Activity
From 11/22/2016 to 12/21/2016
12/21/2016
- 11:18 PM Revision 5b402f8a (ceph): Merge remote-tracking branch 'ceph/jewel-next' into jewel
- 10:10 PM rbd Feature #15632 (Pending Backport): Expose librbd API methods to directly acquire and release the ...
- Re-opening this ticket for backport to Jewel LTS in support of RBD-backed iSCSI (#17489)
- 10:05 PM rbd Backport #18275 (Resolved): kraken: rbd-nbd: invalid error code for "failed to read nbd request" ...
- Kraken was rebased to master and this fix was automatically picked up.
- 10:05 PM rbd Backport #18279 (Resolved): kraken: RBD diff got SIGABRT with "--whole-object" for RBD whose pare...
- Kraken was rebased to master and this fix was automatically picked up.
- 10:04 PM rbd Backport #18289 (Resolved): kraken: objectmap does not show object existence correctly
- Kraken was rebased to master and this fix was automatically picked up.
- 10:04 PM Revision 2a6d2289 (ceph): incremental
- Signed-off-by: Matt Benjamin <mbenjamin@redhat.com>
- 10:03 PM rbd Backport #18319 (Resolved): kraken: rbd status: json format has duplicated/overwritten key
- Kraken was rebased to master and this fix was automatically picked up.
- 04:36 PM rbd Backport #18319 (Closed): kraken: rbd status: json format has duplicated/overwritten key
- 10:02 PM rbd Backport #18322 (Resolved): kraken: librbd::ResizeRequest: failed to update image header: (16) De...
- Kraken was rebased to master and this fix was automatically picked up.
- 04:36 PM rbd Backport #18322 (Closed): kraken: librbd::ResizeRequest: failed to update image header: (16) Devi...
- 10:01 PM rbd Backport #18324 (Resolved): kraken: JournalMetadata flooding with errors when being blacklisted
- Kraken was rebased to master and this fix was automatically picked up.
- 04:36 PM rbd Backport #18324 (Closed): kraken: JournalMetadata flooding with errors when being blacklisted
- 09:59 PM rbd Subtask #18327 (Resolved): [iscsi]: need an API to break the exclusive lock
- The iSCSI via tcmu-runner+librbd implementation will require the ability to force-break the exclusive lock, even on r...
- 09:41 PM Bug #18265: MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- 03:59 PM Bug #18265 (In Progress): MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- 09:09 PM Revision 957c19b8 (ceph): swift: added "--cluster" to rgw-admin command for multisite support
- Signed-off-by: Ali Maredia <amaredia@redhat.com>
- 08:06 PM rbd Bug #18326 (Resolved): rbd --pool=x rename y z does not work
- Failed:...
- 08:02 PM CephFS Bug #18309 (Fix Under Review): TestVolumeClient.test_evict_client failure creating pidfile
- -https://github.com/ceph/ceph/pull/12606-
- 06:20 PM CephFS Bug #18309: TestVolumeClient.test_evict_client failure creating pidfile
- The problem is that global_init_prefork is calling pidfile_write, and we started using that from the client in 83aaa5...
- 07:41 PM rbd Bug #18269 (Duplicate): rbd info truncates block_name_prefix to 23 chars
- 07:37 PM devops Bug #15560 (Duplicate): Unknown lvalue 'TasksMax' in section 'Service'
- 06:04 PM devops Bug #15560: Unknown lvalue 'TasksMax' in section 'Service'
- Related issues: #15583 #15581
- 07:36 PM rgw Bug #18300 (Fix Under Review): leak from RGWMetaSyncShardCR::incremental_sync
- https://github.com/ceph/ceph/pull/12605
- 07:31 PM rgw Bug #18300: leak from RGWMetaSyncShardCR::incremental_sync
- looking at http://qa-proxy.ceph.com/teuthology/sage-2016-12-16_16:52:37-rgw-master---basic-smithi/639993/remote/smith...
- 07:24 PM Revision f169b6b8 (ceph): osd: fix CEPH_OSD_FLAG_RWORDERED
- Broke this in 3a2ed3b136de68192f661b6992cbb96ce6aafd20.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:17 PM CephFS Backport #18308 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
- 05:20 PM CephFS Backport #18308 (New): ceph-fuse not clearing setuid/setgid bits on chown
- 04:36 PM CephFS Backport #18308: ceph-fuse not clearing setuid/setgid bits on chown
- h3. original description
I had some test failures that showed up in my most recent fs suite run here:
http... - 06:17 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- *master PR*: https://github.com/ceph/ceph/pull/12331
- 04:38 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- @Jeff: Which commit fixes the issue/should be backported to jewel?
- 06:12 PM Bug #18297 (Resolved): ceph cli fails on monitors that don't send 'flags' in command descs
- 06:06 PM Bug #18297: ceph cli fails on monitors that don't send 'flags' in command descs
- No; Sage added that backport note, I haven't checked.
- 05:45 PM Bug #18297: ceph cli fails on monitors that don't send 'flags' in command descs
- @Dan: Are you sure this fix is applicable to jewel? The flags appear to have been introduced by https://github.com/ce...
- 06:12 PM Backport #18318 (Rejected): jewel: ceph cli fails on monitors that don't send 'flags' in command ...
- https://github.com/ceph/ceph/commit/61d63433 which introduced the bug was merged after jewel release
- 04:35 PM Backport #18318 (Rejected): jewel: ceph cli fails on monitors that don't send 'flags' in command ...
- 06:10 PM Cleanup #12863 (Fix Under Review): switch from "timegm()" to "internal_timegm()" for better porta...
- 03:39 PM Cleanup #12863: switch from "timegm()" to "internal_timegm()" for better portability
- Hi. PR Submitted - https://github.com/ceph/ceph/pull/12600
- 06:09 PM Cleanup #12684 (Fix Under Review): Remove no use code in pipe.cc.
- 03:38 PM Cleanup #12684: Remove no use code in pipe.cc.
- Hi. PR submitted - https://github.com/ceph/ceph/pull/12601
- 06:04 PM devops Bug #15583: systemd warns about TasksMax= setting on older distros
- related issue: #15560
- 05:18 PM CephFS Bug #18254 (Resolved): path restricted cephx caps not working correctly
- 05:16 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- *master PR*: https://github.com/ceph/ceph/pull/12505
- 04:52 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- @Jeff: We have a system/service in place for backporting bugfixes to our stable releases. Patches backported via this...
