Activity
From 11/23/2014 to 12/22/2014
12/22/2014
- 11:56 PM Revision e1384afd (ceph): Merge pull request #3200 from boydc2014/master
- fix unmatched op code
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:33 PM Bug #10407: rbd map fail
- thanks!I updated my kernel to version 3.18.1,and it work will.
- 06:30 AM Bug #10407 (Closed): rbd map fail
- you need a newer kernel if you are going to have erasure coded pools (or, more specifically, erasure crush rules) in ...
- 12:43 AM Bug #10407: rbd map fail
- rbd client kernel is:3.10.1 and my ceph cluster version is 0.80.7
- 12:10 AM Bug #10407 (Closed): rbd map fail
- steps?
(1) create image1 in pool rbd1
rbd create -p rbd1 image1 --size 600000000
(2? resize image1 to 600000
... - 09:57 PM Revision 3b98b830 (ceph): Merge pull request #3222 from ceph/wip-watch-notify-2
- librados: fix watch/notify event flushing
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Jason Dillaman <d... - 09:56 PM Revision 1fbe9b6f (ceph): librados: warn about rados_watch_flush() prior to ioctx shutdown
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:54 PM Revision b62187c5 (ceph): tests: histogram prevent re-use of local variables
- By moving the tests to separate functions.
http://tracker.ceph.com/issues/9235 Fixes: #9235
Signed-off-by: Loic Dac... - 09:54 PM Revision 5be6f2f6 (ceph): osd/OSD.cc: parse lsb release data via lsb_release
- Use lsb_release tool to be portable since parsing /etc/lsb-release
is not the same between different distributions. T... - 09:54 PM Revision 754363f4 (ceph): tests: prevent kill race condition
- When trying to kill a daemon, keep its pid in a variable instead of
retrieving it from the pidfile multiple times. It... - 09:54 PM Revision ed6ec293 (ceph): test/ceph-disk.sh: fix for SUSE
- On SUSE 'which' returns always the full path of (shell) commands and
not e.g. './ceph-conf' as on Debian. Add check a... - 09:54 PM Revision 77d39302 (ceph): test/ceph-disk.sh: resolve symlinks before check
- Make sure symlinks are resolved in command_fixture()
before compare result of which command and the current
path.
Si... - 09:54 PM Revision 820dbfd9 (ceph): test/ceph-disk.sh: mkdir -p
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit c2f58e6694a2457200ab3d59e037ad17b9c82028) - 09:54 PM Revision cf102df7 (ceph): tests: avoid tab interpretation problem on fedora 20
- Use . instead of tab in echo to avoid variations in how escape sequences
are interpreted by the shell.
http://tracke... - 09:54 PM Revision e2741c8f (ceph): tests: histogram prevent re-use of local variables
- By moving the test to a separate function.
http://tracker.ceph.com/issues/9235 Fixes: #9235
Signed-off-by: Loic Dac... - 07:41 PM Revision a3c29f44 (ceph): Merge pull request #3114 from xiaoxichen/drop_incorrect_pool
- Cleanup: Drop hobject_incorrect_pool
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat... - 07:40 PM Revision ece079de (ceph): Merge pull request #3138 from ceph/wip-10029
- SimpleMessenger: Retry binding on addresses if binding fails
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: G... - 07:39 PM Revision f76e0e45 (ceph): Merge pull request #3229 from ceph/wip-osd-ctor
- osd/ReplicatedPG: initialize new_backfill in ctor
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:23 PM Revision 2fbad1e4 (ceph): Merge pull request #3239 from ceph/wip-stop.sh-me
- stop.sh: killall -u takes username, not uid
Reviewed-by: John Spray <john.spray@redhat.com> - 07:18 PM Revision 4ce6d252 (ceph): stop.sh: killall -u takes username, not uid
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 06:25 PM CephFS Bug #10415 (Fix Under Review): libcephfs: test failures
- it was hang on umount...
- 09:38 AM CephFS Bug #10415 (Resolved): libcephfs: test failures
- hang on GetOsdCrushLocation test, with no core dumps:
http://pulpito.ceph.com/teuthology-2014-12-17_23:04:01-fs-mast... - 06:16 PM Revision bc4e269b (ceph): Merge pull request #3183 from ceph/wip-10262
- osd: fix handling of create+delete transaction
Reviewed-by: Samuel Just <sjust@redhat.com> - 06:00 PM Revision 547ee783 (ceph): Merge pull request #3238 from ceph/wip-10414
- client: fix uninitialized member
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:57 PM Revision dab53918 (ceph): client: fix uninitialized member
- Fixes: #10414
Signed-off-by: John Spray <john.spray@redhat.com> - 05:34 PM CephFS Bug #10417 (In Progress): snaptest-2.sh is failing
- 09:54 AM CephFS Bug #10417 (Resolved): snaptest-2.sh is failing
- All we've got is the teuthology log, whose last line is when it's deleting the directory tree (but not the snapshots)...
- 04:21 PM Revision 59305ddc (ceph): Merge pull request #3237 from dachary/wip-10408-something-is-better-tha...
- osd: be_compare_scrubmaps uses incorrect j iterator
Reviewed-by: Sage Weil <sage@redhat.com> - 04:21 PM Revision 10e6e222 (ceph): Merge pull request #3236 from ceph/wip-10409
- osd: fix 10409 (object checksums for ec backends)
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:05 PM Revision 3f3f2fa1 (ceph): osd: be_compare_scrubmaps uses incorrect j iterator
- The code moved from be_select_auth_object to be_compare_scrubmaps
74bd8708dfbfd3c8e7ba3f41d8534609dcbc1237 but the j ... - 03:32 PM Revision d87918a6 (ceph): osd: scrub: only assume shard digest == oi digest for replicated pools
- For an EC object, the digest we get from scrub is for the *shard*, and that
is not the same as the *object* digest in... - 03:27 PM Revision a25429c9 (ceph): osd: clean up use of hex for digests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:24 PM Bug #10424: unittest_librados fails
- Assigned by mistake, scrolling got me ;-)
- 03:23 PM Bug #10424 (Resolved): unittest_librados fails
- It currently fails on master...
- 03:13 PM Revision 7d0bfa70 (ceph): Merge pull request #227 from ceph/wip-9881
- #9881 MDS flush journal test
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:12 PM Revision 9c96fbb6 (ceph): osd/ECBackend: use correct seed for (empty) omap digest
- This will be 0 on mixed OSD version PGs, -1 on current PGs.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:58 PM Revision 2bfcf74d (ceph): Merge branch 'wip-10409-removed-object' of git://github.com/dachary/ceph
- 02:51 PM Revision 20a4c57c (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
PendingReleaseNotes - 02:46 PM Revision 4047f2dd (ceph): Merge pull request #3230 from ceph/wip-pg-stat
- mon/PGMap: restructure 'pg stat' formatted output
Reviewed-by: John Spray <jspray@redhat.com> - 02:41 PM Revision 7f9c03d1 (ceph): mon/PGMap: restructure 'pg stat' formatted output
- The + character, which appears in state names, is not a valid XML token.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:39 PM Revision 97c81569 (ceph): Merge pull request #3235 from dachary/wip-10410-port-7110
- tests: use port 7111 for osd-copy-from.sh
Reviewed-by: Sage Weil <sage@redhat.com> - 02:38 PM Revision 864509ff (ceph): Merge pull request #3234 from majianpeng/bug-fix
- objectstore: add fadvise_flags operations in ObjectStore::Transaction::append func.
Reviewed-by: Sage Weil <sage@red... - 02:36 PM Bug #10422: osdmap full crc mismatch due to divergent cache_target_{dirty,full}_ratio_micro
- in a long-past epoch these values diverge. strangely the incremental for that epoch changes the pool info for a *dif...
- 02:00 PM Bug #10422 (Resolved): osdmap full crc mismatch due to divergent cache_target_{dirty,full}_ratio_...
- All test failed in run http://pulpito.front.sepia.ceph.com/teuthology-2014-12-22_09:28:15-upgrade:dumpling-firefly-x:...
- 02:25 PM CephFS Bug #10423 (Closed): update hadoop gitbuilders
- They're building "branch-1", whatever that is, and so I suspect they aren't pointing at cephfs-hadoop. :(
- 01:56 PM Bug #10366 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout failure
- 01:56 PM Bug #10364 (Resolved): watch-notify-same-primary.yaml failure
- 01:33 PM Revision e89bafb5 (ceph): remove unmatched op code comparasion
- Signed-off-by: Dong Lei <leidong@yahoo-inc.com>
- 01:20 PM Revision 4bb6e290 (ceph): tests: use port 7111 for osd-copy-from.sh
- Because port 7110 is already used by mkfs.sh
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 12:56 PM Revision 6f8aad05 (ceph): tests: recovery of a lost object in erasure coded pools
- http://tracker.ceph.com/issues/10409 Refs: #10409
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 12:50 PM Revision f4da356e (ceph): objectstore: add fadvise_flags operations in
- ObjectStore::Transaction::append func.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 12:42 PM Revision 992e7eac (ceph): tests: remove spurious lines from osd-scrub-repair.sh
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 11:38 AM Messengers Feature #10029 (Resolved): Retry binding on IPv6 address if not available
- 11:38 AM Bug #10372: FAILED assert(check_latest_map_ops.find(op->tid) (firefly,giant)
- ...
- 11:36 AM Bug #10421 (Resolved): osd: leaked pg refs on shutdown, canceled flush ops
- ubuntu@teuthology:/a/sage-2014-12-18_20:33:36-rados-master-distro-basic-multi/668519$ zgrep 88\\.1 remote/*/log/*osd....
- 11:28 AM Bug #10420 (Rejected): ceph_test_objectstore ObjectStore/StoreTest.Synthetic/1 fails on clone
- This is failing reliably for master and giant branches:
./ceph_test_objectstore --debug-filestore 30 --filestore... - 10:40 AM Bug #10419 (Rejected): suites/rados/basic/tasks/repair_test.yaml fails
- It actually is correctly handled, I misread the output of the test.
- 10:39 AM Bug #10419 (Rejected): suites/rados/basic/tasks/repair_test.yaml fails
- It was seen on https://github.com/ceph/ceph-qa-suite/pull/250 using the https://github.com/ceph/ceph/pull/3034 branch...
- 10:36 AM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Glad to read you have found it with Craig's logs :)
Just now (accidentally) looked into my work email on vacation.... - 10:16 AM Bug #10262 (Resolved): osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- 10:25 AM devops Bug #10330: apt-mirror timeouts
- Same issue in run http://pulpito.ceph.com/teuthology-2014-12-21_19:13:02-upgrade:dumpling-x-firefly-distro-basic-vps/...
- 09:58 AM CephFS Bug #10414 (Resolved): client: valgrind found uninit value used in conditional
- merged fix to master in 547ee783d44b8598bdf30aad191252aaecca0754
- 09:36 AM CephFS Bug #10414: client: valgrind found uninit value used in conditional
- http://pulpito.ceph.com/teuthology-2014-12-17_23:04:01-fs-master-testing-basic-multi/667065/
- 09:34 AM CephFS Bug #10414 (Resolved): client: valgrind found uninit value used in conditional
- http://pulpito.ceph.com/teuthology-2014-12-17_23:04:01-fs-master-testing-basic-multi/667063/...
- 09:55 AM Linux kernel client Bug #10418 (Resolved): ceph: can't block inside wait loops
- [ 40.067471] ------------[ cut here ]------------
[ 40.079642] WARNING: CPU: 3 PID: 1402 at kernel/sched/core.c:... - 09:49 AM CephFS Bug #10416 (Resolved): quota test failures
- The quota tests failed. Maybe this is fixed already?
http://pulpito.ceph.com/teuthology-2014-12-19_23:04:06-fs-mas... - 09:43 AM Revision 083f8963 (ceph): suites/fs: hook in mds_flush
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:36 AM Bug #10402: ceph-objectstore-tool import may need to add an OSDMap for old epoch
- Moved to bug #10422
- 09:01 AM Bug #10402: ceph-objectstore-tool import may need to add an OSDMap for old epoch
- Moved to bug #10422
- 09:20 AM Fix #9566 (Need More Info): osd: prioritize recovery of OSDs with most work to do
- Waiting on https://github.com/ceph/ceph/tree/wip-read-hole which will help communicate information between OSDs and a...
- 09:20 AM CephFS Bug #9994: ceph-qa-suite: nfs mount timeouts
- teuthology-2014-12-17_23:10:01-knfs-master-testing-basic-multi/667121/
http://pulpito.ceph.com/teuthology-2014-12-17... - 09:16 AM CephFS Bug #10413 (Resolved): samba: coredumps after tests run
- These tests had coredumps without corresponding failures in teuthology.log or backtraces in any of the logs. The clie...
- 09:08 AM CephFS Bug #10412 (Resolved): samba: failed smbtorture run
- http://pulpito.ceph.com/teuthology-2014-12-17_23:14:01-samba-master-testing-basic-multi/667136/
I'm not even sure ... - 09:07 AM Bug #7968: ImportError occurred when run command 'ceph -v'
- Probably not the right way to fix it, but this worked for me.
cp -vrap ceph.git/src/pybind/* /usr/lib/pymodules/py... - 09:06 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Same issue in run http://pulpito.ceph.com/teuthology-2014-12-21_17:13:02-upgrade:firefly-x-next-distro-basic-multi/
... - 09:04 AM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same issue in run http://pulpito.ceph.com/teuthology-2014-12-21_17:13:02-upgrade:firefly-x-next-distro-basic-multi/
... - 08:50 AM rgw Bug #10354: Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-multi run
- Still failed in run http://pulpito.ceph.com/teuthology-2014-12-21_17:10:01-upgrade:dumpling-firefly-x:parallel-next-d...
- 08:27 AM devops Bug #10374: Failed 'sudo rpm -i ceph-release-1-0.el7.noarch.rpm' in octo
- Same type of issue in run http://pulpito.ceph.redhat.com/teuthology-2014-12-20_17:22:59-upgrade:dumpling-dumpling-dis...
- 08:27 AM Bug #10409 (Resolved): erasure code repair regression
- 07:49 AM Bug #10409: erasure code repair regression
- https://github.com/ceph/ceph/pull/3236
- 04:58 AM Bug #10409: erasure code repair regression
- https://github.com/ceph/ceph/pull/3233 reproduces the problem (works on http://workbench.dachary.org/ceph/ceph/commit...
- 04:52 AM Bug #10409 (Resolved): erasure code repair regression
- Somewhere after http://workbench.dachary.org/ceph/ceph/commit/3f7b2cf52f5aeb3a26e5bf5b4b61a233c5e7f8b6 scrub no longe...
- 08:21 AM Bug #10408 (Resolved): PGBackend::be_compare_scrubmaps may have no authoritative object
- 08:09 AM Bug #10408 (Fix Under Review): PGBackend::be_compare_scrubmaps may have no authoritative object
- https://github.com/ceph/ceph/pull/3237
- 02:57 AM Bug #10408 (Resolved): PGBackend::be_compare_scrubmaps may have no authoritative object
- In http://workbench.dachary.org/ceph/ceph/commit/74bd8708dfbfd3c8e7ba3f41d8534609dcbc1237 the j iterator is always end()
- 07:53 AM Bug #10410 (Resolved): duplicate use of port 7110 in tests
- https://github.com/ceph/ceph/pull/3235
- 05:16 AM Bug #10410 (Resolved): duplicate use of port 7110 in tests
- The "osd-copy-from.sh":http://workbench.dachary.org/ceph/ceph/blob/3e6195bf0a23921ea2f8590a02ba0d8107d10fff/src/test/...
- 07:52 AM Bug #10411 (Can't reproduce): PG stuck incomplete after failed node
- Yesterday, I was in the process of expanding the number of PGs in one of our pools. While I was doing this, one of t...
- 12:45 AM Fix #10401 (Resolved): docker images should use install-deps.sh
12/21/2014
- 11:51 PM Revision 3e6195bf (ceph): Merge pull request #3228 from dachary/wip-10401-docker-install-deps
- tests: oneliner to run make check in a container
Reviewed-by: Sage Weil <sage@redhat.com> - 11:35 PM Revision abd35230 (ceph): Merge pull request #3231 from ceph/wip-mon-health
- mon: make 'ceph -s' show pg state counts in reverse descending order
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:22 PM Revision bb921a80 (ceph): packages: add python-virtualenv and xmlstarlet
- python-virtualenv is required to run make check and xmlstarlet is useful
to develop shell base tests using ceph --for... - 10:19 PM Bug #10405: osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill_targets(peer))
- try to restart osd during mark_unfound_lost is running, the following message is displayed but still have unfound obj...
- 10:05 PM Bug #10405 (Can't reproduce): osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill...
- version: firefly 0.80.5
When unfound object is reported with osd.118 crashes due to other error, after restart osd... - 05:12 PM Revision 6ce1469c (ceph): tests: reduce centos docker intermediate steps
- Collapse multiple RUN statements related to systemd into a single line
to reduce the number of steps that are preserv... - 04:53 PM CephFS Bug #10381: health HEALTH_WARN mds ceph239 is laggy
- Greg Farnum wrote:
> Can you provide the output of "ceph mds dump" and "ceph osd dump"?
>
> It looks like the MDS... - 04:53 PM Revision 94abadbd (ceph): tests: replace --enable-docker with --enable-root-make-check
- The --enable-docker logic was that each test that needs privileges to
run uses a container to do so. The problem with... - 04:53 PM Revision 46c83d95 (ceph): tests: run-make-check.sh arguments are passed to configure
- All run-make-check.sh arguments are transparently given to the configure
command. For instance:
run-make-check.s... - 04:53 PM Revision 2d0d3881 (ceph): tests: helpers to run make check in containers
- Add scripts that run make check in a container for a given operating
system version. They are a little more than onel... - 04:53 PM Revision 4a1c3b26 (ceph): tests: add xmlstarlet in containers
- It can be removed once https://github.com/ceph/ceph/pull/3228 is merged
and xmlstarlet is found in ceph.spec.in and d... - 04:53 PM Revision f0805957 (ceph): tests: avoid bash == --shell confusion in docker-test-helper.sh
- Do not force interactive mode when the bash script is specified by the
user because it should be usable to run a smal... - 04:53 PM Revision b15bd60c (ceph): tests: add docker-test.sh --ref giant|firefly etc.
- Add the --ref option to chose the git ref to which the working tree must
be reset instead of HEAD.
test/docker-te... - 04:52 PM Revision 2de2c4b0 (ceph): install-deps.sh: do not require sudo when root
- If the user is root, do not use sudo. The sudo package is not installed
by default on centos by default and when buil... - 04:52 PM Revision 80f20f8e (ceph): tests: run-make-check.sh install jq
- jq is useful to parse json from the command line. It is however not
packaged for all supported distributions (precise... - 04:52 PM Revision d8f84d15 (ceph): tests: docker images must use install-deps.sh
- The dockerfiles must run install-deps.sh instead of duplicating the
package list that is found in ceph.spec.in and de... - 04:52 PM Revision 19b6de3e (ceph): tests: ceph.spec.in or debian/control rebuild docker images
- If any of the files in test/$os_type is newer than the creation date of
a docker image, the image is removed and rebu... - 04:52 PM Revision 62181386 (ceph): tests: enable password-less sudo in containers
- If compilation is run with ./configuire --enable-root-make-check, sudo
is expected to work without human interaction.... - 04:52 PM Revision 812570e8 (ceph): tests: deprecate docker-test.sh --compile option
- It is redundant with the run-make-check.sh script and imposes additional
limitations.
Signed-off-by: Loic Dachary <l... - 04:52 PM Revision 7b68f70a (ceph): tests: docker-test.sh commands are relative to git root
- Instead of being in the src directory. Forcing the working directory to
src is convenient to run unittests individual... - 04:06 PM Revision ee006bb1 (ceph): Merge pull request #3134 from ceph/wip-9059-checksums
- osd: record and validate whole-object checksums during deep scrub
Reviewed-by: Samuel Just <sjust@redhat.com> - 03:43 PM Revision e99da688 (ceph): mon: make 'ceph -s' show pg state counts in reverse descending order
- Because these are in an unordered_map we print this is random order.
Instead sort descending by count.
Signed-off-by... - 03:27 PM Revision 9c8827a5 (ceph): osd/ReplicatedPG: initialize new_backfill in ctor
- *** CID 1260213: Uninitialized scalar field (UNINIT_CTOR)
/osd/ReplicatedPG.cc: 1242 in ReplicatedPG::ReplicatedPG(... - 02:34 PM devops Feature #10046: run make check on every pull request
- After thinking about it for a few days, it becomes clear that I do not have the necessary knowledge and motivation to...
- 08:05 AM Feature #9059 (Resolved): osd: store opportunistic whole-object checksum
- 07:32 AM Bug #10403 (Can't reproduce): ceph_test_rados_api_tier: bad decode of HitSet
- ...
12/20/2014
- 08:12 PM Revision 4ebd4b42 (ceph): librados: add rados_watch_flush() call
- Add a call so that callers can make sure all queued callbacks have
completed before shutting down the ioctx. This av... - 08:12 PM Revision 30678f6d (ceph): librados: watch_flush() on shutdown
- Users can easily forget this. It makes shutdown potentially block, but if
they have racing callbacks they get what th... - 03:30 PM Revision 1646d170 (ceph): osd: change omap data encoding in object_copy_data_t
- Pass the omap data in the struct as an opaque (encoded) bufferlist. This
avoids a decode into an STL map, simplifyin... - 03:30 PM Revision 218de829 (ceph): osd: scrub: wait for digest updates to apply before next scrub chunk
- Wait for any digest updates to apply before we scrub the next chunk. This
bounds the number of repops we initiate by... - 03:30 PM Revision 6d80078a (ceph): rados: use copy_from for rados cp (and cppool) command
- A hammer CLI won't be able to run against a pre-firefly OSD, but I don't
think we care.
Signed-off-by: Sage Weil <sa... - 03:30 PM Revision 925f5727 (ceph): test/osd/osd-copy-from: simple test of copy-from and error injection
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:30 PM Revision 75b2bc28 (ceph): osd: EIO if a full-object read produces a bad digest
- Add a tunable to control this. Returning an EIO instead of garbled data
may not be the best approach in all environm... - 03:30 PM Revision f8c1d401 (ceph): osd: pass and verify data+omap digest on copyfrom
- Two things here:
1- Pass the original digest from the source across the wire, if it is
present.
2- Calculate a... - 03:30 PM Revision 5d2d839d (ceph): osd: add copyfrom error injection
- Unfortunately it's nontrivial to inject this from the usual
ceph_test_rados_api_* tests which need to run despite thr... - 03:30 PM Revision 28d4dd89 (ceph): osd: scrub: record whole-object digest on scrub
- If we do not have a whole-object digest, record one after a deep scrub.
Note that we make no particular attempt to a... - 03:30 PM Revision 55bf020b (ceph): osd: scrub: set a min age before we update whole-object digest
- If an object is being actively updated, the whole-object digest will
quickly be invalidated. On deep scrub, only rec... - 03:30 PM Revision 85f677a4 (ceph): osd: scrub: be explicit about whether bad digest is known bad
- The digest may just disagree with our best guess 'auth' shard, or it may
also disagree with the recorded oi digest. ... - 03:30 PM Revision 6feb4a17 (ceph): osd: scrub: complain about bad digest in final pass auth check
- This will only trigger if we choose an auth that is known bad, but that
currently can happen, so compalin here too.
... - 03:30 PM Revision cf3b0476 (ceph): osd: scrub: share auth oi with caller and be_compare_scrub_objects
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:30 PM Revision 14f3c26a (ceph): osd: scrub: disqualify shards with digests that disagree with oi digest
- The auth may or may not know that the digest is truly bad. Note that we
can only relate scrub digests to those in oi... - 03:30 PM Revision 9c3afccb (ceph): osd: remove more (most? all?) of classic scrub
- Hopefully this is everything
Signed-off-by: Sage Weil <sage@redhat.com> - 03:30 PM Revision 74bd8708 (ceph): osd: move scrub no good auth check out of helper
- This helps call out that this is an exceptional case and simplifies the
helper a bit.
Signed-off-by: Sage Weil <sage... - 03:28 PM Revision 7d73f41f (ceph): osd: use -1 for deep scrub digest seed on new OSDs
- 0 is a weak initial value for a CRC since it doesn't change with a sequence
of 0 bytes (which are relatively common).... - 03:17 PM Revision 591e7e16 (ceph): osd: clean up scrub method debug output
- Use __func__ instead of (usually inaccurate) names.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:17 PM Revision e68d7716 (ceph): osd: drop vestigal invalid_snapcolls fields from scrub
- This isn't used. Snapcolls are ancient.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:16 PM Revision 056de092 (ceph): osd/ReplicatedPG: set and invalidate data/omap digests on osd ops
- When we create an empty object, we have a known digest of -1. In a few
cases, we also know the digest from the op (e... - 03:16 PM Revision 8a758003 (ceph): osd/ReplicatedPG: kill some dead scrub code
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:16 PM Revision 3f7b2cf5 (ceph): osd/osd_types: add {data,omap}_digest to object_info_t
- Also add flags to indicate whether the fields are valid.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:14 PM Revision ecd9de4d (ceph): rados/thrash: add readproxy facet
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:48 PM Linux kernel client Bug #8122: bogus mount error "mount: error writing /etc/mtab: Invalid argumentnothing was mounted"
- Also 0.87 and kernel 3.10
- 09:52 AM Bug #10402 (Rejected): ceph-objectstore-tool import may need to add an OSDMap for old epoch
Failure waiting for osd.5 restart which had the last import:
2014-12-19 23:24:14,498.498 INFO:teuthology.orchest...- 09:26 AM Fix #10401 (Fix Under Review): docker images should use install-deps.sh
- https://github.com/ceph/ceph/pull/3228
- 07:11 AM Fix #10401 (Resolved): docker images should use install-deps.sh
- http://workbench.dachary.org/ceph/ceph/blob/master/src/test/docker-test-helper.sh should build images based on http:/...
- 08:40 AM Revision 154497c6 (ceph): Merge pull request #3227 from nilamdyuti/wip-doc-ceph-deploy
- Fixes a typo in ceph-deploy man page
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:20 AM Revision 9d5d491f (ceph): doc: Adds updated ceph-deploy man page under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 08:17 AM Revision 8c38cc6b (ceph): doc: Fixes a typo in ceph-deploy man page.
- Lack of a single space was restricting the proper rendering of an option in
html. Fixes the error.
Signed-off-by: Ni... - 02:57 AM Revision 46a1a4cb (ceph): If trusty, use older version of qemu
- Fixes #10319
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 01:17 AM Bug #9285: osd: promoted object can get evicted before promotion completes
- We updated our ceph version to giant as described in #10399 and we no longer have slow requests when cache tiering is...
- 12:36 AM Revision 0e6ec8ba (ceph): Merge pull request #3225 from dachary/wip-10400-quota-info-t
- mds: add default ctor for quota_info_t
- 12:08 AM Revision 7f1e5101 (ceph): mds: add default ctor for quota_info_t
- http://tracker.ceph.com/issues/10400 Fixes: #10400
Signed-off-by: Loic Dachary <ldachary@redhat.com>
12/19/2014
- 10:45 PM Revision 243b9e43 (ceph): Merge pull request #3121 from ceph/wip-10277
- Reviewed-by: Greg Farnum <gfarnum@redhat.com>
- 10:21 PM Revision 18d6b200 (ceph): doc/release-notes: v0.90
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:55 PM Revision 60674621 (ceph): Merge remote-tracking branch 'gh/next'
- 07:41 PM Revision 9b78dafd (ceph): osdc/Objecter: do notify completion callback in fast-dispatch context
- The notify completion has exactly one user, the librados caller which
does nothing but take a local (inner) lock and ... - 05:03 PM Revision 61126a2d (ceph): Merge pull request #3199 from ceph/wip-qa-empty-xattr
- qa: test zero size xattr
Reviewed-by: John Spray <john.spray@redhat.com> - 04:36 PM Bug #10400 (Resolved): quota_info_t test 1 dump_json check failed
- 04:19 PM Bug #10400 (Fix Under Review): quota_info_t test 1 dump_json check failed
- https://github.com/ceph/ceph/pull/3225
- 03:53 PM Bug #10400 (Resolved): quota_info_t test 1 dump_json check failed
- src/test/encoding/check-generated.sh...
- 04:05 PM Bug #9008: Objecter: pg listing can deadlock when throttling is in use
- Hi folks, we're running into this on Giant. Is there any estimate as to when this'll be fixed in a maintenance releas...
- 03:45 PM Revision 0a25bee5 (ceph): Merge remote-tracking branch 'gh/wip-fs-quota'
- Conflicts:
src/client/Client.cc - 03:42 PM Revision 676ce2a5 (ceph): Merge pull request #3218 from dachary/wip-10383-disable-unittest-msgr
- tests: temporarily disable unittest_msgr
- 03:21 PM Revision ecbdbb16 (ceph): tests: temporarily disable unittest_msgr
- http://tracker.ceph.com/issues/10383 Refs: #10383
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 03:19 PM Revision 84ae9fd1 (ceph): Merge pull request #2976 from ceph/wip-pgmeta
- osd: move PG metadata to a per-PG object
Passed rados and upgrade tests.
Reviewed-by: Samuel Just <sjust@redhat.com> - 03:10 PM Revision abdbbd6e (ceph): Remove sepia dependency (use fqdn)
- Fixes: #10255
Signed-off-by: Warren Usui <warren.usui@inktank.com>
(cherry picked from commit 19dafe164833705225e168a... - 03:09 PM Revision 531ed8a3 (ceph): Merge pull request #3212 from ceph/wip-10255-wusui
- Remove sepia dependency (use fqdn)
Backport: giant
Reviewed-by: Sage Weil <sage@redhat.com> - 03:02 PM Revision c2951131 (ceph): Merge pull request #3214 from xinxinsh/wip-cleanup
- cleanup : remove sync_epoch
Reviewed-by: Sage Weil <sage@redhat.com> - 02:56 PM Revision 08bd1e1e (ceph): 0.90
- 02:51 PM Revision 49c23221 (ceph): doc: Instead of using admin socket, use 'ceph daemon' command.
- 02:44 PM CephFS Bug #10277 (Pending Backport): ceph-fuse: Consistent pjd failure in getcwd
- Let it cook for a bit in master before doing the giant backport.
- 02:36 PM Revision 11fa1dfb (ceph): Merge pull request #3193 from nilamdyuti/wip-doc-ceph-disk
- Changes format style in ceph-disk to improve readability as html
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:07 PM Revision 71df6451 (ceph): Merge pull request #3210 from ceph/wip-osdmap
- osd: only verify OSDMap crc if it is known
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:57 PM Revision 8c2c48d8 (ceph): Merge pull request #3216 from cstavr/master
- ceph-disk: Fix wrong string formatting
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:40 PM Revision 7696afd3 (ceph): tasks: create mds_flush task
- This tests:
* The new 'flush journal' asok command
* That the resulting on disk structures are as expected
* That ... - 12:51 PM Bug #10399: kvm die with assert(m_seed < old_pg_num)
- If this helps: the cluster was in health_ok state when the command was launched (ceph-report.gz is now during the rec...
- 12:20 PM Bug #10399: kvm die with assert(m_seed < old_pg_num)
- I have attached the ceph-report file.
The crashed kvm processes have a block device on the pool 'r2', the one whe... - 12:04 PM Bug #10399: kvm die with assert(m_seed < old_pg_num)
- Could you please send the output of *ceph report* ? It would also be great to have (if possible) a set of steps to fo...
- 09:51 AM Bug #10399 (Resolved): kvm die with assert(m_seed < old_pg_num)
- Hi, when I increase the pg_num on a pool, all the kvm processes that use the pool die with the following backtrace:
... - 11:46 AM Revision a302c44e (ceph): ceph-disk: Fix wrong string formatting
- Signed-off-by: Christos Stavrakakis <stavr.chris@gmail.com>
- 11:37 AM CephFS Bug #10381: health HEALTH_WARN mds ceph239 is laggy
- Can you provide the output of "ceph mds dump" and "ceph osd dump"?
It looks like the MDS is trying to access a poo... - 11:31 AM rgw Bug #10015 (Resolved): rgw sync agent: 403 when syncing object that has tilde in its name
- Changes included in https://github.com/ceph/radosgw-agent/pull/14
merged commit fbcc438 into master - 09:46 AM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- And the same on next - http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-18_17:13:01-upgrade:firefly-x-next-dist...
- 09:14 AM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same issue http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-18_18:18:01-upgrade:firefly-x-giant-distro-basic-vp...
- 09:42 AM Bug #10398 (Can't reproduce): coredump in remote/vpm089/ in upgrade:dumpling-x-firefly-distro-bas...
- Could not get more info from the crash, so might FYI ticket only.
Note: large number of ceph-client.admin.*.log.gz f... - 09:31 AM CephFS Bug #10382: mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- I tried to reproduce this today with debug_mds set to 10 and 20, but I wasn't able to reproduce it at that moment.
... - 07:00 AM CephFS Bug #10382 (In Progress): mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- 09:17 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Same issue two jobs failed 667642, 667643
Run http://pulpito.ceph.com/teuthology-2014-12-18_18:18:01-upgrade:firef... - 09:05 AM Bug #10397 (Can't reproduce): "Caught signal (Bus error)" in upgrade:dumpling-firefly-x:parallel-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-18_18:15:02-upgrade:dumpling-firefly-x:parallel-gi...
- 08:50 AM Feature #10396 (Resolved): Add ms_inject_* support for AsyncMessenger
- 08:49 AM Bug #10383 (Fix Under Review): unittest_msgr : illegal instruction
- https://github.com/ceph/ceph/pull/3219
- 02:32 AM Bug #10383: unittest_msgr : illegal instruction
- Can also be reproduced anywhere with valgrind...
- 02:04 AM Bug #10383: unittest_msgr : illegal instruction
- ...
- 01:43 AM Bug #10383 (Resolved): unittest_msgr : illegal instruction
- in http://gitbuilder.sepia.ceph.com/gitbuilder-ceph-tarball-trusty-i386-basic/log.cgi?log=5439d9ee708f191a8e1aa758b8e...
- 08:31 AM devops Bug #10330: apt-mirror timeouts
- Same here http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-18_17:00:03-upgrade:firefly-firefly-distro-basic-vps...
- 07:28 AM CephFS Feature #10393 (Rejected): client: remove mount prefix shenanigans for quota
- Once we have a better subvolume abstraction in place, replace the ancestor opens that are needed by snaps with someth...
- 07:26 AM CephFS Feature #10392 (Rejected): mds: refactor subvolume vs snaprealm, capture quota trees
- Unify the subvolume abstraction that is used by snapshots and quotas. This will make the ownership of files by a quo...
- 06:59 AM Bug #10389 (Fix Under Review): init-ceph stop may return before daemons are stopped
- https://github.com/ceph/ceph/pull/3215
- 06:48 AM Bug #10389 (Resolved): init-ceph stop may return before daemons are stopped
- The existence of the pidfile must be checked outside of the loop to send a signal to the daemon. Otherwise the daemon...
- 06:56 AM Bug #10385 (Duplicate): ceph_objectstore_tool.py may race
- 06:21 AM Bug #10385: ceph_objectstore_tool.py may race
- ...
- 03:16 AM Bug #10385 (Duplicate): ceph_objectstore_tool.py may race
- ...
- 06:55 AM Fix #10391 (New): osd: an all/mostly delete pg log stalls during peering
- We generate transactions that zap all new deletes from merge_log. If the pg log is mostly delete operations, these c...
- 06:53 AM CephFS Feature #10390 (Resolved): mds: throttle deletes in flight
- make sure the number of deletes due to purging strays are bounded in some way
- 05:57 AM Bug #9916: osd: crash in check_ops_in_flight
- PR for firely:
https://github.com/ceph/ceph/pull/3217 - 01:19 AM Bug #9916: osd: crash in check_ops_in_flight
- I think this has been fixed by in master:
https://github.com/ceph/ceph/commit/11082f7aa02f3f41c7c74c5930b67216dba88e... - 01:08 AM Bug #9916: osd: crash in check_ops_in_flight
- I think I find the problem.
Firstly, some clarification about the strange data change Wenjun Huang found.
1. ve... - 05:30 AM CephFS Feature #10388 (Resolved): Add MDS perf counters for stray/purge status
- It would be useful to know how many inodes are currently in the stray folders, waiting to be deleted, and also how ma...
- 05:25 AM CephFS Bug #10387 (Resolved): ceph-fuse doesn't release capability on deleted directory
I thought this was a repeat of #10164, but then noticed that the dirfrag objects were deleted once the client unmou...- 04:54 AM Feature #10386 (New): add ceph-report-parsing
- It would be useful to ship https://github.com/inktankstorage/ceph-report-parsing with ceph to use the output of ceph ...
- 03:28 AM Bug #10384 (Fix Under Review): ceph-test-helpers may race
- https://github.com/ceph/ceph/pull/3215
- 03:12 AM Bug #10384 (Resolved): ceph-test-helpers may race
- test_get_last_scrub_stamp may not be able to get the last scrub stamp if the PG are not created because the mon is ru...
- 02:08 AM Bug #10059: osd/ECBackend.cc: 876: FAILED assert(0)
- I applied commit:c87bde64 on top of 0.89 on degraded cluster but it caused many PGs to stuck in "inactive" state so I...
