polish this a bit, but basically there are two separate
issues: request a copy and wait ... - 03:22 PM rgw Feature #6191 (Resolved): rgw: DR: per bucket replica_log handling
- Each agent will try to lock replica log shard, if succeeded then
will get the next bucket that it needs to work in f... - 03:22 PM devops Bug #5763 (In Progress): ceph-deploy new [IP] should error out
- on the latest ceph-deploy version 1.2.3, this problem exists.
ceph-deploy new command seems to accept any number o... - 03:21 PM rgw Feature #6190 (Resolved): rgw: DR: read list of buckets to do full sync on
- read list of buckets and store that info sharded in the replica_log
so that we could later on run multiple agents ag... - 03:17 PM rbd Feature #5275 (Resolved): openstack: port always_use_volumes option to grizzly
- 03:15 PM rbd Feature #4917: iSCSI: Package tgt
- 03:13 PM rgw Documentation #5165 (In Progress): rgw: multisite: regions and global namespace documentation
- 03:11 PM rgw Documentation #5166 (In Progress): rgw: dr: async repl and DR documentation
- 03:11 PM rbd Bug #5454 (In Progress): krbd: assertion failure in rbd_img_obj_callback()
- I think this may be a refcounting race with resends. Looking into it further.
- 03:11 PM rgw Feature #4340 (In Progress): rgw: dr: data sync agent: implement full sync
- 03:04 PM Feature #6189 (Resolved): cachepool: osd: promote on read
- 03:01 PM Feature #6188 (Resolved): cachepool: osd: promote on write and mark object dirty
- 02:56 PM Feature #6186 (Resolved): cachepool: osd: dirty state for an object in cache pool
- 02:56 PM Revision 83cfd438 (ceph): ceph_rest_api.py: create own default for log_file
- common/config thinks the default log_file for non-daemons should be "".
Override that so that the default is
/var... - 02:52 PM Feature #6033 (In Progress): cachepool: osd: basic io decision: read/write from/to cache pool or ...
- 02:50 PM Revision fbd7fe46 (ceph): Merge pull request #62 from ceph/wip-logger
- Add hung job description to email
- 02:48 PM Tasks #6184 (Closed): filestore should record if filestore_xattr_use_omap has ever been enabled a...
- Forgot that I already added ths.
- 02:33 PM Tasks #6184 (Closed): filestore should record if filestore_xattr_use_omap has ever been enabled a...
- 02:46 PM Feature #5993 (In Progress): EC: [link] Refactor recovery to use PGBackend methods
- 02:45 PM Tasks #6185 (New): expand upgrade tests to be able to test downgrade
- 02:41 PM Feature #5998 (Fix Under Review): EC: [link] FileStore must work with ghobjects rather than hobjects
- 02:35 PM Fix #4635 (Resolved): mon: many ops expose uncommitted state
- 02:33 PM Feature #6031 (Fix Under Review): cachepool: osd: COPY from another pool; small objects only
- 02:19 PM Feature #6030 (Resolved): cachepool: osd: pg_pool_t cache_pool property
- This and initial tooling around it is merged into master in commit:b30a1b288996c2f7a6471f38c13030e6047052a2.
- 01:47 PM Bug #6128: glance image-create with rbd --location fails to create image in rdb
- http://pastebin.com/ZwfuGckH --glance-api.log from glance image-create from stdin
http://pastebin.com/YwEEz0xG --gla... - 01:43 PM rgw Documentation #6182 (Resolved): Conflicting locations for s3gw.fcgi
- This applies to the following page: http://ceph.com/docs/next/install/rpm/
When creating an Apache httpd virtual h... - 01:07 PM rbd Feature #4231: librbd: Java bindings
- Wido,
Can we close this ticket now? - 12:29 PM rgw Feature #5605: rgw: teuthology tests to check bucket issues in multi region env
- The ceph-qa-suite commits were actually c37faa8cf90abe54cba051b045edfe4ab9750bbc
The previous specified commit wa... - 11:32 AM rgw Feature #5605 (Resolved): rgw: teuthology tests to check bucket issues in multi region env
- The tests were added to teuthology/task/radosgw-admin.py in commit ff2a209f8d05fd018c0c6709ea70ed5fb1360435
The Y... - 11:53 AM devops Feature #3347: ceph-deploy: allow setting ssh user
- Would suggest default behaviour is to run as the user who is invoking the script.