- 05:18 PM Revision 6c05702a (ceph): Added "bluestore" prefix to new config options
- Signed-off-by: Orlando Moreno <orlando.moreno@intel.com>
- 05:18 PM CephFS Backport #18307: path restricted cephx caps not working correctly
- (removed attachments that are available at #18254)
- 05:17 PM CephFS Backport #18307 (Resolved): path restricted cephx caps not working correctly
- 04:39 PM CephFS Backport #18307 (New): path restricted cephx caps not working correctly
- h3. original description
Ramana noticed this first while testing my ganesha patches to allow restricting exports. ... - 05:14 PM Backport #18312 (Resolved): 'make dist' fails because tar uses `--format=ustar`
- 05:08 PM Revision 8faa809d (ceph): msg/async/rdma: Support for RoCE v2 and SL
- Adding GID support to ceph.conf
Search configured GID in GIDs table with specific RoCE version.
Use it instead of ind... - 04:56 PM rbd Bug #18325 (Resolved): Removing a clone that fails to open its parent might leave dangling rbd_ch...
- Create a parent image in pool X, and a clone in pool Y. Using a user that doesn't have any permission to pool X, remo...
- 04:36 PM rbd Backport #18323 (Resolved): jewel: JournalMetadata flooding with errors when being blacklisted
- https://github.com/ceph/ceph/pull/12739
- 04:36 PM rbd Backport #18321 (Resolved): jewel: librbd::ResizeRequest: failed to update image header: (16) Dev...
- https://github.com/ceph/ceph/pull/13809
- 04:36 PM rbd Backport #18320 (Resolved): jewel: rbd status: json format has duplicated/overwritten key
- https://github.com/ceph/ceph/pull/12741
- 04:35 PM rgw Backport #18317 (Resolved): hammer: TempURL does not behave like its swift counterpart
- https://github.com/ceph/ceph/pull/12619
- 04:34 PM rgw Bug #18316 (Resolved): TempURL does not behave like its swift counterpart
- This issue was fixed in jewel by https://github.com/ceph/ceph/commit/a1ea718096
- 04:06 PM Revision a5b08de5 (ceph): common/config_opts.h: FreeBSD timing changed due to no SO_REUSEADDR
- Some tests could run into max retries if the server is seriously loaded.
So allow for more time, and tries.
One of t... - 03:56 PM Revision af21f0db (ceph): Merge pull request #12598 from ly798/typo-fix-in-docs
- doc: typo fix in s3_compliance
Reviewed-by: Sage Weil <sage@redhat.com> - 03:55 PM rbd Bug #18315 (Resolved): Attempting to remove an image w/ incompatible features results in partial ...
- For example, attempting to remove an image created with Jewel-release features using a Hammer-release rbd CLI will re...
- 03:54 PM Revision fc2b953c (ceph): Merge pull request #12601 from rishabhkumar296/ceph12684
- msg/simple: Remove dead code in pipe.cc
Reviewed-by: Sage Weil <sage@redhat.com> - 03:09 PM Revision fa58ed6b (ceph): Remove dead code in pipe.cc
- Fixes: http://tracker.ceph.com/issues/12684
Signed-off-by: Rishabh Kumar <kris.kr296@gmail.com> - 02:24 PM CephFS Bug #18314 (Fix Under Review): commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" b...
- https://github.com/ceph/ceph/pull/12599
- 08:37 AM CephFS Bug #18314: commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks large directory
- ...
- 08:32 AM CephFS Bug #18314 (Resolved): commit 41d46e492 "osd/ReplicatedPG: limit omap request by bytes" breaks la...
- OPTION(osd_max_omap_bytes_per_request, OPT_U64, 4<<20)
4M can only carry about 5k dentries. It's too small - 02:18 PM Revision e565d892 (ceph): Merge pull request #12591 from jtlayton/wip-18308-jewel
- Clear setuid bits on ownership changes
- 12:56 PM devops Feature #15733 (New): ceph-osd should chown OSD data when --setuser is specified
- 12:56 PM devops Feature #15733 (Rejected): ceph-osd should chown OSD data when --setuser is specified
- Not going to happen.
- 11:14 AM CephFS Bug #15921 (Can't reproduce): segfault in cephfs-journal-tool (TestJournalRepair failure)
- Haven't seen this failure in a long time.
- 11:11 AM CephFS Bug #2375 (Closed): rrdtoll data malfuntion..
- Ancient, closing.
- 11:09 AM CephFS Bug #1206 (Closed): NFS reexport file creation lags 1-3 seconds
- Closing this because it's ancient (and if NFS creates were super-slow we'd notice on the knfs suite)
- 10:39 AM Revision ce7d00ac (ceph): rgw: fix versioned bucket data sync fail when upload is busy
- Fixes: http://tracker.ceph.com/issues/18208
Signed-off-by: lvshuhua <lvshuhua@cmss.chinamobile.com> - 10:11 AM Bug #16036 (Resolved): ceph mon deamon startup side effect running ceph-create-keys
- 09:29 AM Cleanup #14202: the method 'Message::decode_message' is too long
- Rishabh Kumar wrote:
> Hi,Is this issue still open? I wish to take this up if someone else is not working on it.
... - 08:44 AM Cleanup #14202: the method 'Message::decode_message' is too long
- Hi,Is this issue still open? I wish to take this up if someone else is not working on it.
- 08:44 AM Revision 08066eb9 (ceph): osd/PrimaryLogPG: enlarge omap request bytes limitation
- For cephfs, 4M buffer can only encode about 5k dentries. It's too
small for directory.
Fixes: http://tracker.ceph.co... - 07:54 AM Revision 7599f0da (ceph): test/librados: Silence Coverity memory leak warnings
- Use Sam's scope_guard solution to stop warnings about leaked resources.
Signed-off-by: Brad Hubbard <bhubbard@redhat... - 07:49 AM Revision 9c547076 (ceph): src/include: add scope_guard.h
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:22 AM Bug #18153: No space cause osd crash (bluestore)
- I used version 11.0.2, and today I retested it with master, this issue is still there
Attached is the log with (deb... - 06:54 AM Revision 27325119 (ceph): doc: typo fix in s3_compliance
- Signed-off-by: LiuYang <yippeetry@gmail.com>
- 06:49 AM Revision dc6c12c5 (ceph): MessageFactory: stage files
- Descendant factories are not updated. Comments need pruning
from Message.cc. CMakeLists.txt(s) need updating.
Sign... - 02:28 AM Revision 3e40595f (ceph): os/bluestore: add perf variable for throttle info in bluestore
- Signed-off-by: Pan Liu <pan.liu@istuary.com>
- 01:29 AM Revision 725962f8 (ceph): README.alpine: add alpine readme
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:27 AM Revision 4d4360b7 (ceph): tests: add Dockerfile for Alpine edge
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:26 AM Revision 7771adf9 (ceph): client: priority to verify the correctness of the "flag"
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 01:25 AM Revision 86be590c (ceph): make-apk.sh: alpine packaging helper
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:24 AM Revision 84eb9b83 (ceph): install-deps.sh: add alpine support
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:21 AM Revision ce3332fd (ceph): make-dist: add alpine support
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:20 AM Revision 9001d7e6 (ceph): alpine: add alpine packaging support
- Signed-off-by: John Coyle <dx9err@gmail.com>
- 01:14 AM Revision 3d0c778b (ceph): run-make-check.sh: Init defaults after deps are installed.