- 01:19 AM Revision 2f63e54f (ceph): cleanup : remove sync_epoch
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 01:16 AM Revision 19dafe16 (ceph): Remove sepia dependency (use fqdn)
- Fixes: #10255
Signed-off-by: Warren Usui <warren.usui@inktank.com> - 01:10 AM Bug #9738 (Fix Under Review): rados cli: objects not present in a snapshot are listed anyway
- 01:09 AM Bug #9738: rados cli: objects not present in a snapshot are listed anyway
- https://github.com/ceph/ceph/pull/3213
- 12:54 AM Revision af18cf8d (ceph): Merge pull request #3209 from dmick/wip-stop.sh-me
- stop.sh: only try killing processes that belong to me
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:49 AM Revision 1eb0cd5a (ceph): osd: only verfy OSDMap crc if it is known
- Only verify we encode a full map with the correct CRC if we actually
have the value in the Incremental. Otherwise, a... - 12:39 AM Revision 8a2c3287 (ceph): Merge pull request #270 from ceph/wip-cot-rename
- ceph_objectstore_tool: Changes for rename of binary ceph-objectstore-too...
Reviewed-by: Loic Dachary <ldachary@redh... - 12:14 AM Revision 1b7585b3 (ceph): stop.sh: only try killing processes that belong to me
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 12:12 AM Revision 8547d9ba (ceph): Merge pull request #3207 from ceph/wip-cot-rename
- ceph_objectstore_tool: Rename generated binary to ceph-objectstore-tool
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:10 AM Revision 2af416b8 (ceph): Merge pull request #3208 from ceph/wip-10326
- qa/workunits/rest/test.py: fix pg stat test
- 12:08 AM Revision a8bd12e5 (ceph): Merge pull request #271 from dachary/wip-cot-rename
- Reviewed-by: David Zafman <dzafman@redhat.com>
12/18/2014
- 11:56 PM CephFS Bug #10382 (Resolved): mds/MDS.cc: In function 'void MDS::heartbeat_reset()
- While running a Active/Standby set of MDSes I see this happen quite often when stopping the Active MDS:...
- 11:49 PM Revision 0af2a1c1 (ceph): qa/workunits/rest/test.py: fix pg stat test
- Back in e27b0d9e42b7ac3de896c3398689bbdbe03f1bbb we changed pg stat to
not dump everything when a formatter is used.
... - 11:48 PM Revision ac64ef79 (ceph): Merge pull request #263 from ceph/wip-calamari-nosetests
- Add calamari-nosetests task and calamari suite (and remove obsolete calamari task)
- 11:47 PM Revision 1bba98bd (ceph): Remove obsolete tasks/calamari
- Signed-off-by: Dan Mick <dan.mick@redhat.com>
- 11:47 PM Revision efa6c36f (ceph): Add calamari_nosetests task.
- Includes all accumulated review commentary and final 'yum clean all' fix.
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 11:47 PM Revision 25ae69f1 (ceph): Add calamari suite definitions.
- Notes:
- very simple cluster configuration
- selects vps in the actual suite config files
- wheezy is currently disab... - 11:43 PM Revision 75287f08 (ceph): ceph_objectstore_tool: fix pep8 errors
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 11:43 PM Revision 3c2aaa9c (ceph): ceph_objectstore_tool: --op list now prints [pg,object]
- The format of the output of --op list was changed to include the PG to
which the object belong. It simplifies the loo... - 11:33 PM Revision cec763bc (ceph): rados/singleton: debug watch-notify test
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:01 PM Revision 3b46995c (ceph): Merge pull request #3195 from nilamdyuti/wip-doc-ceph-deploy
- doc: Changes format style in ceph-deploy to improve readability as html.
Reviewed-by: John Wilkins <jowilkin@redhat.... - 11:00 PM Revision 3450220b (ceph): Merge pull request #3201 from nilamdyuti/wip-doc-ceph
- doc: Changes format style in ceph to improve readability as html.
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 10:52 PM CephFS Bug #10381 (Resolved): health HEALTH_WARN mds ceph239 is laggy
- Hi there.
Today,I runned a script to do some test on my ceph cluster via a cephfs client,include dd/rm/cp files less... - 10:13 PM Revision 5439d9ee (ceph): Merge pull request #3057 from ceph/wip-crush-straw
- crush: fix straw bucket scaler bugs
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:09 PM Revision 2a1bd761 (ceph): .gitmodules: update ceph-object-corpus auth repo to github
- It's annoying having ceph.com for only this repo, and it's not that big.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:05 PM Revision e3f370f2 (ceph): Merge pull request #3101 from yuyuyu101/wip-10147
- Messenger Unit Tests
Reviewed-by: Sage Weil <sage@redhat.com> - 07:36 PM Revision cc504694 (ceph): Merge pull request #3205 from ceph/wip-caps-init
- messages/MClientCaps: init peer.flags
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:30 PM Revision 834aa829 (ceph): Merge pull request #225 from ceph/wip-7317
- #7317 Tests for ENOSPC and OSD epoch barrier handling
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:23 PM Revision a2112fd0 (ceph): Merge pull request #3123 from linuxbox2/wip-claim-3
- Wip claim 3
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:21 PM Revision 2474a785 (ceph): Merge pull request #3111 from yuyuyu101/wip-10193
- WBThrottle: make bytes/ios/inode_wb's perf counter effective
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:20 PM Revision 0a6d5aef (ceph): Merge pull request #3133 from XinzeChi/wip-2
- OSD: FileJournal: call writeq_cond.Signal if necessary in submit_entry
Reviewed-by: Sage Weil <sage@redhat.com>
Revi... - 07:19 PM Revision a9aaea77 (ceph): Merge pull request #3132 from mslovy/optimazation_collection_map
- os: IndexManager:: optimize map<coll_t, CollectionIndex* > col_indices to unordered_map
Reviewed-by: Samuel Just <sj... - 06:59 PM Bug #10166 (Resolved): fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc: 8706: ...
- 06:58 PM Messengers Feature #10147 (Resolved): Add unittest for Messenger
- https://github.com/ceph/ceph/pull/3101
- 06:58 PM Feature #10193 (Resolved): Perf counter for WBThrottle
- 06:57 PM Feature #10172 (Fix Under Review): AsyncMessenger: Bind async thread to special cpu core
- https://github.com/ceph/ceph/pull/3211
- 06:48 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Do you need beta testers? It looks like you don't. I'm still seeing a few asserts per day, but still no service out...
- 06:41 PM Bug #10326 (Resolved): rest-api: assert('pg_stats_sum' in r.myjson['output'])
- 03:50 PM Bug #10326 (Fix Under Review): rest-api: assert('pg_stats_sum' in r.myjson['output'])
- 06:32 PM Revision 916a211a (ceph): Merge pull request #3204 from ceph/wip-osdmap-leak
- osd: fix leaked OSDMap
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:05 PM Bug #10372: FAILED assert(check_latest_map_ops.find(op->tid) (firefly,giant)
- 08:35 AM Bug #10372 (Resolved): FAILED assert(check_latest_map_ops.find(op->tid) (firefly,giant)
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-17_17:18:01-upgrade:firefly-x-next-distro-basic-vp...
- 03:57 PM Revision 623ebf02 (ceph): osd: clear ReplicatedPG::object_contexts when PG start a new interval
- We call object_contexts.clear() in ReplicatedPG::on_change
Change-Id: I705c72378ebe2ccc424b070cd775329041932e75
Sign... - 03:44 PM devops Bug #10371 (Resolved): "Error: Cannot retrieve repository metadata" in upgrade:firefly-firefly-di...
- This issue was caused by epel already being installed (on our newer images) and it not running the command to fix the...
- 08:09 AM devops Bug #10371 (Resolved): "Error: Cannot retrieve repository metadata" in upgrade:firefly-firefly-di...
- Run http://pulpito.ceph.com/teuthology-2014-12-17_17:00:02-upgrade:firefly-firefly-distro-basic-vps/
Jobs ['666405... - 03:36 PM Revision 1f9c0874 (ceph): AsyncConnection: Fix time event is called after AsyncMessenger destruction
- AsyncConnection uses time event to handle async event partially, but it's not
very effective so here use dispatch_eve... - 03:05 PM Revision f8f69821 (ceph): Merge pull request #269 from ceph/wip-librados-debug
- rados/thrash: enable client debug for api tests
- 02:51 PM Revision 20ea0867 (ceph): PipeConnection: Avoid deadlock when calling is_connected
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:50 PM Revision 9783a5cb (ceph): test/msgr/test_msgr: Fix potential unsafe cond wakeup and wrap check
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:43 PM Feature #9953: osd: efficient ObjectStore::Transaction encoding
- 02:41 PM Revision 95e65785 (ceph): rados/thrash: enable client debug for api tests
- These will help catch watch/notify issues...
Signed-off-by: Sage Weil <sage@redhat.com> - 02:32 PM Revision bba4d357 (ceph): librados: init last_objver
- *** CID 1258788: Uninitialized scalar field (UNINIT_CTOR)
/librados/IoCtxImpl.cc: 44 in
librados::IoCtxImpl::IoCtxI... - 02:29 PM Revision 2cd9dc08 (ceph): messages/MClientCaps: init peer.flags
- *** CID 1258789: Uninitialized scalar field (UNINIT_CTOR)
/messages/MClientCaps.h: 132 in MClientCaps::MClientCaps(... - 02:24 PM Revision 679652ab (ceph): osd: fix leaked OSDMap
- *** CID 1258787: Resource leak (RESOURCE_LEAK)
/osd/OSD.cc: 6118 in OSD::handle_osd_map(MOSDMap *)()
6112 ... - 02:12 PM Bug #10214 (Pending Backport): crush: straw buckets do not have expected/desired properties
- 02:12 PM rgw Bug #10379 (Resolved): rgw: object versioning, remove last version needs to remove olh
- 02:09 PM Revision 18f545b5 (ceph): librados: Avoid copy data from librados to caller buff
- when using rados_read_op_read.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 01:51 PM Revision 001ea293 (ceph): Messenger: Create an Messenger implementation by name.
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 12:45 PM Revision 849e259b (ceph): tasks: add mds_full task
- This is for exercising the CephFS behaviour
when the cluster becomes full.
Signed-off-by: John Spray <john.spray@red... - 12:45 PM Revision d3864df9 (ceph): suites/fs: hook in mds_full task
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 PM Revision dedcc648 (ceph): tasks/cephfs: enable kclient for mds_* tasks
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 PM Revision 9c55b81c (ceph): tasks/kclient: add 'debug' option
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 PM Revision f94ec69f (ceph): tasks/mds_client_limits: fix initial rm -rf
- This was previously a no-op because it was trying
to delete "*" instead of *
Signed-off-by: John Spray <john.spray@r... - 12:45 PM Revision 8fa6b154 (ceph): tasks/cephfs: enable osd epoch get from mounts
- Using new hooks for #7317
Signed-off-by: John Spray <john.spray@redhat.com> - 12:45 PM Revision f9609c46 (ceph): tasks/cephfs: let get_config use non-mon services
- Previously was always using the default values of things
so querying mon instead of the appropriate service
worked fi... - 12:22 PM Revision 2d76bc2d (ceph): Merge pull request #3202 from ceph/wip-fix-asok
- mds: fix asok on rank 0
- 12:16 PM Revision 3a2cb714 (ceph): mds: fix asok on rank 0
- Broken by:
1b2b34431 (MDS: do not allow invocation of most commands on an inactive MDS)
MDS::whoami is a rank, so ch... - 11:43 AM Revision 8de9a0f4 (ceph): doc: Adds updated man page for ceph under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 11:41 AM Revision 8b796173 (ceph): doc: Changes format style in ceph to improve readability as html.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 11:28 AM Revision 2aef17d8 (ceph): Merge pull request #268 from ceph/wip-kcephfs-inline
- kcephfs: test inline data
Reviewed-by: John Spray <john.spray@redhat.com> - 11:20 AM Revision 7093cb37 (ceph): doc: Adds updated man page for ceph-disk under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 11:18 AM Revision 62b3fcdd (ceph): doc: Updates man page for ceph-disk with suggested changes.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 11:04 AM CephFS Fix #10377 (New): Impose lower bound on "mds events per segment"
Currently, if the MDS is started with a small mds_events_per_segment, it can go into a trim/rejournal cycle when fi...- 11:01 AM Revision 3f6be22f (ceph): doc: Updates man page for ceph-disk.
- Changes format style to improve readability as html.
Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com> - 11:01 AM Revision 2862a494 (ceph): doc: Adds updated man page for ceph-disk under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 10:52 AM Revision d61b1d92 (ceph): shared_cache: add lookup_or_create, get_next, etc. and their unittests
- These method has the same logic as SharePtrRegistry and will
be used for ReplicatedPG::object_contexts.
Signed-off-b... - 10:52 AM Revision 98110f65 (ceph): osd: change ReplicatedPG::object_contexts to SharedLRU
- The ReplicatedPG now will cache the ObjectContext to avoid repeated
construction using SharedLRU. The cache is per PG... - 10:52 AM Revision 9252d752 (ceph): osd: add ObjectContext cache perf counter
- l_osd_object_ctx_cache_total: all lookup count
l_osd_object_ctx_cache_hit: hit lookup count
Signed-off-by: Dong Yu... - 10:18 AM devops Bug #10374: Failed 'sudo rpm -i ceph-release-1-0.el7.noarch.rpm' in octo
- Looks like it was:
http://pulpito.ceph.redhat.com/teuthology-2014-12-17_02:10:02-samba-firefly-distro-basic-magna/67... - 10:12 AM devops Bug #10374: Failed 'sudo rpm -i ceph-release-1-0.el7.noarch.rpm' in octo
- So, you pasted a huge traceback without saying which job it came from, and left out the stderr as well :-/
- 09:06 AM devops Bug #10374 (Rejected): Failed 'sudo rpm -i ceph-release-1-0.el7.noarch.rpm' in octo
- Run http://pulpito.ceph.redhat.com/teuthology-2014-12-17_02:10:02-samba-firefly-distro-basic-magna/
Jobs ['6740', ... - 09:59 AM Revision 883e1aea (ceph): doc: Show how new data pools can be added to CephFS for file layouts
- 09:51 AM Bug #10375 (Rejected): OSD journal partition link could be broken after off linking the disk via ...
- 1. offline the disk via stocli
/opt/MegaRAID/storcli/storcli64 /c0 /e20 /s6 set offline
2. verify OSD goes down ... - 09:02 AM rgw Documentation #10373 (Closed): Document about S3 POST requests
- Looks like S3 POST requests are supported (atleast for cephx authentication) in rgw. Document about this functionalit...
- 09:02 AM Revision 2b577cef (ceph): packaging: package ceph-deploy(8)
- Fixes merge conflict.
Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com> - 08:55 AM rgw Bug #10354: Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-multi run
- Same in Octo - 5 jobs in run http://pulpito.ceph.redhat.com/teuthology-2014-12-16_22:04:02-rgw-dumpling-distro-basic-...
- 08:49 AM rgw Bug #10354: Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-multi run
- Same issue http://pulpito.ceph.com/teuthology-2014-12-17_17:10:02-upgrade:dumpling-firefly-x:parallel-next-distro-bas...
- 08:01 AM rgw Bug #10354: Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-multi run
- Same issue - http://pulpito.ceph.com/teuthology-2014-12-17_17:15:01-upgrade:dumpling-firefly-x:parallel-next-distro-b...
- 08:43 AM devops Bug #10330: apt-mirror timeouts
- Same here http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-17_17:05:01-upgrade:firefly-firefly-distro-basic-mul...
- 08:21 AM Revision e638469b (ceph): doc: Updates man page for ceph-deploy.
- Changes format style in ceph-deploy to improve readability as html.
Signed-off-by: Nilamdyuti Goswami <ngoswami@redh... - 08:21 AM Revision c6648188 (ceph): doc: Adds updated man page for ceph-deploy under man/
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 07:58 AM Bug #10370 (Duplicate): "MaxWhileTries: 'wait_until_healthy'reached maximum tries (150) after wai...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-17_17:25:01-upgrade:dumpling-firefly-x:stress-spli...
- 07:10 AM CephFS Feature #10369 (Resolved): qa-suite: detect unexpected MDS failovers and daemon crashes
- Currently some of our tests can be run with standby MDSs, and a failover event might occur without our tests noticing...
- 06:48 AM devops Fix #5900: Create a Python package for ceph Python bindings
- if you look into the bootstrapping script you will see that it does in fact call `python setup.py develop` on each py...
- 06:43 AM Revision a8067783 (ceph): qa: test zero size xattr
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:07 AM Bug #10367 (Rejected): 0.89 EC+ KV OSDs crashing
- 06:06 AM Bug #10367: 0.89 EC+ KV OSDs crashing
- Hi, thanks for your report.
I checked your crash OSD commit version(commit:68fdc0f68e6a04e283d2c5140832a3175b4f984... - 03:30 AM Bug #10367 (Rejected): 0.89 EC+ KV OSDs crashing
- Hi,
after issue http://tracker.ceph.com/issues/10119, I tried the same but with the latest version 0.89
Unfort... - 06:05 AM CephFS Bug #10368: Assertion in _trim_expired_segments
- Reproduce (took two tries to see the crash again, so it's intermittent)...
- 05:43 AM CephFS Bug #10368 (Resolved): Assertion in _trim_expired_segments
- ...
- 04:18 AM CephFS Bug #10361: teuthology: only direct admin socket commands to active MDS
- Filesystem::mds_asok would be a good place to put this
- 02:50 AM Revision 42dc9370 (ceph): librados: avoid memcopy for rados_getxattr.
- When call rados_getxattr, pass user buff to libardos to avoid memcopy.
This operation like rados_read.
Signed-off-by:... - 02:32 AM Revision bfa4acf2 (ceph): Merge pull request #3198 from ceph/wip-10335
- MDS: do not allow invocation of most commands on an inactive MDS
- 01:10 AM Revision eec179c6 (ceph): ceph_objectstore_tool: Changes for rename of binary ceph-objectstore-tool
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:09 AM Revision 4f72ba54 (ceph): ceph_objectstore_tool: Rename generated binary to ceph-objectstore-tool
- Signed-off-by: David Zafman <dzafman@redhat.com>
12/17/2014
- 11:32 PM Revision 1b2b3443 (ceph): MDS: do not allow invocation of most commands on an inactive MDS
- They just cause all kinds of trouble!
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 11:20 PM Revision e05d7e3b (ceph): kcephfs: test inline data
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:33 PM CephFS Bug #10344 (In Progress): qa/workunits/snaps/snaptest-git-ceph.sh fails
- 10:12 PM Revision be7b2f8a (ceph): Merge pull request #2836 from ceph/wip-7317
- #7317 ENOSPC and OSD epoch barrier handling
Reviewed-by: Yan, Zheng <zyan@redhat.com>
Reviewed-by: Greg Farnum <gfar... - 09:56 PM Revision f9929409 (ceph): Merge pull request #267 from ceph/wip-firelfy-yuriw
- Removed import_export tests to fix #10176
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:51 PM Revision 5368b93c (ceph): Removed import_export tests to fix #10176
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:00 PM Revision 65be519b (ceph): Merge pull request #3197 from ktdreyer/rpm-spec-comment
- ceph.spec.in: quote %files macro in comment
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:40 PM Bug #10366 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout failure
- ubuntu@teuthology:/a/sage-2014-12-17_16:02:46-rados-wip-pgmeta-distro-basic-multi/666061...
- 08:06 PM Revision 69fa5329 (ceph): ceph.spec.in: quote %files macro in comment
- Prior to this commit, RPM would expand the %files macro that was present
in the comment.
Use a double percent sign t... - 07:46 PM rgw Bug #10365 (Closed): radosgw-agent: buckets to retry logged by full sync won't be fully synced if...
- When buckets to retry are handled by incremental sync, it uses the bucket index log to figure out which objects withi...
- 06:58 PM CephFS Bug #10336: hung ffsb test
- Logs of passed tests also contains "opendir: No such file or directory"
- 06:51 PM Revision aea232c9 (ceph): client, librados, osdc: do not shadow Dispatcher::cct
- * there is no need to have another cct as Dispatch has one already.
* by `using` the parent member variable in `publi... - 06:49 PM CephFS Bug #10335 (Resolved): MDS: disallow flush_path and related commands if not active
- 03:34 PM CephFS Bug #10335 (Fix Under Review): MDS: disallow flush_path and related commands if not active
- https://github.com/ceph/ceph/pull/3198
- 03:19 PM CephFS Bug #10335 (In Progress): MDS: disallow flush_path and related commands if not active
- Oh duh, right, this is us hitting the standby MDS with a flush request. (Thus the mds.-1 up there.) I guess the admin...
- 06:32 PM Revision 38768da1 (ceph): Merge pull request #3171 from tchaikov/refactor-rados-class
- python-rados: refactor class Rados a little bit
Reviewed-by: Josh During <jdurgin@redhat.com>
Reviewed-by: Loic Dach... - 06:05 PM Revision 378ebb79 (ceph): python-rados: refactor class Rados a little bit
- Signed-off-by: Kefu Chai <tchaikov@gmail.com>
- 05:13 PM Revision 1d314e7a (ceph): mon/PGMap: invalidate cached min_last_epoch_clean from new-style pg keys
- We were only invalidating the cache from the legacy apply_incremental(),
which is no longer called on modern clusters... - 05:13 PM Revision f55b0977 (ceph): mon/PGMap and PGMonitor: update last_epoch_clean cache from new osd keys
- We were only invalidating the cached value from apply_incremental, which
is no longer called on modern clusters.
Fix... - 05:06 PM Fix #10363 (Fix Under Review): OSDMonitor setcrushmap tests take a long time on erasure coded rul...
- https://github.com/ceph/ceph/pull/3194
- 04:05 PM Fix #10363: OSDMonitor setcrushmap tests take a long time on erasure coded rulesets
- confirmed. Things can go even worse when you're setting non-default retries on some rules (that is : step set_choose...
- 03:58 PM Fix #10363 (Resolved): OSDMonitor setcrushmap tests take a long time on erasure coded rulesets
- http://workbench.dachary.org/ceph/ceph/blob/giant/src/mon/OSDMonitor.cc#L4007 runs tests by trying to map from min_si...
- 04:40 PM Bug #10364 (Resolved): watch-notify-same-primary.yaml failure
- ubuntu@teuthology:/a/sage-2014-12-17_16:02:46-rados-wip-pgmeta-distro-basic-multi/666048
- 03:18 PM CephFS Bug #10361 (Resolved): teuthology: only direct admin socket commands to active MDS
- Right now our flush and scrub asok command tests are directed at mds.a, but sometimes that's not the active MDS. Find...
- 03:12 PM Bug #8121: ReplicatedBackend::build_push_op() should handle a short read or assert
new acting set [1,5] causes 5 to read 1.3e_head/7fc9453e/plana8413303-32/55e but the read size is only 413696 not t...- 02:30 PM rbd Bug #10122: "LibRBD.TestClone" FAILED in upgrade:dumpling-x-firefly-distro-basic-vps run
- As per Josh, looks like this is fixed in rbd module, hence changing the project to 'rbd'.
- 02:15 PM CephFS Bug #10277: ceph-fuse: Consistent pjd failure in getcwd
- Needs test (or at least test description) and some performance numbers.
- 02:14 PM CephFS Bug #9997 (Resolved): test_client_pin case is failing
- Hum, I was thinking that we could backport the simple fix since most users will be on older kernels where it behaves ...
- 12:10 AM CephFS Bug #9997: test_client_pin case is failing
- The fix is buggy, we shouldn't backport it. we should use patches for #10277 instead
- 12:07 AM CephFS Bug #9997: test_client_pin case is failing
- https://github.com/ceph/ceph/pull/3191
- 02:11 PM CephFS Feature #7317 (Resolved): mds: behave with fs fills (e.g., allow deletion)
- Merged to master in commit:be7b2f8a30b12841d260c4ce486a59ed28953a4f
- 02:05 PM rgw Bug #10194: rgw: fcgi connections are not closed when using mod-proxy-fcgi
- The fix was merged to the firefly branch in this commit:...
- 02:05 PM Bug #10347 (Rejected): duplicate OSD in acting set
- ...
- 04:35 AM Bug #10347 (In Progress): duplicate OSD in acting set
- ...
- 04:27 AM Bug #10347 (Need More Info): duplicate OSD in acting set
- Increasing choose tries as follows will ask CRUSH to try harder to find OSDs to map to the PG. ...
- 03:15 AM Bug #10347: duplicate OSD in acting set
- ...
- 03:11 AM Bug #10347 (Rejected): duplicate OSD in acting set
- In the attachment:map-for-loicd osdmap extracted from a ceph version 0.87 (c51c8f9d80fa4e0168aa52685b8de40e42758578) ...
- 01:53 PM Bug #10176: Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- Fixed, see PR - https://github.com/ceph/ceph-qa-suite/pull/267
- 10:59 AM Bug #10176 (New): Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- Shows up again in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-16_17:00:03-upgrade:firefly-firefly-distro-b...
- 01:50 PM Revision 59b70fe2 (ceph): Cleanup: Drop hobject_incorrect_pool
- This field in MOSDSubOp, used to support very old version
OSD(MOSDSubOp header version < 7, which was introduced in
m... - 01:06 PM Bug #10358 (Resolved): ceph osd erasure-code-profile set myprofile k=1 should fail
- it is invalid and will have undefined side effects. Steps to reproduce:
* ceph osd erasure-code-profile set myprof... - 01:01 PM Revision 0c9d55d4 (ceph): pybind/cephfs: Fix setxattr function. Pass value as character pointer
- This passes the value of the xattr correctly and makes it work.
- 11:37 AM Revision b4214f95 (ceph): Merge pull request #257 from ceph/wip-fs-creation
- Fix PG counts and refactor FS creation during setup
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:46 AM Bug #10356 (Rejected): new optracker requests show up with bad age
- ...
- 09:39 AM rgw Bug #10354 (Duplicate): Failed s3 tests in upgrade:dumpling-firefly-x:parallel-next-distro-basic-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-16_17:10:02-upgrade:dumpling-firefly-x:parallel-ne...
- 08:50 AM Linux kernel client Bug #10351 (Duplicate): mount.ceph prints spurious "mount: error writing /etc/mtab: Invalid argum...
- 08:30 AM Linux kernel client Bug #10351: mount.ceph prints spurious "mount: error writing /etc/mtab: Invalid argument"
- I reported it as #8122 eight months ago...
- 05:57 AM Linux kernel client Bug #10351 (Resolved): mount.ceph prints spurious "mount: error writing /etc/mtab: Invalid argument"
- The mount and update of mtab is apparently successful, but this error message is printed anyway. Googling for the er...
- 08:00 AM Revision 9b73c762 (ceph): Merge pull request #3190 from dachary/wip-test-helpers
- tests: ignore xmlstarlet extra empty lines
- 07:59 AM Revision d1257436 (ceph): client: use remount to trim kernel dcache
- when remounting a file system, linux kernel trims all unused dentry
in the file system.
Fixes: #10277
Signed-off-by:... - 07:59 AM Revision 9de9901c (ceph): client: cleanup client callback registration
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 07:37 AM RADOS Fix #10350 (Fix Under Review): explain how to troubleshoot erasure code mapping failures
- https://github.com/ceph/ceph/pull/3194
- 04:33 AM RADOS Fix #10350 (Resolved): explain how to troubleshoot erasure code mapping failures
- It is common to have X osd and create an erasure coded pool that requires X osd. The CRUSH rule is likely to fail map...
- 07:36 AM Bug #10353 (Fix Under Review): the number of tries should be higher for the default erasure coded...
- https://github.com/ceph/ceph/pull/3194
- 07:03 AM Bug #10353 (Resolved): the number of tries should be higher for the default erasure coded ruleset
- It is common for people to try to map 9 OSDs out of a 9 OSDs total ceph cluster. The default tries (50) is often not ...
- 07:35 AM Bug #10349 (Fix Under Review): crushtool --show-choose-tries is a noop for indep rules
- https://github.com/ceph/ceph/pull/3194
- 04:19 AM Bug #10349 (Resolved): crushtool --show-choose-tries is a noop for indep rules
- 07:02 AM Revision 023a8aca (ceph): tests: ignore xmlstarlet extra empty lines
- With xmlstarlet 1.3.0 (which is on Ubuntu precise)
xmlstarlet sel -t -m '//pg_stat/state[(contains(.,'\''active'\'')... - 06:57 AM Linux kernel client Bug #10313: IO drop outs/timeouts on one of the rbd client
- From a quick look, I doubt it. Anand, are you reporter's colleague?
That commit went into 3.14-rc2 and it fixes an ... - 06:41 AM Linux kernel client Bug #10352 (Resolved): libceph delayed work items aren't teared down properly
- http://qa-proxy.ceph.com/teuthology/dis-2014-12-17_03:17:27-krbd-giant---basic-multi/663896/teuthology.log
[0]kdb>... - 05:47 AM CephFS Bug #10343: qa/workunits/snaps/snaptest-xattrwb.sh fails
- only fuse-client fails
- 04:06 AM RADOS Bug #10348 (Won't Fix): crushtool --show-choose-tries overflows
- The array is allocated according to choose_total_tries although choose_tries local to the ruleset can be set to a gre...
- 02:00 AM Feature #10346 (Resolved): add ceph pg dump_stuck {degraded,undersized}
- and updated doc/rados/troubleshooting/troubleshooting-pg.rst accordingly
implemented by commit:9db596974c82207dc07... - 01:07 AM Revision 82f452cc (ceph): osd/PG: drop PG/collection attrs from ScrubMap
- The collection attrs are often version specific. We should compare the
semantic PG metadata, if anything, not these!... - 01:07 AM Revision 56232d96 (ceph): ceph_test_objectstore_workloadgen: set pgmeta omap instead of collectio...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 17e4e197 (ceph): os/ObjectStore: deprecated collection_getattr et al
- Drop the functional tests for this too.
Return EOPNOTSUPP by default, and tolerate this in the callers.
Signed-off-... - 01:07 AM Revision 43f0bcb1 (ceph): os/MemStore: drop support for collection attrs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision f6ca2bcb (ceph): os/FileStore: better debug on unlink
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision e582135c (ceph): os/FileStore: better debug on omap_setkeys
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision fbf64089 (ceph): ceph_objectstore_tool: Clean-up unused struct_ver in tool's metadata se...
- Exported struct_ver not used by write_info() or write_pg()
Signed-off-by: David Zafman <dzafman@redhat.com> - 01:07 AM Revision f056bdf9 (ceph): ceph_objectstore_tool: Prevent tool from transitioning struct_v on rm-p...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:07 AM Revision cd462d17 (ceph): osd: move pg removal flag into a static helper
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision f93b2937 (ceph): ceph_objectstore_tool: use '_remove' pgmeta omap key to indicate remova...
- We could conceivably mark the PG for backfill, but to do this correctly
we have to do the log rollback, which uses va... - 01:07 AM Revision a599d886 (ceph): osd: drop legacy arg to PG::peek_map_epoch
- The function can figure it out itself, and it's only needed for legacy.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 5877c069 (ceph): osd: drop infos_oid arg from PG::read_info()
- Only needed for legacy.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 880135ab (ceph): osd: drop snap_collections
- This is obsolete since cuttlefish.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision db3daaf1 (ceph): osd/PG: drop PG::read_info support for ancient PGs
- This is rewritten regularly by any vaguely-active OSD; no need for this
any more.
Signed-off-by: Sage Weil <sage@red... - 01:07 AM Revision a1a3e156 (ceph): os/ObjectStore: deprecated collection attr operations
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 8fa94071 (ceph): osd/PGLog: explicitly pass log_oid collection
- Do not assume the log_oid is ine the 'meta' collection.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 6074bdd1 (ceph): osd: move pg log and info to a per-pg object
- Move all PG metadata (info, biginfo, epoch, and log) to a single per-PG
object. This should make it easier for Objec... - 01:07 AM Revision 8cb25cbd (ceph): test/osd/osd-test-helper.sh: enable filestore log
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision d1973f3b (ceph): osd/PGLog: drop support for ancient logs
- Assume that users have at least upgraded to dumpling first.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 9d1466cb (ceph): osd: prevent upgrade from older than v7
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision d6df6eab (ceph): osd: retire meta/infos object entirely
- Do not create it; remove it on upgrade.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 35fcfcef (ceph): osd/PG: define pgmeta_oid member
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 5a5a4a87 (ceph): osd: don't need to pass object names via ctor
- Calculate biginfo on the fly.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision be86cc73 (ceph): osd: move PG collection creation into static PG method
- This way we properly create the pgmeta object and set the infokey attr on
it. Break it into two steps, one part befo... - 01:07 AM Revision 98192217 (ceph): osd/PGLog: take ghobject_t instead of hobject_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision c765de6b (ceph): common/hobject_t: fix whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 033a533a (ceph): common/hobject_t: add pgmeta named ctor and is_pgmeta() check
- There will be exactly one of these per PG. It slots into the flat
(pool, hash, name...)
namespace but is not a l... - 01:07 AM Revision a56f10af (ceph): osd/osd_types: spg_t::make_pgmeta_oid()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 9ebdb99a (ceph): osd/PGBackend: skip pgmeta objects
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision e247cd4b (ceph): ceph-objectstore-tool: skip pgmeta object on export
- We will (eventually) export the contents of this object explicitly as
PG metadata.
Signed-off-by: Sage Weil <sage@re... - 01:07 AM Revision 4d22adf6 (ceph): osd: skip pgmeta object on remove_dir
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:07 AM Revision 456255b7 (ceph): os/DBObjectMap: include hash in header key for EC objects
- We were inadvertantly dropping the hash portion of the header key for EC
objects. This is usually not noticeable, bu... - 01:07 AM Revision 462bad32 (ceph): ceph_test_rados: generate mix of small and large xattrs
- This ensures that we exercise the large xattr handling paths in the OSD.
(Specifically, we want to trigger DBObjectM... - 01:07 AM Revision 69e169d9 (ceph): os/DBObjectMap: new version v2; drop support for upgrading from v1
- - Don't support upgrade from v1 anymore
- Add upgrade for v1 -> v2
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 18214928 (ceph): os/FileStore: move to v4, trigger DBOjectMap upgrade
- From FileStore's perspective, nothing changed from v3 to v4. However, we
need to pass the do_upgrade flag to DBOject... - 01:07 AM Revision 95eccd8e (ceph): osd: add PGMETA ondisk feature
- Once you start using the pgmeta objects there is no going back.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:50 AM Revision 242e28d1 (ceph): Merge pull request #2530 from majianpeng/fiemap
- Fiemap
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Samuel Just <sjust@redhat.com> - 12:44 AM Documentation #10345 (Rejected): operations documentations about backfilling needs an update
12/16/2014
- 11:27 PM CephFS Bug #10344 (Resolved): qa/workunits/snaps/snaptest-git-ceph.sh fails
- 11:26 PM CephFS Bug #10343 (Resolved): qa/workunits/snaps/snaptest-xattrwb.sh fails
- 11:15 PM Revision ca1b216b (ceph): Merge pull request #2137 from yuyuyu101/pg-sparse-recovery
- ReplicatedPG: Make recovery using fiemap and fix perf counter
sage-2014-12-16_08:43:28-powercycle-wip-sage-testing-d... - 11:14 PM Revision 9323ab29 (ceph): Merge pull request #3000 from yuyuyu101/wip-10166
- Wip 10166: fiemap or FileStore::do_sparse_copy_range bug
sage-2014-12-16_08:43:28-powercycle-wip-sage-testing-distr
... - 10:29 PM Revision 47f0a52e (ceph): Merge branch 'wyc-quota-v2' of git://github.com/kylinstorage/ceph into ...
- Conflicts:
src/include/ceph_features.h
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redha... - 10:02 PM Revision f8d37a2c (ceph): Merge remote-tracking branch 'gh/master' into wip-watch-notify
- Conflicts:
PendingReleaseNotes
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Josh During <jdurgin@redhat... - 09:54 PM Revision 868d7496 (ceph): Merge pull request #3033 from dachary/wip-10201-osd-scrub-repair
- osd scrub repair uses ceph_objecstore_tool + shell toolbox
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:44 PM Revision 9d61dec0 (ceph): Merge pull request #3181 from ceph/wip-10299
- librbd: complete all pending aio ops prior to closing image
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:27 PM Revision 4c605676 (ceph): radosgw-admin: wait before trimming usage
- Fixes: #9892
Need to wait through the usage interval before trimming usage, otherwise we might not
remove all pendin... - 09:20 PM Revision 3abb3ff2 (ceph): Merge pull request #266 from ceph/wip-9892-2
- radosgw-admin: wait before trimming usage
- 09:15 PM Revision 47d56d77 (ceph): radosgw-admin: wait before trimming usage
- Fixes: #9892
Need to wait through the usage interval before trimming usage, otherwise we might not
remove all pendin... - 08:55 PM Revision a8611ace (ceph): client: handle ENOSPC in _flush
- Previously we would avoid issuing writes
from _write, but the same condition was
not applied to _flush. This was oka... - 08:55 PM Revision 6fdf8903 (ceph): client: propagate flush errors to fclose/fsync
- Ensure that all calls to _flush get an explicit
context (rather than implicit PutInode used
before), which tags any e... - 08:55 PM Revision a8babcba (ceph): client: add 'status' asok
- Useful in test/debug for querying OSD epoch
and OSD barrier epoch.
Signed-off-by: John Spray <john.spray@redhat.com> - 08:55 PM Revision 9f53eeb8 (ceph): doc: add cephfs ENOSPC and eviction information
- Adding this at this time to give us a sensible place
to talk about the epoch barrier stuff. The eviction
stuff will ... - 08:51 PM Revision 09287fd6 (ceph): osdc: add public Objecter::osdmap_full_flag
- For the (now numerous) places where callers
would like to check this without doing a verbose
lock/unlock cycle.