- 11:48 AM devops Feature #6020 (Need More Info): radosgw-apache opinionated package
- We need a explicit description of what should be packaged up for a new radosgw package.
Eg, config files to add, r... - 11:41 AM devops Feature #6067: ceph-deploy: make mon create catch common errors
- 10:42 AM rgw Bug #6121 (Resolved): key error during readwrite test in upgrade suite
- Fixed a code path where the traceback key was not being set.
The fix has been in for a few days and we've seen no o... - 10:10 AM devops Feature #5956: Implement a radosgw command in ceph-deploy
- ceph-deploy should be able to install/deploy radosgw to a remote host
- 09:21 AM Bug #6178 (Resolved): mon/DataHealthService.cc: 131: FAILED assert(store_size > 0)
- ...
- 08:41 AM Messengers Bug #5508: msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
- ...
- 08:40 AM Bug #6177: osd/ReplicatedPG.cc: 3852: FAILED assert(ctx->user_at_version > ctx->new_obs.oi.user_v...
- ubuntu@teuthology:/a/teuthology-2013-08-30_01:01:28-krbd-master-testing-basic-plana/13463
- 08:30 AM Bug #6177 (Can't reproduce): osd/ReplicatedPG.cc: 3852: FAILED assert(ctx->user_at_version > ctx-...
- ...
- 08:27 AM rgw Bug #6176 (Resolved): rgw: valgrind: leak in copy_obj
- ...
- 08:26 AM rgw Bug #6175 (Resolved): rgw: valgrind: invalid reads in copy_obj
- ...
- 07:48 AM rbd Bug #6174 (Can't reproduce): osdc/ObjectCacher.cc: 526: FAILED assert(i->empty()) on cuttlefish f...
- ...
- 07:36 AM Feature #6173 (Resolved): Add LevelDB support to ceph cluster backend store
- http://wiki.ceph.com/01Planning/02Blueprints/Emperor/Add_LevelDB_support_to_ceph_cluster_backend_store
- 03:27 AM Revision f342baeb (ceph): run: do not import at top level
- This makes a run with --lock hang when connecting, for some
reason. E.g.,
$ teuthology -v a.yaml --lock
...
INFO...
08/29/2013
- 11:34 PM Revision 56ff4101 (ceph): Merge pull request #559 from ceph/wip-osd-rollback
- fixes a few osd dout bugs; make rados model behave with rollback
Reviewed-by: Samuel Just <sam.just@inktank.com> - 11:08 PM Revision 96aaa5e3 (ceph): ceph_test_rados: rollback bumps user_version
- Sigh. This doesn't make much intuitive sense to me, but this is how it
currently works.
Switch to using the async a... - 10:44 PM Bug #6083: fedora18 rpm packages for ceph should be built with proper naming convention for ceph-dbg
- Looks the issue is with the expect script that does the rpm signing timing out. It has a default time out of 10 seco...
- 09:30 AM Bug #6083: fedora18 rpm packages for ceph should be built with proper naming convention for ceph-dbg
- The incorrectly named debug package is valid and signed with the autobuild key. So we know that it's good through at...
- 10:30 PM devops Feature #5847: Build own versions of most recent leveldb for all supported platforms.
- Centos 6.3/6.4 & rhel 6.3/6.4 are backported from the fedora19 leveldb 1.12 package.
12.04 is backported from the Ra... - 09:58 PM devops Feature #5847: Build own versions of most recent leveldb for all supported platforms.
- Can you confirm which versions of LevelDB you are packaging for each OS:
CentOS 6.3
CentOS 6.4
RHEL 6.3
RHEL 6.... - 10:12 PM Revision 42d65b0a (ceph): PGLog: initialize writeout_from in PGLog constructor
- Fixes: 6151
Backport: dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com>
Introduced: f808c205c503f7d32518c916... - 10:08 PM Revision 24991c4a (ceph): Add hung job description to email
- 10:00 PM Revision ed62c457 (ceph): osd_types: add pg_pool_t cache-related fields
- We add fields sufficient to specify
* many pools have a tiering relationship with pool foo
* pool foo is a tier pool ... - 10:00 PM Revision 5e2c86ad (ceph): osd/OSDMonitor: avoid polluting pending_inc on error for 'osd pool set ...