- get_processors() depends on coreutils nproc. Alpine does not install coreutils by default.
Signed-off-by: John Coyle...
12/20/2016
- 11:50 PM Bug #18265: MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- This assert also stops new daemons from running (of course), not just the CLI. Raising to 'Urgent'.
- 11:47 PM Revision 12706d76 (ceph): Merge pull request #12587 from yuriw/wip-fix-subset-script-master
- qa: fixed script to schedule rados and other suites with --subset option
Reviewed-by: Jason Dillaman <dillaman@redha... - 11:34 PM Revision 56975c03 (ceph): changed script name
- added kraken
parameterized suite name to be able to use for rados, rbd etc.
Signed-off-by: Yuri Weinstein <yweinste@... - 11:13 PM Bug #18310 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout FAILED
- 05:48 PM Bug #18310: LibRadosWatchNotify.WatchNotify2Timeout FAILED
- 04:41 PM Bug #18310: LibRadosWatchNotify.WatchNotify2Timeout FAILED
- Looks like fallout from 89fd030bf9436dc4e37cc3a0f935ec077455d9d5
client ops are... - 02:28 PM Bug #18310 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout FAILED
- ...
- 11:13 PM Revision d877b278 (ceph): Merge pull request #12590 from athanatos/wip-ping-write-ordered
- osd: force watch PING to be write ordered
Reviewed-by: Sage Weil <sage@redhat.com> - 09:54 PM Bug #16421 (Rejected): deep-scrub seems to update the omap digest on objects without any omap ent...
- I can't figure out why I thought this was true. I checked the code and it looks like object_info_t comes into the wo...
- 09:02 PM Bug #16421 (In Progress): deep-scrub seems to update the omap digest on objects without any omap ...
- 09:08 PM devops Bug #14839: systemctl stop ceph.target doesn't stop ceph
- Also in http://pulpito.ceph.com/teuthology-2016-12-20_11:55:02-ceph-deploy-kraken-distro-basic-vps/
- 09:01 PM Bug #18303 (Resolved): osd_backfill.py: ENXIO on flush_pg_stats
- 02:56 AM Bug #18303: osd_backfill.py: ENXIO on flush_pg_stats
- https://github.com/ceph/ceph/pull/12577
- 02:55 AM Bug #18303 (Resolved): osd_backfill.py: ENXIO on flush_pg_stats
- ...
- 08:36 PM Revision 5799d5fd (ceph): Merge branch 'jewel' into wip-18308-jewel
- 08:35 PM Revision f97b3998 (ceph): Merge pull request #12592 from jtlayton/wip-18307-jewel
- Fix mount root for ceph_mount users and change tarball format
- 08:07 PM Revision c0b64fb0 (ceph): Merge pull request #12593 from wjwithagen/wip-wjw-freebssd-SO_reuseaddr
- msg/async/net_handler.cc: Do not apply SO_REUSEADDR for FreeBSD
Reviewed-by: Sage Weil <sage@redhat.com> - 07:44 PM Revision f15c8daf (ceph): ceph_disk: fix a jewel checkin test break
- Silly python:
ceph_disk/main.py:173:1: E305 expected 2 blank lines after class or function definition, found 1
... - 07:21 PM Backport #18312: 'make dist' fails because tar uses `--format=ustar`
- Ok, so I think this patch will work around the problem, but I have to wonder...
I have two different branches up r... - 06:54 PM Backport #18312: 'make dist' fails because tar uses `--format=ustar`
- PR is here:
https://github.com/ceph/ceph/pull/12592 - 04:55 PM Backport #18312: 'make dist' fails because tar uses `--format=ustar`
- It looks like this is part of automake. Can we try this patch to jewel?
I just repushed my current test branch tha... - 04:43 PM Backport #18312 (Resolved): 'make dist' fails because tar uses `--format=ustar`
- Build output:...
- 07:00 PM Revision 5563ff34 (ceph): Merge pull request #12584 from mkoderer/openstack_nova_doc
- doc: mention corresponding libvirt section in nova.conf
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:54 PM CephFS Backport #18307: path restricted cephx caps not working correctly
- PR is up here:
https://github.com/ceph/ceph/pull/12592 - 01:00 PM CephFS Backport #18307 (Resolved): path restricted cephx caps not working correctly
- https://github.com/ceph/ceph/pull/12592
- 06:43 PM Revision 0825f170 (ceph): msg/async/net_handler.cc: Do not apply SO_REUSEADDR for FreeBSD
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 06:07 PM Revision 11d6caf3 (ceph): librbd: permit removal of image being bootstrapped by rbd-mirror
- Fixes: http://tracker.ceph.com/issues/16555
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 06:06 PM CephFS Bug #18311 (Fix Under Review): Decode errors on backtrace will crash MDS
- https://github.com/ceph/ceph/pull/12588
- 03:16 PM CephFS Bug #18311 (Resolved): Decode errors on backtrace will crash MDS
- Noticed by inspection:...
- 06:00 PM devops Bug #18313 (Fix Under Review): upstart: radosgw-all does not start on boot if ceph-base is not in...
- 05:39 PM devops Bug #18313: upstart: radosgw-all does not start on boot if ceph-base is not installed
- PR for master: https://github.com/ceph/ceph/pull/12586
- 05:35 PM devops Bug #18313 (Resolved): upstart: radosgw-all does not start on boot if ceph-base is not installed
- The "radosgw-all" Upstart service depends on the "ceph-all" service in order to trigger a start operation. @ceph-all....
- 05:47 PM Revision 3a2ed3b1 (ceph): osd/: treat PINGs as RWORDERED
- 89fd030bf9436dc4e37cc3a0f935ec077455d9d5 switched them to show up
as reads to avoid logging them, but we still pipeli... - 05:46 PM CephFS Bug #18225 (Resolved): MDS doesn't release memory after exceeding its cache size limit
- 05:34 PM CephFS Bug #9935 (Fix Under Review): client: segfault on ceph_rmdir path "/"
- https://github.com/ceph/ceph/pull/12550
- 05:02 PM rbd Backport #18137 (In Progress): jewel: rbd-mirror: image sync should send NOCACHE advise flag
- 05:01 PM rbd Backport #18215 (In Progress): jewel: TestImageSync.SnapshotStress fails on bluestore
- 04:54 PM Revision 8e0cffdd (ceph): automake: convert to tar-pax
- We hit some recent build issues with the merge of ceph-qa-suite into
the main repo. The ustar format barfs on >100 ch... - 04:29 PM Bug #18297: ceph cli fails on monitors that don't send 'flags' in command descs
- *master PR*: https://github.com/ceph/ceph/pull/12540
- 03:56 PM Bug #18297 (Pending Backport): ceph cli fails on monitors that don't send 'flags' in command descs
- 04:11 PM Revision ab6c287d (ceph): osd/osd_types: print notify-ack op properly
- Not like "[notify-ack 0~0]"!