Sign... - 08:51 PM Revision fc7d62a1 (ceph): mds: return ENOSPC on write ops while osds full
- Allow removals and read-only ops, prevent others. This
is a soft policy aimed at reducing the likelihood of a
"full"... - 08:51 PM Revision 68ba7f58 (ceph): messages: add osd_epoch_barrier to cap msgs
- Extension to client-server protocol to allow clients
to release capabilities conditional on the receiver
having a par... - 08:51 PM Revision 2d993c4b (ceph): messages: always encode barrier
- Instead of truncating on INLINE_DATA, send
some blank fields there for clients that
don't support it (the kclient) in... - 08:51 PM Revision 40503ffb (ceph): mds: implement osd epoch barrier on caps
- Signed-off-by: John Spray <john.spray@redhat.com>
- 08:51 PM Revision fcc64f38 (ceph): mds: set epoch barrier on transition to active
- To handle case where MDSs restart after experiencing
a barrier-inducing operation: rather than persisting
OSD barrier... - 08:51 PM Revision cdf679be (ceph): mds: add 'osdmap barrier' admin command
- This is for use with client eviction.
Signed-off-by: John Spray <john.spray@redhat.com> - 08:48 PM Revision ef75d720 (ceph): rgw: return SignatureDoesNotMatch instead of AccessDenied
- Fixes: #10329
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:48 PM Revision 56af795b (ceph): rgw: return InvalidAccessKeyId instead of AccessDenied
- Fixes: #10334
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 08:48 PM Revision 725c8509 (ceph): Merge pull request #3173 from ceph/wip-9555
- osd: fix msgr reconnect crash from MOSDRepScrub messages (bug 9555)
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:45 PM Revision a9912124 (ceph): osdc/ObjectCacher: invoke flush_set_callback on purge_set
- For the benefit of Client, so that it can get its
caps released when using purge_set to deal with
an ENOSPC condition... - 08:45 PM Revision fe32d6ee (ceph): osdc/Objecter: add op_cancel_writes
- This is for use by Client when it encounters
the FULL flag and wants to abort operations
rather than having them paus... - 08:45 PM Revision 3ad6ed3d (ceph): osdc/Objecter: add have_map method
- This is for places we're going to call wait_for_map, so
that we can easily check if we will *probably* get
a true fro... - 08:45 PM Revision c4861a61 (ceph): osdc: continuously subscribe to osd map on pause
- We were doing this on FULL, should also have done it
on PAUSERD and PAUSEWR, to avoid paused requests
staying that wa... - 08:45 PM Revision cf3101af (ceph): osdc: implement Objecter::set_epoch_barrier
- For use in MDS and Client when they want to wait
for a particular OSDMap epoch before using caps
that depend on a pri... - 08:45 PM Revision bab3d3d4 (ceph): osdc: remove spurious _maybe_request_map return value
- This was always zero: make the function return void, and
remove all the places we asserted on its return value.
Sign... - 06:13 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Finally..mini test case.
1. New rgw instance
2. Create bucket + 4 x 10m objects (2 by fastcgi, 2 by civetweb)
3.... - 05:54 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- 1. The issue is reproducible only on objects created by civetweb.
The bucket can be created by either civetweb or... - 05:44 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Weird - the problem occurs with objects *created* by civetweb.
How to reproduce:
1. create new rgw instance
2.... - 05:06 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- The corruption occurs if civetweb is the first thing that touches a new rgw setup.
How to reproduce:
1. rmpool .... - 04:35 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Suddenly civetweb is working, huh!!??
1. Delete 3 objects in succession
[
{ "tag": "default.7460.27",
... - 04:23 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Logs with good gc behaviour:
1. rm 1 object # 3 oids expected
[root@cephadm ~]# radosgw-admin gc list --include-a... - 08:33 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Can you provide logs to both your apache and civetweb gateways, when removing objects? (set 'debug rgw = 20', and 'de...
- 01:36 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- civetweb seems to "corrupt" the gc list.
1. rm one object (10M size) with civetweb, 3 oids in gc list
2. rm 2nd o... - 04:49 PM Revision eef17053 (ceph): Merge pull request #2300 from ceph/wip-osdmap
- add osdmap checksums
sage-2014-12-16_06:27:10-rados:singleton-wip-sage-testing2-distro-basic-multi
sage-2014... - 04:46 PM Revision e27d3bda (ceph): Merge pull request #3166 from ceph/wip-librados-fadvise
- fadvise for librados, librbd + osd guts
sage-2014-12-16_06:27:10-rados:singleton-wip-sage-testing2-distro-basic-... - 04:38 PM Revision dacab7b7 (ceph): Merge pull request #3080 from ceph/wip-fadvise
- osd: reenable fadvise; use it more often
sage-2014-12-16_06:27:10-rados:singleton-wip-sage-testing2-distro-basic-mul... - 04:13 PM Revision 8241f114 (ceph): Merge pull request #3165 from nilamdyuti/wip-doc-ceph
- doc: Updates man page for Ceph
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 03:05 PM rgw Feature #10342 (Resolved): rgw: tool to clean up clutter
- ...
- 02:10 PM Revision f614fae1 (ceph): Merge pull request #3184 from dachary/wip-10325-cauchy
- erasure-code: relax cauchy w restrictions
Reviewed-by: David Zhang <david.z1003@yahoo.com> - 02:03 PM Fix #2343 (Resolved): librados, osd: notify with special type on object deletion
- 02:03 PM Bug #2339 (Resolved): osd: EBUSY on object delete when watchers present
- 02:03 PM Fix #4205 (Resolved): librados: Improve Watch-notify semantics
- 02:03 PM Feature #9197 (Resolved): librados/osd: notify reply payload
- 02:03 PM Feature #9198 (Resolved): librados: notify callback includes gid of notifier
- 02:03 PM Fix #9199 (Resolved): librados: watch linger pings need to verify pg mapping hasn't changed
- 02:02 PM Fix #9195 (Resolved): librados: issue watch callback on (possibly) missed notifies
- 02:02 PM Fix #9196 (Resolved): librados: watch_check() to synchronous verify we haven't missed notifies
- 02:02 PM Fix #9194 (Resolved): librados/osd: watch reconnect needs to be exclusive to detect possibly miss...
- 01:58 PM Linux kernel client Bug #5429 (Resolved): libceph: rcu stall, null deref in osd_reset->__reset_osd->__remove_osd
- What Josh got a report of was not a referenced trace, but the
following (pulled off of the vmcore):
[197102.90280... - 01:57 PM Bug #8620 (Won't Fix): rest/test.py occasional failure (dumpling)
- 01:56 PM Bug #10341 (Resolved): ceph-monstore-tool: crashes when run without arguments
- 01:53 PM Bug #10104 (Resolved): rados.py: wait_for_* don't wait; should have poll, wait, and wait+cb versions
- 01:52 PM Bug #10201 (Resolved): tests must use ceph_objectstore_tool
- 01:49 PM Bug #10118 (Can't reproduce): messenger drops messages between osds
- 01:48 PM Bug #10153 (Pending Backport): Rados.shutdown() dies with Illegal instruction (core dumped)
- 01:48 PM Bug #10176 (Resolved): Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- 01:46 PM Bug #10294: ceph-osd --mkfs segfaults when journal dev is a symlink
- https://github.com/ceph/ceph/commit/25e37837c363619bc3f39b55fb2dc270b231fea6 and related patches
- 01:45 PM Bug #10294 (Resolved): ceph-osd --mkfs segfaults when journal dev is a symlink
- fixed in master
- 01:45 PM Bug #10287 (Resolved): ceph v0.80.7 ceph-mon --mkfs crash
- 01:43 PM rbd Bug #10299 (Pending Backport): "ObjectCacher.cc: 530: FAILED assert(i->empty())" in rbd-firefly-d...
- 01:43 PM CephFS Bug #10302 (Resolved): "fsync-tester.sh: line 10: lsof: command not found"
- 01:36 PM Bug #9844 (Won't Fix): "initiating reconnect" (log) race; crash of multiple OSDs (domino effect)
- Closing this, it looks like fallout from the keyvaluestore_dev OSDs :(
- 01:33 PM Bug #9874 (Duplicate): ceph_test_rados, out of order ops
- 01:32 PM Bug #10340 (Resolved): "[ FAILED ] LibRadosIo.ReadTimeout" in upgrade:dumpling-firefly-x:parall...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-15_18:15:01-upgrade:dumpling-firefly-x:parallel-gi...
- 01:32 PM devops Bug #10339 (Won't Fix): downburst doesn't recognize an os version of 14.04(trusty)
- While testing issue 10279 I noticed that a yaml file that contained the os_version: 14.04(trusty) would successfully ...
- 01:28 PM rgw Bug #9892 (Resolved): radosgw_admin.py: failed len(out['entries']) == 0 on usage show
- merged commit 3abb3ff into master, giant, firefly, and dumpling
Commit hash is actually 47d56d779eb145f5bca1e8e1e... - 01:15 PM rgw Bug #9892 (Fix Under Review): radosgw_admin.py: failed len(out['entries']) == 0 on usage show
- changes had been made by yehuda already, PR opened https://github.com/ceph/ceph-qa-suite/pull/266
After it merges ... - 01:26 PM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- Dmitry Smirnov wrote:
> Can this bug get a little attention please? It has profound effect on my crippled cluster an... - 01:19 PM Bug #10326: rest-api: assert('pg_stats_sum' in r.myjson['output'])
- Yep, someone changed pg dump output, which broke rest/test.py where it looks for pg_stats_sum in that output.
- 08:30 AM Bug #10326 (Resolved): rest-api: assert('pg_stats_sum' in r.myjson['output'])
- 2014-12-16T07:00:10.071 INFO:tasks.workunit.client.0.plana77.stdout:PUT pg/set_nearfull_ratio?ratio=0.90: 200
2014-... - 01:18 PM Bug #9796 (Won't Fix): osd: crash on blacklisted watcher reconnect (dumpling)
- this is very rare and complicated to fix
- 01:15 PM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Same issue http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-15_18:18:01-upgrade:firefly-x-giant-distro-basic-vp...
- 01:10 PM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Actually, the problem is likely that the hinfo_key was missing on whatever osd ended up as the "authoritative" osd. ...
- 01:12 PM Bug #10214 (Fix Under Review): crush: straw buckets do not have expected/desired properties
- 01:10 PM Bug #10242 (Need More Info): FAILED assert(backfill_targets.empty() || backfill_targets == want_b...
- upstart will automatically restart the daemon. sysvinit will not. soon systemd will (hammer).
- 01:10 PM Bug #10010 (Resolved): ceph_osd.cc calls global_init_shutdown_stderr even when running with -f or...
- 01:08 PM Bug #10220 (Pending Backport): "mon/Paxos.cc: 1033: FAILED assert(mon->is_leader())" in upgrade:d...
- 01:08 PM Bug #9998 (Pending Backport): Replaced OSD weight below 0
- 12:56 PM Revision bb80437f (ceph): erasure-code: relax cauchy w restrictions
- A restriction that the w parameter of the cauchy technique is limited to
8, 16 or 32 was added incorrectly while refa... - 12:52 PM Feature #10338: ceph: 'daemon list' command to enumerate daemon sockets we can connect to
- 12:49 PM Feature #10338 (New): ceph: 'daemon list' command to enumerate daemon sockets we can connect to
- ceph daemon <daemon name> ...
ceph daemon <asok path> ...
both let you talk to a running daemon via the CLI. T... - 12:49 PM Bug #9555 (Pending Backport): msg/Pipe.cc: 1513: FAILED assert(0 == "old msgs despite reconnect_s...
- Merged to master in commit:725c8509e6a11a8d1ec5f5238ce622c6546f4865
- 12:44 PM devops Fix #5900: Create a Python package for ceph Python bindings
- I've rebased wip-5900 today and pushed it to ceph.git. There's one last thing we need to resolve. It looks like the i...
- 12:04 PM devops Fix #5900: Create a Python package for ceph Python bindings
- This is the BZ ticket associated with the work on this issue: https://bugzilla.redhat.com/show_bug.cgi?id=1116757
- 12:22 PM CephFS Bug #10316 (Won't Fix): pool quota no offect for cephfs client
- Oh, you mean you got to 1050MB instead of exactly 1GB.
Yeah, that's expected behavior; these are all soft limits. ... - 12:09 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- http://pulpito.ceph.redhat.com/teuthology-2014-12-15_19:45:01-fs-giant-distro-basic-magna/4867/
- 12:09 PM CephFS Bug #9997 (Pending Backport): test_client_pin case is failing
- Can we get a giant backport for this, please?
- 12:07 PM Revision 058f4339 (ceph): man: Deprecate preferred OSD setting for cephfs
- In the source code of cephfs there is no reference to it anymore,
but it's still in the man page. Leave it there for ... - 11:02 AM CephFS Bug #10336 (Can't reproduce): hung ffsb test
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-14_23:08:01-kcephfs-next-testing-basic-multi/
It looks like... - 10:56 AM CephFS Bug #10335 (Resolved): MDS: disallow flush_path and related commands if not active
- ...
- 10:54 AM rgw Bug #10334 (Resolved): rgw: s3 need to return InvalidAccessKeyId instead of AccessDenied
- commit:56af795b1046a4c1bfba59e1fefde272bb0e5c1e...
- 10:07 AM rgw Bug #10329 (Fix Under Review): rgw: s3 need to return SignatureDoesNotMatch instead of AccessDenied
- 08:58 AM rgw Bug #10329 (Resolved): rgw: s3 need to return SignatureDoesNotMatch instead of AccessDenied
- commit:ef75d720f289ce2e18c0047380a16b7688864560
- 10:00 AM rgw Feature #10333 (Resolved): rgw: support AWS4 authentication
- 09:59 AM rgw Bug #10195: s3 java jdk conn.getobject(...) (get s3 object) method fails with latest version of a...
- It seems that the jdk uses a new type of authentication (AWS4), that radosgw is yet to support.
- 09:55 AM rgw Bug #10177: test_multipart_upload failed in upgrade:dumpling-firefly-x:parallel-giant-distro-basi...
- For some reason boto got here a timeout (no real reason that I can see, everything flows nicely):...
- 09:51 AM Linux kernel client Bug #10208 (Need More Info): libceph: intermittent hangs under memory pressure
- Andrei, does the below mean you had OSDs and cephfs mounted on the same box? I missed this completely because the pr...
- 09:40 AM rgw Bug #10221 (Resolved): Crash in "radosgw-admin" in upgrade:firefly:singleton-firefly-distro-basic...
- Fixed in commit:9d5e4edc15678de675d7a77badcbace0b710d553
- 09:35 AM Linux kernel client Bug #9928 (Resolved): kernel BUG at fs/ceph/caps.c:2307!
- This patch has been in testing for a while.
- 09:34 AM devops Feature #10332 (Rejected): Provide a fedora21 cloud image as a teuthology vps target
- FC21 was released recently and I want to use it to for packaging development of calamari.
- 09:20 AM rbd Bug #9405 (Resolved): rbd/test_librbd.sh outputs garbage
- 09:17 AM rgw Bug #10227 (Duplicate): "Segmentation fault" radosgw() in smoke-master-distro-basic-multi suite
- 09:17 AM devops Bug #10330: apt-mirror timeouts
- more:
http://pulpito.ceph.com/teuthology-2014-12-15_17:13:01-upgrade:firefly-x-next-distro-basic-multi/ - 09:09 AM devops Bug #10330 (Resolved): apt-mirror timeouts
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-15_17:13:01-upgrade:firefly-x-next-distro-basic-mu...
- 09:15 AM rgw Bug #10188 (Won't Fix): Can not create new rgw user when specifying an email already assigned to ...
- 09:11 AM rgw Bug #10102 (Resolved): sync agent: does not handle gracefully transient errors
- https://github.com/ceph/radosgw-agent/pull/13
- 09:10 AM rgw Bug #10194: rgw: fcgi connections are not closed when using mod-proxy-fcgi
- fix for master needs to be reviewed / merged.
- 09:10 AM Feature #10331 (Resolved): osd: osdmap checksum
- 09:08 AM Feature #9959 (Resolved): osd: pass client fadvise hints through to objecstore
- 09:08 AM Feature #9960 (Resolved): osd: adjust hint(s) for replica vs primary writes
- 09:08 AM Feature #9957 (Resolved): librados: add fadvise op
- 09:08 AM Feature #9958 (Resolved): osd: add fadvise op to Objectstore::Transaction
- 09:03 AM rgw Bug #10251 (Resolved): "Segmentation fault" (radosgw()) in upgrade:dumpling-firefly-x:parallel-ne...
- 09:03 AM rgw Bug #9254 (Pending Backport): rgw: civetweb requires explicit \r\n for http headers
- 09:02 AM rgw Bug #10066 (Pending Backport): rgw: failed md5sum on s3tests-test-readwrite
- 08:57 AM Bug #10327 (Closed): "FAILED assert(allow_eio || !m_filestore_fail_eio || got != -5)" in upgrade:...
- Not a bug
- 08:38 AM Bug #10327 (Closed): "FAILED assert(allow_eio || !m_filestore_fail_eio || got != -5)" in upgrade:...
- Assertion due to bad drive, this may not be a bug, just making sure our assertion is correct.
Drives on mira076 ar... - 07:36 AM Revision cbc6c7ca (ceph): Merge pull request #2970 from ceph/wip-swift-storage-policy
- rgw: support swift storage policy api
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:35 AM Revision 75a165db (ceph): Merge pull request #3163 from ceph/wip-9254
- rgw: http headers need to end with \r\n
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Sage Weil <sweil@... - 06:53 AM CephFS Bug #8576 (Resolved): teuthology: nfs tests failing on umount
- Haven't seen this since we made those changes!
- 06:26 AM Bug #6003: journal Unable to read past sequence 406 ...
- ubuntu@teuthology:/a/sage-2014-12-01_11:11:52-rados-next-distro-basic-multi/629379
- 06:19 AM rgw Bug #10268: s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3CreateError not ra...
- 06:12 AM Bug #10325: Erasure coding's cauchy parameter "w" in CEPH giant is incompatible with the one in f...
- * giant backport https://github.com/ceph/ceph/pull/3185
- 04:32 AM Bug #10325 (Fix Under Review): Erasure coding's cauchy parameter "w" in CEPH giant is incompatibl...
- https://github.com/ceph/ceph/pull/3184
- 04:27 AM Bug #10325: Erasure coding's cauchy parameter "w" in CEPH giant is incompatible with the one in f...
- This restriction was added incorrectly while refactoring parameter parsing in the jerasure plugin and should be relaxed
- 04:07 AM Bug #10325: Erasure coding's cauchy parameter "w" in CEPH giant is incompatible with the one in f...
- Your erasure code profile is...
- 04:05 AM Bug #10325 (In Progress): Erasure coding's cauchy parameter "w" in CEPH giant is incompatible wit...
- 03:59 AM Bug #10325 (Resolved): Erasure coding's cauchy parameter "w" in CEPH giant is incompatible with t...
- Because of following incompatible issue, we are not able to upgrade our production cluster to giant from firefly.
... - 05:49 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- * Solving Constraint Integer Programs http://scip.zib.de/
* A Free and Open-Source Java Library for Constraint Progr... - 05:45 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- Go simulation of the current algorithm http://play.golang.org/p/l-0Z4u-O3C...
- 04:25 AM Revision 37a99694 (ceph): librbd: complete all pending aio ops prior to closing image
- It was possible for an image to be closed while aio operations
were still outstanding. Now all aio operations are tr... - 03:08 AM Bug #10324 (Can't reproduce): Free space over-reported when OSDs have weight > 1.0
- ...
- 01:43 AM CephFS Bug #10323 (Resolved): lock get stuck in snap->sync state
- ...
- 01:04 AM Revision 02fae9fc (ceph): osd: handle no-op write with snapshot case
- If we have a transaction that does something to the object but it !exists
both before and after, we will continue thr... - 12:11 AM Revision db951aed (ceph): cls/refcount: ENOENT when put on non-existent object
- If we get ENOENT, do not that that to mean an implicit reference count of
1. That means that if you put a non-existe...
12/15/2014
- 10:29 PM Linux kernel client Bug #10313: IO drop outs/timeouts on one of the rbd client
- Looks like fixed by the following commit:
commit ff513ace9b772e75e337f8e058cc7f12816843fe
Author: Ilya Dryomov <i... - 07:23 PM Revision 9ff91440 (ceph): librados: do not choke on asphyxiate doc generation
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 07:19 PM CephFS Bug #10316: pool quota no offect for cephfs client
- I think the data is already put into Rados, because my ceph cluster and client are rebooted but my data is not lo...
- 11:32 AM CephFS Bug #10316: pool quota no offect for cephfs client
- I suspect this is just that you're writing into the local page cache (and ceph client userspace cache), rather than t...
- 06:44 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Revert rgw_gc_max_objs to 32, problem remains.
- 06:40 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- civetweb:
when you delete a second object, it does not appear in gc list --incude-all
How to reproduce:
1. add... - 05:35 PM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- The rgw parameters are in the global section.
- 11:18 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Not sure how civetweb could affect gc work. I do see that your rgw_gc_max_objs is non standard. Did you put this conf...
- 09:53 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Summary of bug:
civetweb 0.89 is not correctly preparing the garbage collection list:
1. create 100 rgw objects (... - 09:40 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Should have written:
It is a civetweb bug.
With apache/fastcgi: I added 100 objects and rm'ed - 10M ea,
300 s... - 09:39 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- It is a civetweb bug.
I added 100 objects and rm'ed - 10M ea, 300 shadow objects created.
All 300 shadow objects ... - 09:02 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- No - I am following the exemplary simple configuration
with default zones; only changes are custom cluster name
and... - 08:44 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Do you by any chance have non default zone configuration?
- 08:24 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Reproduced this on a fresh 0.89.
Created 400 objects, deleted 300.
Found 3 objects in gc list --include-all.
... - 12:42 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Tested again: reduced rgw_gc settings to 300s.
On 0.80.7, the shadow object were purged.
On 0.87, 0.89 the garb... - 06:44 PM Revision a282f7e1 (ceph): Merge pull request #3142 from ceph/wip-10220
- mon: suspend proposing paxos values when flushing pending writes
Reviewed-by: Sage Weil <sage@redhat.com> - 06:40 PM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- This is caused by the same problem that caused #10308
- 12:04 PM devops Bug #10310: Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- In RHEL 6.7 and RHEL 7.1, the librados and librbd packages (specifically version 0.80.7) are included in the RHEL Bas...
- 06:40 PM devops Bug #10309 (Duplicate): "Error: Nothing to do" in rados-dumpling-distro-basic-magna run
- This is caused by the same problem that caused #10308
- 06:38 PM devops Bug #10308: "FATAL: Chef::Exceptions::ChildConvergeError" in upgrade:dumpling-x-firefly-distro-ba...
- This should be fixed by cleanup that I did on the octo lab machines.
- 06:18 PM Revision 1396e55d (ceph): Merge pull request #3182 from ceph/wip-9405
- librbd: fixed garbage output from test LibRBD.TestIOPP
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:44 PM Revision 394fd4c2 (ceph): librbd: fixed garbage output from test LibRBD.TestIOPP
- buffer::list::c_str does not actually provide a C-style, NULL
terminated string. As a result, its use for console ou... - 05:37 PM Revision 3b5ff219 (ceph): Merge pull request #3161 from anandgbhat/wip-jemalloc
- jemalloc-support: Added --with-jemalloc configure option
Reviewed-by: Sage Weil <sage@redhat.com> - 05:20 PM Revision 0b8512eb (ceph): Merge pull request #3180 from ktdreyer/doc-corpus-spelling
- doc: fix spelling in corpus page
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:07 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- btw it's the combination of pool snapshots and rgw that triggers this, which is why almost nobody else has seen it (i...
- 05:06 PM Bug #10262 (Fix Under Review): osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- 01:18 PM Bug #10262 (In Progress): osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- 04:57 PM devops Feature #10046: run make check on every pull request
- https://github.com/ceph/ceph-build/pull/39
- 01:15 PM devops Feature #10046: run make check on every pull request
- slave is gitbuilder-cdep-rpm-cloud-fedora20-amd64-basic.cloud.sepia.ceph.com
- 01:07 PM devops Feature #10046: run make check on every pull request
- http://jenkins.ceph.com/job/ceph-pull-requests/
- 04:49 PM Revision 18534615 (ceph): mon: Paxos: reset accept timeout before submiting work to the store
- Otherwise we may trigger the timeout while waiting for the work to be
committed to the store -- and it would only tak... - 04:36 PM Revision 639096d9 (ceph): Merge pull request #3146 from ceph/wip-9323
- mon: allow full flag to be manually cleared
Reviewed-by: Joao Eduardo Luis <joao@redhat.com> - 04:18 PM Revision d28c8e0f (ceph): mon/PGMap and PGMonitor: update last_epoch_clean cache from new osd keys
- We were only invalidating the cached value from apply_incremental, which
is no longer called on modern clusters.
Fix... - 04:18 PM Revision 7646f239 (ceph): mon/PGMap: invalidate cached min_last_epoch_clean from new-style pg keys
- We were only invalidating the cache from the legacy apply_incremental(),
which is no longer called on modern clusters... - 04:14 PM RADOS Feature #6114: Complete python binding interfaces for librados
- One of the most useful missing parts is multi-operation requests, which includes omap operations as well.
- 03:05 PM Revision b5381c22 (ceph): ReplicatedPG: Make pull and push op use sparse read
- If user enable fiemap feature in osd side, there exists three ways to make
read/write sprase:
1. normal sparse read/... - 02:57 PM Revision 31adfeb0 (ceph): doc: fix spelling in corpus page
- Signed-off-by: Ken Dreyer <kdreyer@redhat.com>
- 02:33 PM rgw Feature #10322 (Resolved): rgw: s3-tests, coverage for object versioning
- Some work has already been done (wip-rgw-object-versioning). Need to see if anything is missing, extend tests if needed.
- 02:30 PM rgw Feature #10321 (New): rgw: verify proper tests coverage for bucket sharding
- 02:29 PM rgw Feature #10320 (New): rgw: ability to configure bucket sharding params in rgw teuthology test suite
- 02:29 PM Messengers Bug #5508: msg/SimpleMessenger.cc: 230: FAILED assert(!cleared)
- http://magna002.ceph.redhat.com/teuthology-2014-12-14_19:35:01-kcephfs-giant-testing-basic-magna/4344/
(Unfortunat... - 12:40 PM rgw Bug #10268: s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3CreateError not ra...
- And the last one is correct too, using a valid Key ID but a wrong access_key on S3:...
- 11:45 AM rgw Bug #10268: s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3CreateError not ra...
- The second failure I can confirm it is a problem with RGW, it should return 'InvalidAccessKeyId':...
- 07:44 AM rgw Bug #10268 (In Progress): s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3Crea...
- Reverted first test. S3 docs state a duality in behavior depending on US Standard vs Regions and we support the forme...
- 12:15 PM Revision 7e840341 (ceph): os: free space tracking for MemStore
- Allow users to set an artificial upper bound
on size of the memstore OSD, and report actual
usage information in fsst... - 12:15 PM Revision 12808b9e (ceph): osdc/Objecter: respect honor_osdmap_full setting
- With this, it no longer needs to special case the MDS,
as the MDS can just call unset_honor_osdmap_full.
Signed-off-... - 10:22 AM Revision aa546408 (ceph): tests: shell functions toolbox dedicated to testing
- The osd/osd-test-helpers.sh mon/mon-test-helpers.sh are useful to create
shell based functional tests. Since they wer... - 10:22 AM Revision e8d33998 (ceph): tests: convert osd-scrub-repair to ceph_objectstore_tool
- http://tracker.ceph.com/issues/10201 Fixes: #10201
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 10:08 AM devops Bug #10200: tgtd error: undefined symbol: rbd_discard
- tgt_1.0.38-48.*.ceph_amd64.deb packages need a dependency on librbd1 >= v0.46 since that is when the rbd_discard meth...
- 09:44 AM rbd Bug #9405 (Fix Under Review): rbd/test_librbd.sh outputs garbage
- 09:43 AM rbd Bug #10299 (Fix Under Review): "ObjectCacher.cc: 530: FAILED assert(i->empty())" in rbd-firefly-d...
- 09:38 AM rbd Bug #6494: High memory consumption of qemu/librbd with enabled cache
- Hi Sage,
Is this fix already released in FireFly 0.80.7 ? I've been checking the release notes of 80.6 and 80.7 an... - 09:26 AM Revision 7ccd5eec (ceph): crush/CrushWrapper: fix _search_item_exists
- Reported-by: Pawel Sadowski <ceph@sadziu.pl>
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit ee... - 09:26 AM Revision cee51af9 (ceph): crush/builder: prevent bucket weight underflow on item removal
- It is possible to set a bucket weight that is not the sum of the item
weights if you manually modify/build the CRUSH ... - 09:26 AM Revision 465eedea (ceph): crush/CrushWrapper: fix create_or_move_item when name exists but item d...
- We were using item_exists(), which simply checks if we have a name defined
for the item. Instead, use _search_item_e... - 09:16 AM Revision a58385a8 (ceph): Merge pull request #3075 from theanalyst/doc/v0.89/mailmap
- mailmap updates
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:34 AM Feature #9323 (Resolved): osdmonitor: allow users to set/clear cluster state flags (CEPH_OSDMAP_F...
- 08:23 AM Feature #9440 (In Progress): mon: log all changes to health in the central log
- 06:48 AM CephFS Feature #9883 (In Progress): journal-tool: smarter scavenge (conditionally update dir objects)
- 05:52 AM Revision 6d683d10 (ceph): mailmap: Sandon Van Ness name normalization
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:52 AM Revision b0e88a02 (ceph): mailmap: Lei Dong affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:52 AM Revision f0961ae9 (ceph): mailmap: Blaine Gardner affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:52 AM Revision 973e9f75 (ceph): jemalloc-support: Added --with-jemalloc configure option
- If --with-jemalloc option is not specified, then it defaults to tcmalloc.
If --with-jemalloc is specified, then --wi... - 05:52 AM Revision ad205511 (ceph): mailmap: Chendi Xue name normalization
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
Conflicts:
.mailmap - 05:50 AM Revision 41707ee0 (ceph): mailmap: Nilamdyuti Goswami affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision cc055181 (ceph): mailmap: Adam Spiers affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision e90818fd (ceph): mailmap: Dan Mick name normalization
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision 1fd074d2 (ceph): mailmap: Karl Eichwalder affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision 5d973846 (ceph): mailmap: Xinze Chi affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision c40176ee (ceph): mailmap: Michal Jarzabek affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision a3dd8b0b (ceph): mailmap: Kefu Chai affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision d048ec90 (ceph): mailmap: Dongmao Zhang affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:50 AM Revision 04ab4099 (ceph): mailmap: Ding Dinghua affiliation
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:31 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Any idea ?
- 05:29 AM Bug #10306 (Rejected): EC pool pgs stuck active+undersized+degraded with invalid osds in acting set
- 2147483647 means that there were not enough OSDs to map the PG. Although you have exactly 9 hosts and the rule expect...
- 05:23 AM Bug #9384: OSD is crashing while io is running and querying withadmin socket
- We're running 0.80.7-1trusty and I observed the exact same trace in the log of the crashed OSD.
I tried to figure o... - 05:20 AM Fix #9566 (In Progress): osd: prioritize recovery of OSDs with most work to do
- 05:18 AM Bug #9810 (Duplicate): dout_emergency is silenced in ceph-osd
- http://tracker.ceph.com/issues/10113
- 05:17 AM Bug #10199 (Resolved): ceph --format xml daemon {daemon}.{id} config get is not valid XML
- 05:16 AM Bug #10197 (Resolved): arch detection on armv8 must check asimd
- 05:15 AM Bug #9785 (Resolved): /etc/ceph/dmcrypt-keys and key contents are created world-readable
- 05:14 AM Fix #10264 (Resolved): docker-test-helper fails on detached head
- 03:40 AM Bug #10216 (Fix Under Review): gf-complete and jerasure call exit(1)
- https://github.com/ceph/jerasure/pull/2
- 02:38 AM Bug #10282 (Fix Under Review): gf-complete: missing .gitignore entry for .dirstamp
- https://github.com/ceph/gf-complete/pull/3
- 02:17 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- Thanks for explaining, that makes me slightly less worried about the reliability of the partition/udev notification c...
- 01:47 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- For OSD devices (one dev -- one OSD), I haven't observed any problems, regardless of load. (In this case, the OSD pro...
- 01:36 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- Ok. Have you ever seen a problem under load where udev would fail to notice the creation / removal of a partition alt...
- 01:23 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- Loic Dachary wrote:
> I'm under the impression (although I've never actually tried to prove it) that the udev event... - 01:11 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- Dan van der Ster wrote:
> Instead we tried changing the guid of the journal partition, but that doesn't trigger ud... - 12:55 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- Hi Loic,
In this case, ceph-disk zap doesn't apply. The use-case is that you have say 4-5 partitions on a shared jou... - 01:26 AM Bug #9998 (Fix Under Review): Replaced OSD weight below 0
- * giant backport https://github.com/ceph/ceph/pull/3178
* firefly backport https://github.com/ceph/ceph/pull/3179
- 01:03 AM Bug #10318 (Won't Fix): local deep scrub messsages
- Following issue #10317 the deep-scrub messages were only present in the primary OSD for that PG. It would help if the...
- 01:01 AM Bug #10317 (Can't reproduce): pg repair doesn't fix missing attr
- I have a size 4 replicated pool and got theses messages in the primary OSD for a PG:
2014-12-10 09:38:09.348110 7f8f... - 12:51 AM rgw Bug #10311 (Fix Under Review): Object is deleted automatically if conditional PUT returns 412
- Sent out the PR for fix: https://github.com/ceph/ceph/pull/3176
Also committed some functional test cases in: http... - 12:21 AM rgw Documentation #10305: Update documentation on http://ceph.com/docs/master/radosgw/keystone/
- In addition, this issue was pretty cryptic to debug (...a pun... I know) and it would have been pretty straightforwar...
12/14/2014
- 11:58 PM CephFS Bug #10316 (Won't Fix): pool quota no offect for cephfs client
- ceph version:0.87
ceph cluster os:redhat 6
mds num: 1
step:
(1) set pool 'data' max-byte limit is 1G
[root... - 11:47 PM CephFS Bug #10315 (Resolved): set last snapid according to removed snaps in data pools
- handle the case that we create cephfs using existing pools and the existing pools' removed snaps are not empty.
- 10:51 PM Bug #10314 (Duplicate): use a new disk as journal disk,ceph-disk prepare execute fail
- ceph version:0.87
os:redhat 7.0
use a new disk, has not partion, as journal disk, ceph-disk prepare fail
[roo... - 09:38 PM Linux kernel client Bug #10313 (Need More Info): IO drop outs/timeouts on one of the rbd client
Seeing IO drop outs/timeouts in one of the rbd clients:
Setup details:
OS : ubuntu 14.04 LTS
kernel: 3.13...- 07:36 PM Revision 38867340 (ceph): ceph_test_rados_api_io: fix new test
- From 0c802e11d9f0ee993994d391d1e00aeb76965d6a.
Signed-off-by: Sage Weil <sage@redhat.com> - 07:24 PM CephFS Bug #10312 (Resolved): creating snapshot makes parent snapshot lost
- [root@zhyan-kvm1 testdir]# mkdir dir1
[root@zhyan-kvm1 testdir]# cd dir1
[root@zhyan-kvm1 dir1]# mkdir dir2
[root@... - 06:59 PM rgw Bug #10311 (Resolved): Object is deleted automatically if conditional PUT returns 412
- After back-porting conditional PUT feature, test shows object will be deleted automatically if conditional PUT return...
- 05:44 PM Revision bd9be5fd (ceph): Merge pull request #265 from ceph/wip-test-huge-tickets
- krbd: add huge_tickets workunit
- 05:44 PM Revision ee108968 (ceph): Merge pull request #3175 from ceph/wip-test-huge-tickets
- qa: add script to test how libceph handles huge auth tickets
Reviewed-by: Sage Weil <sage@redhat.com> - 11:46 AM Bug #9916: osd: crash in check_ops_in_flight
- 11:45 AM Bug #9916: osd: crash in check_ops_in_flight
- just saw this on another cluster:...
- 10:53 AM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- It happened again today. I had a mix of slow OSDs being marked down, and OSDs throwing this assertion.
I ran `cep... - 10:37 AM Revision 98f750b4 (ceph): krbd: add huge_tickets workunit
- Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
- 09:09 AM Feature #9962 (Resolved): osd: kill 'category' in stats and public API
- 06:09 AM Revision af76f781 (ceph): Merge pull request #3174 from dachary/wip-warning
- tests: fix signedness compilation warnings
- 05:51 AM Revision e3ba3d22 (ceph): ceph_test_rados_api_watch_notify: use 5 min timeout for notifies
- This should make them tolerate thrashing.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:40 AM Revision a2572c38 (ceph): ceph_test_stress_watch: do not unwatch if watch failed
- Signed-off-by: Sage Weil <sage@redhat.com>
12/13/2014
- 11:52 PM Revision 4b9b0417 (ceph): Merge pull request #2986 from ceph/wip-9998
- crush: fix weight underfloat issue
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:49 PM Revision 35f084d0 (ceph): qa: add script to test how libceph handles huge auth tickets
- Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
- 05:22 PM Revision b9ddb833 (ceph): Merge pull request #3112 from xiaoxichen/cleanup_getheader
- Cleanup:Use get_type()instead of get_header().type
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:55 PM Revision e7d434b5 (ceph): tests: fix signedness compilation warnings
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 04:42 PM Revision 71068018 (ceph): Merge pull request #3172 from dachary/wip-10146-retrigger-udev
- ceph-disk: test re-using an existing journal partition
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:06 PM Revision 847e5e10 (ceph): osd: check that source OSD is valid for MOSDRepScrub
- Make sure the message we got from the peer OSD is valid. Specifically,
this avoids a race like this:
- A marks down... - 04:03 PM Revision 09c1648b (ceph): osd: drop redundant check in handle_replica_op
- This is what require_self_aliveness checks.