- Signed-off-by: Sage Weil <sage@inktank.com>
- 10:00 PM Revision af0a0cd7 (ceph): mon/OSDMonitor: 'osd pool tier <add|remove> <pool> <tierpool>'
- Signed-off-by: Sage Weil <sage@inktank.com>
Signed-off-by: Greg Farnum <greg@inktank.com> - 09:28 PM Revision 4f7fce52 (ceph): osd/ReplicatedPG: drop dout from object_context_destructor_callback
- We don't hold the pg lock; cannot call dout here.
Signed-off-by: Sage Weil <sage@inktank.com> - 09:27 PM Revision 00b6a94c (ceph): osd/ReplicatedPG: remove debug lines from snapset_context get/put
- The dout() prefix does get_osdmap(), which requires (and asserts) that we
hold the pg lock, but in some cases we do n... - 09:26 PM Revision 47f16bd9 (ceph): Merge pull request #61 from ceph/wip-logger
- Log all the things! (Things like exceptions.)
- 09:12 PM Revision 44401f9a (ceph): Workers: only log child's stderr, not stdout
- 08:05 PM Revision 83a5ab19 (ceph): Pretty-up write_initial_metadata; s/run/name/
- 08:05 PM Revision 40f1d4fc (ceph): Don't print colon if there's no exception message. Also, remove testing
- exception.
- 08:04 PM Revision f6430df2 (ceph): run: write info.yaml on job start
- Include basic metadata bout the job.
Signed-off-by: Sage Weil <sage@inktank.com> - 08:04 PM Revision 9550b499 (ceph): Add exception hook
- 08:03 PM Revision 649bddf7 (ceph): run: set up archive dir and logger output sooner
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:03 PM Revision 27eea4ad (ceph): test
- 08:03 PM Revision a0e86c05 (ceph): Move logging setup out of main()
- 07:51 PM rbd Bug #5636 (Fix Under Review): krbd: crash in image refresh
- branch wip-rbd-bugs-shutdown-lock contains a few fixes
- 07:48 PM rbd Bug #5391 (Duplicate): krbd: crash in rbd_obj_request_create -> strlen
- pretty sure this is the same notify vs shutdown race as #5636
- 07:42 PM rbd Feature #5003: cinder/nova: don't require ceph.conf on a compute host / support multiple clusters
- I can't edit status for some reason, but this was merged a couple months ago https://review.openstack.org/#/c/30790/
- 06:39 PM Revision 9cc40a52 (ceph): Merge pull request #556 from ceph/wip-user-version
- make ceph_test_rados / RadosModel validate the versions exposed by librados
Reviewed-by: Greg Farnum <greg@inktank.c... - 05:56 PM Revision 7a7361d7 (ceph): rgw: Fix S3 auth when using response-* query string params
- Reviewed-by: Yehuda Sadeh <yehuda@inktank.com>
Signed-off-by: Sylvain Munaut <s.munaut@whatever-company.com> - 04:46 PM rbd Bug #6139: kernel panic in vms during disk benchmarking
- I've updated kernel to the latest linux-image-lts-raring and I am also having vm crashes. I can get the crash by runn...
- 04:12 PM Revision 91616ce4 (ceph): ceph.spec.in: remove trailing paren in previous commit
- Signed-off-by: Gary Lowell <gary.lowell@inktank.com>
- 04:12 PM Revision b03f2417 (ceph): ceph.spec.in: Don't invoke debug_package macro on centos.
- If the redhat-rpm-config package is installed, the debuginfo rpms will
be built by default. The build will fail whe... - 03:43 PM Feature #6032 (In Progress): cachepool: objecter: send requests to cache pool
- wip-6032-cache-objecter, currently based on top of https://github.com/ceph/ceph/pull/554
The objecter will follow th... - 03:14 PM Bug #6151 (Resolved): OSD: FAILED assert(!log_keys_debug->count(i->first))
- 42d65b0a7057696f4b8094f7c686d467c075a64d
- 01:14 AM Bug #6151 (Resolved): OSD: FAILED assert(!log_keys_debug->count(i->first))
- <b>/a/teuthology-2013-08-28_21:55:13-krbd-master-testing-basic-plana/11274$ zless remote/ubuntu@plana24.front.sepia.c...
- 03:04 PM Linux kernel client Feature #6163 (Resolved): support caching pool and redirects
- This is the kernel client analogue to #6032.
- 02:03 PM Linux kernel client Feature #6162 (Resolved): support user_version & replay_version
- We've now implemented separate user and replay versions in the userspace Ceph stuff, but the kernel client still only...
- 01:26 PM rbd Feature #4917: iSCSI: Package tgt
- Looks right to me. The "split into .so's" patch still hasn't been accepted, but that probably doesn't bother us yet....