Signed-off-by: Sage Weil <sage@redhat.com> - 03:56 PM Revision e0903c9e (ceph): Merge pull request #12540 from dmick/wip-18297
- ceph.in: allow 'flags' to not be present in cmddescs
- 03:51 PM Revision a84de427 (ceph): Merge pull request #12577 from liewegas/wip-osd-backfill
- qa/tasks/osd_backfill.py: wait for osd.[12] to start
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:22 PM Revision 82e3aac7 (ceph): os/bluestore/bluestore_types: drop std::bitset for blob unused
- The complex type screws up struct packing. This takes
bluestore_blob_t from 64 to 56 bytes.
Signed-off-by: Sage Wei... - 03:22 PM Revision 284fd0bd (ceph): os/bluestore/bluestore_types: reorder onode_t types
- Save 8 bytes.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:43 PM Revision d5d86418 (ceph): Merge pull request #12574 from liewegas/wip-bluestore-split
- os/bluestore: preserve source collection cache during split
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:33 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- http://pulpito.ceph.com/sage-2016-12-20_03:05:39-rados-wip-sage-testing---basic-smithi/
8 hung jobs out of 236 on ... - 01:52 PM Revision 6229edfe (ceph): DOC: Mention corresponding section in nova.conf
- rbd_user and rbd_secret_uuid are part of the libvirt configuration.
Signed-off-by: Marc Koderer <marc@koderer.com> - 01:25 PM Revision a0ae9a83 (ceph): client: drop setuid/setgid bits on ownership change
- When we hold exclusive auth caps, then the client is responsible for
handling changes to the mode. Make sure we remov... - 01:19 PM CephFS Bug #18309 (Resolved): TestVolumeClient.test_evict_client failure creating pidfile
- Consistent on master
http://pulpito.ceph.com/jspray-2016-12-19_21:05:25-fs-master-distro-basic-smithi/648157
I ... - 01:16 PM Revision d49e6283 (ceph): mds: clear setuid/setgid bits on ownership changes
- If we get a ownership change, POSIX mandates that you clear the
setuid and setgid bits unless you are "appropriately ... - 01:13 PM CephFS Backport #18308 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
- https://github.com/ceph/ceph/pull/12591
- 01:07 PM Revision f2dfc200 (ceph): client: set metadata["root"] from mount method when it's called with a ...
- Currently, we only set the root properly config file or the
--client_metadata command line option. If a userland clie... - 01:01 PM CephFS Bug #18131 (Pending Backport): ceph-fuse not clearing setuid/setgid bits on chown
- 12:59 PM CephFS Bug #18254 (Pending Backport): path restricted cephx caps not working correctly
- 12:21 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- Patch merged. We'll also want this backported to jewel.
- 12:32 PM rbd Bug #18261: rbd status: json format has duplicated/overwritten key
- Ok,thank you for the fast help!
- 12:05 PM rbd Cleanup #18170 (In Progress): rbd-mirror: pool replayer should re-use pool watcher
- 12:05 PM rbd Cleanup #18171 (In Progress): rbd-mirror: remove the need for a polling loop within the pool repl...
- 11:24 AM Revision 19439f39 (ceph): rbd: the length of args on create_v3 should be 3 instead of 2
- Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.com>
- 11:16 AM CephFS Bug #18306 (Resolved): segfault in handle_client_caps
- http://pulpito.ceph.com/jspray-2016-12-19_21:05:25-fs-master-distro-basic-smithi/648247...
- 11:11 AM rbd Bug #18244 (Pending Backport): librbd::ResizeRequest: failed to update image header: (16) Device ...
- 11:10 AM Revision 47d26629 (ceph): Merge pull request #12472 from dillaman/wip-18244
- librbd: remove image header lock assertions
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 09:54 AM rgw Bug #18210: rgw: multisite: commit period issue when creating multiple zonegroups
- I would like to ask is how to configure multiple zonegroup bucket and userid in realm only.
Can give a configuration... - 09:53 AM rgw Bug #18210: rgw: multisite: commit period issue when creating multiple zonegroups
- radosgw-admin period update --commit --url=http://192.168.250.68:80
Has been resolved, But multiple zonegroups can n... - 08:53 AM Revision e7d544b1 (ceph): os/filestore: version will be uninitialized varible if store_version do...
- http://people.redhat.com/bhubbard/scan-build/report-95c661.html#EndPath
Signed-off-by: liuchang0812 <liuchang0812@gm... - 08:44 AM Bug #18305: ceph-osd systemd unit files incomplete
- logs again with correct formatting:...
- 08:41 AM Bug #18305: ceph-osd systemd unit files incomplete
- note that the fix for http://tracker.ceph.com/issues/17889 should make this issue more obvious, as the ceph-osd@ serv...
- 08:37 AM Bug #18305 (New): ceph-osd systemd unit files incomplete
- tested with the Debian Jewel 10.2.5 packages on up-to-date Debian Jessie, probably applies to other version/distros u...
- 06:32 AM Revision 6b181eca (ceph): filestore: avoid copy ghobject_t in _check_replay_guard
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:40 AM Revision 883d9b1e (ceph): client: fix clang warn of "argument is an uninitialized value"
- http://people.redhat.com/bhubbard/scan-build/report-faad49.html#EndPath
Signed-off-by: liuchang0812 <liuchang0812@gm... - 05:37 AM Revision 46ced9dd (ceph): rgw: Get civetweb ssl enhancement: wip-listen4 = wip-civetweb-1.8-2 + m...
- The logic inside of radosgw that computes aws v4 signatures wants to know
what server port the client connected. The... - 05:37 AM Revision a113cf5f (ceph): rgw: s3: secure_port should override port, also apply ssl default right.
- Without https, only port is set. With https, secure_port and port are
both set to the same value. The previous logi... - 05:37 AM Revision 8bc6decc (ceph): rgw: Handle multiple listening addreses w/ optional ssl "correctly" wit...
- For civetweb: accept a range of port numbers joined with '+'.
Port numbers may include an ipaddress: prefix and 's' s... - 05:36 AM Revision d4e72dfe (ceph): rgw: Document that radosgw now supports SSL.
- This includes information on file format and configuration file syntax.
Signed-off-by: Marcus Watts <mwatts@redhat.com> - 05:36 AM Revision 7caa0bd0 (ceph): rgw: civetweb/openssl: Load libssl.so and libcrypto.so by soname.