Signed-off-by: Sage Weil <sage@redhat.com> - 04:03 PM Revision 707a111d (ceph): osd: pass Message* to most require_* helpers
- These do nothing but op->get_req(); pass the Message* explicitly so that
non-OpRequest callers can use them.
Signed-... - 03:50 PM Bug #9998 (Pending Backport): Replaced OSD weight below 0
- 03:44 PM Revision b6401c10 (ceph): ceph-disk: LOG.info instead of print
- When a non fatal error happens with parted, use LOG.info to display it
instead of print.
Signed-off-by: Loic Dachary... - 03:20 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Hi Craig, can you upload the logs to cephdrop? can email you the credentials if you don't have them yet. Thanks!
- 02:50 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- I'm not (yet) having an outage, but I have had three different crashes in an hour. They all match this assert and st...
- 02:01 PM Revision 29eb1350 (ceph): ceph-disk: don't change the journal partition uuid
- We observe that the new /dev/disk/by-partuuid/<journal_uuid>
symlink is not always created by udev when reusing a jou... - 02:01 PM Revision 0e4cb57b (ceph): ceph-disk: fix get_partition_uuid for loop/cciss
- Loopback and cciss devices have an extra 'p' before the partition
number. Add exceptional handling of these devices.
... - 02:01 PM Revision e0f052a1 (ceph): ceph-disk: test re-using an existing journal partition
- Add a ceph-disk test to first setup an OSD with a separate journal
block device, then tear down the OSD (simulating a... - 02:01 PM Revision b9ddf97a (ceph): documentation: simplify running make check
- Encapsulate the compilation steps (install dependencies, autogen.sh,
configure, make check) in the run-make-check.sh ... - 01:43 PM Revision 35e4f425 (ceph): tests: install parted in centos container
- Because ceph-disk depends on it.
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 12:48 PM Fix #9566 (Fix Under Review): osd: prioritize recovery of OSDs with most work to do
- 01:46 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- ...
- 11:18 AM Revision 85ab278a (ceph): tests: install hdparm in containers
- The ceph-disk tests use hdparm, install it in containers that run
them.
Signed-off-by: Loic Dachary <ldachary@redhat... - 11:18 AM Revision 60bca677 (ceph): tests: update centos docker file to epel 7.5
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 11:17 AM Revision e038b126 (ceph): tests: docker tests only need a workdir, not a clone
- Instead of cloning the repository, create a work directory that has
symbolic links to the original .git, using
https... - 10:29 AM devops Bug #10310 (Resolved): Error "'sudo yum install ceph-devel-0.XXX -y'" across nighties runs
- In Octo lab several jobs failed.
Logs are in http://magna002.ceph.redhat.com/teuthology-2014-12-13_12:33:46-rados-... - 09:47 AM devops Bug #10309 (Duplicate): "Error: Nothing to do" in rados-dumpling-distro-basic-magna run
- Several jobs fail in run http://pulpito.ceph.redhat.com/teuthology-2014-12-13_12:33:46-rados-dumpling-distro-basic-ma...
- 09:41 AM Revision 53929ba1 (ceph): librbd: gracefully handle deleted/renamed pools
- snap_unprotect and list_children both attempt to scan all
pools. If a pool is deleted or renamed during the scan,
th... - 09:37 AM Revision f79b7fe4 (ceph): librados: Added new API methods to create an ioctx by pool id
- A new pool_list method includes the unique pool id for all pools.
This pool id can be used with the new rados_ioctx_c... - 09:26 AM devops Bug #10308: "FATAL: Chef::Exceptions::ChildConvergeError" in upgrade:dumpling-x-firefly-distro-ba...
- Same issue in - http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-12_15:07:54-upgrade:firefly-x-giant-distro-bas...
- 09:18 AM devops Bug #10308 (Resolved): "FATAL: Chef::Exceptions::ChildConvergeError" in upgrade:dumpling-x-firefl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-12_19:13:02-upgrade:dumpling-x-firefly-distro-basi...
- 09:10 AM Documentation #10265 (Resolved): building from source should be a onliner
- 08:08 AM Bug #9555 (Fix Under Review): msg/Pipe.cc: 1513: FAILED assert(0 == "old msgs despite reconnect_s...
- 07:58 AM Bug #9555 (In Progress): msg/Pipe.cc: 1513: FAILED assert(0 == "old msgs despite reconnect_seq fe...
- ubuntu@teuthology:/a/teuthology-2014-12-12_02:32:02-rados-giant-distro-basic-multi/651682
- 02:56 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- I think what happens is the following sequence
* partition 1 is created
* partprobe called so the kernel notices ... - 01:48 AM Bug #10146: ceph-disk: sometimes the journal symlink is not created
- I'm able to reproduce that frequently by running ...
- 01:15 AM Revision 5cf193c8 (ceph): rgw: use s->bucket_attrs instead of trying to read obj attrs
- Fixes: #10307
Backport: firefly, giant
This is needed, since we can't really read the bucket attrs by trying to
read... - 01:00 AM Revision f773c749 (ceph): rgw: cannot modify swift bucket policy
- When trying to set a policy on the bucket, fail unless policy matches
current placement rule.
Signed-off-by: Yehuda ... - 12:42 AM Revision de29fada (ceph): Merge pull request #3126 from ceph/wip-cleanup-removal
- osd: Remove dead code related to old pg removal mechanism
Reviewed-by: Samuel Just <sjust@redhat.com>
12/12/2014
- 10:29 PM Revision 07dc42a6 (ceph): rgw: dump X-Storage-Policy header on bucket HEAD
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:20 PM Revision f16da1cb (ceph): rgw: compare placement target on bucket recreation
- and return -EEXIST (409) if requested a mismatching placement target.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:11 PM Revision c55d7da4 (ceph): librados: remove IoCtxImpl lock member
- It is dead!
Signed-off-by: Sage Weil <sage@redhat.com> - 10:11 PM Revision c598e633 (ceph): librados: stop using IoCtxImpl lock for watch/notify functions
- This is a carry-over from olden times when Objecter didn't do its own
locking.
Signed-off-by: Sage Weil <sage@redhat... - 09:53 PM Revision 90246c17 (ceph): osdc/Objecter: only ping after watch is registered
- If we ping before the watch is registered we will get ETIMEDOUT (the ping
is are a read op that will fail to see the ... - 09:18 PM Revision 50e9e398 (ceph): librados: do not overload C++ API methods with new signatures
- Bah! C++ sucks for libraries.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:09 PM Revision cf2113eb (ceph): Merge remote-tracking branch 'gh/master' into wip-librados-fadvise
- Conflicts:
src/test/librbd/test_librbd.cc - 08:57 PM Revision ffd6c7e4 (ceph): doc: Adds man page for ceph under man/.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 08:54 PM Revision 76da87a6 (ceph): doc: Adds man page for ceph.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 07:20 PM Revision 7409ab3d (ceph): rgw: http headers need to end with \r\n
- Fixes: #9254
Backport: firefly, giant
Reported-by: Benedikt Fraunhofer <fraunhofer@traced.net>
Signed-off-by: Yehuda... - 07:08 PM Revision 08013616 (ceph): mon/OSDMonitor: dump inc and full maps we get a crc mismatch
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM Revision d8986980 (ceph): osd: verify our OSDMap encoding based on crc
- When we generate a full map and can't replicate teh expected CRC, request
the full map from the mon.
Note that we sh... - 07:08 PM Revision 32a837dd (ceph): osd: add osd_inject_bad_map_crc_probability option
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM Revision 8a674da7 (ceph): osdmaptool: allow OSDMap encode
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM Revision b1f13815 (ceph): ceph-dencoder: mark OSDMap as featureful, but with stray data
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:08 PM Revision f31135c1 (ceph): mon/OSDMonitor: do not reencode OSDMap on 'osd getmap'
- Return the bits unmolested.
This is a slight change in that we do not reencode based on the client's
features. Howe... - 07:08 PM Revision 716f90f3 (ceph): mon/OSDMonitor: verify full_crc when available
- Crash if it is wrong. The monitors should *always* agree.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:47 PM Revision d818a24e (ceph): Merge pull request #3141 from ceph/wip-librbd-test-cleanup
- tests: Minor cleanup to librbd test
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:41 PM Revision d8600c06 (ceph): Merge pull request #3160 from xylv/wip-8562-rebase
- rgw: Conditional PUT on ETag
Reviewed-by: Yehuda Sadeh <yehuda@rehat.com> - 05:35 PM rbd Bug #10270 (Fix Under Review): "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-dist...
- 05:04 PM rgw Bug #10307 (Fix Under Review): rgw: setting bucket attributes (swift POST on bucket) sometimes fail
- 04:53 PM rgw Bug #10307 (Resolved): rgw: setting bucket attributes (swift POST on bucket) sometimes fail
- Issue related to the way we read the bucket attributes.
- 02:37 PM Bug #10259 (Pending Backport): mon health stuck with phantom hung requests
- 02:37 PM Bug #10157 (Pending Backport): PGLog::(read|write)_log don't write out rollback_info_trimmed_to
- 02:37 PM Bug #10150 (Pending Backport): osd/ReplicatedPG.cc: 10853: FAILED assert(r >= 0) (in _scan_range)
- 02:24 PM Bug #8011 (Pending Backport): osd/ReplicatedPG.cc: 5244: FAILED assert(soid < scrubber.start || s...
- 02:24 PM Bug #10059 (Pending Backport): osd/ECBackend.cc: 876: FAILED assert(0)
- 02:22 PM Revision cc382d10 (ceph): Merge remote-tracking branch 'gh/next'
- 02:21 PM Revision e21071b2 (ceph): Merge pull request #3153 from ceph/wip-10296
- osd: fix block device discard detection
Reviewed-by: Loic Dachary <loic@dachary.org>
Tested-by: Jianpeng Ma <jianpen... - 02:19 PM Revision b1ab685e (ceph): Merge pull request #3124 from ceph/wip-10194-firefly
- rgw: optionally call FCGX_Free() on the fcgi connection
Reviewed-by: Sage Weil <sage@redhat.com> - 01:25 PM Revision 5fc7a0be (ceph): rgw: change multipart upload id magic
- Fixes: #10271
Backport: firefly, giant
Some clients can't sign requests correctly with the original magic
prefix.
R... - 11:47 AM rgw Bug #9254: rgw: civetweb requires explicit \r\n for http headers
- opened a new pull request:
https://github.com/ceph/ceph/pull/3163 - 11:35 AM rgw Bug #10066 (Fix Under Review): rgw: failed md5sum on s3tests-test-readwrite
- PR opened: https://github.com/ceph/s3-tests/pull/26
- 11:19 AM Bug #10220 (In Progress): "mon/Paxos.cc: 1033: FAILED assert(mon->is_leader())" in upgrade:dumpli...
- anotated mon log
- 10:43 AM rgw Feature #8562 (Resolved): rgw: Conditional PUT on ETag
- Merged, commit:7925b82c20c94043dd5e4ca69d3ef55ea43db1e0.
Tests commit:3e1e2ee43893264eb9ca2a3fbc581ebe46c06d0e - 10:37 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- * Amend the current patch so that priorities are calculated depending on which osd the pg belong to, not the total re...
- 06:35 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- It is probably best to decide which PG should be granted the next slot in the {local,remote}_reserver whenever a slot...
- 02:13 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- ...
- 08:48 AM Revision 421c0a28 (ceph): Merge pull request #3144 from ceph/wip-aarch64
- fixes for aarch64
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Haomai Wang <haomaiwang@gmail.com> - 08:31 AM Revision 7925b82c (ceph): rgw: Conditional PUT on ETag
- Fixes: #8562
Signed-off-by: Ray Lv <raylv@yahoo-inc.com> - 07:29 AM Bug #10306: EC pool pgs stuck active+undersized+degraded with invalid osds in acting set
- It was brought to my attention that that large number is probably a signed 32 bit -1, printed unsigned. Maybe this is...
- 07:18 AM Bug #10306: EC pool pgs stuck active+undersized+degraded with invalid osds in acting set
- I tried making a pool with 4 and 4 and it had 1 pg get stuck this way.
- 07:08 AM Bug #10306 (Rejected): EC pool pgs stuck active+undersized+degraded with invalid osds in acting set
- Ceph version: 0.87 (c51c8f9d80fa4e0168aa52685b8de40e42758578)
Osd Hosts: 9
Osds: 575
EC profile:
directory=/usr/l... - 06:38 AM Revision 023927bc (ceph): ReplicatedPG: For MAPEXT, using bl.length() instead of op.extent.length...
- For fiemap, it don't real read the data(offset,length). It only fetech the infos of
extents. So don't use length as n... - 06:38 AM Revision c1dc3619 (ceph): ReplicatedPG: Don't use the return value of getattr_maybe_cache as attr...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision c9d15b0a (ceph): FileStore: Implement fadvise handle for read-operation.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision bf156e53 (ceph): test/librbd: Add test case for librbd function which can handle fadvise...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 0c802e11 (ceph): test/librados: Add test case for librados function which can handle fad...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 7b11c47b (ceph): librbd: Add m_op_flags in AioRead to track op flags for rbd read.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 847d9889 (ceph): librbd: Add set_op_flags in AioWrite to set op_flags for rbd write.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 5896f997 (ceph): librbd: add new read/write api for librbd C interface which handle op
- flags.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 06:23 AM Revision d2b01520 (ceph): librbd: add new read/write api for librbd C++ interface which handle op...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision d3ce0d6c (ceph): librbd: increment version for new functions rbd_read2/write2,rbd_aio_re...
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 7853f8d0 (ceph): osd: print OSDOp flags
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 2dedf31c (ceph): ObjectStore: Modify read function can handle fadvise flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision fc639b19 (ceph): PGBackend: Make objects_read_sync can handle fadvise flags
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision edaacf95 (ceph): encoding: Add type boost::tuple<A,B,C> encoding/decode func.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 9b1f3478 (ceph): types: Add operator<< for type boost::tuple<A, B, C>.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision a7274701 (ceph): include: Remove unused code: class triple.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 5f92d825 (ceph): osd: Make async-read can handle fadvise flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 8acc9321 (ceph): PGTransaction: Modify append/write function can handle fadvise flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 37528648 (ceph): ObjectStore/Transaction: Add fadvise_flags to track write fadvise flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 4f129748 (ceph): ECBackend: Make parity data don't cache.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision f5abed7a (ceph): librados.h: Add read/write op fadvise flags LIBRADOS_OP_FLAG_FADVISE_*.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision 5b544101 (ceph): librados: Add read/write fadvise op flags in ObjectOperationFlags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision b35cb48f (ceph): librados: Add read/write fadvise op flags CEPH_OSD_OP_FLAG_FADVISE_*.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:23 AM Revision c5ed33d3 (ceph): librados/ObjectOperation: add new function set_op_flags2
- After adding four read/write fadvise flags OP_FADVISE_*, those flags
can set multi flags at the same time. For compat... - 06:23 AM Revision da862e2b (ceph): librbd/internal: Modify read/write api to handle op flags.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:20 AM Bug #10296 (Resolved): OSD crashes if device name does not start with sd
- 04:58 AM Revision e8e27a81 (ceph): unittest_blkdev: test an abbreviated /sys/block dir
- Note that we assume unittest_blkdev is run from the current directory (or
rather that test/common/test_blkdev_sys_blo... - 01:03 AM Revision 6ec14b07 (ceph): Merge pull request #3159 from ceph/wip-10229-giant
- osdc/Filer: use finisher to execute C_Probe and C_PurgeRange [giant backport]
Reviewed-by: Greg Farnum <gfarnum@redh... - 12:42 AM rgw Documentation #10305: Update documentation on http://ceph.com/docs/master/radosgw/keystone/
- Unassigning myself because I'm not the best candidate ;-)
12/11/2014
- 11:33 PM rgw Documentation #10305 (Closed): Update documentation on http://ceph.com/docs/master/radosgw/keystone/
- Hi,
In the URL http://ceph.com/docs/master/radosgw/keystone/, where it mentions about converting the OpenSSL certi... - 10:49 PM Revision 7bbf80ff (ceph): osdc/Filer: use finisher to execute C_Probe and C_PurgeRange
- Currently contexts C_Probe/C_PurgeRange are executed while holding
OSDSession::completion_lock. C_Probe and C_PurgeRa... - 09:46 PM Revision 5e454a8e (ceph): common/blkdev: add simple sandboxing function for testing
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:42 PM Revision cfa54bbb (ceph): Merge pull request #3155 from athanatos/wip-8011
- ReplicatedPG: fail a non-blocking flush if the object is being scrubbed
Reviewed-by: Sage Weil <sage@redhat.com> - 09:30 PM Revision 9b26de3f (ceph): ReplicatedPG: fail a non-blocking flush if the object is being scrubbed
- Fixes: #8011
Backport: firefly, giant
Signed-off-by: Samuel Just <sjust@redhat.com> - 09:28 PM Revision 9a04e751 (ceph): Merge pull request #3154 from athanatos/wip-10059
- Wip 10059
Reviewed-by: Sage Weil <sage@redhat.com> - 09:23 PM Revision 69507e51 (ceph): Merge pull request #3156 from athanatos/wip-10150
- ReplicatedPG::scan_range: an object can disappear between the list and t...
Reviewed-by: Sage Weil <sage@redhat.com> - 09:22 PM Revision f6a02697 (ceph): Merge pull request #3157 from athanatos/wip-10157
- PGLog: include rollback_info_trimmed_to in (read|write)_log
Reviewed-by: Sage Weil <sage@redhat.com> - 09:16 PM Revision 2667eed9 (ceph): Merge pull request #3158 from athanatos/wip-10259
- osd_types: op_queue_age_hist and fs_perf_stat should be in osd_stat_t::o...
Reviewed-by: Sage Weil <sage@redhat.com> - 09:05 PM Revision dce6f288 (ceph): ReplicatedPG::scan_range: an object can disappear between the list and ...
- The first item in the range is often last_backfill, upon which writes
can be occuring. It's trimmed off on the prima... - 09:02 PM Revision 449d7d47 (ceph): Merge pull request #2579 from yuandong1222/cache-hboject-filestore
- Cache hobject filestore_key to avoid massive _reverse_nibbles calls
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:00 PM Revision b03fc614 (ceph): Merge pull request #3018 from tchaikov/wip-fix-safe_read_file
- safe_io: do not set ending \0 in safe_read_file()
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Loic Dach... - 08:59 PM Revision 81af4753 (ceph): Merge pull request #3070 from ceph/wip-10080
- SimpleMessenger: allow RESETSESSION whenever we forget an endpoint
Reviewed-by: Sage Weil <sage@redhat.com> - 07:03 PM Revision 61102203 (ceph): debian: enable libgoogle-perftools-dev on arm64
- These binaries haven't landed in Ubuntu, but they are in
sid and jessie for arm64. On Saucy I've installed them by
ha... - 06:47 PM Revision 758d9cf3 (ceph): Merge pull request #3151 from ceph/wip-10288-giant
- mon: fix `fs ls` on peons [giant backport]
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:47 PM Revision a09a87ad (ceph): Merge pull request #3150 from ceph/wip-10288
- mon: fix `fs ls` on peons
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:18 PM Revision 25e37837 (ceph): common/blkdev: get_block_device_base
- And a test. Ideally the test would get run on a machine with weirdo
devices like /dev/cciss/c0d1.
This mirrors the ... - 06:18 PM Revision 2246dca0 (ceph): common/blkdev: fix block device discard check
- - fix base name calculation (do not assume sda)
- reverse sense of check (it was returning false when true before?)
-... - 06:15 PM Revision c64b3c53 (ceph): Merge pull request #3152 from dachary/wip-10296-journal-discard
- os: do not attempt to detect discard by default
Reviewed-by: Sage Weil <sage@redhat.com> - 05:49 PM Revision beaa04e4 (ceph): mon: MonitorDBStore: allow randomly injecting random delays on writes
- Adds two new config options:
mon_inject_transaction_delay_probability : DOUBLE (0.0-1.0, default: 0.0)
mon_inject_tr... - 05:35 PM Revision 2ad55cd6 (ceph): tests: do not ignore ceph-disk.sh::test_activate_dev failure
- The status of the test commands must be tested instead of being
silently ignored.
Signed-off-by: Loic Dachary <ldach... - 05:35 PM Revision 9c5fd8c2 (ceph): os: do not attempt to detect discard by default
- If the journal_discard option is false, the journal should no try to
guess if the device has discard capabilities.
h... - 05:07 PM Revision 21e07eb6 (ceph): rgw: url decode http query params correctly
- Fixes: #10271
Backport: firefly
This got broken by the fix for #8702. Since we now only url_decode if
we're in query... - 02:57 PM Revision 008d788f (ceph): ceph_test_rados_api_watch_notify: print err to debug
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:57 PM Revision 531e8bb7 (ceph): ceph_test_rados_api_watch_notify: use GT macro
- so we can see the value
Signed-off-by: Sage Weil <sage@redhat.com> - 02:57 PM Revision 279c1999 (ceph): ceph_test_rados_api_watch_notify: fix a zillion warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:26 PM Revision c1dd92bd (ceph): osdc/Objecter: normalize watch error (ENOENT on delete)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:02 PM Revision 994dcbbe (ceph): mon: fix `fs ls` on peons
- This was incorrectly using pending_mdsmap instead
of mdsmap. We didn't notice in test because of
single-mon configur... - 02:00 PM Revision 5559e6ae (ceph): mon: fix `fs ls` on peons
- This was incorrectly using pending_mdsmap instead
of mdsmap. We didn't notice in test because of
single-mon configur... - 01:51 PM Messengers Bug #10080 (Pending Backport): Pipe::connect() cause osd crash when osd reconnect to its peer
- Merged to master in commit:81af47531822343bc39ced6e4d9bad72ac982439
I guess it should get backported at some point... - 01:44 PM rgw Bug #10303 (Can't reproduce): "..s3.test_list_multipart_upload ... FAIL" in upgrade:firefly:newer...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-10_17:00:02-upgrade:firefly:newer-firefly-distro-b...
- 01:40 PM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- The 'LibRBD.ListChildren' test failed because other tests running in the background (cls_rgw and cls_rbd) deleted the...
- 01:25 PM Revision 44a4f957 (ceph): Merge pull request #3149 from ceph/wip-typo
- mds: fix log typo
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:49 PM CephFS Bug #10302: "fsync-tester.sh: line 10: lsof: command not found"
- LSOF is definitely being installed on the machines but it appears to be a $PATH issue. Dan and I talked about this a ...
- 12:45 PM CephFS Bug #10302 (Resolved): "fsync-tester.sh: line 10: lsof: command not found"
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-09_13:44:11-powercycle-giant-distro-basic-multi/64...
- 12:47 PM rgw Bug #10301 (Resolved): "FATAL ERROR: cannot find a valid <xfs/xfs.h> header file" in powercycle-g...
- A commit was made to ceph-qa-chef to include xfsprogs-devel shortly after this test ran:
038fdda63d363b193b028495e... - 12:40 PM rgw Bug #10301 (Resolved): "FATAL ERROR: cannot find a valid <xfs/xfs.h> header file" in powercycle-g...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-09_13:44:11-powercycle-giant-distro-basic-multi/64...
- 12:40 PM Revision b025f56e (ceph): mds: fix log typo
- s/trvserse/traverse/
Signed-off-by: John Spray <john.spray@redhat.com> - 11:43 AM rbd Bug #10299: "ObjectCacher.cc: 530: FAILED assert(i->empty())" in rbd-firefly-distro-basic-multi run
- Based on that log it looks like the write (doing copy-up, and thus reading from the parent) was still in flight when ...
- 09:15 AM rbd Bug #10299 (Resolved): "ObjectCacher.cc: 530: FAILED assert(i->empty())" in rbd-firefly-distro-ba...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-09_23:00:03-rbd-firefly-distro-basic-multi/646076/...
- 11:26 AM devops Bug #10152: drop tiobench references
- This would also involve deleting the tiobench package from ceph-extras and removing all tiobench source code files fr...
- 11:19 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Ok. Then I guess the problem is to find which workload is walking all objects and complaining about "hinfo_key". In h...
- 11:16 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- Loic Dachary wrote:
> I'm not sure how that's possible. All objects in an erasure coded pool (3.59s0 shard shows it ... - 11:14 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- ...
- 11:12 AM Bug #10297: missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefly-x-next-dis...
- I'm not sure how that's possible. All objects in an erasure coded pool (3.59s0 shard shows it is one because of the t...
- 08:51 AM Bug #10297 (Duplicate): missing attr hinfo, error: "extra attr hinfo_key" error in upgrade:firefl...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-10_17:13:01-upgrade:firefly-x-next-distro-basic-mu...
- 10:54 AM CephFS Bug #10288 (Resolved): ceph fs ls fails to list newly created fs
- 06:02 AM CephFS Bug #10288 (Fix Under Review): ceph fs ls fails to list newly created fs
- https://github.com/ceph/ceph/pull/3150 (master)
https://github.com/ceph/ceph/pull/3151 (giant) - 10:53 AM Feature #10300 (New): Per-pool PG recovery prioritisation
- Sometimes, users would like to prioritise some pools over others during recovery.
For example, in Ceph FS it is mo... - 10:21 AM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Wenjun Huang wrote:
> I'm sorry, that I forgot use correct format before, so it omitted some character:
> [...]
Ju... - 10:11 AM Bug #10296 (Fix Under Review): OSD crashes if device name does not start with sd
- 09:39 AM Bug #10296: OSD crashes if device name does not start with sd
- workaround https://github.com/ceph/ceph/pull/3152 that bypasses the problem until a proper fix is committed
- 08:57 AM Bug #10296: OSD crashes if device name does not start with sd
- argh, i caught this in review but then forgot about it before merge. i think it needs to do all manner of weirdness ...
- 08:29 AM Bug #10296: OSD crashes if device name does not start with sd
- Original report https://github.com/ceph/ceph/pull/2955#issuecomment-66638515
- 08:27 AM Bug #10296 (Resolved): OSD crashes if device name does not start with sd
- http://workbench.dachary.org/ceph/ceph/blob/master/src/common/blkdev.cc#L31 will set p to NULL if sd does not show in...
- 08:18 AM rgw Bug #10295: rgw deleting S3 objects leaves __shadow_ objects behind
- Need to wait for gc to run its course. Not all entries are going to show in the gc listing immediately. You need to r...
- 05:55 AM rgw Bug #10295 (Resolved): rgw deleting S3 objects leaves __shadow_ objects behind
- Using 0.80.7, observed also on .87, .89
1. Create 100 objects 10MB ea in rgw.
2. Observe that .rgw.buckets occupi... - 05:35 AM Revision 11995b32 (ceph): Call Rados.shutdown() explicitly before exit
- This is mostly a demonstration of good behavior, as the resources will
be reclaimed on exit anyway.
Signed-off-by: D... - 05:35 AM Revision e00270b5 (ceph): rados.py: remove Rados.__del__(); it just causes problems
- Recent versions of Python contain a change to thread shutdown that
causes ceph to hang on exit; see http://bugs.pytho... - 05:30 AM Revision 319f9c93 (ceph): Call Rados.shutdown() explicitly before exit
- This is mostly a demonstration of good behavior, as the resources will
be reclaimed on exit anyway.
Signed-off-by: D... - 05:29 AM Revision ed8c9af3 (ceph): rados.py: remove Rados.__del__(); it just causes problems
- Recent versions of Python contain a change to thread shutdown that
causes ceph to hang on exit; see http://bugs.pytho... - 05:10 AM Revision 1dc064a8 (ceph): Merge pull request #3137 from thesues/fix-strtol
- Fix libstriprados::remove, use strtoll insdead of strtol
Reviewed-by: Sage Weil <sage@redhat.com> - 05:00 AM Revision a8f85dcc (ceph): mon: allow full flag to be manually cleared
- This is like a temporary measure as the mon will try to set them again,
but we have run into cases where the mon was ... - 04:39 AM Revision d562886f (ceph): Merge pull request #260 from ceph/wip-mds-readonly
- tasks: add test case for readonly MDS
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 04:39 AM Revision a1eb443e (ceph): Merge pull request #3038 from ceph/wip-mds-readonly
- Wip mds readonly
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 04:34 AM Revision 69c1f486 (ceph): Merge pull request #3145 from XinzeChi/wip-finisher
- Finisher: call cond signal if necessary in function queue
Reviewed-by: Sage Weil <sage@redhat.com> - 04:33 AM Revision 2e5ee308 (ceph): Finisher: call signal if necessary in function queue
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 04:05 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- The results above are the same with or without the priority patch (below is the tail wit the patch)....
- 02:47 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- With max_backfill = 3...
- 01:48 AM Revision d92e2caf (ceph): lttng: add int type definitions
- The normal path through #include <lttng/tracepoint.h> doesn't
appear to include int defintions like uint64_t that are... - 01:47 AM Revision 060cbaac (ceph): cycles: add reader for i386 and aarch64
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 01:41 AM Bug #10294 (Resolved): ceph-osd --mkfs segfaults when journal dev is a symlink
- Version: git master.
This happens when activating an OSD with ceph-disk normally (ceph-disk activate /dev/sdd1)
... - 12:13 AM Revision 370bb967 (ceph): Add unittests for safe sharing and make_shareable()
- Checks the following assertions:
1. a bufferlist shared with buffer::list::share yields shared
raw memory
2. a buff... - 12:13 AM Revision 6a45d757 (ceph): Add diagnostic unshareable buffer.
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 12:12 AM Revision 28725eb2 (ceph): Restore zero-copy buffers in OSD fast path.
- This change restores volatile sharing semantics in the Message
decode path, and also in the OSD write path for FileSt... - 12:12 AM Revision 5f551cc0 (ceph): Add safe-sharing to buffer::list and buffer::ptr.
- Formerly known as "strong claim," this change introduces a new
is_shareable() property to ceph::buffer::raw objects, ...
12/10/2014
- 11:32 PM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- When backfilling there are two possible situations that could be optimized with priorities:
* The longest(s) runni... - 02:14 PM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- The cluster was populated initially with ...
- 12:14 PM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- ...
- 10:23 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- Same as above with a max backfill set to 5:...
- 09:20 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- After a ...
- 08:47 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- In a cluster with 10 OSDs and a osd_max_backfills of 5, it is possible for the OSD with the most PGs to backfill to w...
- 05:09 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- When the busiest OSD becomes less busy, the priority of the reservations queued when it was more busy should be lower...
- 11:21 PM Revision d3f2ec34 (ceph): Merge pull request #3119 from ceph/wip-8797
- rados.py: remove Rados.__del__(); it just causes problems
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by:... - 11:09 PM Revision b038e8fb (ceph): Call Rados.shutdown() explicitly before exit
- This is mostly a demonstration of good behavior, as the resources will
be reclaimed on exit anyway.
Signed-off-by: D... - 10:07 PM Bug #10012: Configuration parameters not picked up outside of the [global] section.
- A Deis user confirmed this still happens on Giant. For him, the radosgw was only ever talking to the single monitor i...
- 09:19 PM Revision 5ba9b8f2 (ceph): rados.py: remove Rados.__del__(); it just causes problems
- Recent versions of Python contain a change to thread shutdown that
causes ceph to hang on exit; see http://bugs.pytho... - 09:14 PM Revision 616c46e5 (ceph): Merge pull request #3129 from ceph/wip-gfcomplete-dirty
- gf-complete: update submodule to newest upstream
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:00 PM Feature #9059: osd: store opportunistic whole-object checksum
- 01:33 PM Feature #9059 (In Progress): osd: store opportunistic whole-object checksum
- 09:00 PM Feature #9197: librados/osd: notify reply payload
- 09:00 PM Feature #9198: librados: notify callback includes gid of notifier
- 08:59 PM Feature #9323 (Fix Under Review): osdmonitor: allow users to set/clear cluster state flags (CEPH_...
- 07:04 PM Revision 24ca9f1c (ceph): Merge pull request #3071 from ceph/wip-10164
- mds: drop dirty dentries in deleted directory
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:46 PM Revision 8b195ecc (ceph): check endpoints is not empty before use it.
- Signed-off-by: VRan Liu <gliuwr@gmail.com>
(cherry picked from commit 9d5e4edc15678de675d7a77badcbace0b710d553) - 06:19 PM Revision 9b7a2f18 (ceph): Merge pull request #264 from ceph/wip-wn
- tasks/watch_notify_same_primary: fix test for new watch/notify
Reviewed-by: Samuel Just <sjust@redhat.com> - 06:14 PM Linux kernel client Bug #10208: libceph: intermittent hangs under memory pressure
- do nfs mount and cephfs mount on the same machine?
- 06:05 PM Revision 320c2560 (ceph): osdc/Objecter: only issue one error per watch; do it through one path
- Send all errors through C_DoWatchError for simplicity.
Only deliver one error per watch. This simplifies callers lo... - 06:01 PM Revision 78eed527 (ceph): ceph_test_rados_api_watch_notify: weak assert cookie is valid (it's a ptr)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:01 PM Revision 1e32e3bd (ceph): ceph_test_rados_api_watch_notify: wait longer for osd to time us out
- If cluster is thrashing this can fail.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:58 PM Bug #10250 (Closed): PG stuck incomplete after interrupted backfill.
- yay!
- 05:45 PM Bug #9285: osd: promoted object can get evicted before promotion completes
- Laurent: I'm skeptical this is the issue you are seeing. Can you capture an osd log (debug osd = 20, debug ms = 1) o...
- 02:42 AM Bug #9285: osd: promoted object can get evicted before promotion completes
- Hi,
Any news on this "high" priority bug?
Sincerely,
Laurent - 05:44 PM Revision 6f43c6c5 (ceph): osdc/Objecter: pass correct cookie value to error
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:20 PM rgw Bug #10188: Can not create new rgw user when specifying an email already assigned to a user
- Yehuda Sadeh wrote:
> That's by design. Users cannot share the same email, as S3 permissions can be granted by email... - 05:00 PM Revision b34e5452 (ceph): os/FileStore.cc: insert not empty list<Context*> to op_finisher/ondisk_...
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 04:39 PM Revision f02d2d72 (ceph): Merge pull request #3135 from XinzeChi/wip-3
- os/FileStore.cc: insert not empty list<Context*> to op_finisher/ondisk_finisher
Reviewed-by: Sage Weil <sage@redhat.... - 04:36 PM Revision 0f9192f2 (ceph): tasks/watch_notify_same_primary: fix test for new watch/notify
- It now checks for 'notify1' and 'notify2' strings, allowing it to work
on both old and new versions of rados watch co... - 03:21 PM Bug #8797 (Pending Backport): "ceph status" do not exit with python_2.7.8
- giant also ?
- 02:43 PM Revision d56eccdc (ceph): Merge pull request #3140 from leseb/sample-ceph.conf
- ceph.conf: update sample
Reviewed-by: Sage Weil <sage@redhat.com> - 02:32 PM Revision 7ab4a393 (ceph): ceph.conf: update sample
- This commit adds:
* client admin socket
* change some default
* re-indent
Signed-off-by: Sébastien Han <sebastien.h... - 01:56 PM Revision efd9d8df (ceph): tests: Minor cleanup to librbd test
- The tests can now be repeated to increase the chance of hitting
edge condition failures. Also added additional logic... - 01:42 PM Documentation #10293 (Resolved): Change "ceph-deploy mon create {ceph-node}" to "ceph-deploy mon ...
- http://docs.ceph.com/docs/master/start/quick-ceph-deploy/
The "Adding Monitors" section of the Storage Cluster Qui... - 01:34 PM Feature #9959: osd: pass client fadvise hints through to objecstore
- 01:34 PM Feature #9980: osd: cache: proxy reads during promote
- 01:34 PM Feature #9979: osd: cache: proxy reads (instead of redirect)
- 01:34 PM Feature #9957: librados: add fadvise op
- 01:34 PM Feature #9958: osd: add fadvise op to Objectstore::Transaction
- 01:34 PM Feature #9960: osd: adjust hint(s) for replica vs primary writes
- 01:34 PM Feature #9961: osd: new MOSDClientSubOp and Reply
- 01:33 PM Feature #9953 (In Progress): osd: efficient ObjectStore::Transaction encoding
- 01:33 PM devops Bug #10292 (Resolved): Replace dependency on junit4 with junit on recent Fedora versions.
- The junit4 package has been removed from recent versions of Fedora. The junit package is at version 4 and can be used...
- 11:03 AM CephFS Bug #10164 (Resolved): Dirfrag objects for deleted dir not purged until MDS restart
- Merged to master as of commit:24ca9f1c259d6222b54290bc4ea2030f0271af8f.
Test run at http://pulpito.ceph.com/gregf-20... - 10:55 AM Revision 78a15ee4 (ceph): Fix libstriprados::remove, use strtoll insdead of strtol
- Signed-off-by: Dongmao Zhang <deanraccoon@gmail.com>
- 10:34 AM rgw Bug #10251: "Segmentation fault" (radosgw()) in upgrade:dumpling-firefly-x:parallel-next-distro-b...
- cherr picked, commit:8b195eccadbd4d48518e33e08670b25527c3ca23
- 09:28 AM rgw Bug #10251: "Segmentation fault" (radosgw()) in upgrade:dumpling-firefly-x:parallel-next-distro-b...