- 01:16 PM rbd Feature #4917 (Fix Under Review): iSCSI: Package tgt
- Dan - do you agree with Gary's steps above?
- 01:07 PM Revision ed575251 (ceph): Merge pull request #58 from ceph/queue
- Don't assume anything about the base path here.
- 01:06 PM devops Bug #6104: ceph-deploy should workaround pseudo-tty in SSH
- One possible solution to this is to detect a `root` user and just not do the sudo connection.
Other than that, I t... - 10:12 AM devops Bug #6104: ceph-deploy should workaround pseudo-tty in SSH
- pushy dev says this might not be straightforward so fixing this will depend on pushy fixing it on their end.
- 01:03 PM rgw Bug #6161 (Resolved): radosgw 0.67.2 update -> "ERROR: failed to initialize watch"
- off the mailing list.
- 12:40 PM devops Bug #6160 (Resolved): allow installation of packages only
- A lot of users care for their own repositories and keys making ceph-deploy a no-go when attempting to install ceph.
... - 12:20 PM rgw Bug #6159 (Won't Fix): syncing an existing user causes an error
- It's not uncommon for the system users in a sync relationship to use the same keys. If this occurs, every metadata sy...
- 11:25 AM devops Bug #6158: selective sync of ceph precise dependencies from havana cloud archive
- Packages for 12.04 that Ceph Dumpling requires are: perftools, leveldb, libs3, libunwind, qemu
- 11:24 AM devops Bug #6158 (Rejected): selective sync of ceph precise dependencies from havana cloud archive
- leveldb
libs3-dev
gperfootls
libunwind
reprepro lets you do a selective sync, according to james. - 10:55 AM rgw Bug #6152 (Pending Backport): New S3 auth code fails when using response-* query string params to...
- 07:20 AM rgw Bug #6152 (Resolved): New S3 auth code fails when using response-* query string params to overrid...
- Previously there was a list of subresources to ignore when generating a signature. This has changed to a list of subr...
- 10:22 AM devops Feature #6018: Build ceph via jenkins
- 10:16 AM rbd Feature #5938: openstack: nova: allow live-migration without detach/reattach for rbd
- 10:00 AM devops Feature #3347: ceph-deploy: allow setting ssh user
- Changing subject so we are not prescriptive about where the ssh user is set. IMO it should be a ceph-deploy switch, n...
- 09:38 AM rbd Bug #6129 (Resolved): krbd: build broken when CEPH_FSCACHE disabled
- 09:35 AM devops Feature #6154: ceph-deploy should be able to use an argument "fs-type" to specify the filesystem ...
- As a workaround until this gets implemented, you can specify "fs type = foo" in the ceph.conf (at whatever granularit...
- 08:20 AM devops Feature #6154 (Resolved): ceph-deploy should be able to use an argument "fs-type" to specify the ...
- According to the documentation, it seems intended and expected that ceph-deploy should be able to define which filesy...
- 09:22 AM Bug #5896 (Fix Under Review): mon: MonmapMonitor: 'ceph mon add' always returns 'mon already exists'
- wip-5896, pull request 557
- 08:40 AM devops Feature #4954 (Need More Info): ceph-deploy: help and document need to be updated for osd create
- From what I see, `prepare` does `activate`, how are you running ceph-deploy and what are you seeing as output that te...
- 08:32 AM devops Bug #6035 (Need More Info): ceph-deploy: ceph-create-keys stuck on fedora 18 VMs
- 08:31 AM devops Bug #6035: ceph-deploy: ceph-create-keys stuck on fedora 18 VMs
- I can no longer replicated this.
Also the hosts have changed from Fedora to Ubuntu. And I really don't see where i... - 08:07 AM devops Bug #6138 (Resolved): 'ceph-deploy disk list' fails on CentOS 6.4
- Merged to ceph-deploy master branch
Hash: 69a765cfa94716813e5d77aa910c3ad21951b93b
Now the $PATH is always pass... - 06:05 AM devops Bug #6138 (Fix Under Review): 'ceph-deploy disk list' fails on CentOS 6.4
- Opened pull request: https://github.com/ceph/ceph-deploy/pull/55
- 07:59 AM Bug #6153 (Duplicate): osd/PGLog.cc: 632: FAILED assert(!log_keys_debug->count(i->first))
- #6151
- 07:37 AM Bug #6153 (Duplicate): osd/PGLog.cc: 632: FAILED assert(!log_keys_debug->count(i->first))
- ...