- If building with radosgw, always look for openssl library (even when
building with nss). Then, use objdump to fetch ... - 05:36 AM Revision 8308a13b (ceph): rgw: cmake: remove useless civetweb include path side effect.
- For 'target_include_directories" for the cmake object library
'civetweb_common_objs', change from PUBLIC to PRIVATE. ... - 05:31 AM Revision f7d7824a (ceph): osd/PG: check the connection first in fulfill_log
- No need to prepare reply message if the connection not exist
Signed-off-by: huangjun <hjwsm1989@gmail.com> - 05:21 AM Revision 1d359455 (ceph): os/filestore: fix clang static check warn use-after-free
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 04:36 AM Revision b57c1ce2 (ceph): filestore: remove unused routine
- _kludge_temp_object_collection is unused routine now.
Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com> - 04:34 AM Revision a681c03c (ceph): filestore: avoid unnecessary copy with coll_t
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:26 AM Revision 6a786a83 (ceph): Merge pull request #12532 from ifed01/wip-bluestore-large-onode-test
- os/bluestore: add UT for an estimation of Onode in-memory size
Reviewed-by: Sage Weil <sage@redhat.com> - 03:22 AM Revision c2f5f960 (ceph): filestore: avoid unnecessary copy with ghobject_t
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:18 AM Revision 34ab0000 (ceph): Merge pull request #12505 from ceph/wip-jlayton-submount
- client: set metadata["root"] from mount method when it's called with …
Reviewed-by: Greg Farnum <gfarnum@redhat.com>... - 03:17 AM Revision 73fa8386 (ceph): Merge pull request #12570 from wjwithagen/patch-9
- common/str_list.h: fix clang warning about std::move
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 03:15 AM Revision f674fa24 (ceph): Merge pull request #12541 from liewegas/wip-bluestore-omap-flush
- os/bluestore: include modified objects in flush list even if onode unchanged
Reviewed-by: Igor Fedotov <ifedotov@mir... - 02:56 AM Revision c922404a (ceph): qa/tasks/osd_backfill.py: wait for osd.[12] to start
- ...before sending a tell command. Otherwise osd.2 might
start without 1, the io unblocks, and the tell fails
because... - 01:52 AM Revision c4fa36ad (ceph): bluestore: avoid unnecessary copy with coll_t
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 12:45 AM Revision f7bf8004 (ceph): common: make attempts of auth rotating configurable
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 12:45 AM Revision 47fe4d4f (ceph): osd/OSDMap: drop redundant statements
- calc_pg_rank() will do the same check inside.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
12/19/2016
- 11:57 PM Revision d548d5a1 (ceph): os/bluestore: allow multiple SPDK BlueStore OSD instances
- Fixes: http://tracker.ceph.com/issues/16966
Signed-off-by: Orlando Moreno <orlando.moreno@intel.com> - 10:53 PM RADOS Bug #18165 (Won't Fix): OSD crash with osd/ReplicatedPG.cc: 8485: FAILED assert(is_backfill_targe...
- This machinery was rewritten in jewel to make it work properly in this case. The fix can't really be backported to h...
- 10:52 PM Bug #18163: platform.linux_distribution() is deprecated; stop using it
- oops, ceph-detect-init is still using it.
- 10:52 PM Bug #18163 (Resolved): platform.linux_distribution() is deprecated; stop using it
- 10:52 PM RADOS Bug #18178: Unfound objects lost after OSD daemons restarted
- David: I know why it's losing the unfound status, but it should be losing the inconsistent pg state, right?
- 10:49 PM Messengers Bug #14120 (Resolved): Pipe::do_recv() may loop infinitely
- 10:48 PM Bug #18203 (Closed): Additional Ceph Monitors failed verifying authorize reply
- It sounds like the mon. key wasn't installed properly on the new mons. try copying it into your ceph-deploy dir or d...
- 10:45 PM Bug #18153: No space cause osd crash (bluestore)
- What version?
- 10:45 PM Bug #18153 (Need More Info): No space cause osd crash (bluestore)
- Can you reproduce this with a bluestore log? (debug bluestore = 20)
- 10:44 PM Bug #18224 (Can't reproduce): Mass OSD failure with Bluestore
- 10:43 PM Bug #18224: Mass OSD failure with Bluestore
- This is from a few months ago, you'll want to retest with a more recent version.
- 10:42 PM Bug #18226 (Can't reproduce): assert in bluestore_extent_ref_map_t::record_t::bound_encode with d...
- 10:41 PM Bug #18251 (Need More Info): There are some scrub errors after reset a node.
- Look in ceph.log for the actual scrub error.
Also, make sure you aren't running with nobarrier -- that will corrup... - 10:41 PM Bug #18251: There are some scrub errors after reset a node.
- Can you describe in much more detail how you are "resetting" that node? Also, can you include the mount options for ...
- 10:34 PM Bug #16331: teuthology hang joining thrashosds, specifically Thrasher.thread
- this is probably a dup of http://tracker.ceph.com/issues/13522 ... ceph-objectstore-tool is ususally what hangs when ...
- 10:34 PM Bug #16331 (Can't reproduce): teuthology hang joining thrashosds, specifically Thrasher.thread
- 10:34 PM Revision 2826aaa0 (ceph): rgw: really rebase rgw to civetweb 1.8 now
- We previously rebased to a pre-1.8 version (accidentally)
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 10:33 PM RADOS Bug #17257 (Can't reproduce): ceph_test_rados_api_lock fails LibRadosLockPP.LockExclusiveDurPP
- 10:33 PM Bug #13897 (Resolved): (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED as...
- This is actually two different bugs. The former doesn't seem to have recurred. The latter is a kstore bug and the t...
- 10:32 PM RADOS Bug #17945: ceph_test_rados_api_tier: failed to decode hitset in HitSetWrite test
- 633e81f3a6343ef4d5b8b421e693356c17f698b9 will hexdump to help debug this next time it happens
- 10:24 PM Bug #17645 (Can't reproduce): "terminate called after throwing an instance of 'std::out_of_range'...
- 10:16 PM Bug #18246 (Resolved): trusty kernel loses aios
- fixed upstream
- 10:11 PM Bug #18173 (Resolved): selinux denial on /var/lib/ceph/osd/ceph-1/type
- 10:11 PM Bug #18105 (Resolved): bluestore: rocksdb preconditioning does not seem to work
- 10:10 PM RADOS Bug #18054 (Resolved): os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- 10:10 PM Bug #18291 (Resolved): ceph-disk: bluestore wal/db partitions must be optional
- 10:05 PM Revision ec5ba4e8 (ceph): os/bluestore: preserve source collection cache during split
- OSD split transactions look something like
mkcoll new
split old
...
omap_rmkey_range old
omap_setkeys old
omap... - 09:50 PM Bug #15943 (Pending Backport): crash adding snap to purged_snaps in ReplicatedPG::WaitingOnReplicas
- This needs to be backported again to both jewel and hammer.