- need the string = null patch to be backported still?
- 09:19 AM rgw Bug #10251: "Segmentation fault" (radosgw()) in upgrade:dumpling-firefly-x:parallel-next-distro-b...
- Same problem in run http://pulpito.front.sepia.ceph.com/teuthology-2014-12-09_17:15:03-upgrade:dumpling-firefly-x:par...
- 10:12 AM Revision a3912d23 (ceph): Merge pull request #3120 from ceph/wip-10010
- ceph-osd: don't close stderr if not daemonizing
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Loic Dachary <... - 10:09 AM Bug #10115: mon not running. osd is dead
- Also, ideally, logs from before the crash started to happen.
- 10:09 AM Bug #10115 (Need More Info): mon not running. osd is dead
- From the log it looks like there's (at least) an incremental missing (epoch 140).
This bug should not be related w... - 10:07 AM Feature #10290 (Resolved): ceph_objectstore_tool should support --dry-run option
This is do as much processing as it can without modifying the objectstore or writing out export data. For query op...- 09:56 AM Revision 2d4dca75 (ceph): SimpleMessenger: Retry binding on addresses if binding fails
- If binding on a IP-Address fails, delay and retry again.
This happens mainly on IPv6 deployments. Due to DAD (Duplic... - 09:33 AM Bug #10210 (Closed): "Caught signal" in upgrade:dumpling-x-firefly-distro-basic-vps run
- This looks a lot like an ENOMEM. I've seen this happening on vps and sometimes during memory hungry operations (say,...
- 08:41 AM rbd Bug #10270: "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic-multi run
- Same issue in run http://pulpito.front.sepia.ceph.com/teuthology-2014-12-09_13:52:17-upgrade:firefly-x-giant-distro-b...
- 07:11 AM Revision e8063a1a (ceph): test: modify cephfs quota test case
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 07:07 AM Revision 31a0cdc6 (ceph): mds: fix parse_quota_vxattr for invalid data
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 07:06 AM Revision bab71229 (ceph): OSD: FileJournal: call writeq_cond.Signal if necessary in submit_entry
- Signed-off-by: Xinze Chi <xmdxcxz@gmail.com>
- 05:21 AM Revision 17d63904 (ceph): os: IndexManager:: optimaze map<coll_t, CollectionIndex* > col_indices
- col_indices is just used to cache CollectionIndex, and use col_indices.find() to get its corresponding index. Without...
- 04:50 AM Revision 4036b91f (ceph): os: FileJournal:: fix, uninitialization of FileJournal throttle
- Since after firefly, take() in class throttle add if(0 == max.read()) return. If throttle is not initialized with max...
- 03:32 AM Revision 6b51a9f5 (ceph): mds: set dirfrag version when fetching dirfrag is skipped
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 03:28 AM Revision 17c72f59 (ceph): ceph-osd: remove extra close of stderr
- Otherwise, one loses log messages when running with -f or -d. When
daemonizing, stderr is already closed in global_i... - 01:48 AM Revision 09b82e2b (ceph): tasks: add test case for readonly MDS
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 12:52 AM Revision 58368999 (ceph): Revert "client: support listxattr for quota attributes"
- This reverts commit 55413482698c61e877312f1e749c657550965890.
this cause 'cp -a' copies quota setting. It's not the ... - 12:09 AM Revision dd7b58f3 (ceph): crush: set straw_calc_version=1 for default+optimal; do not touch for p...
- When using the presets for compatibility (i.e., based on version), do not
touch the straw behavior, as it does not af... - 12:09 AM Revision 89b2feea (ceph): mon: 'osd crush reweight-all'
- This corresponds to the crushtool --reweight command.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:09 AM Revision 9000068a (ceph): mon: add 'osd crush {get,set}-tunable <name> [value]' commands
- For now, just add the straw_calc_version tunable.
Signed-off-by: Sage Weil <sage@redhat.com> - 12:09 AM Revision adf5c6de (ceph): crush/builder: a note about the original crush_calc_straw()
- Signed-off-by: Sage Weil <sage@redhat.com>
12/09/2014
- 11:28 PM Revision 606b004d (ceph): gf-complete: update submodule to newest upstream
- Keep the tree cleaner!
Signed-off-by: Greg Farnum <gfarnum@redhat.com> - 10:24 PM CephFS Bug #10288: ceph fs ls fails to list newly created fs
- This is probably going to be something obvious in the MDSMonitor.
- 09:38 PM CephFS Bug #10288 (Resolved): ceph fs ls fails to list newly created fs
- Hi!
After upgrading from .6 to .8 (giant current from ceph ubuntu packages), I wanted to play with CephFS. I foll... - 10:24 PM Bug #10287: ceph v0.80.7 ceph-mon --mkfs crash
- change to leveldb 1.12, everything works fine. Please close it.
- 08:25 PM Bug #10287: ceph v0.80.7 ceph-mon --mkfs crash
- ceph.conf file...
- 08:24 PM Bug #10287 (Resolved): ceph v0.80.7 ceph-mon --mkfs crash
- ceph version v0.80.7 a new install machine "CentOS Linux release 7.0.1406 (Core)" run, the rpm build in same OS platf...
- 09:52 PM Revision 7faae891 (ceph): Revert "ceph.spec.: add epoch"
- If ICE ships 0.80.8, then it will be newer than what RHCEPH ships
(0.80.7), and users won't be able to seamlessly upg... - 08:38 PM Revision be373398 (ceph): Merge remote-tracking branch 'gh/next'
- Conflicts:
machine_types/vps.yaml - 07:17 PM Revision bf0d8d3a (ceph): osd: Remove dead code related to old pg removal mechanism
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:43 PM Revision ef3773ac (ceph): rgw: optionally call FCGX_Free() on the fcgi connection
- Fixes: #10194
A new configurable controls this behavior. This forces disconnection of
the fcgi connection when done ... - 04:35 PM Feature #10198: PG removal occupy the disk thread several hours
- In that case, two things:
1) move scrubbing into the OpWQ (I'm working on that one)
2) restructure pg removal to on... - 03:23 PM Bug #10281 (Fix Under Review): firefly: make check fails on fedora 20
- https://github.com/ceph/ceph/pull/3128
- 02:45 PM Bug #10281 (Resolved): firefly: make check fails on fedora 20
- http://paste.ubuntu.com/9447409/
- 03:16 PM Bug #10282 (Resolved): gf-complete: missing .gitignore entry for .dirstamp
- upstream Greg's fix https://github.com/ceph/gf-complete/pull/2 :
* -https://github.com/ceph/gf-complete/pull/3-
* ... - 01:49 PM CephFS Bug #10248: messenger: failed Pipe;:connect::assert(m) in Hadoop client
- Hmm, the client only calls _closed_mds_session if:
1) it gets back a session close
2) the session goes stale
2a)... - 01:11 PM Feature #7862: allow backfill/recovery while below min_size
- 01:10 PM Feature #8635 (In Progress): add scrub, snap trimming, should be items in the OpWQ with cost/prio...
- 01:06 PM Feature #7861: osd: allow writes on degraded objects
- 01:06 PM Feature #9781 (In Progress): ceph_objectstore_tool: On import handle splits
- 01:05 PM Feature #9780: ceph_objectstore_tool: Add OSDMap information to pg export
- 12:05 PM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- 11:32 AM Bug #9503: Dumpling: removing many snapshots in a short time makes OSDs go berserk
- Sam, is it correct to assume that this was fixed for dumpling in commit:1be9476afb9f715502a14749dd44e08371535b54, and...
- 10:41 AM Revision cdb11053 (ceph): Merge pull request #3073 from cholcombe973/get_pool_values_docs
- Updating docs for Get Pool Value
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:06 AM Revision 0827bb79 (ceph): client: use remount to trim kernel dcache
- when remounting a file system, linux kernel trims all unused dentry
in the file system.
Fixes: #10277
Signed-off-by:... - 06:49 AM rgw Bug #10268: s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3CreateError not ra...
- ubuntu@teuthology:/a/teuthology-2014-12-08_02:35:02-smoke-master-distro-basic-multi/642112
- 06:26 AM Revision dfcb1c9a (ceph): client: cleanup client callback registration
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 06:25 AM Revision 2f522029 (ceph): Revert "client: invalidate kernel dentries one by one"
- This reverts commit 491da5173fc33fec944865f0e2e9a506ec71fc5b.
Since 3.18 kernel, d_invalidate() unhash dentry even w... - 02:43 AM Bug #10272: objects misplaced after reweight
- Of course... thanks for explaining
- 01:05 AM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- So there not exists OSD superblock issue? only EC+KV problem that #9978 mentioned?
- 12:36 AM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- This issue has something to do with down time. On KV OSDs I've checked 'superblock' files and found that they are OK ...
- 12:39 AM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- Can this bug get a little attention please? It has profound effect on my crippled cluster and I'm talking about files...
- 12:21 AM Revision eeadd607 (ceph): crush/CrushWrapper: fix _search_item_exists
- Reported-by: Pawel Sadowski <ceph@sadziu.pl>
Signed-off-by: Sage Weil <sage@redhat.com> - 12:21 AM Revision 8c87e950 (ceph): crush/builder: prevent bucket weight underflow on item removal
- It is possible to set a bucket weight that is not the sum of the item
weights if you manually modify/build the CRUSH ... - 12:21 AM Revision 9902383c (ceph): crush/CrushWrapper: fix create_or_move_item when name exists but item d...
- We were using item_exists(), which simply checks if we have a name defined
for the item. Instead, use _search_item_e... - 12:10 AM Revision a198deea (ceph): Modifying the docs to add the Get pool commands to match the CLI.
- Signed-off-by: Chris Holcombe <chris.holcombe@nebula.com>
12/08/2014
- 11:12 PM CephFS Bug #10277 (Fix Under Review): ceph-fuse: Consistent pjd failure in getcwd
- 02:58 PM CephFS Bug #10277 (Resolved): ceph-fuse: Consistent pjd failure in getcwd
- "job-working-directory: error retrieving current directory: getcwd: cannot access parent directories: No such file or...
- 11:03 PM Revision 9bca0777 (ceph): Merge pull request #3108 from ceph/dumpling-10263
- mds: store backtrace for straydir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:02 PM Revision 5158a682 (ceph): Merge pull request #3107 from ceph/emperor-10263
- mds: store backtrace for straydir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:02 PM Revision dd7c8c2b (ceph): Merge pull request #3109 from ceph/firefly-10263
- mds: store backtrace for straydir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:07 PM Revision 3a84602b (ceph): Include common/likely.h in buffer.h
- Signed-off-by: Matt Benjamin <matt@cohortfs.com>
- 09:39 PM Bug #10010 (Fix Under Review): ceph_osd.cc calls global_init_shutdown_stderr even when running wi...
- Seems pretty simple; just check g_conf->daemonize, and don't close if not set.
- 09:19 PM Revision d7594672 (ceph): Merge pull request #3009 from dachary/wip-10018-primary-erasure-code-hi...
- osd: deep scrub must not abort if hinfo is missing (firefly)
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:19 PM Revision a8e56380 (ceph): Merge pull request #3010 from dachary/wip-10018-primary-erasure-code-hi...
- osd: deep scrub must not abort if hinfo is missing (giant)
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:08 PM Bug #10242: FAILED assert(backfill_targets.empty() || backfill_targets == want_backfill)
- Since this is from online product environment, it never happened again. And I cannot reproduce it in my test/staging ...
- 02:53 PM Bug #10242: FAILED assert(backfill_targets.empty() || backfill_targets == want_backfill)
- Mmm, that assert is essentially saying that choose_acting is only called in two situations:
1) On a new interval. I... - 08:56 PM Bug #10171 (Fix Under Review): DBObjectMap: ghobject_t header key excludes hash for EC pools
- 08:55 PM Bug #10272 (Rejected): objects misplaced after reweight
- problem is the (post-crush) reweights. you're rejecting almost all osds with 80% probability. eventually crush will...
- 02:54 PM Bug #10272: objects misplaced after reweight
- This is a problem with the crush rule. Crush retried a bunch of times, but was unable to get 3 replicas for that pg.
- 10:35 AM Bug #10272 (Rejected): objects misplaced after reweight
- Steps to reproduce, after compiling from sources:...
- 08:36 PM Revision 247a6fac (ceph): Merge pull request #3110 from ceph/giant-10263
- mds: store backtrace for straydir
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:27 PM Revision ab822cb3 (ceph): Merge pull request #261 from ceph/wip-10223
- Fixes #10269 http://tracker.ceph.com/issues/10269
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:12 PM Revision 1156a747 (ceph): Fixes #10269 http://tracker.ceph.com/issues/10269
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:13 PM Bug #10018: OSD assertion failure if the hinfo_key xattr is not there (corrupted?) during scrubbing
- It's waiting on https://github.com/ceph/ceph-qa-suite/pull/250
- 03:30 PM Bug #10018 (In Progress): OSD assertion failure if the hinfo_key xattr is not there (corrupted?) ...
- Loic: are the tests for this in the regression suite yet?
- 03:23 PM Bug #10018 (Resolved): OSD assertion failure if the hinfo_key xattr is not there (corrupted?) dur...
- 03:33 PM rbd Bug #10180 (Resolved): qemu tests crash host kernel
- 03:26 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Unfortunately I doubt it. From what I have read, cranking up the logs so much would extremely quickly eat up availabl...
- 03:20 PM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Can you reproduce? The logs don't have much information, I need it reproduced with
debug osd = 20
debug filestor... - 09:48 AM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- Replicated Pool. No cache tiering.
- 09:47 AM Bug #10262: osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- is this an erasure or replicated pool? are you using cache tiering?
- 03:25 PM Bug #9503 (Resolved): Dumpling: removing many snapshots in a short time makes OSDs go berserk
- 03:03 PM CephFS Bug #10263 (Resolved): [ERR] bad backtrace on dir ino 600
- They're all happy now, merged everything in.
- 12:36 PM CephFS Bug #10263: [ERR] bad backtrace on dir ino 600
- Merged in the patch for Giant as of commit:247a6fac54854e92a7df0e651e248a262d3efa05.
The others are a little unhap... - 02:05 PM CephFS Bug #10248: messenger: failed Pipe;:connect::assert(m) in Hadoop client
- the new assert for wip-10057 would trigger this.
this looks like a corner case is the session close + reopen seque... - 11:59 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- Awesome, looks like it worked, it started backfilling right away and now my vms are unfrozen. Thanks a lot!
- 11:30 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- install wip-last_epoch_started, set osd_find_best_info_ignore_history_les = true in ceph.conf, and restart the primar...
- 10:59 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- ...
- 10:21 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- I actually had already marked 11 as lost a few days ago. Just this morning I re-activated the disk and it came up as ...
- 08:52 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- Can you try 'ceph osd lost 11' ? (I take it osd.11 is the one that you wiped and removed?)
If you can catpure the... - 06:48 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- I found more info in the log relating to this pg. It looks like it's kicking it, but still hanging requests. At this ...
- 11:48 AM Bug #8935: operations not idempotent when enabling cache
- ubuntu@teuthology:/a/samuelj-2014-12-05_23:56:18-rados-wip-sam-firefly-testing-wip-testing-vanilla-fixes-basic-multi/...
- 11:47 AM Bug #8797: "ceph status" do not exit with python_2.7.8
- I think the right fix for this is to remove Rados.__del__. I'll come up with a pull request unless you want to, Joe.
- 10:33 AM rgw Bug #10066 (In Progress): rgw: failed md5sum on s3tests-test-readwrite
- 10:19 AM Bug #10241 (Need More Info): Incorrect OSD mapping with EC 6+2 setup in Giant
- need osdmap or crushmap that triggers the failed mapping
- 09:47 AM Bug #10258 (Duplicate): ceph health reporting blocked op indefinitely
- #10259
- 09:45 AM rgw Bug #10271 (Resolved): Radosgw urlencode
- When performing a multipart upload using AWS SDK JS v.2.0.29 I can see that the uploadId always starts with "2/" whic...
- 09:28 AM devops Bug #10266: Can't kill runs on magan002 "AuthenticationException: Authentication failed."
- What even caused this? I can't of course log in to the machines to check it out.
- 09:12 AM rbd Bug #10270 (Resolved): "[ FAILED ] LibRBD.ListChildren" in upgrade:firefly-x-giant-distro-basic...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-07_18:13:01-upgrade:firefly-x-giant-distro-basic-m...
- 08:40 AM Feature #10192 (Resolved): ceph_objectstore_tool object lookup
- 08:18 AM Bug #10215 (Resolved): vstart_wrapper.sh kills daemons that do not belong to it
- 07:33 AM Revision bc2b9f6b (ceph): Merge pull request #3106 from danderson/asan-fixes
- Asan fixes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:09 AM Revision 7d381a60 (ceph): Merge pull request #3113 from wonzhq/name-norm
- mailmap: Zhiqiang Wang name normalization
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:56 AM devops Bug #10200: tgtd error: undefined symbol: rbd_discard
- tgt_1.0.38-48.bf6981.precise.ceph_amd64.deb from ceph-extras depends on rbd_discard, which is not available in stock ...
- 05:43 AM Bug #9916: osd: crash in check_ops_in_flight
- Sorry for the repetition of #5 and #6 for network problem.
- 05:41 AM Bug #9916: osd: crash in check_ops_in_flight
- In file osd/OSD.cc:
OSD::_dispatch(Message *m) method:... - 05:01 AM Fix #9566: osd: prioritize recovery of OSDs with most work to do
- ...
- 02:50 AM Fix #9566 (In Progress): osd: prioritize recovery of OSDs with most work to do
- 04:33 AM Revision e8b412cb (ceph): mailmap: Zhiqiang Wang name normalization
- Signed-off-by: Zhiqiang Wang <zhiqiang.wang@intel.com>
- 04:30 AM Linux kernel client Feature #5109: libceph: implement message signatures
- 04:04 AM Messengers Feature #10029: Retry binding on IPv6 address if not available
- Logs I'm seeing on a monitor when it boots:...
- 04:03 AM Revision c0ce4a5e (ceph): Cleanup:Use get_type()instead of get_header().type
- Cleanup the code ,use get_type() instead of get_header().type
for messages.
Signed-off-by: Xiaoxi Chen <xiaoxi.chen@... - 03:45 AM Revision c2d93336 (ceph): WBThrottle: make bytes/ios/inode_wb's perf counter effective
- Since sync thread will cause unstable iops and latency performance curve, we
may want make WBThread do more(or modera... - 02:49 AM Cleanup #10253 (Closed): gf-complete dead code
- False positive according to Kevin & Janne.
- 02:03 AM Bug #9485: Monitor crash due to wrong crush rule set
- But you understand that when CRUSH can not find enough racks using the indep mode, things go wrong and the wrong rule...
- 01:41 AM Bug #9485: Monitor crash due to wrong crush rule set
- Although I've marked the issue as verified, I did not actually get to reproduce it. I meant to a number of times usin...
- 01:48 AM Revision c25e6e77 (ceph): mds: store backtrace for straydir
- Backport: giant, firefly, emperor, dumpling
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 0d... - 01:48 AM Revision a5970963 (ceph): mds: store backtrace for straydir
- Backport: giant, firefly, emperor, dumpling
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 0d... - 01:47 AM Revision 309fd5f5 (ceph): mds: store backtrace for straydir
- Backport: giant, firefly, emperor, dumpling
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 0d... - 01:46 AM Revision 81891f26 (ceph): mds: store backtrace for straydir
- Backport: giant, firefly, emperor, dumpling
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 0d...
12/07/2014
- 10:40 PM Revision 12d85c64 (ceph): Fix stack buffer overflow reported by ASan.
- Signed-off-by: David Anderson <dave@natulte.net>
- 08:02 PM Revision f6f6ea29 (ceph): Fix alloc-dealloc mismatch reported by ASan (new[] vs. delete).
- Signed-off-by: David Anderson <dave@natulte.net>
- 07:52 PM Revision 5bb86664 (ceph): Fix alloc-dealloc mismatch reported by ASan (malloc vs. C++ delete).
- Signed-off-by: David Anderson <dave@natulte.net>
- 07:46 PM Feature #10193 (Fix Under Review): Perf counter for WBThrottle
- https://github.com/ceph/ceph/pull/3111
- 06:40 PM Bug #9485: Monitor crash due to wrong crush rule set
- Hi sage:
According to my test earlier, crushtool may not be able to make it crash. I remember that crushtool will ... - 10:11 AM Bug #9485: Monitor crash due to wrong crush rule set
- Just to offer some debriefing on the issue.
After installing the patch, I managed to get the monitor up and runnin... - 06:36 PM Revision 8ed536e1 (ceph): ceph_test_rados_api_watch_notify: fix signed/unsigend
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:36 PM Revision 45223d9a (ceph): librados: mark new API watch/notify calls
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:50 PM CephFS Bug #10263 (Fix Under Review): [ERR] bad backtrace on dir ino 600
- It's introduced by the 'verify backtrace on fetching dirfrag' patch. Stray directories of old fs has no backtrace, th...
- 10:12 AM Revision 6010f178 (ceph): Merge pull request #3103 from danderson/ceph-dev-mode-python-envvar
- ceph: respect the PYTHON environment variable for dev mode.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:06 AM rgw Bug #10268 (Resolved): s3tests.functional.test_s3.test_bucket_create_exists fails with 'S3CreateE...
- ...
- 10:02 AM Revision 812ff7aa (ceph): ceph: respect the PYTHON environment variable for dev mode.
- On OSes where `python` is python3, dev mode's re-exec makes the
ceph tool fail. The standard way to fix this is by ex... - 08:44 AM devops Bug #10266 (Resolved): Can't kill runs on magan002 "AuthenticationException: Authentication failed."
- ...
- 05:47 AM devops Bug #10148: Giant/Wheezy SysV: /etc/init.d/ceph -a start shifts crushmap to executing host
- Duplicate of #9407
- 05:04 AM Revision 1bf39db0 (ceph): AsyncConnection: Add loopback connection support
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:00 AM Fix #10264 (Fix Under Review): docker-test-helper fails on detached head
- https://github.com/ceph/ceph/pull/3104
- 03:19 AM Fix #10264 (Resolved): docker-test-helper fails on detached head
- If the working tree is on a detached head (i.e. the commit may be unreachable from from any git refs), docker-test-he...
- 04:59 AM Documentation #10265: building from source should be a onliner
- https://github.com/ceph/ceph/pull/3104
- 04:46 AM Documentation #10265 (Resolved): building from source should be a onliner
- Building Ceph from sources is documented as multiple steps although it could be a oneliner grouping...
- 12:31 AM Feature #9888 (Resolved): AsyncMessenger: Async event threads can shared by all AsyncMessenger
12/06/2014
- 07:06 PM Revision 33720608 (ceph): Merge pull request #3088 from dachary/wip-10063-hobject-shard-giant
- common: do not omit shard when ghobject NO_GEN is set (giant)
- 07:06 PM Revision adf9a758 (ceph): Merge pull request #3089 from dachary/wip-10063-hobject-shard-firefly
- common: do not omit shard when ghobject NO_GEN is set (firefly)
- 06:59 PM Revision dea38a7a (ceph): Merge pull request #2480 from dachary/wip-9420-erasure-code-non-regress...
- erasure-code: store and compare encoded contents (firefly)
- 06:42 PM Bug #10125 (Resolved): radosgw is being started as root not apache with systemd
- 05:36 PM CephFS Bug #10263 (Resolved): [ERR] bad backtrace on dir ino 600
- ubuntu@teuthology:/a/sage-bug-10171-base/639742
and the other runs in this set. It's an upgrade test:... - 05:34 PM Bug #9485: Monitor crash due to wrong crush rule set
- I've fixed Panayiotis's issue, but it is different than the original bug.
Dong Lei, I've tried to reproduce this b... - 12:22 PM Bug #9485: Monitor crash due to wrong crush rule set
- https://github.com/ceph/ceph/commit/wip-9485
- 11:17 AM Bug #9485: Monitor crash due to wrong crush rule set
- for the attached linked, this is the result of the command (crushtool, as compiled from git tree with --with-debug --...
- 11:16 AM Bug #9485: Monitor crash due to wrong crush rule set
- for the attached linked, this is the result of the command (crushtool, as supplied by debian packages -- 0.80)
htt... - 11:09 AM Bug #9485: Monitor crash due to wrong crush rule set
- This is the crashing crushmap
https://www.dropbox.com/s/gbusu8jf2ku6k62/crushmap.orig?dl=0 - 05:28 PM rbd Bug #10180: qemu tests crash host kernel
- For the kernel fixes see https://github.com/ceph/teuthology/pull/380
Rbd suite run - http://pulpito.front.sepia.ce... - 04:33 PM Revision fca14dc6 (ceph): AsyncMessenger: Fix accept connection replacing process
- Original there exists bugs that we don't modify existing file event,
it will let remaining alive connection's event w... - 04:33 PM Revision e446a8f6 (ceph): AsyncConnection: Avoid name conflicting with AsyncMessenger
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:33 PM Revision b3e3fae3 (ceph): AsyncConnection: Avoid hungry if mark_down's caller is the eventcenter'...
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 04:14 PM Revision 09b3e77d (ceph): FileStore: Move ftruncate to do_sparse_copy
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 03:56 PM Revision a368533e (ceph): Merge pull request #3099 from sileht/sileht/python-rados-object-lock
- python-rados: Add object lock support
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:28 PM Revision f5bf75fa (ceph): python-rados: Add object lock support
- This change adds to the python binding the support of:
- rados_lock_exclusive
- rados_lock_shared
- rados_unlock
... - 12:23 PM Revision f6d81d39 (ceph): PipeConnection: Modify "is_connected" semantic
- "is_connected" should be used to judge whether have built a successful
connection with peer. Since "pipe == NULL" is ... - 12:23 PM Revision 2dfda545 (ceph): Messenger: Add unit tests
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 11:08 AM Bug #10063 (Resolved): ceph_objectstore_tool does not support getting attributes for erasure code...
- 11:02 AM Feature #9420 (Resolved): erasure-code: tools and archive to check for non regression of encoding
- 06:26 AM RADOS Feature #6114: Complete python binding interfaces for librados
- * lock support https://github.com/ceph/ceph/pull/3099
- 06:04 AM Bug #10262 (Resolved): osd/osd_types.h: 2944: FAILED assert(rwstate.empty())
- During the night of 2014-12-06 our cluster (4 nodes, 12x4TB spinning disks, Firefly 0.80.7.1 on Ubuntu 14.04.1) suffe...
- 05:04 AM Revision f3b3d755 (ceph): radosgw_admin: test full sync using existing tests
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 02:00 AM Revision dc67cd69 (ceph): rgw: switch to new watch/notify API
- Note that we don't use it properly, yet!
Signed-off-by: Sage Weil <sage@redhat.com> - 01:33 AM Revision 1f004209 (ceph): Merge pull request #3095 from dachary/wip-9785-dmcrypt-keys-permissions...
- ceph-disk: dmcrypt file permissions (giant)
- 01:33 AM Revision ccc8b46b (ceph): Merge pull request #3096 from dachary/wip-9785-dmcrypt-keys-permissions...
- ceph-disk: dmcrypt file permissions (firefly)
- 01:31 AM Revision 53fe2961 (ceph): Merge pull request #3035 from dachary/wip-10197-arch-arm
- arch: add support for HW_CAP based neon runtime detection
Reviewed-by: Sage Weil <sage@redhat.com> - 01:30 AM Revision 3b65226d (ceph): Merge pull request #3006 from dachary/wip-9420-erasure-code-non-regress...
- erasure-code: store and compare encoded contents (giant)
- 12:49 AM Revision 1ac17c0a (ceph): osd_types: op_queue_age_hist and fs_perf_stat should be in osd_stat_t::...
- Fixes: 10259
Backport: giant, firefly, dumpling
Signed-off-by: Samuel Just <sjust@redhat.com>
12/05/2014
- 10:21 PM Revision 9029813b (ceph): common/ceph_context: don't import std namespace
- This was broken by 7fed5dee4f96a83d1d6914f6fc0895bba2d15b99
Signed-off-by: Sage Weil <sage@redhat.com> - 09:56 PM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- Sage Weil wrote:
> Just a reminder that the "_dev" in "keyvaluestore_dev" means "experimental! danger! danger!". Th... - 07:01 AM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- Just a reminder that the "_dev" in "keyvaluestore_dev" means "experimental! danger! danger!". This code is not well-...
- 09:02 PM Revision e6558b47 (ceph): Merge pull request #3020 from dachary/wip-10192-objectstore-tool-lookup
- objectstore tool lookup by name & --op list filter
Reviewed-by: David Zafman <dzafman@redhat.com>
Reviewed-by: Loic ... - 08:09 PM Revision cca85a53 (ceph): ceph_objectstore_tool: Add --format and --pretty-format support
- --pretty-format defaults true
Add --format so xml output can be requested
--op list defaults to single line of json p... - 08:09 PM Revision 32c832f0 (ceph): ceph_objectstore_tool: Remove extraneous endl on error throw messages
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 08:09 PM Revision eae7c02f (ceph): ceph_objectstore_tool: Fix errors messages in newer code
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 08:09 PM Revision de6384fd (ceph): ceph_objectstore_tool: Improve object spec parsing error messages
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 08:09 PM Revision 59b423e2 (ceph): ceph_objectstore_tool: Accept json object with --pgid instead of array
- It isn't anticipated that anyone would use this but keeps backward compatible
Signed-off-by: David Zafman <dzafman@r... - 07:48 PM Revision 980f0948 (ceph): common: bufferlist::get_contiguous return 0 when param len == 0
- Change-Id: I3eaee45b12c634687cd1b294b3c264aed8cab03a
Signed-off-by: Dong Yuan <yuandong1222@gmail.com> - 06:43 PM Revision 00c96c28 (ceph): doc: Adds ceph-deploy man page in TOC.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 06:40 PM Revision d93e561f (ceph): doc: Adds ceph-deploy man page under /man.
- Adds entry for ceph-deploy man page in man/Makefile.am
Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com> - 06:37 PM Revision 9191005c (ceph): doc: Adds man page for ceph-deploy.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 05:57 PM Revision f4735cff (ceph): .gitignore: add ceph_perf_objectstore
- Signed-off-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage@redhat.com> - 05:47 PM Revision cabb57a2 (ceph): FileStore: Fix _do_sparse_copy_range don't truncate zero sections
- If calling clone_range and zero filled sections is at the ending of src
range, the target fd won't write zero filled ... - 05:47 PM Revision bcee92ee (ceph): StoreTest: Add tests for clone_range op
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:32 PM Revision cd3447d0 (ceph): ceph-disk: dmcrypt file permissions
- The directory in which key files are stored for dmcrypt must be 700 and
the file 600.
http://tracker.ceph.com/issues... - 05:30 PM Revision 1ec557c0 (ceph): ceph-disk: dmcrypt file permissions
- The directory in which key files are stored for dmcrypt must be 700 and
the file 600.
http://tracker.ceph.com/issues... - 05:20 PM Revision f1dc5125 (ceph): Merge pull request #2987 from yuyuyu101/wip-9888
- AsyncMessenger: Async event threads can shared by all AsyncMessenger
Reviewed-by: Sage Weil <sage@redhat.com> - 05:11 PM Bug #9485: Monitor crash due to wrong crush rule set
- Hello, I can verify that I am facing the same problem.
After trying to edit the crushmap in order to separate grou... - 05:06 PM Revision 4c3b1299 (ceph): Merge pull request #3043 from yuyuyu101/objectstore-perf
- Objectstore::Transaction Perf Program
Reviewed-by: Sage Weil <sage@redhat.com> - 05:04 PM Revision bef363c1 (ceph): Merge pull request #3086 from dachary/wip-10125-radosgw-init-firefly
- rgw: run radosgw as apache with systemd (firefly)
- 05:03 PM Revision 691f0118 (ceph): Merge pull request #3085 from dachary/wip-10125-radosgw-init-giant
- rgw: run radosgw as apache with systemd (giant)
- 04:39 PM Revision d7a9bf7c (ceph): Merge pull request #3087 from dachary/wip-9785-dmcrypt-keys-permissions
- ceph-disk: dmcrypt file permissions
Reviewed-by: Sage Weil <sage@redhat.com> - 04:33 PM Revision 26747d43 (ceph): Merge pull request #3094 from yuandong1222/bufferlist-get_contiguous
- common: bufferlist::get_contiguous return 0 when param len == 0
Reviewed-by: Sage Weil <sage@redhat.com> - 04:01 PM Revision d6a7a7c6 (ceph): os/FileStore: merge filestore_replica_fadvise -> filestore_fadvise
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:01 PM Revision be11a451 (ceph): os/FileStore: stop disabling fadvise on XFS
- This was an issue with mixing fadvise and sync_file_range, not with just
fadvise.
Signed-off-by: Sage Weil <sage@red... - 03:26 PM Bug #10259 (Resolved): mon health stuck with phantom hung requests
- commit:1ac17c0a662e6079c2c57edde2b4dc947f547f57
(03:22:47 PM) sjust: sage: osd_stat_t
(03:22:59 PM) sjust: does n... - 02:36 PM Bug #10258 (Duplicate): ceph health reporting blocked op indefinitely
- On the performance test cluster, when creating an EC pool, ceph health reports that an op is blocked many hours after...
- 12:08 PM Bug #10257 (Resolved): Ceph df doesn't report MAX AVAIL correctly when using rulesets and OSD in ...
- In our setup we have two rulesets, one for SSDs and another one for HDDs. Ceph df normally reports the MAX AVAIL spac...
- 12:01 PM Revision a90233c8 (ceph): objectstore_tool: update usage strings
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 12:01 PM Revision d9e747b1 (ceph): objectstore_tool: refactor list-lost and fix-lost
- Abstract out the PG exploration loops and encapsulate the list-lost and
fix-lost semantic in a callable object.
Sign... - 12:01 PM Revision 7c1165f9 (ceph): objectstore_tool: lookup objects by name
- If the object is not a parsable JSON string, assume an object name and
look it up in all the PGs. If multiple objects... - 12:01 PM Revision c69aacea (ceph): objectstore_tool: filter --op list and explore all PGs
- The positional object name is used to filter the output of --op list and
only show the objects with a matching name. ... - 12:01 PM Revision df9d5c5c (ceph): objectstore_tool: parse new object description format
- The object format changed from
{json object}
to
[pgid,{json object}]
The parser is updated accordingly. I... - 12:01 PM Revision ddba2676 (ceph): objectstore_tool: test --op list variants
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 12:01 PM Revision bc6ea9cb (ceph): ceph_objectstore_tool: In error case umount objectstore
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:01 PM Revision 5a66db94 (ceph): ceph_objectstore_tool: For terminal output of list one object per line
- Instead of a parsable array make it easier to cut and paste listed objects
Signed-off-by: David Zafman <dzafman@redh... - 12:01 PM Revision b617ee2d (ceph): ceph_objectstore_tool: BUG: --op list wasn't including snapshots
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:01 PM Revision 5eacd3c5 (ceph): ceph_objectstore_tool: Strip _* (always _head) from pgid in list entry ...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 11:58 AM devops Bug #10252 (Resolved): apt-mirror having issues
- This was being caused by a proxy issue (needed another reload) which is used to access apt-mirror from the redhat net...
- 09:37 AM devops Bug #10252: apt-mirror having issues
- From magna002 curl sees the same:...
- 08:25 AM devops Bug #10252 (Resolved): apt-mirror having issues
- That prevent installation on some machines:...
- 10:32 AM Revision 6de83d49 (ceph): Cache hobject filestore_key to avoid massive _reverse_nibbles calls
- Signed-off-by: Dong Yuan <yuandong1222@gmail.com>
- 10:16 AM Feature #10231 (Resolved): gperftools headers have moved
- 10:06 AM Revision 58682d17 (ceph): ceph-disk: dmcrypt file permissions
- The directory in which key files are stored for dmcrypt must be 700 and
the file 600.
http://tracker.ceph.com/issues... - 09:32 AM Bug #9785 (Fix Under Review): /etc/ceph/dmcrypt-keys and key contents are created world-readable
- * giant backport https://github.com/ceph/ceph/pull/3095
* firefly backport https://github.com/ceph/ceph/pull/3096
- 08:38 AM Bug #9785 (Pending Backport): /etc/ceph/dmcrypt-keys and key contents are created world-readable
- 09:25 AM Feature #10254 (New): mon,osd: long-term non-clean PGs prevent osdmap trimming
- sometimes clusters have pgs that are degraded for long periods of time. this forces the mon to retain lots of old os...
- 08:58 AM Cleanup #10253 (Closed): gf-complete dead code
- ...
- 08:40 AM Revision 2b59c5a8 (ceph): common/Initialize.h: add header file to Makefile.am
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 08:12 AM rgw Bug #10251 (Resolved): "Segmentation fault" (radosgw()) in upgrade:dumpling-firefly-x:parallel-ne...
- Run http://pulpito.ceph.com/teuthology-2014-12-04_17:15:01-upgrade:dumpling-firefly-x:parallel-next-distro-basic-vps/...
- 07:42 AM Bug #9844: "initiating reconnect" (log) race; crash of multiple OSDs (domino effect)
- I have had this same issue on my cluster as well.
My cluster originally had 4 nodes, with 7 osds on each node, 28 ... - 07:18 AM Revision 5da15ee9 (ceph): mds: drop dentry leases in deleted directory
- we will never link dentry in deleted directory to inode, so it's
OK to remove client leases prematurely. This optimiz... - 06:37 AM Bug #10250: PG stuck incomplete after interrupted backfill.
- Oh I forgot to mention, min_size is 1 on this pool.