- 07:50 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- this will go into the next dumpling point release. thanks again for helping track it down!
- 07:49 AM devops Bug #4924 (Pending Backport): ceph-deploy: gatherkeys fails on raring (cuttlefish)
- 12:40 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- P.S.:
When does the fix will make it into the main branch (dumpling)?
I keep working with wip-4924 for now?
- 12:36 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Sage Weil wrote:
> thanks for helping test this!
better free software ;-)
> add the --zap-disk argument to blo... - 07:40 AM Fix #6116: osd: incomplete pg from thrashing on next
- ubuntu@teuthology://a/teuthology-2013-08-28_01:00:04-rados-master-testing-basic-plana/10150
- 05:29 AM Revision 444a0ab1 (ceph): Enabling multi-region S3 tests
- This file turns on multi-region
S3 tests. Ticket #5842.
Signed-off-by: Joe Buck <jbbuck@gmail.com> - 04:54 AM Revision ef85facb (ceph): schedule_suite.sh: allow partial 'suite' names
- Mangle the name (/ -> :) in the run name. Separate base from
relative path so that the job names don't include a ful... - 04:53 AM Revision 4fbec834 (ceph): suite: return [] for build_matrix base case
- This gives us an empty list instead of a crash on an empty dir
or bad symlink
Signed-off-by: Sage Weil <sage@inktank... - 01:52 AM Revision d3f13698 (ceph): Merge pull request #60 from ceph/sentry
- Add run name to first line of email.
- 12:54 AM Revision 02659cd5 (ceph): Merge pull request #361 from atwardowski/patch-1
- Update adminops.rst add capabilities
Reviewed-by: Yehuda Sadeh <yehuda@inktank.com> - 12:05 AM Revision 9374dc8b (ceph): messages/MOSDOpReply: fix user_version in reply (add missing braces)
- Presumbly a mismerge somewhere back around
de20997445803dca4225ed0dac1bad6a8a1e6512.
Signed-off-by: Sage Weil <sage@... - 12:05 AM Revision c8dcd2ea (ceph): osd/ReplicatedPG: set version, user_version correctly on reads
- Set the user version to the *current* object version, not the version
we would use if we were to modify it. We move ... - 12:05 AM Revision e20d1f8e (ceph): ceph_test_rados: validate user_version
- Signed-off-by: Sage Weil <sage@inktank.com>
- 12:05 AM Revision 985a1405 (ceph): librados: add get_version64()
- The C++ AioCompletion::get_version() method only returns 32-bits. Sigh.
Add a get_version64() method that returns a...
08/28/2013
- 11:48 PM Revision b2b0f202 (ceph): qa: workunits: mon: test snaps ops using rbd.
- Regression test for #6047
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com> - 11:48 PM Revision 7e722245 (ceph): rbd.cc: propagate some errors to user-space when they're available
- There was a bunch of situations in which we would have a proper error to
propagate to user-space but we would always ... - 11:48 PM Revision 0e850744 (ceph): mon: OSDMonitor: return earlier on no-ops over currently committed state
- Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com>
- 11:48 PM Revision 274b4b96 (ceph): mon: OSDMonitor: don't propose on prepare_pool_op()
- Except in very special cases, we should let PaxosService take its course
and trigger the proposals itself. In this c... - 11:48 PM Revision fab79543 (ceph): mon: OSDMonitor: check if pool is on unmanaged snaps mode on mk/rmsnap
- Backport: dumpling
Fixes: #6047
Signed-off-by: Joao Eduardo Luis <jecluis@gmail.com> - 09:26 PM Revision 778c0857 (ceph): Merge pull request #59 from ceph/wip-collections
- redo the way we describe test collections
- 09:10 PM Revision 3e63c1a4 (ceph): Merge pull request #550 from ceph/wip-6040
- Wip 6040
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Loic Dachary <loic@dachary.com> - 08:41 PM Revision df73f503 (ceph): Add run name to first line of email.
- 08:25 PM Revision b8295433 (ceph): suite: generalize collection expansion
- Previous, a collection was a directory like this:
mycollection/
mycollection/facet1/
mycollection/facet1/1a.yaml
... - 08:25 PM Revision 7163e89b (ceph): suite: allow individual files to be scheduled
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:25 PM Revision 7ce66962 (ceph): suite: build_matrix as a list of filenames, not file content
- Signed-off-by: Sage Weil <sage@inktank.com>
- 08:18 PM Revision f808c205 (ceph): PGLog: maintain writeout_from and trimmed
- This way, we can avoid omap_rmkeyrange in the common append
and trim cases.