- 09:50 PM Revision dc639fd9 (ceph): Merge pull request #12571 from athanatos/wip-15943
- osd: Fix map gaps again (bug 15943)
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Reviewed-by: Sage Weil <sage@red... - 09:17 PM rbd Cleanup #18243 (Pending Backport): JournalMetadata flooding with errors when being blacklisted
- 09:14 PM Bug #17782: performance drop with Linux Kernel 4.4.0 (ceph tell osd.* bench)
- Hello,
some new benchmarks with the latest jewel release (10.2.5) on 4 nodes (Each node has 10 OSDs)
I ran 2 ti... - 08:25 PM Revision c3afbbf3 (ceph): Merge pull request #12572 from liewegas/wip-python-rados-test
- qa/workunits: include extension for nose tests
- 08:15 PM Revision e8229134 (ceph): Merge pull request #12568 from ifed01/wip-bluestore-onode-diet2
- os/bluestore: reduce Onode in-memory footprint
Reviewed-by: Sage Weil <sage@redhat.com> - 08:13 PM Revision 3079dfc8 (ceph): Merge pull request #12555 from socketpair/usr_bin
- systemd: Fix startup of ceph-mgr on Debian 8
Reviewed-by: Sage Weil <sage@redhat.com> - 08:13 PM Revision 3649d1fc (ceph): Merge pull request #12355 from chhabaramesh/bit_alloc_mempool
- os/bluestore: simplified allocator interfaces to single apis
Reviewed-by: Sage Weil <sage@redhat.com> - 08:11 PM Bug #18138 (Can't reproduce): OSD hits EAGAIN on pthread_create
- 07:08 PM Revision 5666fd61 (ceph): qa/workunits: include extension for nose tests
- When you have a relative path you have to include the extension.
Weird.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:26 PM Revision 20f936e8 (ceph): Merge pull request #12412 from ceph/wip-jlayton-suid
- client/mds: Clear setuid bits when writing or truncating
- 04:29 PM Revision d9acbf58 (ceph): Clang/str_list.h: fix clang warning about std::move
- /home/jenkins/workspace/ceph-master/src/include/str_list.h:99:10: warning: moving a local object in a return statemen...
- 03:45 PM Revision 9263613a (ceph): rocksdb: add option: writable_file_max_buffer_size = 0
- This reduce memcopy between rocksdb and bluefs.
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 03:33 PM Revision 2d982ae1 (ceph): Merge pull request #12565 from trociny/wip-18247-fixup
- common: fix clang compilation error
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:06 PM Revision 7d1f46b2 (ceph): os/bluestore: remove duplicate sbid member for Blob, use one from share...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:06 PM Revision a6158d5c (ceph): os/bluestore: declare a member for Blob's cached bufferlist if explicit...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:06 PM Revision b07f3ffe (ceph): os/bluestore: recalculate shared blob key instead of keeping it in memory
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:03 PM Revision 1b319f2e (ceph): os/bluestore: include modified objects in flush list even if onode unch...
- We use the onode flush list so that we can ->flush() as
a barrier before doing any read/modify/write. For
example, o... - 02:44 PM Revision 991141c3 (ceph): Merge pull request #12548 from Liuchang0812/add-document-rgw
- doc: explain rgw_fcgi_socket_backlog in rgw/config-ref.rst
Reviewed-by: Sage Weil <sage@redhat.com> - 02:38 PM Revision 071cdbe3 (ceph): Merge pull request #12561 from kylinstorage/wip-fix-osdmaptool-zero
- osdmaptool: fix divide by zero error
Reviewed-by: Sage Weil <sage@redhat.com> - 02:04 PM Revision 56ce5ed0 (ceph): tools/rados: remove useless function declaration
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 01:58 PM Revision 8da0f348 (ceph): Merge pull request #12497 from dillaman/wip-18243
- journal: prevent repetitive error messages after being blacklisted
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 09:12 AM Revision 838339d7 (ceph): ECBackend: cleanup for unnecessary copy with pg_stat_t
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 08:17 AM Revision 9ce95bb1 (ceph): remove unused wait argument and related function versions
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:44 AM Revision bd584fe7 (ceph): common: fix clang compilation
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 04:56 AM Revision 45a0286e (ceph): osdmaptool: fix divide by zero error
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 04:12 AM Revision cbebe7db (ceph): mon: drop support for "classic" (dumpling) mons
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:12 AM Revision a2ad2d91 (ceph): mon/OSDMonitor: do not use PGMap to check pg existence
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:12 AM Revision cf39776a (ceph): mon/OSDMonitor: remove obsolete pg[p]_num vs creating pgs restriction
- This dates back to the original split code circa
78ddc62b356cd0f26a9ac666b0f58ac0d0da8798 (v0.2) when the creating pg... - 04:11 AM Revision 904913b3 (ceph): mon/OSDMonitor: remove 'osd thrash' command
- This is a dev hack to generate a bunch of bogus osdmaps. The maps are
all screwed up anyway (e.g., invalid addrs) an... - 01:59 AM Revision e293d40e (ceph): Merge pull request #12558 from Adirl/fix_bad_len_msg
- msg/async/rdma: fix bad message that went to the user
Reviewed-by: Haomai Wang <haomai@xsky.com>
12/18/2016
- 10:13 PM Revision ccd7ebb5 (ceph): src/CMakeLists.txt:
- The Rocksdb code under Clang complains about:
/home/jenkins/workspace/ceph-master/src/rocksdb/util/thread_local.h:205... - 06:40 PM Revision 6ad9814b (ceph): os/bluestore:Bluefs balance should use alloc_extent api with bluefs_all...
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision f9338b1a (ceph): allocator alloc_extents min_alloc
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision 8ed5ec02 (ceph): allocator min_alloc arguments in call stack and tests
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision 2942bc62 (ceph): consolidate allocator calls to single alloc_extent api
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision 78b49025 (ceph): remove cont alloc alloc_blocks calls from allocator code and test
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision 86b6ca3d (ceph): allocat_extent api rename and tests for new api
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 06:40 PM Revision f1e9aee7 (ceph): zone block offset bug fix and related unit test case
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
zone block offset related test case
Signed-off-by: Rames... - 04:52 PM Revision daca8f68 (ceph): msg/async/rdma: fix bad message that went to the user
- 1. the printed value of "bad length" was incorrect, because 'r' was changed before the log line.