- 05:57 AM Bug #10250 (Closed): PG stuck incomplete after interrupted backfill.
- Ceph version: 0.87
OS: Ubuntu 14.04
Cluster: 3x osd nodes with ~24 osds each
Issue: I had a pool accidentally se... - 03:55 AM Bug #9916: osd: crash in check_ops_in_flight
- Sage Weil wrote:
> how is the OSDOp being formed? this looks like a bug on the client side to me. the attr ops sho... - 03:06 AM Bug #10246 (Resolved): add el7 to the list of supported version for centos in ceph-deploy install...
- 02:49 AM Revision f55a1f87 (ceph): mds: disallow flush dentry/journal when MDS is readonly
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:40 AM Revision f4f1880c (ceph): mds: properly unregister asok commands
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 01:15 AM rbd Feature #10226: Add pool quota reporting for Libvirt and other clients
- Assigning this one to me.
Need to figure a way out to fetch the pool's quota from the cluster first. - 01:12 AM Fix #9566 (Fix Under Review): osd: prioritize recovery of OSDs with most work to do
- 01:10 AM Bug #10018 (Fix Under Review): OSD assertion failure if the hinfo_key xattr is not there (corrupt...
- 12:56 AM Revision 818a8073 (ceph): mds: drop dirty dentries in deleted directory
- opened dirfrags and null dirty dentries in deleted directory inode
prevent MDCache::eval_stray() from purging the del... - 12:54 AM Revision cfb03b2d (ceph): Merge pull request #3081 from dachary/wip-10246-centos7
- doc: add centos 7 to ceph-deploy installation
Reviewed by: John Wilkins <jowilkin@redhat.com> - 12:00 AM Revision b4a4b75e (ceph): common: do not omit shard when ghobject NO_GEN is set
- Do not silence the display of shard_id when generation is NO_GEN.
Erasure coded objects JSON representation used by c...
12/04/2014
- 11:07 PM Revision 744c309e (ceph): Merge pull request #3031 from dachary/wip-10199-config-get-xml
- common: admin sock output XML elements whitespace
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@redhat.com> - 10:53 PM Revision ff901b5c (ceph): arch: add support for HW_CAP based neon runtime detection
- Rename the files from neon to arm to reflect the fact that it's related
to arm processors and also because NEON was r... - 10:50 PM Revision 50abebb5 (ceph): Merge pull request #259 from ceph/wip-10223
- Changed workloads in 2-workload to run in parallel
- 10:48 PM Revision 4487c3b0 (ceph): Changed workloads in 2-workload to run in parallel
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 09:39 PM Revision bff67475 (ceph): common: do not omit shard when ghobject NO_GEN is set
- Do not silence the display of shard_id when generation is NO_GEN.
Erasure coded objects JSON representation used by c... - 09:36 PM Revision 15763114 (ceph): Merge pull request #2959 from ceph/wip-10104
- rados.py: fix misnamed 'wait_*' routines, add true wait/wait-with-cb
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:21 PM Revision 43a2c3aa (ceph): Merge pull request #2985 from CzBiX/quick-fix
- rgw: check endpoints is not empty before use it.
This fixes a regression due to commit 3c4b782bcb5460523982a04b1e5c7... - 09:08 PM Revision 360d627f (ceph): pybind/test_rados: add test for wait_for_complete_and_cb()
- Also, factor out some common code between the two tests
Signed-off-by: Dan Mick <dan.mick@redhat.com> - 09:08 PM Revision 19212cde (ceph): rados.py: fix misnamed 'wait_*' routines, add true wait/wait-with-cb
- Also modify aio_read test for wait: write an object, take its active set
down, try to aio_read; verify read doesn't c... - 08:07 PM Revision 9f3b21d1 (ceph): rgw: run radosgw as apache with systemd
- Same as sysv.
http://tracker.ceph.com/issues/10125 Fixes: #10125
Signed-off-by: Loic Dachary <loic@dachary.org>
(ch... - 08:03 PM Revision dabf6f5f (ceph): rgw: run radosgw as apache with systemd
- Same as sysv.
http://tracker.ceph.com/issues/10125 Fixes: #10125
Signed-off-by: Loic Dachary <loic@dachary.org>
(ch... - 07:36 PM CephFS Bug #10229 (Resolved): Filer: lock inversion with Objecter
- 07:32 PM Revision dea84def (ceph): Merge pull request #3079 from ceph/wip-10030-dumpling
- librbd: don't close an already closed parent image upon failure
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:32 PM Revision cb2c83b2 (ceph): Merge pull request #3078 from ceph/wip-10030-firefly
- librbd: don't close an already closed parent image upon failure
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:32 PM Revision 81295c5a (ceph): Merge pull request #3077 from ceph/wip-10030-giant
- librbd: don't close an already closed parent image upon failure
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:39 PM Revision a53dbabd (ceph): librados:: carry IoCtx ref from WatchInfo
- The WatchInfo gets totally async notifications. Make sure our ioctx
ref is valid when that happens.
Signed-off-by: ... - 06:39 PM Revision 61fc317d (ceph): librados: remove failed notify
- Decided this wasn't useful.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:39 PM Revision 6fa05dbf (ceph): osdc/Objecter: queued_async() gets called inside watch_lock from caller
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:39 PM Revision 1c5bba67 (ceph): osd/ReplicatedPG: pass obc to OpContext ctor
- We always set it, except for the handle_watch_timeout caller, which needs
to.
Signed-off-by: Sage Weil <sage@redhat.... - 06:39 PM Revision 1c6944f7 (ceph): osd/ReplicatedPG: do watch effects only when change commits
- Do not tell the client their watch succeeded until it is durable and
visible to clients doing a notify. This is less... - 06:39 PM Revision a989fece (ceph): osd: allow deletion of objects with watchers
- If we delete an object with a watcher, forcefully disconnect the watcher
instead of preventing the deletion with EBUS... - 06:38 PM Revision 0a612876 (ceph): librados: s/handle/cookie/ in headers
- Be consistent.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:37 PM Revision 1a36eb37 (ceph): PendingReleaseNotes: a few notes about watch/notify changes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:37 PM Revision 27ceb169 (ceph): ceph_test_rados_api_watch_notify: test ENOENT case
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:37 PM Revision f0614a10 (ceph): ceph_test_rados_watch_notify: do not unwatch on invalid handle
- It is not safe to call rados_unwatch on an undefined handle.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision 7f8ffae8 (ceph): osdc/Objecter: set last_error before async error event delivery
- No reason to delay this.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision a824be97 (ceph): test_async_driver: fix warning
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 8ec0af47 (ceph): librados: use Objecter's linger_id as the cookie
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision de9f18dd (ceph): osdc/Objecter: take Finisher ref from creator
- Only needed for watch/notify users, so most can pass NULL.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision cd6a4aa9 (ceph): rados: break out notify replies by client
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision e72035f3 (ceph): librados: move watch/notify into the Objecter
- Several things here:
- we move all of the junk from librados' RadosClient into Objecter
- we use fast-dispatch to s... - 06:34 PM Revision e8df0771 (ceph): osdc/Objecter: drop ACK callback for watch
- It is semantically useless.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision 45aaa340 (ceph): osdc/Objecter: only reconnect watches; skip ack unless needed
- Only watches get a RECONNECT op; lingers just get resent.
Only request an ACK in the non-watch reconnect case and wh... - 06:34 PM Revision 88233696 (ceph): osdc/Objecter: ignore pings from previous registrations
- If we have a ping in flight and then reregister (due to interval change
or whatever), ignore the result of the previo... - 06:34 PM Revision 9d9e66e6 (ceph): osd: rejigger watch connect/disconnect callers
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 32043a38 (ceph): encoding: multiset encode/decode
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 5e994508 (ceph): librados: include missed watchers in notify reply data
- Include a list of who missed their notify in the notify reply.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision 14e933d2 (ceph): librados: use (gid,cookie) to identify notify participants
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 955a2f0e (ceph): osdc/Objecter: use recast LingerOp* as OTW cookie, too
- This makes the OSD reply's cookie values match up with what the librados
users see. And it makes life less confusing... - 06:34 PM Revision 5c0a8c41 (ceph): osdc/Objecter: make watch_check time reflect async delivery
- When a librados user calls watch_check(), the age they get back should
establish a timestamp for which:
1) we know ... - 06:34 PM Revision 26440fd7 (ceph): osdc/Objecter: use RWLock for watch_lock
- This makes the linger_check fast path an RWLock read lock. Drop the
unnecessary write lock on rwlock and drop the un... - 06:34 PM Revision 42e4baa0 (ceph): librados: unwatch doesn't need the oid argument
- The handle is like a file handle: there is internal state that is getting
freed and the user needn't provide it again... - 06:34 PM Revision 8c867b8f (ceph): ceph_test_rados: use new watch/notify API
- Ignore error events for now; we are just stressing the OSD.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision 03778502 (ceph): librados: watch_check() to check on status of watch
- Return either an accumulated error code, or the time since the watch was
last confirmed.
Signed-off-by: Sage Weil <s... - 06:34 PM Revision 889cd874 (ceph): messages/MWatchNotify: print more nicer
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:34 PM Revision 5f90c20d (ceph): osdc/Objecter: expose LingerOp instead of linger_id
- We want a reference-counted handle, not an id.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:34 PM Revision 34c9d729 (ceph): osdc/Objecter: spit out linger register step
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:33 PM Revision 219f8248 (ceph): librados: mark old rollback call deprecated
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:33 PM Revision ea53983a (ceph): librados: no need for '2' suffix in c++
- Compiler disambiguates based on the rest of the signature.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:33 PM Revision 85f336d5 (ceph): rados: use new notify API
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:33 PM Revision d3ec70ee (ceph): librados: mark old watch calls deprecated
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision b583152e (ceph): osdc/Objecter: stop sending pings once we get an error
- If we get ENOTCONN or ETIMEDOUT we can stop pinging.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision f68fcc0f (ceph): osdc/Objecter: objecter_inject_no_watch_ping
- Tunable to prevent PINGs. This will let us test paths the client gets
disconnected from the OSD (at least from the c... - 06:32 PM Revision 872012f1 (ceph): osdc/Objecter: skip ping if PAUSERD
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 485daaba (ceph): osdc/Objecter: factor out _send_op_account()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision b4d769cf (ceph): osdc/Objecter: fix whitespace
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 2c6076b0 (ceph): ceph_test_rados_api_watch_notify: verify notify after missed notify works
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 0601b5f9 (ceph): ceph_test_rados_watch_notify: fix signed/unsigned warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision a4eeaf5a (ceph): ceph_test_rados_api_watch_notify: drop 'Test' suffix
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 14cd7197 (ceph): ceph_test_rados_api_watch_notify: reorder tests
- Group by function, not language/pool type.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision 300131ea (ceph): osd: send watch DISCONNECT to client when a watch is removed
- This is an explicit notification to the client that a watch is no longer
valid and needs to be re-registered.
Signed... - 06:32 PM Revision cdc9f5f2 (ceph): ceph_test_rados_api_watch_notify: test watch disconnect, reconnect
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision b5751947 (ceph): scratchtoolpp: suppress deprecation warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 6c83ec57 (ceph): librados: mark deprecated watch/notify methods with deprecated attribute
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 1b6bcfe3 (ceph): librados: mark old rollback method deprecated
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 5e794c11 (ceph): librados: mark old object listing api deprecated
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 22572a39 (ceph): librados: add infrastructure to deliver an error notification
- Use a reusable context in the WatchNotifyInfo to trigger an error
event, delivered via the existing Finisher thread. ... - 06:32 PM Revision 5e113ce2 (ceph): rados: improve watch command output
- - hexdump the notify payload, and include all of the new metadata
- print error events too
Signed-off-by: Sage Weil ... - 06:32 PM Revision e4241033 (ceph): osdc/Objecter: separate WATCH from RECONNECT
- Use WATCH op for the initial registration. This is idempotent in that
it will succeed whether the watch information ... - 06:32 PM Revision 909bdbc5 (ceph): osdc/Objecter: queue an error if reconnect fails
- If we fail to reconnect, trigger the on_error (reusable) context to
let the user know about it.
Signed-off-by: Sage ... - 06:32 PM Revision bdef13c9 (ceph): osdc/Objecter: send regular PING ops
- Send a full PING op to the object to ensure we are still connected. For
now just use the existing ping interval; we m... - 06:32 PM Revision 89e033c7 (ceph): clean up CEPH_WATCH_EVENT_* namespace, and make COMPLETE distinct
- Use a proper prefix and make a separate event for the notify completion
message.
Signed-off-by: Sage Weil <sage@redh... - 06:32 PM Revision 29802bf5 (ceph): ceph_test_rados_api_watch_notify: s/handle/cookie/
- Use consist nameing for C and C++ tests.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision e8f36efd (ceph): ceph_test_rados_api_watch_notify: verify we get the right # of notifies
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 66747c8b (ceph): osd/Watch: fix comment typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 7c8a1cd3 (ceph): osd/Watch: drop redundant in_progress_watchers
- This is essentially watchers.size() at all times and obfuscates the code.
In particular this makes the maybe_complete... - 06:32 PM Revision aa7ea5b9 (ceph): librados: behave if errcb is NULL
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision e0e90f71 (ceph): librados: EINVAL on bad args to watch2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 7f00b722 (ceph): osd/Watch: inform watchers when they cause a notify timeout
- If a watcher doesn't ack in time, let them know that they triggered a
notify failure.
Signed-off-by: Sage Weil <sage... - 06:32 PM Revision 10ac6295 (ceph): librados: tell watcher if we cause a notify timeout
- If we are a watcher and we fail to notify in a timely manner, or
circumstances otherwise conspire to prevent out ack ... - 06:32 PM Revision 1a82cc39 (ceph): osd, librados: distinguish between old and new watchers
- Use a new watch op code that is different from the legacy one so we can
tell when the client is doing all the new stu... - 06:32 PM Revision b76fc39a (ceph): osdc/Objecter: only ping watches (not notifies)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 83189b07 (ceph): make ping verify we are connected
- 06:32 PM Revision 26e2fc73 (ceph): osd/Watch: set timeout event for new watchers
- For a new watcher, we set the timeout event on connect, and reset it when
we get a ping.
For an old watcher, we cont... - 06:32 PM Revision 7e0c4efc (ceph): librados: define updated watch/notify interface
- - new notify callback with the correct values:
- notify_id
- watch handle
- payload
- new notify_ack call
- n... - 06:32 PM Revision 81cdff27 (ceph): osd: implement notify ack payloads
- If the notified send back reply payloads, pass them back to the notifier.
Note that we have changed the on-wire beha... - 06:32 PM Revision 7589bfcc (ceph): librados: update notify2 API to accept reply payloads
- Allow the notify2 callers to provide bufferlists or char ** pointers
so that we can pass the reply buffer back to the... - 06:32 PM Revision e1a3bc87 (ceph): ceph_test_rados_api_watch_notify: test notify2 api
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 8b409d49 (ceph): librados: include notifier's gid in notify
- The notify replies include the identify of everyone who acked the
notify. For symmetry, inform the notified client w... - 06:32 PM Revision 6183dccd (ceph): osd: allow multiple watchers/notify replies per client
- It is perfectly valid to register multiple watchers via the same
librados client. Make the notify_replies a multimap... - 06:32 PM Revision 6af4e1f6 (ceph): librados: unconditionally pass WATCH_NOTIFY to legacy callback
- This was always WATCH_NOTIFY; just pass that explicitly. No need to
pay attention to what's in the message.
Signed-... - 06:32 PM Revision 0d6aa20d (ceph): librados: define CEPH_OSD_WATCH_OP_*
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision 73720130 (ceph): librados: use new watch op codes; simplify Objecter helpers
- - drop the useless add_watch() helper; do it explicitly
- drop the unused var arg everywhere
- make a separate notify... - 06:32 PM Revision 2e508d05 (ceph): osdc/Objecter: fix assert_src_version
- Don't use the add_watch() helper; do it like assert_version
does it.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 PM Revision 2288f318 (ceph): librados: define RECONNECT and PING watch ops
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision d44bd2b0 (ceph): osd/ReplicatedPG: handle PING and RECONNECT watch ops
- The ping will essentially assert that a watch is still valid.
A reconnect will reestablish session state *only* if t... - 06:32 PM Revision 97661e1a (ceph): librados: remove crufty declaration
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:32 PM Revision c973c93f (ceph): librados: define error callback
- This is the async notification of a watch error (failure to reconnect to
the object's OSD after a peering event or ne... - 06:31 PM Revision 12940c9f (ceph): librados: drop useless ver arg to _notify_ack
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:31 PM Revision 96d06a5f (ceph): Merge pull request #3076 from ceph/wip-mon-mdsdne
- MDSMonitor.cc: fix assertion caused by MDSMap::STATE_DNE state
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:13 PM Revision 19e6c586 (ceph): Merge pull request #3072 from ceph/wip-10231-gperftools-location
- heap_profiler: support new gperftools header locations
gitbuilders are happy
Reviewed-by: Sage Weil <sage@redhat.com> - 06:11 PM Revision 12098b41 (ceph): Merge pull request #3084 from ceph/wip-rados-include
- librados: Fix rados include problem reported by "sponce"
Reviewed-by: Sage Weil <sage@redhat.com> - 06:06 PM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- I'm sorry, that I forgot use correct format before, so it omitted some character:...
- 06:04 PM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Wenjun Huang wrote:
> Sorry for my carelessness, I meant:
> @if (r == -ENOENT || r == -ENOATTR)
> continue;@
... - 06:06 PM Revision 22c1d9b0 (ceph): librados: Fix rados include problem reported by "sponce"
- Caused by a03f85a8e7fab296ea2df70a929a1c5e4aa0f7fb
Signed-off-by: David Zafman <dzafman@redhat.com> - 06:05 PM Revision cc469b23 (ceph): erasure-code: enforce chunk size alignment
- Let say the ErasureCode::encode function is given a 4096 bytes
bufferlist made of a 1249 bytes bufferptr followed by ... - 06:05 PM Revision ad04a677 (ceph): common: add bufferlist::rebuild_aligned_size_and_memory
- The function bufferlist::rebuild_aligned checks memory and size
alignment with the same variable. It is however usefu... - 06:05 PM Revision 5205d4da (ceph): common: allow size alignment that is not a power of two
- Do not assume the alignment is a power of two in the is_n_align_sized()
predicate. When used in the context of erasur... - 06:04 PM Revision f9c602a2 (ceph): Merge pull request #3059 from dachary/wip-10125-radosgw-init
- rgw: run radosgw as apache with systemd
Reviewed-by: Sage Weil <sage@redhat.com> - 05:57 PM Revision 7b621f4a (ceph): rgw: run radosgw as apache with systemd
- Same as sysv.
http://tracker.ceph.com/issues/10125 Fixes: #10125
Signed-off-by: Loic Dachary <loic@dachary.org> - 05:30 PM Revision cad4edce (ceph): Merge pull request #2997 from ceph/wip-snapmapper
- osd: require SNAPMAPPER feature; drop tolerate_collection_add_enoent
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:29 PM Revision a6a8aeae (ceph): Merge pull request #2979 from ceph/wip-kill-category
- osd: kill 'category' from pg_stats_t
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:26 PM Revision d212ced8 (ceph): Merge pull request #2694 from dachary/wip-9728-jerasure-neon
- erasure-code: jerasure support for NEON
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:25 PM Revision 08aa6d3e (ceph): Merge pull request #3082 from scuttlemonkey/wip-doc-10247
- Changed os-recommendation table sorting to remove implied bias.
Reviewed-by: Sage Weil <sage@redhat.com> - 05:25 PM Revision 473e36ca (ceph): Merge pull request #3048 from ceph/wip-10209
- osd: tolerate sessionless con in fast dispatch path
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 05:24 PM Revision 6b270898 (ceph): Merge pull request #3049 from dachary/wip-10211-erasure-code-buffer-ali...
- erasure-code: enforce chunk size alignment
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:15 PM Revision 3f2f42dd (ceph): doc/release-notes: v0.89
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:39 PM Revision c0685ec7 (ceph): Merge remote-tracking branch 'gh/next'
- 04:27 PM Revision 237b29c2 (ceph): Changed os-recommendation table sorting to remove implied bias.
- Fixes: #10247
signed-of by: Patrick McGarry <pmcgarry@redhat.com> - 04:11 PM Revision a6102f0b (ceph): documentation: add centos 7 to ceph-deploy installation
- http://tracker.ceph.com/issues/10246 Fixes: #10246
Signed-off-by: Loic Dachary <ldachary@redhat.com> - 03:49 PM devops Feature #10046 (In Progress): run make check on every pull request
- https://github.com/ceph/ceph-build/pull/35
- 03:05 PM Revision 1fba28f9 (ceph): WBThrottle: Call posix_fadvise to free page cache if nocache set in cle...
- Because FileStore will sync fs and call clear() to clear all pending
ghobjct. So in clear(), the pending object can f... - 03:05 PM Revision 7631b102 (ceph): os: add filestore_fadvise to control whether use posix_fadvise.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:10 PM Revision ec2677ea (ceph): Merge pull request #3024 from ceph/wip-librados-symbols
- librados: Only public API symbols from the shared library
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:58 PM Bug #10063 (Fix Under Review): ceph_objectstore_tool does not support getting attributes for eras...
- * firefly backport https://github.com/ceph/ceph/pull/3089
* giant backport https://github.com/ceph/ceph/pull/3088
- 01:29 PM Bug #10125 (Fix Under Review): radosgw is being started as root not apache with systemd
- 12:07 PM Bug #10125: radosgw is being started as root not apache with systemd
- * giant backport https://github.com/ceph/ceph/pull/3085
* firefly backport https://github.com/ceph/ceph/pull/3086 - 10:03 AM Bug #10125 (Pending Backport): radosgw is being started as root not apache with systemd
- 09:58 AM Bug #10125 (Fix Under Review): radosgw is being started as root not apache with systemd
- ...
- 04:45 AM Bug #10125: radosgw is being started as root not apache with systemd
- I would like to test it manually but I don't know how to get a centos7 VPS. Help ?
- 01:23 PM Fix #9566 (In Progress): osd: prioritize recovery of OSDs with most work to do
- 01:22 PM Bug #9785 (Fix Under Review): /etc/ceph/dmcrypt-keys and key contents are created world-readable
- https://github.com/ceph/ceph/pull/3087
- 12:44 PM Bug #10246 (Fix Under Review): add el7 to the list of supported version for centos in ceph-deploy...
- 08:06 AM Bug #10246: add el7 to the list of supported version for centos in ceph-deploy installation instr...
- https://github.com/ceph/ceph/pull/3081
- 08:00 AM Bug #10246 (Resolved): add el7 to the list of supported version for centos in ceph-deploy install...
- http://ceph.com/docs/master/start/quick-start-preflight/#red-hat-package-manager-rpm
- 12:28 PM Revision e42df6af (ceph): MDSMonitor.cc: fix assertion caused by MDSMap::STATE_DNE state
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 11:31 AM rbd Bug #10030 (Resolved): Crash when attempting to open non-existent parent image
- 10:37 AM CephFS Bug #10248 (New): messenger: failed Pipe;:connect::assert(m) in Hadoop client
- We have logs and a core dump from the QA run: http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-30_23:12:01-hado...
- 10:05 AM Bug #10211 (Fix Under Review): gf-complete exit(1) because of misaligned structure
- giant backport https://github.com/ceph/ceph/pull/3083
- 10:00 AM Bug #10211 (Pending Backport): gf-complete exit(1) because of misaligned structure
- 09:25 AM Feature #9728 (Resolved): erasure-code: jerasure support for NEON
- 09:24 AM Documentation #10247 (Resolved): Alpha sort os-recommendataions
- 08:14 AM Documentation #10247 (Resolved): Alpha sort os-recommendataions
- to remove implied bias.
- 09:24 AM Bug #10209 (Resolved): osd/OSD.cc: 5410: FAILED assert(session)
- 09:11 AM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- CentOS7 needs...
- 07:55 AM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- For RHEL, we should cover the basics of "Check if you're subscribed to Red Hat with @subscription-manager@ ?" and "ru...
- 07:53 AM Documentation #10245: RPM quick start for RHEL should explain where to get tcmalloc & python-flask
- Bumping the priority so that it gets triaged
- 07:47 AM Documentation #10245 (Resolved): RPM quick start for RHEL should explain where to get tcmalloc & ...
- http://ceph.com/docs/master/start/quick-start-preflight/#red-hat-package-manager-rpm...
- 08:59 AM rgw Bug #10066: rgw: failed md5sum on s3tests-test-readwrite
- That's the conf file I'm using for reproduction:...
- 07:12 AM Fix #10244 (New): double resource for setting up ceph-deploy
- And one of them is missing instructions on installing via RPM.
This causes issues with users that find the incompl... - 07:02 AM Revision 80463596 (ceph): Merge pull request #3062 from ceph/wip-10123-giant
- librbd: protect list_children from invalid child pool IoCtxs
Reviewed-by: Sage Weil <sage@redhat.com> - 07:02 AM Revision 4e201554 (ceph): Merge pull request #3064 from ceph/wip-10123-dumpling
- librbd: protect list_children from invalid child pool IoCtxs
Reviewed-by: Sage Weil <sage@redhat.com> - 07:01 AM Revision e2ec37bf (ceph): Merge pull request #3063 from ceph/wip-10123-firefly
- librbd: protect list_children from invalid child pool IoCtxs
Reviewed-by: Sage Weil <sage@redhat.com> - 06:56 AM Linux kernel client Bug #4553 (Can't reproduce): kclient: lockdep report, crash involving ceph fs and libceph
- 06:39 AM Revision f9bd970e (ceph): Merge pull request #3028 from majianpeng/fix4
- Add perf reset command.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:36 AM rgw Bug #10243: civetweb is hitting a limit (number of threads 1024)
- The problem is in [1] as:
#define MAX_WORKER_THREADS 1024
I changed this to "MAX_WORKER_THREADS 20480" and it worke... - 04:00 AM rgw Bug #10243 (Resolved): civetweb is hitting a limit (number of threads 1024)
- When setting "rgw thread pool size" to a number higher than 1024 and enabling civetweb 'rgw_frontends="civetweb port=...
- 06:30 AM rbd Bug #10123 (Resolved): "Segmentation fault" in upgrade:dumpling-x-firefly-distro-basic-vps run
- 06:21 AM Bug #10067 (Can't reproduce): ::posix_memalign abort ceph::buffer::create_page_aligned in 0.80.7
- 06:04 AM Bug #10067: ::posix_memalign abort ceph::buffer::create_page_aligned in 0.80.7
- The ...
- 05:37 AM Bug #10067: ::posix_memalign abort ceph::buffer::create_page_aligned in 0.80.7
- ...
- 05:21 AM Bug #10067: ::posix_memalign abort ceph::buffer::create_page_aligned in 0.80.7
- It's a stress split test therefore no erasure code involved after upgrading to firefly.
- 05:32 AM Revision f11fd66f (ceph): Merge pull request #3074 from ceph/wip-10229
- osdc/Filer: use finisher to execute C_Probe and C_PurgeRange
- 05:26 AM Revision d3ee89ac (ceph): osdc/Filer: use finisher to execute C_Probe and C_PurgeRange
- Currently contexts C_Probe/C_PurgeRange are executed while holding
OSDSession::completion_lock. C_Probe and C_PurgeRa... - 05:05 AM Revision f2ebce04 (ceph): doc: fix formatting in README
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:05 AM Revision 5d79dd97 (ceph): test: make read/write test simpler
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:05 AM Revision 507dc20b (ceph): doc: add read/write example to readme
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 05:03 AM Revision 43d5c7ca (ceph): crush: fix crush_calc_straw() scalers when there are duplicate weights
- The straw bucket was originally tested with uniform weights and with a
few more complicated patterns, like a stair st... - 05:02 AM Revision 85498bc8 (ceph): crush: fix distortion of straw scalers by 0-weight items
- The presence of a 0-weight item in a straw bucket should have no effect
on the placement of other items. Add a test ... - 04:54 AM Bug #10042 (Duplicate): OSD crash doing object recovery with EC pool
- http://tracker.ceph.com/issues/8588
- 04:48 AM Bug #10065 (Duplicate): hung ec-lost-unfound.yaml, failed of osd.{0,2,3}
- http://tracker.ceph.com/issues/10211
- 04:47 AM Revision 04fbadc6 (ceph): test: add basic read/write test
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 04:14 AM Revision b0bfca11 (ceph): doc: add badges
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 03:51 AM Bug #8588 (In Progress): In the erasure-coded pool, primary OSD will crash at decoding if any dat...
- 03:42 AM Bug #10017 (Fix Under Review): OSD wrongly marks object as unfound if only the primary is corrupt...
- https://github.com/ceph/ceph/pull/3034 ready for review
- 12:33 AM Bug #10242: FAILED assert(backfill_targets.empty() || backfill_targets == want_backfill)
- Since the osd went down, so please upgrade the priority and severity.
- 12:19 AM Bug #10242 (Can't reproduce): FAILED assert(backfill_targets.empty() || backfill_targets == want_...
- version: 0.80.7
config:
osd max backfills = 1
osd recovery max active = 1
One osd went down after hitting...
12/03/2014
- 09:31 PM CephFS Bug #10229: Filer: lock inversion with Objecter
- 10:40 AM CephFS Bug #10229 (Resolved): Filer: lock inversion with Objecter
- Saw this on a next test (http://qa-proxy.ceph.com/teuthology/sage-2014-12-01_11:11:17-fs-next-distro-basic-multi/6289...
- 09:17 PM Revision a45663c5 (ceph): Merge pull request #212 from ceph/wip-9117-wusui
- Move output in task/s3readwrite
- 09:02 PM Bug #10241 (Resolved): Incorrect OSD mapping with EC 6+2 setup in Giant
- Hit this on the performance test cluster during nightly giant testing. Notice the very incorrect mapping....
- 08:44 PM Revision 6edaf4e7 (ceph): heap_profiler: support new gperftools header locations
- The google/ headers location has been deprecated as of gperftools 2.0.
As of gperftools 2.2rc, the google/ headers wi... - 07:11 PM Feature #10198: PG removal occupy the disk thread several hours
- Samuel Just wrote:
> Radosgw creates unbounded size index objects, will change eventually.
Hi Sam,
It is more like... - 06:45 PM Revision d5e2c2cf (ceph): mon: fix signed/unsigned comparison warning
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:56 PM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Sorry for my carelessness, I meant:
@if (r == -ENOENT || r == -ENOATTR)
continue;@ - 04:10 AM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Samuel Just wrote:
> Right, the deleting the object portion is what I was talking about. I think that's the right w... - 05:43 PM Bug #10176: Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- See PR - https://github.com/ceph/ceph-qa-suite/pull/253
- 05:25 PM Revision 9565621d (ceph): crush: default to straw_calc_version 1
- Stick with bobtail tunables where it affects compatibility. Use v1 of
straw_calc, though, since that does not, and w... - 05:25 PM Revision f35a3d88 (ceph): crush: pass crush_map * to various builder methods
- In particular, we will need it for crush_calc_straw().
Signed-off-by: Sage Weil <sage@redhat.com> - 05:25 PM Revision 7c120363 (ceph): crush/builder: break out new version 1 of crush_calc_straw
- No change, yet.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:25 PM Revision 50e2ceef (ceph): crush: add straw_calc_version tunable
- It doesn't do anything, yet.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:24 PM Revision c133a83f (ceph): crush/CrushWrapper: dump chooseleaf_vary_r with other tunables
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:24 PM Revision 3877f008 (ceph): crush/CrushTester: add new --show-mappings option
- This makes --show-utilization and --show-statistics usable.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:24 PM Revision 35062937 (ceph): crush: recalculate straw scalers during a reweight
- The crushtool --reweight function triggers a fresh calculation of bucket
weights so that they are always the sum of t... - 05:24 PM Revision 294b06c6 (ceph): crushtool/CrushTester: output utilization even with 1 batch
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:24 PM Revision 7a99b489 (ceph): osdmaptool: --test-map-pgs-dump
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:24 PM rgw Bug #10195: s3 java jdk conn.getobject(...) (get s3 object) method fails with latest version of a...
- Both test runs used the exact same code, same endpoint, same authentication keys, and same GET request. The only thin...
- 04:18 PM Revision 68fdc0f6 (ceph): 0.89
- 03:28 PM Revision 6e69955a (ceph): Merge pull request #3065 from ceph/wip-cephtool-exec
- qa: fix cephtool tests not getting run
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:26 PM Revision d98cec7f (ceph): qa: fix teardown in cephtool's test_mon_mds
- This was missing from 17b5fc9a but we didn't notice
because the test wasn't being run by the gitbuilders.
Signed-off... - 02:44 PM Revision 26e8cf17 (ceph): Merge pull request #3055 from ceph/wip-10135-giant
- mon: OSDMonitor: allow adding tiers to FS pools
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:52 PM Feature #10231: gperftools headers have moved
- Work-in-progress pushed to https://github.com/ceph/ceph/tree/wip-10231-gperftools-location, submitted for review at h...
- 12:44 PM Feature #10231 (Resolved): gperftools headers have moved
- The @google/@ headers location has been deprecated as of gperftools 2.0. As of gperftools 2.2rc, the @google/@ header...
- 10:18 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- ...
- 10:10 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- Here is a tentative approach. The idea is to accumulate authoritative peers instead of just keeping the last one. For...
- 08:56 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- Exploring a two options:
* changing PG::scrub_compare_maps to collect all shards for a given missing object so tha... - 08:49 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- When the primary shard is lost in k=2, m=2, the PG has an unfound object (because, as explained in the description) t...
- 08:45 AM rgw Bug #10227 (Duplicate): "Segmentation fault" radosgw() in smoke-master-distro-basic-multi suite
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-30_02:35:03-smoke-master-distro-basic-multi/626596...
- 08:35 AM rbd Feature #10226 (New): Add pool quota reporting for Libvirt and other clients
- Currently when adding a Ceph RBD pool into Libvirt it will set the pool size as the maximum capacity of the entire cl...
- 08:20 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- The initial run for this report passed - http://pulpito.front.sepia.ceph.com/teuthology-2014-12-02_17:00:03-upgrade:f...
- 06:56 AM CephFS Fix #10135 (Resolved): OSDMonitor: allow adding cache pools to cephfs pools already in use
- 26e8cf174b8e76b4282ce9d9c1af6ff12f5565a9
- 05:33 AM Revision 8cd1fdd7 (ceph): SimpleMessenger: allow RESETSESSION whenever we forget an endpoint
- In the past (e229f8451d37913225c49481b2ce2896ca6788a2) we decided to disable
reset of lossless Pipes, because lossles... - 05:25 AM Bug #10211: gf-complete exit(1) because of misaligned structure
- For the record, strace on the process shows:...
- 05:16 AM CephFS Bug #10164 (Fix Under Review): Dirfrag objects for deleted dir not purged until MDS restart
- https://github.com/ceph/ceph/pull/3071
- 04:56 AM Revision c4f93499 (ceph): Merge pull request #3044 from osynge/wip=suse-systemd
- better systemd support
Reviewed-by: Sage Weil <sage@redhat.com> - 04:53 AM Revision cbac4609 (ceph): Merge pull request #3067 from dachary/wip-cephtool
- fix cephtools running only part of the tests + avoid killing wrong daemons
Reviewed-by: Sage Weil <sage@redhat.com> - 02:33 AM Bug #10202 (Can't reproduce): ceph_objecstore_tool.py : OSD has the store locked
- Thanks for trying, since armv8 based machines & the ubuntu distribution matching are not out yet, let's close this.
- 02:28 AM Revision 8e5dbe7d (ceph): common/perf_counters: Remove the duplicated code.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:26 AM Revision 963b7649 (ceph): test/perf_counters: Replace perfcounters_dump to perf dump.
- The func of command perfcounters_dump and 'perf dump' are the same .
But from the print 'ceph --admin-daemon help', ... - 02:23 AM Revision eafb2245 (ceph): test/perf_counters: Add test case for cmd 'perf reset'
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 02:10 AM Revision 5f8186b1 (ceph): common/perf_counters: Add 'perf reset all|perfcountername' for 'ceph
- --admin-daemon'
Using this command, we can reset all perfcounters or reset on specified
perfcounter.
Signed-off-by:... - 12:23 AM Revision f152bc69 (ceph): Merge pull request #3068 from ktdreyer/doc-os-recommendations-cleanup
- doc: os recommendations cleanup
Reviewed-by: Loic Dachary <ldachary@redhat.com>
12/02/2014
- 11:33 PM Revision 5d3bff04 (ceph): doc: rm Fedora minor versions in os recommendations
- Fedora doesn't have point releases, so it doesn't make sense to talk
about "Fedora 18.0" or "Fedora 19.0" - it's just... - 11:20 PM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- I reported KV OSD init problem as #10225.
- 11:19 PM Revision bc5a22b5 (ceph): osd: require SNAPMAPPER feature from peers
- This was introduced before cuttlefish. We require users to upgrade first
to a newer release, so there is no need to ... - 11:19 PM Revision 0d4dd10b (ceph): os/ObjectStore: drop tolerate_collection_add_enoent
- This is no longer needed and clutters the interface.
Signed-off-by: Sage Weil <sage@redhat.com> - 11:18 PM Revision e83321ee (ceph): Merge pull request #3061 from ktdreyer/rpm-ceph-disk-man-page
- packaging: package ceph-disk(8)
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:18 PM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- Oh yeah, another thing: some filestore based OSDs crash at the end of boot sequence so I didn't bother to start them ...
- 11:15 PM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- I didn't do anything to Ceph because cluster was down so I didn't even start those OSDs. No upgrades to Ceph was depl...