Fixes: #6040
Backport: Dumpling
Signed-o... - 08:08 PM Revision 8a1da62d (ceph): ceph-post-file: single command to upload a file to cephdrop
- Use sftp to upload to a directory that only this user and ceph devs can
access.
Distribute an ssh key to connect to ... - 06:41 PM Revision 8314140d (ceph): suite: clean up imports
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:40 PM Revision 2dd889e4 (ceph): suite: make collection args (optionally) relative to a base dir
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:40 PM Revision 8894ff6b (ceph): suite: add --dry-run
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:40 PM Revision 802fa51d (ceph): suite: make names a bit more friendly
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:36 PM Revision 6175a133 (ceph): Don't assume anything about the base path here.
- 06:30 PM Revision a1a3358a (ceph): README: update for new flexible structure.
- Signed-off-by: Sage Weil <sage@inktank.com>
- 06:24 PM Revision 30c56cc1 (ceph): mark all existing collections with %
- This is ignored by old teuthology, but used by newer code to tell us when
to generate a product of all directory item... - 05:39 PM Revision fd3fd596 (ceph): doc/release-notes: v0.56.6 and .7 bobtail
- Signed-off-by: Sage Weil <sage@inktank.com>
- 05:29 PM Revision cb2abad9 (ceph): Merge pull request #539 from dachary/master
- doc : erasure code developer notes updates
- 05:08 PM Revision f271a73c (ceph): Merge pull request #552 from ceph/wip-4924-master
- mon: discover mon addrs, names during election state too
Reviewed-by: Joao Eduardo Luis <joao.luis@inktank.com> - 04:50 PM Revision c2402857 (ceph): mon: discover mon addrs, names during election state too
- Currently we only detect new mon addrs and names during the probing phase.
For non-trivial clusters, this means we ca... - 04:49 PM Bug #6047 (Pending Backport): mon: Assert and monitor-crash when attemting to create pool-snapsho...
- 04:41 PM Feature #6147 (Resolved): mon: calculate, expose per-pool pg stat deltas
- so we can get iops, recovery stats on a per-pool basis
- 04:38 PM Revision a472f501 (ceph): Merge pull request #54 from ceph/sentry
- Add logs and Sentry events to suite emails
- 04:36 PM Revision 38a47ece (ceph): Don't return inside __init__
- 04:34 PM Revision 61b40f48 (ceph): doc/dev/cache-pool: document cache pool management interface
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:33 PM Revision b91c1c52 (ceph): add CEPH_FEATURE_OSD_CACHEPOOL
- Signed-off-by: Sage Weil <sage@inktank.com>
- 04:30 PM Subtask #5862: FileStore must work with ghobjects rather than hobjects
- pg_info_t has our standard encode/decode function versioning. We've got some fairly complex ones you can examine wher...
- 04:06 PM Subtask #5862: FileStore must work with ghobjects rather than hobjects
- The ceph-filestore-dump probably needs a version bump to prevent an import of an export which includes erasure coding...
- 04:15 PM Revision be9a39b7 (ceph): Merge pull request #549 from ceph/wip-6029
- Make user_version a first-class citizen
Reviewed-by: Sage Weil <sage@inktank.com>
Reviewed-by: Sam Just <sam.just@ink... - 04:15 PM Revision 53cea02a (ceph): Add apology for non-public links
- 04:12 PM Revision 25defd40 (ceph): Indent wrapped exceptions.
- 04:01 PM Revision ffac4ad2 (ceph): s3tests: extend for multi-region tests
- Added code to the s3tests task to extract
multi-region info so that that data
can be added to the S3TEST_CONF file
us... - 04:01 PM Revision 2346f1d7 (ceph): s3tests: extend for multi-region tests
- Added code to the s3tests task to extract
multi-region info so that that data
can be added to the S3TEST_CONF file
us... - 04:00 PM Revision db518885 (ceph): rgw: persist the region info
- The rgw task deletes the region info
from the config structure. The s3tests
task needs this info, so we persist
it by... - 04:00 PM Revision 2877e272 (ceph): radosgw-agent: store radosgw_agent server/port
- Persist the hostname and port number used
by the radosgw-agent http server.