2. log appeared to u... - 04:16 PM Revision a567fa66 (ceph): libcephfs.cc: fix memory leak
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 01:07 PM Revision 2ccd02a8 (ceph): Fix startup of Ceph cluster manager daemon on Debian 8
- Signed-off-by: Mark Korenberg <socketpair@gmail.com>
- 08:59 AM Revision 049641df (ceph): Merge pull request #12531 from dachary/wip-18291-bluestore
- ceph-disk: do not create bluestore wal/db partitions by default
Reviewed-by: Sage Weil <sage@redhat.com>
12/17/2016
- 07:55 PM Revision c83d030d (ceph): ceph-disk: do not create bluestore wal/db partitions by default
- Fixes: http://tracker.ceph.com/issues/18291
Signed-off-by: Loic Dachary <loic@dachary.org> - 02:49 PM Revision 6fc0e59a (ceph): doc: explain rgw_fcgi_socket_backlog in rgw/config-ref.rst
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 04:54 AM Revision a30d90cd (ceph): Merge pull request #12458 from Liuchang0812/add-more-log-for-network-error
- osd: enhance logging for osd network error
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: xie xingguo <xie.x... - 04:20 AM rgw Documentation #18301 (Closed): RGW: update deployment document for the nginx frontend
- As we know, Nginx is the most popular web-server currently. Our document doesn't introduce how to configure nginx as ...
- 04:07 AM Revision 7ceadba3 (ceph): ods: enhance logging for osd network error
- Signed-off-by: liuchang0812 <liuchang0812@gmail.com>
- 02:21 AM Revision 72b97ee5 (ceph): osdc/ObjectCacher: use state instead of get_state()
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 02:00 AM Revision 9e19b867 (ceph): osd/ECBackend: remove unused variable "ReadCB"
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 12:56 AM Bug #18266: MOSDPGTrim wrongly decode during backfill
- https://github.com/ceph/ceph/pull/12517
- 12:40 AM Revision 25efc6f0 (ceph): test: add new testcase for request admin_socket with long request
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 12:20 AM rgw Bug #18299 (Duplicate): Invalid read of size 4: RGWRados::get_obj_iterate_cb
- This is duplicate of #18071
Would be likely fixed by this:
https://github.com/ceph/ceph/pull/12377
12/16/2016
- 11:44 PM rgw Bug #18300 (Resolved): leak from RGWMetaSyncShardCR::incremental_sync
- ...
- 11:43 PM rgw Bug #18299 (Duplicate): Invalid read of size 4: RGWRados::get_obj_iterate_cb
- ...
- 11:40 PM Revision 3cf1ca5d (ceph): Merge pull request #12343 from liewegas/wip-bluestore-release
- os/bluestore: simplify allocator release flow
Reviewed-by: Sage Weil <sage@redhat.com> - 11:40 PM Revision 45d698eb (ceph): Merge pull request #12351 from xiexingguo/xxg-wip-bluestore-1207
- os/bluestore: clear omap flag if parent has none
Reviewed-by: Sage Weil <sage@redhat.com> - 11:40 PM Revision 4444540d (ceph): Merge pull request #12353 from xiexingguo/xxg-wip-bluestore-1207-01
- os/bluestore: don't implicitly create the source object for clone
Reviewed-by: Sage Weil <sage@redhat.com> - 11:40 PM Revision 87a2a95a (ceph): rgw: Replacing '+' with "%20" in canonical uri for s3 v4 auth.
- s3cmd encodes space as "%20" while signature computation and
encodes space as '+' while sending the canonical uri. Th... - 11:39 PM Revision be4c0c72 (ceph): Merge pull request #12466 from kylinstorage/wip-remove-unused-class-dec...
- remove unused declaration
Reviewed-by: Sage Weil <sage@redhat.com> - 11:38 PM Revision 2c7c27ab (ceph): Merge branch 'master' into wip-remove-unused-class-declaration
- 11:10 PM Bug #18298 (Resolved): mon: force_create_pg could leave pg stuck in creating state
- If the osdmap didn't update, we would have the pg in creating state but no mapping and the osd wouldn't get the pg cr...
- 10:59 PM Revision e72c8019 (ceph): ceph.in: allow 'flags' to not be present in cmddescs
- the 'flags' key in the command description dict may not be
present on older monitors. Check for existence before
usi... - 10:55 PM Bug #18297 (Resolved): ceph cli fails on monitors that don't send 'flags' in command descs
- 61d63433dfdcc08ecc21ba4f645794da5e01823c added the ability to mark commands with flags to say they are obsolete or de...
- 09:38 PM Revision 26ab33ae (ceph): Merge pull request #12538 from liewegas/wip-workunits
- qa/tasks/workunit: retry on ceph.git if checkout fails
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:33 PM Bug #18265: MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- Spoke with Joao in IRC; he has some ideas
- 05:50 AM Bug #18265: MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- The hack in question:...
- 05:09 AM Bug #18265 (Resolved): MonMap::sanitize_mons() does not like monmaps built from -m/mon_hosts
- I have a ceph.conf that I've used for some time that declares mons with ...
- 08:08 PM Revision 02d301bf (ceph): Merge pull request #12534 from liewegas/wip-truncate-fix
- osd/PrimaryLogPG: don't truncate if we don't have to for WRITEFULL
Reviewed-by: Sage Weil <sage@redhat.com> - 08:06 PM Revision 72d73b8c (ceph): qa/tasks/workunit: retry on ceph.git if checkout fails
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:06 PM rbd Bug #18247 (Resolved): Changing 'rbd_default_features' to a string breaks Cinder
- 07:15 PM rbd Bug #18247 (Pending Backport): Changing 'rbd_default_features' to a string breaks Cinder
- 07:15 PM Revision 4fe7e2a4 (ceph): Merge pull request #12486 from dillaman/wip-18247
- librbd: keep rbd_default_features setting as bitmask
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 06:49 PM Revision 57f12ec0 (ceph): cls/rgw: Clean up the "magic string" usage in the cls layer for RGW.
- This set of changes, should make following what is going on across the cls
barrier much easier for people using code ... - 05:46 PM Revision de318620 (ceph): Merge pull request #12514 from vasukulkarni/wip-cd-shaman
- qa/tasks/ceph_deploy: use dev option instead of dev-commit
Reviewed-by: Sage Weil <sage@redhat.com> - 05:40 PM Revision 2323aa17 (ceph): ReplicatedPG: don't truncate if we don't have to for WRITEFULL
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:51 PM Bug #18293 (Resolved): osd: leaked MOSDMap
- ...
- 04:42 PM Revision ed3e9c1d (ceph): Merge pull request #10160 from jmunhoz/bugfix-16463-presigned-url
- rgw: aws4: add presigned url bugfix in runtime
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:25 PM rgw Bug #18292 (New): multisite: improved consistency model for requests forwarded to meta master
- When a metadata request (such as bucket a operation) is sent to a non-master zone, the request is forwarded to the me...