- 11:01 PM Bug #10225: keyvaluestore: OSDs do not start after few weeks of downtime (osd init failed / unabl...
- Hmm, I'm not sure why this happen. It seemed keyvaluestore lose "osd_superblock"?
Do you upgrade ceph? - 10:45 PM Bug #10225 (Closed): keyvaluestore: OSDs do not start after few weeks of downtime (osd init faile...
- On "Giant" I've created seven KV OSDs (on 4 or 5 different hosts) before cluster went down due to cascade of OSD cras...
- 11:13 PM Revision b743a951 (ceph): packaging: package ceph-disk(8)
- The ceph-disk man page was added in
a450cab2b8148cb8a9b043d629feccf89e5aabac, but this was not added to the
RPM or DE... - 10:55 PM Revision 2497f16a (ceph): doc: rm old releases in os recommendations page
- Similar to the change in commit
4cdc9c793627eec13c65543c09c604ec27a4dd8a, remove the references to old
Ceph releases.... - 10:55 PM Revision 0bb2e1ed (ceph): doc: clarify "B" flag in os recommendations page
- We don't exactly do continuous builds on all the platforms marked with
"B", but we have published binary RPMs for the... - 10:54 PM Bug #10202: ceph_objecstore_tool.py : OSD has the store locked
On a virtual machine.
$ cat /etc/issue
Ubuntu 14.04 LTS \n \l
$ uname -a
Linux ubuntu 3.13.0-24-generic #46-U...- 03:09 PM Bug #10202: ceph_objecstore_tool.py : OSD has the store locked
- It is ubuntu 14.04 on ARMv8
- 12:57 PM Bug #10202: ceph_objecstore_tool.py : OSD has the store locked
Could this be a platform specific bug using init-ceph to kill daemons? Do we know what platform they are running on?- 10:52 PM Revision e3e57415 (ceph): tests: vstart_wrapper.sh must call vstart.sh with a list of daemons
- The list of daemons is provided in the $CEPH_START environment variable
but vstart_wrapper.sh incorrectly uses the $V... - 10:52 PM Revision 3047c9e0 (ceph): qa: cephtool/test.sh use regular strings to list tests
- Using the array notation to list test is error prone and more
complicated to write.
It also fixes a bug : only the f... - 10:32 PM Revision 946bebd9 (ceph): crush: add dprintk's for crush_calc_straw
- These are compiled out by default.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:48 PM Revision 1b656450 (ceph): osd: initialize purged_snap on backfill start; restart backfill if change
- If we backfill a PG to a new OSD, we currently neglect to initialize
purged_snaps. As a result, the first time the s... - 09:48 PM Revision c4c63e82 (ceph): ReplicatedPG: don't move on to the next snap immediately
- If we have a bunch of trimmed snaps for which we have no
objects, we'll spin for a long time. Instead, requeue.
Fix... - 09:46 PM Revision 7cd8c3f8 (ceph): mon: OSDMonitor: allow adding tiers to FS pools
- This was an overly-strict check. In fact it is perfectly
fine to set an overlay on a pool that is already in use
as ... - 09:32 PM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- https://github.com/ceph/ceph/pull/3070
- 08:15 PM Revision 73ad2d63 (ceph): common: allow size alignment that is not a power of two
- Do not assume the alignment is a power of two in the is_n_align_sized()
predicate. When used in the context of erasur... - 08:15 PM Revision 4e955f41 (ceph): erasure-code: enforce chunk size alignment
- Let say the ErasureCode::encode function is given a 4096 bytes
bufferlist made of a 1249 bytes bufferptr followed by ... - 08:15 PM Revision 9ade88e8 (ceph): common: add bufferlist::rebuild_aligned_size_and_memory
- The function bufferlist::rebuild_aligned checks memory and size
alignment with the same variable. It is however usefu... - 07:23 PM Revision 56dae09b (ceph): doc: Reformatting on rbd replay doc.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:23 PM Revision b8f6b5f7 (ceph): doc: Added rbd-replay-many and restructured index.
- Signed-off-by: John Wilkins <john.wilkins@inktank.com>
- 07:23 PM Revision 54d5ed37 (ceph): doc: Fixed index syntax.
- Signed-off-by: John Wilkins <jowilkin@redhat.com>
- 07:09 PM Revision deaae3f5 (ceph): Merge pull request #3051 from ceph/wip-doc-rbd-replay
- doc: Document RBD Replay
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 07:07 PM Revision b1aa23ee (ceph): Merge pull request #3060 from ktdreyer/doc-os-recommendations-centos-7
- doc: add CentOS 7 to recommended OSes
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 06:53 PM Revision 3012c4a0 (ceph): doc: add CentOS 7 to recommended OSes
- CentOS 7 was missing from the list of recommended OSes for Firefly. Add
it to the list.
Reported-By: Frank Even <lis... - 06:07 PM Revision 547bfcfd (ceph): librbd: don't close an already closed parent image upon failure
- If librbd is not able to open a child's parent image, it will
incorrectly close the parent image twice, resulting in ... - 06:04 PM Revision 02d4685c (ceph): librbd: don't close an already closed parent image upon failure
- If librbd is not able to open a child's parent image, it will
incorrectly close the parent image twice, resulting in ... - 06:03 PM Revision 3ff94ed7 (ceph): librbd: don't close an already closed parent image upon failure
- If librbd is not able to open a child's parent image, it will
incorrectly close the parent image twice, resulting in ... - 05:39 PM Revision 06fe0f6f (ceph): Merge pull request #2993 from theanalyst/s3/keystone-date-fixes
- rgw: check for timestamp for s3 keystone auth
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:25 PM Revision 108dab6a (ceph): Update vps.yaml
- See http://tracker.ceph.com/issues/10178
- 05:24 PM Revision 2bb1e524 (ceph): Update vps.yaml
- 05:16 PM Revision 2604ae09 (ceph): Merge pull request #3058 from nilamdyuti/wip-doc-ceph-disk
- doc: Adds man page for ceph disk in TOC.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:04 PM Revision 6862891c (ceph): doc: Adds man page for ceph disk in TOC.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 03:41 PM Bug #10153: Rados.shutdown() dies with Illegal instruction (core dumped)
- This is not specific to rados.py, of course.
- 01:15 PM Bug #10153: Rados.shutdown() dies with Illegal instruction (core dumped)
- This was fixed by the application of commit:92615ea and commit:cf2104d in master. Please backport to firefly.
- 02:19 PM Revision adaa291e (ceph): Merge pull request #3056 from ceph/wip-9997-1
- client: invalidate kernel dentries one by one
Reviewed-by: John Spray <john.spray@redhat.com> - 01:49 PM Revision 491da517 (ceph): client: invalidate kernel dentries one by one
- Our trick to trim the whole kernel dentry tree does not work for 3.18+ kernel.
The fix is trim kernel dentries one by... - 01:47 PM Bug #9487 (Resolved): dumpling: snaptrimmer causes slow requests while backfilling. osd_snap_trim...
- 01:43 PM Bug #9891 (Rejected): "Assertion: os/DBObjectMap.cc: 1214: FAILED assert(0)" in upgrade:firefly-x...
- 01:40 PM Bug #10085 (Resolved): dirty exit ("Illegal instruction") on pthread_rwlock_unlock()
- 01:39 PM Bug #10157: PGLog::(read|write)_log don't write out rollback_info_trimmed_to
- 01:37 PM Bug #9459 (Can't reproduce): osd: blocked request
- 01:36 PM Bug #8595 (Resolved): osd: client op blocks until backfill starts (dumpling)
- 01:35 PM Bug #10126 (Rejected): "Exception: timed out waiting for admin_socket" in upgrade:giant-x-next-di...
Second time this was reproduced a misc.log was available. The load average was 17 on node with osd.13 which must n...- 01:34 PM Bug #9806 (Pending Backport): Objecter: resend linger ops on split
- 01:34 PM Bug #9806 (Resolved): Objecter: resend linger ops on split
- 01:34 PM Bug #8885 (Can't reproduce): SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- 01:33 PM Bug #9731 (Can't reproduce): Ceph 0.80.6 OSD crashes
- 01:32 PM Messengers Bug #9898 (Pending Backport): osd: fast dispatch deadlock in mark_down (giant)
- 01:32 PM Messengers Bug #9898 (Resolved): osd: fast dispatch deadlock in mark_down (giant)
- 01:31 PM Revision 8fc35500 (ceph): tasks/ceph: move FS creation inside Filesystem
- Leave the legacy handling out in cephfs_setup, move
the filesystem creation stuff into Filesystem. I
anticipate this... - 01:30 PM Bug #10058 (Can't reproduce): next stuck in recovery, no progress
- 01:30 PM Revision 89beed1b (ceph): tasks/ceph: conservative PG count in FS pools
- This was tripping over the recent commit 42c85e80
in Ceph master, which tightens the limits on
acceptable PG counts p... - 01:28 PM Bug #10105 (Can't reproduce): crash in PG::peek_map_epoch on upgrade from 0.80.4 to 0.80.7
- 01:27 PM Bug #10138 (Need More Info): osd: crash in SnapSet::from_snap_set
- 01:19 PM Bug #8797: "ceph status" do not exit with python_2.7.8
- The SIGILL was cured in master with the application of 92615ea and cf2104d. I've tested backporting these to firefly ...
- 01:18 PM Bug #10209: osd/OSD.cc: 5410: FAILED assert(session)
- 01:18 PM Bug #10178 (Resolved): mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- 01:18 PM Revision 017f669c (ceph): Merge pull request #3052 from ceph/wip-flush-journal-fix
- mds: fix race of trimming log segments
Reviewed-by: John Spray <john.spray@redhat.com> - 01:17 PM Bug #9939 (Resolved): "giant" no longer log scrub errors
- commit:d392f44891a064e08f28244673c43a869e1f6014
- 01:14 PM Bug #10109 (Duplicate): "LibRadosTwoPoolsECPP.PromoteSnap" test failed in upgrade:dumpling-firefl...
- 01:13 PM Bug #10113 (Duplicate): --log-to-stderr with -f/-d sends a lot of things to logfile
- #9180
- 01:13 PM Bug #10124 (Rejected): monitor recieves bus error signal
- leveldb bug
- 01:11 PM Bug #10146 (In Progress): ceph-disk: sometimes the journal symlink is not created
- Still open, needs tests.
- 01:10 PM Bug #10146 (Resolved): ceph-disk: sometimes the journal symlink is not created
- 01:10 PM Bug #10118 (Need More Info): messenger drops messages between osds
- 01:08 PM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Right, the deleting the object portion is what I was talking about. I think that's the right way.
- 01:07 PM Bug #10173 (Resolved): autogen.sh will fail if submodule URL changes
- 01:06 PM Bug #10175 (Resolved): deps.deb.txt is obsolete
- 01:06 PM Feature #10198: PG removal occupy the disk thread several hours
- Radosgw creates unbounded size index objects, will change eventually.
- 12:41 PM rgw Bug #10015 (Fix Under Review): rgw sync agent: 403 when syncing object that has tilde in its name
- PR opened https://github.com/ceph/radosgw-agent/pull/12
- 11:37 AM rbd Bug #10122: "LibRBD.TestClone" FAILED in upgrade:dumpling-x-firefly-distro-basic-vps run
- Josh, can you take a look? Not sure if the project has to change to rbd or not tho.
- 11:35 AM Revision aac79461 (ceph): Merge pull request #2990 from ceph/wip-10151-giant
- mon: fix MDS health status from peons
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:57 AM Bug #9788: "Assertion: common/HeartbeatMap.cc: 79" placeholder for "hit suicide timeout" issues
- One more in run http://pulpito.ceph.com/teuthology-2014-12-01_18:18:01-upgrade:firefly-x-giant-distro-basic-vps/
L... - 10:56 AM rgw Bug #10066: rgw: failed md5sum on s3tests-test-readwrite
- test fails, and can be reproduced with the specific random seeds, with a specific object size (at the larger side of ...
- 10:53 AM rgw Bug #10221 (Resolved): Crash in "radosgw-admin" in upgrade:firefly:singleton-firefly-distro-basic...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-01_17:05:01-upgrade:firefly:singleton-firefly-dist...
- 10:50 AM Revision fd3aaec8 (ceph): Merge pull request #249 from ceph/wip-9557
- tasks: add mds_auto_repair
Reviewed-by: John Spray <john.spray@redhat.com> - 10:27 AM rgw Bug #10062: s3-test failures using keystone authentication
- Hi Yehuda, Sage
the patch addressed only the first 5 or so failures as mentioned.
The post_object* tests were s... - 09:38 AM rgw Bug #10062 (Resolved): s3-test failures using keystone authentication
- 09:38 AM rgw Bug #10062: s3-test failures using keystone authentication
- Fix merged into master.
- 10:12 AM rbd Bug #9513 (Resolved): rbd_cache=true default setting is degading librbd performance ~10X in Giant
- Reverted in master commit:b808cdfaa8823f0747f78938f3ed9a7a75e9bed1
Reverted in Giant commit:3b1eafcabb6139133b5ff0bd... - 10:11 AM Linux kernel client Bug #9896: krbd: EPERM from map-snapshot-io.sh
- /a/teuthology-2014-10-24_23:06:01-krbd-giant-testing-basic-multi/570830...
- 10:09 AM rbd Bug #9936 (Resolved): Exporting images larger than 2GB fails
- 10:09 AM rbd Bug #9936: Exporting images larger than 2GB fails
- Master: commit:4b87a81c86db06f6fe2bee440c65fc05cd4c23ce
Giant: commit:65c565701eb6851f4ed4d2dbc1c7136dfaad6bcb
- 09:50 AM rgw Bug #10162 (Duplicate): s3tests-test-readwrite failure
- A duplicate of #10082
- 09:34 AM rgw Bug #10188: Can not create new rgw user when specifying an email already assigned to a user
- That's by design. Users cannot share the same email, as S3 permissions can be granted by email address, so email need...
- 09:32 AM rgw Bug #10195 (Need More Info): s3 java jdk conn.getobject(...) (get s3 object) method fails with la...
- Can you provide rgw log (debug rgw = 20), for such a failed request?
- 09:32 AM Revision d0641b0e (ceph): Merge pull request #2994 from dachary/wip-10175-compile-dependencies
- script replacement for deps.{rpm,deb}.txt
Reviewed-by: Ken Dreyer <kdreyer@redhat.com>
Reviewed-by: Thorsten Behrens... - 09:29 AM rgw Bug #10106: rgw acl response should start with <?xml version="1.0" ?>
- Note that Amazon's API definition does not specify this:
http://docs.aws.amazon.com/AmazonS3/latest/API/RESTObjectGE... - 09:28 AM rbd Bug #10116 (Need More Info): Ceph vm guest disk lockup when using fio
- Warren, can you provide an stack backtraces from when you encountered the issue and a list of any OSD ops-in-flight?
- 09:24 AM rgw Bug #10108 (Duplicate): s3tests fail in upgrade:dumpling-firefly-x:parallel-next-distro-basic-mul...
- Duplicate of #10082
- 09:24 AM rbd Bug #9078 (Rejected): Removing an RBD is very slow whenever there is write's in other RBD which a...
- 09:23 AM rbd Bug #9742 (Resolved): `rbd map lun` fails with: (2) No such file or directory on kernel 3.14.14 w...
- 09:22 AM rgw Bug #10121 (Duplicate): "test.functional.tests.TestAccountUTF8" error in upgrade:dumpling-x-firef...
- Duplicate of #10082
- 09:20 AM rbd Bug #8329 (Won't Fix): qemu-img rpm provided breaks snapshooting functionality on centos
- 09:18 AM rgw Bug #9886 (Resolved): rgw: apache 2.4 does not send http status reason string
- 09:11 AM Bug #10125: radosgw is being started as root not apache with systemd
- https://github.com/ceph/ceph/pull/3059
- 09:11 AM rgw Bug #10145 (Can't reproduce): rgw swift functional test: testChunkedPut (test.functional.tests.Te...
- 09:11 AM rgw Bug #10144 (Can't reproduce): rgw swift functional test: testChunkedPut (test.functional.tests.Te...
- 09:08 AM rgw Bug #9899 (Resolved): Error "coverage ceph osd pool get '' pg_num" in upgrade:dumpling-dumpling-d...
- 09:05 AM Bug #10220 (Resolved): "mon/Paxos.cc: 1033: FAILED assert(mon->is_leader())" in upgrade:dumpling-...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-12-01_18:25:01-upgrade:dumpling-firefly-x:stress-spli...
- 09:04 AM rgw Bug #10219 (Resolved): s3-tests failing to clone
- http://pulpito.ceph.com/sage-2014-12-01_11:07:39-rgw-next-distro-basic-multi
- 08:26 AM Revision d7618311 (ceph): tasks: add mds_auto_repair
- New CephFS tests for MDS's auto repair functions. (So far the only
test case is verify/repair backtrace on fetch dirf... - 08:20 AM Revision 2fa4884f (ceph): mds: fix race of trimming log segments
- trimming old log segments can start new log segments, make sure
MDLog::trim_all() not expire newly started log segmen... - 08:01 AM devops Bug #10218 (Rejected): "Gem::DependencyError" error in upgrade:firefly-x-next-distro-basic-vps run
- In run http://pulpito.front.sepia.ceph.com/teuthology-2014-12-01_17:18:01-upgrade:firefly-x-next-distro-basic-vps/
... - 07:35 AM Revision acc3bf6c (ceph): librbd: protect list_children from invalid child pool IoCtxs
- While listing child images, don't ignore error codes returned
from librados when creating an IoCtx. This will prevent... - 07:34 AM Revision af121942 (ceph): librbd: protect list_children from invalid child pool IoCtxs
- While listing child images, don't ignore error codes returned
from librados when creating an IoCtx. This will prevent... - 07:33 AM Revision 3dc62982 (ceph): librbd: protect list_children from invalid child pool IoCtxs
- While listing child images, don't ignore error codes returned
from librados when creating an IoCtx. This will prevent... - 06:57 AM CephFS Bug #9997 (Resolved): test_client_pin case is failing
- Merged to next (https://github.com/ceph/ceph/pull/3056)
- 06:53 AM CephFS Bug #10217 (Resolved): old fuse should warn on flock
- This works in master.
- 06:19 AM CephFS Bug #10217: old fuse should warn on flock
- yes, we need recent version of ceph-fuse and MDS. old version does not support interrupting flock
- 03:37 AM CephFS Bug #10217 (Resolved): old fuse should warn on flock
Test failure: test_filelock (tasks.mds_client_recovery.TestClientRecovery):
http://pulpito.front.sepia.ceph.com/sa...- 05:40 AM devops Tasks #8366: Update ceph.com/docs to default to the latest major release (0.80)
- 04:47 AM Revision 9e3e4c8e (ceph): Merge pull request #3041 from xiaoxichen/cleanup-noop
- Cleanup noop in message
Reviewed-by: Sage Weil <sage@redhat.com> - 04:45 AM Revision 70e1a5dc (ceph): doc: Document RBD Replay
- Signed-off-by: Adam Crume <adamcrume@gmail.com>
- 03:46 AM CephFS Fix #10135 (Fix Under Review): OSDMonitor: allow adding cache pools to cephfs pools already in use
- giant backport PR: https://github.com/ceph/ceph/pull/3055
- 03:35 AM CephFS Bug #10151 (Resolved): mds client cache pressure health warning oscillates on/off
- The version on next has a pass on client-limits (the one that exercises health): http://pulpito.front.sepia.ceph.com/...
- 02:48 AM Revision dafef3c2 (ceph): mds: add asok command to force MDS readonly
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:48 AM Revision 9b9e3edf (ceph): mds: allow choosing action for wirte error
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:48 AM Revision 131f0922 (ceph): mds: don't blindly create empty object when dirfrag is missing
- mark the corresponding CDir as bad instead.
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:47 AM Revision 4f6474f2 (ceph): mds: disallow write operations when MDS is readonly
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:47 AM Revision 2d4a746f (ceph): mds: don't trim log when MDS is readonly
- When MDS is readonly, keep metadata objects (not include the journal) of
cephfs unchanged. This allows us to submit n... - 02:47 AM Revision 4aed0476 (ceph): mds: keep locks in sync state when MDS is readonly
- when transit locks to sync state, we may submit new entries to the log.
This should be safe as long as we don't trim ... - 02:47 AM Revision cfef5151 (ceph): mds: disallow slave requests when MDS is readonly
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:47 AM Revision 44d9abb5 (ceph): mds: disable misc internal activitiles when MDS is readonly
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:47 AM Revision 5db3bbf5 (ceph): mds: disallow reconnectiong to readonly MDS
- this force reconnecting clients to drop any write caps.
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:47 AM Revision e0637b47 (ceph): mds: add helper to force MDS readonly
- the helper function marks MDS readonly, then revokes write caps from
clients.
Signed-off-by: Yan, Zheng <zyan@redhat... - 02:47 AM Revision f7169038 (ceph): mds: notify clients when MDS goes to readonly
- notice clients that MDS goes to readonly and MDS won't issue write
caps any more.
Signed-off-by: Yan, Zheng <zyan@re... - 02:47 AM Revision 6b59eade (ceph): client: handle MDS 'force readonly' message
- make client return -EROFS for write when MDS is readonly, instead of
waiting forever.
Signed-off-by: Yan, Zheng <zya... - 02:15 AM Revision 01df2227 (ceph): osd: tolerate sessionless con in fast dispatch path
- We can now get a session cleared from a Connection at any time. Change
the assert to an if in ms_fast_dispatch to co... - 02:05 AM Revision 25fc21b8 (ceph): Merge pull request #3008 from ceph/wip-10135
- mon: OSDMonitor: allow adding tiers to FS pools
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 01:59 AM Revision 65f68148 (ceph): Merge pull request #3047 from ceph/wip-10011-giant
- osdc: fix Journaler write error handling [giant backport]
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 01:30 AM Revision 772a0d53 (ceph): Merge pull request #3050 from dachary/wip-10213-const
- msg: do not const methods that return a mutable pointer
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 01:20 AM Revision 0f1c9fd1 (ceph): msg: do not const methods that return a mutable pointer
- Add remove misleading const on post_rx_buffer argument.
http://tracker.ceph.com/issues/10213 Fixes: #10213
Signed-o... - 12:14 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- Fixed #10211 that showed up while experimenting
12/01/2014
- 11:27 PM Bug #10216 (Resolved): gf-complete and jerasure call exit(1)
- On error, gf-complete and jerasure call exit(1) instead of assert. This causes the OSD to disapear instead of display...
- 11:06 PM Bug #10211 (Fix Under Review): gf-complete exit(1) because of misaligned structure
- 04:26 PM Bug #10211 (In Progress): gf-complete exit(1) because of misaligned structure
- https://github.com/ceph/ceph/pull/3049
- 01:00 PM Bug #10211: gf-complete exit(1) because of misaligned structure
- https://github.com/ceph/gf-complete/pull/1
- 01:00 PM Bug #10211 (Resolved): gf-complete exit(1) because of misaligned structure
- Steps to reproduce (this is fragile because it depends on the version of the allocator):
* rm -fr dev out ; mkdir... - 10:42 PM Bug #10215 (Fix Under Review): vstart_wrapper.sh kills daemons that do not belong to it
- https://github.com/ceph/ceph/pull/3054
- 10:28 PM Bug #10215 (Resolved): vstart_wrapper.sh kills daemons that do not belong to it
- When vstart_wrapper.sh "calls vstart.sh":https://github.com/ceph/ceph/blob/master/src/test/vstart_wrapper.sh#L32 it u...
- 07:01 PM Revision 26a33c3a (ceph): Move output in task/s3readwrite
- The s3readwrite.py task formerly wrote too much output while excuting.
It now saves the data on the local machine in ... - 06:05 PM CephFS Fix #10135 (Pending Backport): OSDMonitor: allow adding cache pools to cephfs pools already in use
- merged to next in commit:25fc21b837ba74bab2f6bc921c78fb3c43993cf5
This also should go into giant (I think Firefly ... - 05:58 PM CephFS Bug #10011 (Resolved): Journaler: failed on shutdown or EBLACKLISTED
- giant commit:65f6814847fe8644f5d77a9021fbf13043b76dbe
- 06:37 AM CephFS Bug #10011 (Fix Under Review): Journaler: failed on shutdown or EBLACKLISTED
- Haven't seen any failures around this, let's backport to giant: https://github.com/ceph/ceph/pull/3047
- 05:47 PM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- I'll turn that fpaste into a real patch and get Sam or somebody to put it in some testing so we should at least see i...
- 05:37 PM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- If a connection gets marked down, we *cannot* reconnect to that endpoint again; it needs to recycle itself to a new e...
- 05:37 PM Revision 4e1f4cfe (ceph): rados: drop optional 'create [category]' arg
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:37 PM Revision d229548d (ceph): osd/ReplicatedPG: drop cateogry support from CREATE
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:37 PM Revision 5ecdce3b (ceph): osdc/Objecter: drop category from copy-get
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:37 PM Revision 0d6c803d (ceph): osd/osd_types: drop category from object_info_t
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:37 PM Revision 3008ca4e (ceph): rados: change 'df' output now that categories are gone
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:36 PM Revision 39c46a2d (ceph): PendingReleaseNotes: not about dropping category
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:36 PM Revision c94c33b9 (ceph): mon/PGMonitor: do not report per-category stats
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:36 PM Revision ee3b5b26 (ceph): osd/osd_types: remove cat_sum from object_stat_collection_t
- This type is now just a useless wrapper around object_stat_sum_t, but that
is not easy to drop.
Note that now if we ... - 05:36 PM Revision ee4f6d72 (ceph): osd/osd_types: drop useless conditionals on object_info_t decode
- The incompat decode version is 8, so we will never see struct_v < 5.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:36 PM Revision 080fae6e (ceph): librados: mark category args and ops as unused
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:36 PM Revision 5020bbe2 (ceph): librados: add new get_pool_stats() variant; deprecate others
- A new call will return a simple map of pool -> stats. Drop the old ones
that did pool -> category -> stats, and depr... - 05:36 PM Revision bebcd146 (ceph): librados: drop create category args
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:36 PM Revision 387d055f (ceph): osd: stop doing per-category accounting
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:29 PM Bug #10213 (Resolved): Some inappropriate consts
- Thanks!
- 05:21 PM Bug #10213 (Fix Under Review): Some inappropriate consts
- My apologies for not being careful enough on this review. https://github.com/ceph/ceph/pull/3050
- 02:15 PM Bug #10213 (Resolved): Some inappropriate consts
- https://github.com/ceph/ceph/pull/3011/files
https://github.com/ceph/ceph/pull/3037/files
These added some consts... - 05:23 PM Revision f868ca04 (ceph): Merge pull request #2825 from ceph/wip-9921
- SimpleMessenger: Pipe: do not block on takeover while holding global locks
Reviewed-by: Sage Weil <sage@redhat.com> - 05:23 PM Revision dff5b739 (ceph): AsyncMessenger: Make WorkerPool use CephContext's singleton
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:23 PM Revision 7fed5dee (ceph): CephContext: Add AssociatedSingletonObject to allow CephContext's singl...
- If some objects associated to CephContext want to create a singleton object,
it can inherit AssociatedSingletonObject... - 05:16 PM Bug #10214 (Resolved): crush: straw buckets do not have expected/desired properties
- two issues:
- straw scaling factors calculated for straw buckets do not produces the correct distribution when the... - 05:10 PM Revision 8cb8854f (ceph): Merge pull request #3046 from yuyuyu101/fix-kinetic
- KnieticStore: add necessary header file
Reviewed-by: Sage Weil <sage@redhat.com> - 05:08 PM Revision 44b101c8 (ceph): Merge pull request #2922 from ceph/wip-da-SCA-20141111
- Coverity fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 05:07 PM Revision 77deeaa4 (ceph): Merge pull request #2937 from simon3z/master
- common: do not unlock rwlock on destruction
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Sage Weil <sage... - 05:05 PM Revision 310a3f1c (ceph): Merge pull request #2945 from ceph/wip-9321
- mon: PaxosService: can be readable even if proposing
Reviewed-by: Sage Weil <sage@redhat.com> - 05:05 PM Revision 42c85e80 (ceph): Merge pull request #2788 from ceph/wip-warn-max-pg
- mon: warn when there are too many pgs per osd
Reviewed-by: Joao Eduardo Luis <joao@redhat.com>
Reviewed-by: Samuel J... - 05:00 PM Revision 34f0bfd1 (ceph): Merge pull request #2735 from ceph/wip-pg-stat
- mon: make 'pg stat -f json' not pg dump; make JSON dump of floats floats and not strings
Reviewed-by: Samuel Just <s... - 03:15 PM Revision 06593813 (ceph): documentation: replace deps.{deb,rpm}.txt with scripts
- install-deps.sh installs the dependencies based on the content of
debian/control (if apt-get is found) or ceph.spec.i... - 02:37 PM Revision 9158326e (ceph): osdc: fix Journaler write error handling
- Since we started wrapping the write error
handler in a finisher, multiple calls to
handle_write_error would hit the a... - 02:24 PM Revision e0190bd3 (ceph): KnieticStore: add necessary header file
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:23 PM Revision 49bedd4c (ceph): ObjectStoreBenchmark: Used to perf ObjectStore::Transaction
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:45 PM Revision 929fcd67 (ceph): better systemd support
- Added ceph.target
Made ceph-mds, ceph-mon, ceph-osd services part of ceph.target
Made ceph-mds, ceph-mon, ceph-osd se... - 01:35 PM Revision 3376fee9 (ceph): Cleanup noop in message
- The noop loop are dead, so clean it up
Signed-off-by: Xiaoxi Chen <xiaoxi.chen@intel.com> - 12:20 PM Revision f9e2112b (ceph): Merge pull request #2855 from ceph/wip-9881
- #9881 MDS flush journal asok command
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 12:18 PM rgw Bug #10195: s3 java jdk conn.getobject(...) (get s3 object) method fails with latest version of a...
- typo... in bug title/description anywhere you see "jdk" I meant "sdk"... it was late before thanksgiving when I compo...
- 12:09 PM Revision 2ec67733 (ceph): mds: fix MDLog I/O callback without finisher
- This could deadlock if another caller was waiting
on a write_head callback while holding mds_lock.
Signed-off-by: Jo... - 12:09 PM Revision efeaaaa0 (ceph): mds: in segment expiry, use end instead of start
- Previously we were always leaving the last log
segment un-expired from Journaler's POV, because
we were updating expi... - 12:09 PM Revision 5b5493db (ceph): mds: implement "flush journal" asok
- Start a new segment and flush everything older
to the backing store.
Signed-off-by: John Spray <john.spray@redhat.com> - 10:28 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Modified vps.yaml:...
- 06:35 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- mon_lease_ack_timeout: 25...
- 09:38 AM Revision dba078a1 (ceph): Cycles: A precious performance profile tool using rdstc
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 09:30 AM Bug #10209 (Fix Under Review): osd/OSD.cc: 5410: FAILED assert(session)
- https://github.com/ceph/ceph/pull/3048
- 09:23 AM Bug #10209 (In Progress): osd/OSD.cc: 5410: FAILED assert(session)
- 08:50 AM Bug #10209 (Resolved): osd/OSD.cc: 5410: FAILED assert(session)
- This was with wip-sam-testing, but I don't think it's related to any of the patches.
ubuntu@teuthology:/a/samuelj-... - 09:22 AM Bug #9921 (Pending Backport): msgr/osd/pg dead lock giant
- 09:04 AM Bug #9321 (Resolved): pgmap updates from OSDMap can be delayed indefinitely
- 08:53 AM Bug #10210 (Closed): "Caught signal" in upgrade:dumpling-x-firefly-distro-basic-vps run
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-29_19:13:03-upgrade:dumpling-x-firefly-distro-basi...
- 06:59 AM CephFS Bug #10164 (In Progress): Dirfrag objects for deleted dir not purged until MDS restart
- Zheng: assigning to you since you mentioned you were working on it
- 06:34 AM CephFS Bug #9997 (Fix Under Review): test_client_pin case is failing
- https://github.com/ceph/ceph/pull/3045
- 04:42 AM CephFS Bug #9994: ceph-qa-suite: nfs mount timeouts
- http://pulpito.ceph.com/teuthology-2014-11-23_23:10:01-knfs-next-testing-basic-multi/617093/
http://pulpito.ceph.com... - 04:20 AM CephFS Feature #9881 (Resolved): mds: admin command to flush the mds journal
- Merged to master (forgot the Fixes:, doh)...
- 01:57 AM RADOS Bug #9523: Both op threads and dispatcher threads could be stuck at acquiring the budget of files...
- > I am wondering if it makes sense to add a new parameter named *should_take_filestore_budget* to dispatch_context an...
11/30/2014
- 11:35 PM RADOS Bug #9523: Both op threads and dispatcher threads could be stuck at acquiring the budget of files...
- There seems two problems here:
# Dispatcher thread hang due to filestore throttling
# Op thread hang due to filesto... - 10:31 PM Revision efdfec48 (ceph): Merge pull request #3037 from stiopaa1/cleanup
- added some consts, some cleanup
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:01 PM Revision 62a8f2d9 (ceph): added consts, cleanup
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 06:23 PM Revision 1a8aea71 (ceph): AsyncMessenger: Fix thread destroy when no active Messenger
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 06:12 PM Revision 83b86d4d (ceph): Merge pull request #3015 from dachary/wip-9665-ceph-disk-partprobe-dump...
- ceph disk zap must call partprobe
- 06:12 PM Revision c982da44 (ceph): Merge pull request #3014 from dachary/wip-9665-ceph-disk-partprobe-firefly
- ceph disk zap must call partprobe
- 01:35 PM Linux kernel client Bug #10208: libceph: intermittent hangs under memory pressure
- The kern.log attached, with the data got shortly after running the following command:
time dd if=/dev/zero of=4G00... - 11:15 AM devops Bug #9665 (Resolved): ceph-disk zap should call partprobe
- 09:23 AM Revision f1296fd8 (ceph): Merge pull request #3019 from theanalyst/doc/typo/ceph-auth
- doc: minor fix in ceph-authtool man page
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:18 AM Revision f3d97282 (ceph): Merge pull request #3023 from ktdreyer/rpm-rbd-replay-prep-conditional
- rpm: unconditionally package rbd-replay-prep(8)
Reviewed-by: Adam Crume <adamcrume@gmail.com> - 05:50 AM Revision faa4cbbe (ceph): doc: minor fix in ceph-authtool man page
- Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com>
- 05:00 AM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- Haomai Wang wrote:
> A related bug is fixed. But I'm not fully sure whether fix this problem.
I'm not sure which...
11/29/2014
- 11:45 PM Linux kernel client Bug #10208 (Resolved): libceph: intermittent hangs under memory pressure
11/28/2014
- 11:04 PM Revision 936542c6 (ceph): Merge pull request #3032 from dachary/wip-osd-log-cosmetics
- osd: log message content cosmetics
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@redhat.com> - 05:02 PM Revision 0fe5bc60 (ceph): osd: log message content cosmetics
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 04:59 PM Revision 8658911d (ceph): common: admin sock output XML elements whitespace
- Replace white space with underscore in XML elements displayed from admin
socket commands. <config get>...</config get... - 01:01 PM Documentation #10207 (New): documentation: auth service required needs clarification
- In http://ceph.com/docs/master/rados/configuration/auth-config-ref/#configuration-settings the distinction between *a...
- 12:59 PM Revision bc90df1e (ceph): Merge pull request #2769 from ceph/wip-9557
- mds: verify backtrace when fetching dirfrag
Reviewed-by: John Spray <john.spray@redhat.com> - 12:49 PM Documentation #10206 (Resolved): documentation: Network Configuration Reference duplicate string
- The string *You may configure this range at your discretion.* shows twice in http://ceph.com/docs/master/rados/config...
- 12:41 PM Documentation #10205 (Resolved): documentation: reference to ceph-deploy should be a link
- In http://ceph.com/docs/master/rados/configuration/ceph-conf/#running-multiple-clusters the phrase *See ceph-deploy n...
- 12:36 PM Documentation #10204 (Resolved): documentation: mon should be listed before osd
- When deploying a Ceph cluster, the mon must be run first. In the list shown at http://ceph.com/docs/master/rados/conf...
- 12:28 PM Documentation #10203 (Resolved): documentation: explain the term MON
- http://ceph.com/docs/master/rados/ should read *and a Ceph Monitor (MON) maintains* of *and a Ceph Monitor maintains*...
- 12:08 PM Feature #9815 (Resolved): run make check in parallel
- 12:07 PM Bug #10201 (Fix Under Review): tests must use ceph_objectstore_tool
- https://github.com/ceph/ceph/pull/3033
- 07:55 AM Bug #10201 (Resolved): tests must use ceph_objectstore_tool
- Tests such as "osd-scrub-repair":https://github.com/ceph/ceph/blob/giant/src/test/osd/osd-scrub-repair.sh#L64 must no...
- 12:00 PM Feature #9403: Make rados import/export fully functional and re-enable
Created wip-9403 to preserve a change needed to make this feature work. Also, the existing code sort of supports x...- 10:20 AM Bug #10197: arch detection on armv8 must check asimd
- Janne, I would very much appreciate a run of src/unittest_arch on ARMv8 if you can spare the time ( the branch is htt...
- 10:17 AM Bug #10197 (Fix Under Review): arch detection on armv8 must check asimd
- https://github.com/ceph/ceph/pull/3035
- 09:44 AM Bug #10202 (Can't reproduce): ceph_objecstore_tool.py : OSD has the store locked
- Janne Grunau (jannau irc) can reproduce this reliably. I suspect it is because it does not wait long enough for the o...