Signed-off-by: Joe Buck <jbbuck@gmail.co... - 03:59 PM Revision 6c5a7af1 (ceph): move multi_region_enabled() into util class
- Moving a helper function into a more general
location so that it can be used by other
classes.
Signed-off-by: Joe Bu... - 02:11 PM Bug #6040 (Pending Backport): Significant slowdown of osds since v0.67 Dumpling
- 01:51 PM Feature #6143 (Resolved): OSD: kill filestore_xattr_use_omap, leave it enabled forever, adjust xa...
- Otherwise you might get a corrupt osd.
- 01:28 PM Bug #6083: fedora18 rpm packages for ceph should be built with proper naming convention for ceph-dbg
- The problem with suffix on the debug package is happening intermittently on fedora17, fedora18, and sles11sp2 gitbuil...
- 01:15 PM rbd Feature #4917: iSCSI: Package tgt
- It looks like what is needed:
1) Clone upstream source, https://github.com/fujita/tgt, into the github repo
2) Ad... - 12:56 PM rbd Bug #6140 (Rejected): qa: add phoronix-test-suite benchmark to rbd test suite
- This just runs benchmarks we already have like bonnie, iozone, and dbench.
- 09:03 AM rbd Bug #6140 (Rejected): qa: add phoronix-test-suite benchmark to rbd test suite
- for krbd and/or qemu+librbd. see #6139
- 11:49 AM Bug #6110 (Resolved): v0.67.1 branch is missing on gitbuilder for debian precise
- This time for sure.
It really is there:
$ curl http://gitbuilder.ceph.com/ceph-deb-precise-x86_64-basic/ref/v0.... - 10:02 AM Bug #6110 (In Progress): v0.67.1 branch is missing on gitbuilder for debian precise
- I still dont see it on http://gitbuilder.ceph.com/ceph-deb-precise-x86_64-basic/ref/
Gary is looking into it. - 10:44 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- bernhard glomm wrote:
> Sage Weil wrote:
> > Bernhard, thanks for those logs--I think I've identified the problem. ... - 10:43 AM devops Bug #4924 (Resolved): ceph-deploy: gatherkeys fails on raring (cuttlefish)
- thanks for helping test this!
- 09:22 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Sage Weil wrote:
> Bernhard, thanks for those logs--I think I've identified the problem. Can you try with wip-4924 ... - 08:22 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- sorry, didn't realised on the first glance it was a normal package repository...
got it, will post results ASAP - 01:54 AM devops Bug #4924: ceph-deploy: gatherkeys fails on raring (cuttlefish)
- Sage Weil wrote:
> Bernhard, thanks for those logs--I think I've identified the problem. Can you try with wip-4924 ... - 10:16 AM Bug #6141: OSDs crash on recovery
- Dropping the caches was not a problem. Freeing Dentries an Inodes took about 30 Minutes and I guess ceph was not able...
- 10:00 AM Bug #6141: OSDs crash on recovery
- What was happening on your cluster at the time you dropped the caches? There are internal and external limits well be...
- 09:39 AM Bug #6141 (Can't reproduce): OSDs crash on recovery
- After (mistakenly) executing "echo 2 > /proc/sys/vm/drop_caches" instead of "echo 1 > /proc/sys/vm/drop_caches" to cl...
- 09:45 AM Documentation #6142 (Resolved): Ceph needs mor than 32k pids
- I kinda painfully discovered that one of my Hosts with 45 OSDs on it spawned 1.4 Million threads when starting it int...
- 09:19 AM Feature #6029 (Resolved): cachepool: osd: separate object version from pg version
- I merged this in this morning, commit:be9a39b766ba825ef348ca6e2de1f4db7c091dff
A suite run saw a lot of the btrfs ... - 08:31 AM devops Bug #6138 (In Progress): 'ceph-deploy disk list' fails on CentOS 6.4
- 07:48 AM devops Bug #5193: RHEL6 does not ship with xfsprogs
- Xfsprogs only in Scalable File System add on to RHEL 6.4 but xfs will be default fs in RHEL 7.
- 05:39 AM rbd Bug #6139 (Closed): kernel panic in vms during disk benchmarking
- Hi
I am having regular issues with virtual machines running heavy disk io benchmarks.
My ceph setup:
Ceph v... - 04:41 AM Revision 951177b8 (ceph): internal: whitelist btrfs lock imbalance bug 6097
- Signed-off-by: Sage Weil <sage@inktank.com>
- 01:48 AM Revision c30310af (ceph): ceph.conf.template: add osd_debug_pg_log_writeout = true
- Signed-off-by: Samuel Just <sam.just@inktank.com>
- 01:45 AM Revision 1c0d75db (ceph): PGLog: don't maintain log_keys_debug if the config is disabled
- Fixes: #6040
Backport: Dumpling
Signed-off-by: Samuel Just <sam.just@inktank.com> - 01:44 AM Revision fe68b15a (ceph): PGLog: move the log size check after the early return
- There really are stl implementations (like the one on my ubuntu 12.04
machine) which have a list::size() which is lin... - 12:26 AM Revision 9101433a (ceph): Merge remote-tracking branch 'origin/master' into wip-6029
- Conflicts:
src/librados/AioCompletionImpl.h - 12:24 AM Revision 6c432f19 (ceph): doc: update to describe new OSD version support as it actually exists
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:24 AM Revision 57e346b1 (ceph): ReplicatedPG: Fill in the MOSDOpReply's user_version
- As part of this, rename OpContext::reply_version->reply_user_version.
The semantics that necessitate the reply_versio... - 12:24 AM Revision 2e764a81 (ceph): osd: switch object_info_t::user_version to be a version_t
- We never expose the full eversion_t data to users, and do not want to.
However, we pull some tricks in the encode/dec... - 12:24 AM Revision 69280e2a (ceph): ReplicatedPG: remove OpContext::reply_user_version
- ctx->new_obs.oi.user_version is initialized to ctx->obs.oi.user_version,
and for read ops it won't be changed. That m... - 12:24 AM Revision cc1c4a75 (ceph): osd: add last_user_version to pg_info_t
- We add a corresponding user_version to pg_log_entry_t, and the logic
to assign from one to the other and to recover l... - 12:24 AM Revision dc9d3fc3 (ceph): osd: actually fill in user_version in pg_log_entry_t
- We now require it when creating a pg_log_entry_t. The user_version
is the version which info.last_user_version should... - 12:24 AM Revision de209974 (ceph): MOSDOpReply: add enough fields to be backwards compatible.
- The system we've been building up works out very nicely for new clients,
but they could not have interoperated with o... - 12:24 AM Revision 2c05b4fe (ceph): MOSDOpReply: switch to comprehensive instead of individual version setters
- There's little point to updating versions individually when we can
do so en masse and avoid mistakes in duplication.
... - 12:24 AM Revision 7db71fc2 (ceph): MOSDOpReply: stop filling in replay_version from the MOSDOp to begin with
- It's just asking for trouble.
Signed-off-by: Greg Farnum <greg@inktank.com> - 12:24 AM Revision c119afa0 (ceph): ReplicatedPG: add OpContext::user_at_version
- Set this up with the existing at_version member, but only increase
it for user_modify ops. Use this when logging the ... - 12:24 AM Revision 17e32f95 (ceph): MOSDOpReply: add user_version field
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:24 AM Revision 931bf7e8 (ceph): Objecter: rename Op::version to Op::replay_version
- This is used for replay, so let's be more precise!
Signed-off-by: Greg Farnum <greg@inktank.com> - 12:24 AM Revision ff1a5730 (ceph): Objecter: librados: mass switch from eversion_t to version_t
- There are a lot of pointers throughout our request infrastructure used solely
for exporting the version to users. The... - 12:24 AM Revision e42ef0c0 (ceph): Objecter: expose MOSDOp's new user_version instead of the replay_version
- We don't want users to ever see the replay_version, which is about
to become private RADOS data.
Signed-off-by: Greg... - 12:24 AM Revision 9b998a96 (ceph): ReplicatedPG: set the replay version based on the at_version
- The replay version is not for users to consume, so we don't want
to use the user_version for it.
Signed-off-by: Greg... - 12:00 AM Revision 37bba41b (ceph): ReplicatedPG: remove long-dead branch
- This was confusing the heck out of me when trying to figure out
why I was hitting an assert. So replace the if-else b... - 12:00 AM Revision 1f608bd9 (ceph): ReplicatedPG: do not do a redundant set of ctx->new_obs.oi.version
- We set this in the if below for writes, and for reads it doesn't need to
be updated (and isn't). Remove the confusing... - 12:00 AM Revision 295a84b9 (ceph): doc: include plan for new user_version support
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 12:00 AM Revision f4008164 (ceph): MOSDOpReply: rename *_version() -> *_replay_version()
- We have been returning the object's "user version" and using that
for replay, but that is in fact incorrect. In prepa...
Also available in: Atom