- 09:25 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- https://github.com/ceph/ceph/pull/3034
- 06:12 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- The same problem shows up when two OSDs are missing (k=2, m=2).
- 08:59 AM Bug #10199 (Fix Under Review): ceph --format xml daemon {daemon}.{id} config get is not valid XML
- https://github.com/ceph/ceph/pull/3031
- 03:03 AM Bug #10199 (Resolved): ceph --format xml daemon {daemon}.{id} config get is not valid XML
- ...
- 07:12 AM Revision d3e286e7 (ceph): Merge pull request #3027 from majianpeng/fix1
- Add "make check" dep python-virtualenv in deps.rpm.txt
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:24 AM Revision b9d7f794 (ceph): Add "make check" dep python-virtualenv in deps.rpm.txt
- In fedora20, When 'make check' and met those error messages:
/src/test/run-cli-tests: virtualenv not installed, skip... - 05:43 AM Revision ea3d4d7a (ceph): AsyncConnection: Ensure "mark_down" complete when returned
- Now AsyncConnection try to process or modify any own variables within self
thread. It means actual function will be c... - 05:43 AM Revision 30194e80 (ceph): AsyncConnection: Introduce "signal" event
- Ensure signal cond after all previous events has be done
Signed-off-by: Haomai Wang <haomaiwang@gmail.com> - 05:43 AM Revision 5e478a53 (ceph): Event: Fix Coverity error
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:43 AM Revision 02c602fa (ceph): AsyncConnection: Avoid deadlock for AsyncConnection::lock
- accept and connection will be send to queue and deliver to dispatcher. So
it can avoid caller stuck into AsyncConnect... - 05:43 AM Revision f714697c (ceph): AsyncConnection: Skip delete_file_event if sd < 0
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 05:43 AM Revision bdedad28 (ceph): AsyncMessenger: Async event threads shared by all AsyncMessenger
- WorkerPool is a singleton class which is served to AsyncMessenger. All
AsyncMessenger used the same worker pool.
Sig... - 05:11 AM devops Bug #10200 (Rejected): tgtd error: undefined symbol: rbd_discard
- Saw this error in syslog from an unrelated test. Presumably this is a bug somewhere?
/a/teuthology-2014-11-23_23:... - 12:58 AM Feature #10198: PG removal occupy the disk thread several hours
- ...
- 12:56 AM Feature #10198 (Resolved): PG removal occupy the disk thread several hours
- We found an issue after we enable scrubbing/deep-scrubbing when doing recovering. The phenomenon is that all the rado...
- 12:57 AM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- Pull request - https://github.com/ceph/ceph/pull/3029
- 12:44 AM Revision 9ebff556 (ceph): doc: add semver note to readme
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:42 AM Revision 860a0316 (ceph): Merge pull request #5 from noahdesu/wip-travis-ci-build
- test: fix travis-ci builds
Signed-off-by: Noah Watkins noahwatkins@gmail.com - 12:36 AM Revision e89a709f (ceph): test: display stat changes
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:28 AM Revision 70e32582 (ceph): test: use micro-osd script to setup ci build
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:28 AM Revision d0609a1c (ceph): test: add micro-osd script for travis-ci build
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:27 AM Revision 802930e9 (ceph): test: check for any stat change
- The memstore doesn't seem to refresh kb_used, so we wait for anything to
change. It looks like num_objects changes fo... - 12:27 AM Revision a5f7bb13 (ceph): test: check numeric osd id
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 12:26 AM Revision e2332ecd (ceph): test: fix import path
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
11/27/2014
- 06:53 PM Revision ced9be02 (ceph): license: add MIT license
- Signed-off-by: Noah Watkins <noahwatkins@gmail.com>
- 06:27 PM Bug #10163: rados bench parameter -b producing wrong values when different blocksize used in writes
- From "rados --help":
-b op_size
set the size of write ops for put or benchmarking
We can see -b only for w... - 05:12 PM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- Guang Yang wrote:
> Update more logs from the *crashed* OSD:
> [...]
>
> It seems that the peer OSD was marked d... - 03:41 AM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- Update more logs from the *crashed* OSD:...
- 01:16 AM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- AFAR, if server rebind and client try to connect, client won't get CEPH_MSGR_TAG_SEQ tag from server because no repla...
- 12:02 AM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- > The next question is, why B's in_seq is a very large number even after rebinding?
After more deep dive, I think th... - 02:33 PM Bug #10197 (Resolved): arch detection on armv8 must check asimd
- instead of neon in https://github.com/ceph/ceph/blob/master/src/test/test_arch.cc...
- 09:17 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-26_09:31:02-upgrade:giant-x-next-distro-basic-vps/...
- 08:56 AM Revision 50de36ed (ceph): Merge pull request #3025 from majianpeng/fix1
- Add isa-erasure yasm dep for deps.rpm.txt
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:11 AM Revision c10d6390 (ceph): Add isa-erasure yasm dep for deps.rpm.txt
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:04 AM Bug #10196: [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other nodes.
- You are welcome! :)
- 05:50 AM Bug #10196 (Rejected): [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other...
- Thanks for the update :-)
- 03:15 AM Bug #10196: [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other nodes.
- The output of ssh in verbose mode just showed the error "Bad owner or permissions in /home/ceph/.ssh/config". So, the...
- 02:06 AM Bug #10196: [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other nodes.
- See also https://github.com/ceph/ceph/pull/3007
- 01:59 AM Bug #10196: [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other nodes.
- Could you please attach the output of ssh in verbose mode when trying to connect to the remote host ? That will show ...
- 01:19 AM Bug #10196 (Rejected): [RHEL7] Modification of ~/.ssh/config in admin node restricts ssh to other...
- While setting up Ceph cluster using RHEL7 VMs, I found that modifying ~/.ssh/config file in admin node with details i...
- 12:01 AM Revision 6a98dacd (ceph): rpm: unconditionally package rbd-replay-prep(8)
- The build system will conditionally build and install the
rbd-replay-prep utility based on the presence of lttng.
Co...
11/26/2014
- 11:34 PM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- Add some peer's logs to prove the two-ways connect:...
- 11:14 PM Feature #9420 (Fix Under Review): erasure-code: tools and archive to check for non regression of ...
- the "non regression tests":https://github.com/ceph/ceph/blob/master/qa/workunits/erasure-code/encode-decode-non-regre...
- 10:26 PM CephFS Bug #9997: test_client_pin case is failing
- For 3.18+ kernel, I think we can iterate the all dir inodes and invalidate dentry one by one.
- 12:19 AM CephFS Bug #9997: test_client_pin case is failing
- yes, I think it caused by the d_invalidate change. In 3.18-rc kernel, d_invalidate() unhash dentry regardless if the...
- 09:53 PM Revision dbb5a48e (ceph): librados: Only public API symbols from the shared library
- The librados shared library was previously exporting all
symbols. librados public API methods are now explicitly
exp... - 09:37 PM Revision 8766ca33 (ceph): Merge pull request #3022 from leseb/fix-opts
- Minor typos and trailing spaces
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:33 PM Revision 03a61d27 (ceph): Minor typos and trailing spaces
- Fix typos and trailing spaces.
Signed-off-by: Sébastien Han <sebastien.han@enovance.com> - 07:49 PM Feature #9951: librados, osd: per-object scrub operation
- Hi sage:
I'm interested in this feature(From that i'll know the process of scurb). Is there somebody already did... - 07:30 PM Revision c2c53d72 (ceph): Merge pull request #3016 from yuyuyu101/fix-kinetic-support
- KineticStore: Fix compile error and add _test_init
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:26 PM Revision 782a74cd (ceph): KineticStore: Fix compile error and add _test_init
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 06:24 PM Revision 60e7fddf (ceph): Merge pull request #2995 from nilamdyuti/wip-doc-ceph-disk
- doc: Adds man page for ceph-disk utility.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:21 PM Revision 76892c3b (ceph): Merge pull request #3021 from tchaikov/wip-fix-typos
- doc: fix some typos in ObjectStore.h
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:16 PM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- Hi Dmitry,
A related bug is fixed. But I'm not fully sure whether fix this problem. So could you give a crash keyv... - 05:01 PM Bug #9978: keyvaluestore: void ECBackend::handle_sub_read
- It's been another week -- is there any chance to get this fixed please?
- 06:04 PM Revision 21798f9a (ceph): doc: fix some typos in ObjectStore.h
- Signed-off-by: Kefu Chai <tchaikov@gmail.com>
- 05:17 PM Revision 7fd26c4d (ceph): Update vps.yaml
- Fixed syntax
- 05:17 PM Revision 7e0fd502 (ceph): Update vps.yaml
- Fixed syntax
- 04:51 PM Revision 016080d2 (ceph): doc: Adds the updated man page for ceph-disk utility.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 04:49 PM Revision 8a48847c (ceph): doc: Updates the man page for ceph-disk utility with some changes.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 03:56 PM rgw Bug #10195 (Closed): s3 java jdk conn.getobject(...) (get s3 object) method fails with latest ver...
- For instance,
in the Java example ( http://docs.ceph.com/docs/master/radosgw/s3/java/ )
The example: ... - 03:13 PM Revision 3b00c6f7 (ceph): safe_io: do not set ending \0 in safe_read_file()
- Signed-off-by: Kefu Chai <tchaikov@gmail.com>
- 03:09 PM rgw Bug #10194 (Resolved): rgw: fcgi connections are not closed when using mod-proxy-fcgi
- 10:23 AM Revision d6af0e4c (ceph): ceph-disk: use update_partition in prepare_dev and main_prepare
- In the case of prepare_dev the partx alternative was missing and is not
added because update_partition does it.
http... - 10:22 AM Revision 6de6f575 (ceph): ceph-disk: run partprobe after zap
- Not running partprobe after zapping a device can lead to the following:
* ceph-disk prepare /dev/loop2
* links are c... - 10:22 AM Revision f64d742e (ceph): ceph-disk: encapsulate partprobe / partx calls
- Add the update_partition function to reduce code duplication.
The action is made an argument although it always is -a... - 10:14 AM Revision c4e4a310 (ceph): ceph-disk: use update_partition in prepare_dev and main_prepare
- In the case of prepare_dev the partx alternative was missing and is not
added because update_partition does it.
http... - 09:59 AM Revision e70a8146 (ceph): ceph-disk: run partprobe after zap
- Not running partprobe after zapping a device can lead to the following:
* ceph-disk prepare /dev/loop2
* links are c... - 09:57 AM Revision 5a5f427b (ceph): ceph-disk: encapsulate partprobe / partx calls
- Add the update_partition function to reduce code duplication.
The action is made an argument although it always is -a... - 09:06 AM Feature #10192 (Fix Under Review): ceph_objectstore_tool object lookup
- https://github.com/ceph/ceph/pull/3020
- 05:04 AM Feature #10192 (Resolved): ceph_objectstore_tool object lookup
- It would be convenient for test purposes to have...
- 07:22 AM Feature #10193 (Resolved): Perf counter for WBThrottle
- Since sync thread will cause unstable iops and latency performance curve, we may want to WBThread do more(or moderate...
- 05:18 AM Revision 28e27080 (ceph): Merge pull request #3005 from dachary/wip-9665-ceph-disk-partprobe-giant
- ceph disk zap must call partprobe
- 04:40 AM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Wenjun Huang wrote:
> Samuel Just wrote:
> > This should probably be a feature request for the backlog. We need a ... - 02:18 AM devops Bug #9665: ceph-disk zap should call partprobe
- * firefly backport https://github.com/ceph/ceph/pull/3014
* dumpling backport https://github.com/ceph/ceph/pull/3015
11/25/2014
- 11:20 PM Revision 5b500fac (ceph): Merge pull request #3011 from stiopaa1/someConsts
- added some consts
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:58 PM Revision e6410ebf (ceph): added some consts
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 06:25 PM Revision e7faed5d (ceph): osd: deep scrub must not abort if hinfo is missing
- Instead it should set read_error.
http://tracker.ceph.com/issues/10018 Fixes: #10018
Signed-off-by: Loic Dachary <l... - 06:18 PM Revision 73b47dbe (ceph): osd: deep scrub must not abort if hinfo is missing
- Instead it should set read_error.
http://tracker.ceph.com/issues/10018 Fixes: #10018
Signed-off-by: Loic Dachary <l... - 04:54 PM Revision 17b5fc9a (ceph): mon: OSDMonitor: allow adding tiers to FS pools
- This was an overly-strict check. In fact it is perfectly
fine to set an overlay on a pool that is already in use
as ... - 04:35 PM Revision 6086ad53 (ceph): Fix fro #10178
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:30 PM Revision 3d47b730 (ceph): Fix for #10178
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 04:07 PM rgw Bug #8233: Installation & Documentation broken for Ubuntu Trusty 14.04 - rgw
- The 100-Continue stuff was all in fastcgi, not httpd. So you can use Ubunu's httpd 2.4 if you want. Here's the patch ...
- 03:57 PM Revision 8d3d6bf5 (ceph): erasure-code: workunit to check for encoding regression
- Clone the archive of encoded objects and decode all archived objects, up
to and including the current ceph version.
... - 03:57 PM Revision 5138091a (ceph): erasure-code: add corpus verification to make check
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
- 03:57 PM Revision 4f435870 (ceph): erasure-code: store and compare encoded contents
- Introduce ceph_erasure_code_non_regression to check and compare how an
erasure code plugin encodes and decodes conten... - 03:53 PM Revision 9a118d56 (ceph): doc: Adds man page for ceph-disk utility.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 03:46 PM Revision 242dd1c0 (ceph): doc: Removes ceph-deploy usage instances from ceph-disk man page.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 03:31 PM Revision 1b7fc7e4 (ceph): erasure-code: store and compare encoded contents
- Introduce ceph_erasure_code_non_regression to check and compare how an
erasure code plugin encodes and decodes conten... - 03:31 PM Revision 1def82d5 (ceph): erasure-code: workunit to check for encoding regression
- Clone the archive of encoded objects and decode all archived objects, up
to and including the current ceph version.
... - 03:31 PM Revision 208a5ee1 (ceph): erasure-code: s/alignement/alignment/ typos in jerasure
- The jerasure-per-chunk-alignment prameter was mispelled and while
useable that would lead to confusion.
Signed-off-b... - 03:31 PM Revision ca4c2702 (ceph): erasure-code: Makefile.am cosmetics
- Cluster benchmark related lines together.
Signed-off-by: Loic Dachary <loic-201408@dachary.org>
(cherry picked from ... - 03:31 PM Revision ba8ceb1f (ceph): erasure-code: add corpus verification to make check
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
(cherry picked from commit 6fdbdff2ad1b55d4a37dcb95cfbb06c4454c... - 03:31 PM Revision c855f395 (ceph): erasure-code: ceph_erasure_code does not need to avoid dlclose
- The only reason for not dlclosing plugins at exit is for callgrind but
ceph_erasure_code has no workload that would r... - 03:31 PM Revision da9a7f07 (ceph): erasure_code: implement ceph_erasure_code to assert the existence of a ...
- This is handy when scripting in the context of teuthology and only
conditionally run tests for the isa plugin, for in... - 03:31 PM Revision 32daa9b0 (ceph): erasure-code: add erasure_code_benchmark --verbose
- Signed-off-by: Loic Dachary <loic-201408@dachary.org>
(cherry picked from commit 3ff2816b3eecfb7277295583387549dac542... - 03:31 PM Revision 36c7484c (ceph): erasure-code: erasure_code_benchmark exhaustive erasure exploration
- Add the --erasure-generation exhaustive flag to try all combinations of
erasures, not just one at random.
Signed-off... - 03:09 PM rgw Documentation #10142 (Resolved): Update S3 compatibility table to reflect bucket location support
- 03:06 PM rgw Feature #10191 (Resolved): rgw: object versioning multi-zone support
- 03:05 PM rgw Feature #8216 (Fix Under Review): rgw: object versioning objclass support
- 03:05 PM rgw Feature #8218 (Fix Under Review): rgw: object versioning manifest changes
- 03:05 PM rgw Feature #8217 (Fix Under Review): rgw: object versioning object overwrite / delete changes
- 03:03 PM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- I think https://github.com/ceph/ceph-qa-suite/pull/250 reproduces the problem reliably. ...
- 02:47 PM Bug #10017 (In Progress): OSD wrongly marks object as unfound if only the primary is corrupted fo...
- 03:03 PM Bug #10126 (New): "Exception: timed out waiting for admin_socket" in upgrade:giant-x-next-distro-...
- 03:02 PM Bug #10126: "Exception: timed out waiting for admin_socket" in upgrade:giant-x-next-distro-basic-...
- Still an issue, not sure what to make of it.
Run http://pulpito.ceph.com/teuthology-2014-11-24_17:05:01-upgrade:gian... - 02:06 PM Revision 5c9cd3c2 (ceph): ceph-disk: encapsulate partprobe / partx calls
- Add the update_partition function to reduce code duplication.
The action is made an argument although it always is -a... - 02:06 PM Revision d9c04b88 (ceph): ceph-disk: use update_partition in prepare_dev and main_prepare
- In the case of prepare_dev the partx alternative was missing and is not
added because update_partition does it.
http... - 02:06 PM Revision cb1d6811 (ceph): ceph-disk: run partprobe after zap
- Not running partprobe after zapping a device can lead to the following:
* ceph-disk prepare /dev/loop2
* links are c... - 01:23 PM Bug #9788 (New): "Assertion: common/HeartbeatMap.cc: 79" placeholder for "hit suicide timeout" is...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-24_17:18:03-upgrade:firefly-x-next-distro-basic-vp...
- 01:17 PM Revision 990c6d5b (ceph): erasure-code: build and use a NEON jerasure variant
- 01:17 PM Revision 59f78b06 (ceph): erasure-code: always compile SSE and NEON tests
- They do not actually depend on CPU features and are required to validate
the plugin selection logic.
Signed-off-by: ... - 01:17 PM Revision a7888290 (ceph): erasure-code: include new headers in distribution
- The NEON optimization introduced new headers that must be listed
explicitly to be included in tarbals.
Signed-off-by... - 01:17 PM Revision cb820f81 (ceph): erasure-code: test NEON arch selection logic
- The jerasure plugin loads the plugin that matches the architecture
supported by the CPU at runtime. Include the NEON ... - 01:17 PM Revision ba520bf7 (ceph): erasure-code: conditionally build jerasure sse3/sse4 plugins
- 01:17 PM Revision cec00c9f (ceph): autotools: ARM/AArch64 NEON detection similar to x86
- 01:17 PM Revision 987d54b7 (ceph): aarch64: add support for HW_CAP based neon runtime detection
- 01:17 PM Revision 8351fd69 (ceph): erasure-code: gf-complete use neon enabled branch
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 01:14 PM Revision 80c816c7 (ceph): Merge pull request #3003 from dachary/wip-10185-neon
- arch: fix neon feature detection
Reviewed-by: Sahid Orentino Ferdjaoui <sahid.ferdjaoui@redhat.com> - 12:13 PM Documentation #6465: admin/build-doc should have some kind of build check for broken links
- No one else agrees this is urgent, so, dropping pri
- 11:44 AM Revision 0b985d2b (ceph): arch: fix neon feature detection
- The fread function returns the number of elements read, not the number
of bytes.
Introduced by 1cef8339f7a2a503327c2... - 11:07 AM Revision 2e1664c5 (ceph): Merge pull request #3002 from thesues/fix-init
- Remove pidfile and asok after stopping ceph
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:52 AM rgw Bug #10188 (Won't Fix): Can not create new rgw user when specifying an email already assigned to ...
- The error can be seen in the output of the commands below. In the first command we create a user "jj1" with an email ...
- 10:25 AM Bug #10018: OSD assertion failure if the hinfo_key xattr is not there (corrupted?) during scrubbing
- * firefly backport https://github.com/ceph/ceph/pull/3009
* giant backport https://github.com/ceph/ceph/pull/3010
- 10:03 AM Bug #10018 (Pending Backport): OSD assertion failure if the hinfo_key xattr is not there (corrupt...
- 10:04 AM Revision 24eb5647 (ceph): Remove pidfile and asok after stopping ceph
- Signed-off-by: Dongmao Zhang <deanraccoon@gmail.com>
- 09:27 AM CephFS Fix #10135 (Fix Under Review): OSDMonitor: allow adding cache pools to cephfs pools already in use
- https://github.com/ceph/ceph/pull/3008
- 08:44 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Committed vps.yaml on master, gaint and next
Fixed syntax for
@mon lease = 15@
to
@mon lease: 15@ - 06:55 AM Bug #9487 (Pending Backport): dumpling: snaptrimmer causes slow requests while backfilling. osd_s...
- oops, still need firefly
- 06:19 AM devops Bug #9665 (Fix Under Review): ceph-disk zap should call partprobe
- 06:19 AM devops Bug #9665: ceph-disk zap should call partprobe
- * giant backport https://github.com/ceph/ceph/pull/3005
- 06:17 AM Bug #10183: OSD dispatcher thread hangs several seconds due to contention for osd_lock
- https://github.com/ceph/ceph/pull/3004
- 05:51 AM Bug #9073 (Resolved): OSD with device/partition journals down after fresh deploy or upgrade to 0.83
- 05:46 AM Feature #9728: erasure-code: jerasure support for NEON
- 05:13 AM Bug #10185 (Resolved): neon runtime detection is always false
- 02:01 AM Bug #10185 (Fix Under Review): neon runtime detection is always false
- https://github.com/ceph/ceph/pull/3003
- 04:56 AM Revision 1f6d6168 (ceph): Merge pull request #255 from ceph/revert-251-wip-10178-firefly
- Revert "fix mon restart in firefly upgrade tests"
- 04:55 AM Revision f9a3afdd (ceph): Revert "fix mon restart in firefly upgrade tests"
- 04:42 AM CephFS Bug #9997: test_client_pin case is failing
- After much head scratching and log examination, this appears to be a kernel regression (assuming our behaviour was va...
- 04:00 AM Bug #10117: OSD crashes if xattr "_" is absent for the file when doing backfill scanning (Replica...
- Samuel Just wrote:
> This should probably be a feature request for the backlog. We need a test reproducing it and s... - 01:19 AM Revision aa4d1478 (ceph): Merge pull request #2996 from ceph/wip-10151
- mon: fix MDS health status from peons
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
11/24/2014
- 11:31 PM Bug #10185 (Resolved): neon runtime detection is always false
- The neon CPU feature detection function should test if the number of elements returned is 1 "instead of the size of t...
- 10:21 PM Bug #10166 (Fix Under Review): fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc...
- https://github.com/ceph/ceph/pull/3000
I'm not fully ensure that this issue is caused by inconsistence size. Maybe... - 12:14 PM Bug #10166: fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc: 8706: FAILED asse...
- Hmm, this might be as simple as truncating out to the full copy_range size.
- 12:11 PM Bug #10166: fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc: 8706: FAILED asse...
- Going back to the full log, it appears to be related to _do_sparse_copy_range and therefore fiemap:
2014-11-23 19:... - 11:38 AM Bug #10166: fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc: 8706: FAILED asse...
- /a/teuthology-2014-11-23_18:13:01-upgrade:firefly-x-giant-distro-basic-multi/615700
2014-11-23 19:18:14.224698 7f4... - 09:26 PM Revision c5d272c9 (ceph): Merge pull request #2872 from dachary/wip-10018-primary-erasure-code-hinfo
- osd: erasure code deep scrub must not abort if hinfo is missing
Reviewed-by: David Zafman <dzafman@redhat.com> - 08:52 PM Revision f4a7a106 (ceph): Merge pull request #253 from ceph/wip-firelfy-yuriw
- Removed import_export tests to fix #10176
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:47 PM Revision 29fa2ad3 (ceph): Merge pull request #2984 from stiopaa1/includeFix
- remove unneeded include file
Reviewed-by: Sage Weil <sage@redhat.com> - 08:36 PM Revision 7dcc8504 (ceph): doc: Updates man page for ceph-disk utility.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 08:21 PM Revision ed71f622 (ceph): Removed import_export tests to fix #10176
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
- 08:02 PM Revision e983230c (ceph): remove unneeded include file
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:56 PM rgw Documentation #10184 (Resolved): rgw: document swift temp url functionality
- Swift-temp-url functionality seems to have been merged from v0.78 or so. (Feature #3454) This needs to be documented....
- 07:35 PM Revision 5c92a0cb (ceph): Merge pull request #2998 from theanalyst/doc/rgw-s3-bucket-loc
- doc: rgw document s3 bucket location features.
Reviewed-by: John Wilkins <jowilkin@redhat.com> - 07:32 PM Revision 77c08433 (ceph): Merge pull request #251 from ceph/wip-10178-firefly
- fix mon restart in firefly upgrade tests
- 07:19 PM Revision ca66f591 (ceph): upgrade/firefly: do not wait for clean when restarting mons
- This may fail is the quorum features to not match.
Fixes: #10178
Signed-off-by: Sage Weil <sage@redhat.com> - 06:41 PM Bug #10183 (Resolved): OSD dispatcher thread hangs several seconds due to contention for osd_lock
- Recently when investigating the long tail latency during backfilling/recovering, I found on some OSDs, the dispatcher...
- 06:21 PM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Sage, OK
I changed vps.ayml on teuthology to:... - 05:36 PM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Yuri, new plan: let's just add 'mon lease = 15' to vps.yaml and see if this comes up again.
- 12:04 PM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- on giant fix - https://github.com/ceph/ceph-qa-suite/pull/252
- 11:24 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- RE: https://github.com/ceph/ceph-qa-suite/pull/251...
- 11:21 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- ok, new plan. instead of changing mon behavior, make the tests more resilient.
if we upgrade all mons, then resta... - 11:02 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- https://github.com/ceph/ceph/pull/2999
- 11:00 AM Bug #10178 (Fix Under Review): mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- 10:46 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- ...
- 10:34 AM Bug #10178: mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- ...
- 10:29 AM Bug #10178 (Resolved): mon rejects peer during election based on OSD_SET_ALLOC_HINT feature?
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-22_17:00:03-upgrade:firefly:newer-firefly-distro-b...
- 06:18 PM Revision 1be9476a (ceph): Merge pull request #2918 from ceph/wip-9113-9487-dumpling
- dumpling snap trimming
Tested-by: Dan Van Der Ster <daniel.vanderster@cern.ch> - 06:06 PM Revision a1ba3852 (ceph): doc: rgw document s3 bucket location features
- Fixes: #10142
Reported-by: Neil Levine <nlevine@redhat.com>
Signed-off-by: Abhishek Lekshmanan <abhishek.lekshmanan@r... - 05:59 PM Revision cd72cf2b (ceph): swift: set full access to subusers creation
- Default subuser permissions are 'none'.
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 05:22 PM Revision c8b46d68 (ceph): mon: fix MDS health status from peons
- The health data was there, but we were attempting
to enumerate MDS GIDs from pending_mdsmap (empty on
peons) instead ... - 05:19 PM CephFS Bug #10151 (Pending Backport): mds client cache pressure health warning oscillates on/off
- Merged to master as of commit:aa4d1478647ce416e9cf4e8fcd32411230639f40. I like to let things go through testing befor...
- 09:20 AM CephFS Bug #10151: mds client cache pressure health warning oscillates on/off
- Opened PR against master instead of next by mistake. Next PR is https://github.com/ceph/ceph/pull/2996
- 03:16 AM CephFS Bug #10151 (Fix Under Review): mds client cache pressure health warning oscillates on/off
- master: https://github.com/ceph/ceph/pull/2989
giant: https://github.com/ceph/ceph/pull/2990 - 05:18 PM Revision 0c33930e (ceph): mon: fix MDS health status from peons
- The health data was there, but we were attempting
to enumerate MDS GIDs from pending_mdsmap (empty on
peons) instead ... - 04:35 PM Revision a450cab2 (ceph): doc: Adds man page for ceph-disk utility.
- Signed-off-by: Nilamdyuti Goswami <ngoswami@redhat.com>
- 03:33 PM Revision a4222b43 (ceph): Merge pull request #2992 from dachary/wip-10173-autogen
- autogen.sh: git submodule sync
Reviewed-by: Sage Weil <sage@redhat.com> - 01:32 PM Revision 4b35ae06 (ceph): rgw: check for timestamp for s3 keystone auth
- This commit ensures that we check for timestamp of s3 request is within
acceptable grace time of radosgw
Addresses so... - 12:11 PM Bug #10165 (Duplicate): ceph_test_rados got short read
- 12:10 PM Bug #10165: ceph_test_rados got short read
- I think this also is due to enabling fiemap in the nightlies, teuthology commit:
0f97481ce44e0487ac6cffa051a05590f... - 10:34 AM Bug #10165: ceph_test_rados got short read
- Repeated issue in run http://pulpito.ceph.com/teuthology-2014-11-22_17:05:01-upgrade:giant-x-next-distro-basic-multi/...
- 08:36 AM Bug #10165: ceph_test_rados got short read
- Same problem in run http://pulpito.front.sepia.ceph.com/teuthology-2014-11-23_09:54:59-powercycle-giant-distro-basic-...
- 11:35 AM Revision 61cae541 (ceph): autogen.sh: git submodule sync
- It is not enough to git submodule update on a existing git clone: if the
URL of the repository has been changed, the
... - 11:28 AM rbd Bug #10180 (Resolved): qemu tests crash host kernel
- ...
- 11:16 AM Bug #10176: Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- I think we should remove import_export.sh from these tag-based upgrades, where we're hitting issues that are fixed la...
- 09:12 AM Bug #10176 (Resolved): Segmentation fault in upgrade:firefly:singleton-firefly-distro-basic-vps run
- Log are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-22_17:05:01-upgrade:firefly:singleton-firefly-distr...
- 11:04 AM rbd Bug #10123 (Pending Backport): "Segmentation fault" in upgrade:dumpling-x-firefly-distro-basic-vp...
- 10:49 AM Bug #8204: "timed out waiting for admin_socket to appear after osd.5 restart" in upgrade:dumpling...
- Same issue in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-21_17:18:01-upgrade:firefly-x-next-distro-basic-...
- 10:18 AM Bug #9487 (Resolved): dumpling: snaptrimmer causes slow requests while backfilling. osd_snap_trim...
- 10:17 AM Bug #9113 (Resolved): osd: snap trimming eats memory, linearly
- 09:47 AM Bug #10097: failed: mon_thrash
- Same issue in run http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-22_17:15:01-upgrade:giant-giant-distro-basic...
- 09:41 AM rgw Bug #10177 (Can't reproduce): test_multipart_upload failed in upgrade:dumpling-firefly-x:parallel...
- Logs are in http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-22_18:15:02-upgrade:dumpling-firefly-x:parallel-gi...
- 09:25 AM Bug #9920: admin socket check hang, osd appears fine
- Same issue in run http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-22_17:18:02-upgrade:firefly-x-next-distro-ba...
- 09:19 AM Bug #10018: OSD assertion failure if the hinfo_key xattr is not there (corrupted?) during scrubbing
- Same issue on next in run http://pulpito.ceph.com/teuthology-2014-11-22_17:18:02-upgrade:firefly-x-next-distro-basic-...
- 09:07 AM CephFS Bug #9997 (In Progress): test_client_pin case is failing
- 08:29 AM Revision 00da9744 (ceph): test: extend quota test case
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 07:40 AM devops Feature #10046: run make check on every pull request
- http://tracker.ceph.com/issues/10175 will make it possible to rely on the content of deps.deb.txt to install the requ...
- 07:38 AM Revision 5515cc41 (ceph): client: fix problem with move files between quota tree
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 07:33 AM Feature #9817 (Resolved): display X.XX deep-scrub starts
- 07:27 AM Revision 42974e12 (ceph): Merge pull request #2936 from ceph/wip-mailmap
- Update Inktank attribution to point to Red Hat
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:51 AM Bug #10175 (Fix Under Review): deps.deb.txt is obsolete
- https://github.com/ceph/ceph/pull/2994
- 05:18 AM Bug #10175 (Resolved): deps.deb.txt is obsolete
- It is not consistently maintained because it is not tested
- 06:34 AM Revision b2c15d6f (ceph): mds: Fix a problem with rstat refresh.
- rstat.version seems will always be zero, so it will block
the broadcast routine for rstat refresh.
Signed-off-by: Yu... - 05:12 AM Revision 12f1f21a (ceph): mailmap: Update Warren Usui's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:12 AM Revision 43c75ee4 (ceph): mailmap: Update Tyler Brekke's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:11 AM Revision 9df46244 (ceph): mailmap: Update Tamil Muthamizhan's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:10 AM Revision fb741524 (ceph): mailmap: Update Sandon Van Ness' attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:08 AM Revision c5d5e063 (ceph): mailmap: Update Samuel Just's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:06 AM Revision a6a2a055 (ceph): mailmap: Update Patrick McGarry's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:04 AM Revision 4d2f63e7 (ceph): mailmap: Update Noah Watkins' attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:02 AM Revision 4ee3a876 (ceph): mailmap: Update Neil Levine's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:01 AM Revision 12e511b5 (ceph): mailmap: Update Mark Nelson's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:00 AM Revision bdf534a5 (ceph): mailmap: Update Ken Dreyer's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 05:00 AM Revision df194106 (ceph): mailmap: Update Josh Durgin's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:59 AM Revision d9ee8d60 (ceph): mailmap: Update John Wilkins' attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:56 AM Revision c84aa394 (ceph): mailmap: Update Joao Luis' attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:54 AM Revision 806a478e (ceph): mailmap: Update Ilya Dryomov's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:49 AM Revision eaa9889b (ceph): mailmap: Update Dan Mick's attribution
- Point his addresses at Red Hat now, but revert the Inktank->Redhat mappings
so we have more historical accuracy.
Sig... - 04:47 AM Revision 330b09de (ceph): mailmap: Update Alfredo Deza's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:42 AM Revision 1853af3d (ceph): mailmap: Update Greg Farnum's attribution to Red Hat
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 04:30 AM Feature #9728 (In Progress): erasure-code: jerasure support for NEON
- 04:29 AM Bug #10017: OSD wrongly marks object as unfound if only the primary is corrupted for EC pool
- 03:41 AM Bug #10173 (Fix Under Review): autogen.sh will fail if submodule URL changes
- https://github.com/ceph/ceph/pull/2992
- 03:30 AM Bug #10173 (Resolved): autogen.sh will fail if submodule URL changes
- After an initial "git submodule update":https://github.com/ceph/ceph/blob/master/autogen.sh#L32, if the URL of a subm...
- 02:55 AM Revision 47bc8da3 (ceph): Merge remote-tracking branch 'gh/next'
- 02:35 AM Revision 9d5e4edc (ceph): check endpoints is not empty before use it.
- Signed-off-by: VRan Liu <gliuwr@gmail.com>
- 02:29 AM Linux kernel client Bug #10141: rbd_img_obj_request_fill+0x81/0x200
- For the record, since the stack trace doesn't explain anything, this was the following BUG_ON in osd_req_op_extent_in...
- 02:21 AM Linux kernel client Bug #10141 (Resolved): rbd_img_obj_request_fill+0x81/0x200
- Fixed with "rbd: don't treat CEPH_OSD_OP_DELETE as extent op". I rebased it into testing before "libceph: add CREATE...
- 01:38 AM Revision 55413482 (ceph): client: support listxattr for quota attributes
- Signed-off-by: Yunchuan Wen <yunchuanwen@ubuntukylin.com>
- 12:59 AM Messengers Bug #10080: Pipe::connect() cause osd crash when osd reconnect to its peer
- I am wondering if the following race occurred:
Let us assume A and B are two OSDs having the connection (pipe) bet...
11/23/2014
- 11:32 PM Bug #10017 (In Progress): OSD wrongly marks object as unfound if only the primary is corrupted fo...
- 11:29 PM Bug #10018 (Fix Under Review): OSD assertion failure if the hinfo_key xattr is not there (corrupt...
- 11:08 PM Feature #10172 (Resolved): AsyncMessenger: Bind async thread to special cpu core
- Now, 1-2 async op thread can fully meet a OSD's network demand with SSD backend. So maybe we can bind limited thread ...
- 10:56 PM rgw Bug #10145: rgw swift functional test: testChunkedPut (test.functional.tests.TestFileUTF8)
- I am using Ubuntu 14.04
And these are my apache ang fast cgi version:... - 08:59 PM Revision ca13ce1b (ceph): Merge pull request #2983 from tchaikov/wip-fix-lock-dep
- lockdep: do not use $CEPH_LOCKDEP for g_lockdep
Reviewed-by: Sage Weil <sage@redhat.com> - 08:31 PM Bug #10166: fiemap or FileStore::do_sparse_copy_range bug: osd/ReplicatedPG.cc: 8706: FAILED asse...
- ubuntu@teuthology:/a/teuthology-2014-11-23_18:13:01-upgrade:firefly-x-giant-distro-basic-multi/615700
- 08:30 PM CephFS Bug #9997: test_client_pin case is failing
- http://qa-proxy.ceph.com/teuthology/teuthology-2014-11-16_23:04:01-fs-next-testing-basic-multi/603971/
- 07:19 PM Revision 5470914f (ceph): lockdep: do not use $CEPH_LOCKDEP for g_lockdep
- * a non-zero CEPH_LOCKDEP brings ceph down because g_lockdep_ceph_ctx
is still being constructed when dout_impl() d... - 06:53 PM Bug #9998 (Fix Under Review): Replaced OSD weight below 0
- https://github.com/ceph/ceph/pull/2986
- 05:13 AM Revision 6e3b6f0e (ceph): common: Add cctid meta variable
- Fixes: #6228
Signed-off-by: Adam Crume <adamcrume@gmail.com>
(cherry picked from commit bb45621cb117131707a85154292a3...
Also available in: Atom