- 04:24 PM Revision 3d1ec3c9 (ceph): Merge pull request #12530 from liewegas/wip-bluestore-ceph-disk
- ceph-disk: adjust bluestore default device sizes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:14 PM Revision 1b668577 (ceph): test: add mempool dump to Onode size tracking test case
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:51 PM Revision 9a783879 (ceph): os/bluestore: add an estimation for Onode in-memory size
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 03:29 PM Bug #18291: ceph-disk: bluestore wal/db partitions must be optional
- 03:24 PM Bug #18291: ceph-disk: bluestore wal/db partitions must be optional
- https://github.com/ceph/ceph/pull/12531
- 03:11 PM Bug #18291 (Resolved): ceph-disk: bluestore wal/db partitions must be optional
- Instead of being created by default, they should be created only if the user explicitly asks for it with the appropri...
- 03:28 PM Bug #16783: Build fails if you disable radosgw (--without-radosgw) during linking
- The failure when compiling without OpenLDAP is new in 10.2.3 -- it worked in 10.2.2 (which is what this bug report is...
- 02:49 PM Bug #16783: Build fails if you disable radosgw (--without-radosgw) during linking
- Similarly, radosgw fails to build when configured --without-openldap:
CXXLD radosgw
CXXLD radosgw-admin... - 03:27 PM Revision 38a501a2 (ceph): Merge pull request #12516 from hjwsm1989/fix-rpg
- osd/PG: fix the unreadable log in choose_acting
Reviewed-by: Sage Weil <sage@redhat.com> - 03:24 PM Revision 15fdc67c (ceph): Merge pull request #12521 from kylinstorage/wip-for-coverity
- osd/osdmap: fix divide by zero error
Reviewed-by: Sage Weil <sage@redhat.com> - 03:19 PM Revision 9f881000 (ceph): client: set metadata["root"] from mount method when it's called with a ...
- Currently, we only set the root properly config file or the
--client_metadata command line option. If a userland clie... - 03:02 PM rbd Backport #18270 (In Progress): jewel: add image id block name prefix APIs
- 01:19 PM rbd Backport #18270: jewel: add image id block name prefix APIs
- The following two commits should be backported to jewel:
https://github.com/ceph/ceph/pull/11353/commits/366e6075c... - 01:19 PM rbd Backport #18270 (Resolved): jewel: add image id block name prefix APIs
- https://github.com/ceph/ceph/pull/12529
- 03:02 PM Revision 478551e9 (ceph): Merge pull request #12507 from ifed01/wip-bluestore-fix-cache
- os/bluestore: fix target_buffer value overflow in Cache::trim()
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 03:01 PM Revision aa8e57d0 (ceph): rbd: utilize new API methods for image id and block name prefix
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 0a0a88c71552aa5858384fa802a3161da90e7c... - 02:52 PM Revision 05295eff (ceph): librbd: new API methods to retrieve image id and block name prefix
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 366e6075cab2748efab395cd23882eaee4ba402f) - 02:47 PM rbd Bug #18261 (Pending Backport): rbd status: json format has duplicated/overwritten key
- 12:09 PM rbd Bug #18261 (Fix Under Review): rbd status: json format has duplicated/overwritten key
- PR: https://github.com/ceph/ceph/pull/12525
- 10:24 AM rbd Bug #18261 (In Progress): rbd status: json format has duplicated/overwritten key
- 02:47 PM Revision 1b0a9d8c (ceph): Merge pull request #12525 from trociny/wip-18261
- rbd: fix json formatting for image and journal status output
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:45 PM Revision 19346c7e (ceph): ceph-disk: default DB size of 20GB
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:45 PM Revision 7a5051af (ceph): ceph-disk: default WAL size of 576 MB
- Enough for 2 256MB write buffers, and then some.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:44 PM rbd Backport #18290 (Resolved): jewel: objectmap does not show object existence correctly
- https://github.com/ceph/ceph/pull/12909
- 02:44 PM rbd Backport #18289 (Closed): kraken: objectmap does not show object existence correctly
- 02:43 PM rbd Backport #18288 (Resolved): jewel: rbd-mirror: image sync object map reload logs message
- https://github.com/ceph/ceph/pull/12753
- 02:43 PM rgw Backport #18287 (Closed): kraken: multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED ...
- 02:43 PM rgw Backport #18286 (Resolved): jewel: multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED...
- https://github.com/ceph/ceph/pull/12738
- 02:42 PM rbd Backport #18285 (Resolved): jewel: partition func should be enabled When load nbd.ko for rbd-nbd
- https://github.com/ceph/ceph/pull/12754
- 02:42 PM rbd Backport #18284 (Resolved): jewel: Need CLI ability to add, edit and remove omap values with bina...
- https://github.com/ceph/ceph/pull/12755
- 02:42 PM CephFS Backport #18283 (Closed): kraken: monitor cannot start because of "FAILED assert(info.state == MD...
- 02:42 PM CephFS Backport #18282 (Resolved): jewel: monitor cannot start because of "FAILED assert(info.state == M...
- https://github.com/ceph/ceph/pull/13123
- 02:42 PM Backport #18281 (Resolved): hammer: mon: osd flag health message is misleading
- https://github.com/ceph/ceph/pull/12687
- 02:41 PM Backport #18280 (Resolved): jewel: mon: osd flag health message is misleading
- https://github.com/ceph/ceph/pull/13117
- 02:41 PM rbd Backport #18279 (Closed): kraken: RBD diff got SIGABRT with "--whole-object" for RBD whose parent...
- 02:41 PM rbd Backport #18278 (Resolved): jewel: RBD diff got SIGABRT with "--whole-object" for RBD whose paren...
- https://github.com/ceph/ceph/pull/12649
- 02:41 PM rgw Backport #18277 (Resolved): jewel: multisite: trim data changes log as peers zones catch up
- https://github.com/ceph/ceph/pull/20061
- 02:41 PM rbd Backport #18276 (Resolved): jewel: rbd-nbd: invalid error code for "failed to read nbd request" m...
- https://github.com/ceph/ceph/pull/12756
- 02:41 PM rbd Backport #18275 (Closed): kraken: rbd-nbd: invalid error code for "failed to read nbd request" me...
- 02:41 PM Backport #18274 (Resolved): jewel: Memory leaks in object_list_begin and object_list_end
- https://github.com/ceph/ceph/pull/13118
- 02:26 PM Revision 8ddfb453 (ceph): librbd: keep rbd_default_features setting as bitmask
- Support both human readable, comma delimited list of feature
names and also integer bitmask value. Attempting to read... - 02:21 PM Revision 9a79286d (ceph): Merge pull request #12407 from majianpeng/rbd-stripe-unit
- rbd : make option --stripe-unit w/ B/K/M work
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:46 PM rbd Bug #16179 (Pending Backport): rbd-mirror: image sync object map reload logs message
- 01:45 PM Revision d5f34108 (ceph): Merge pull request #12484 from runsisi/wip-fix-rollback-warn
- librbd: ignore error when object map is already locked by current client
Reviewed-by: Jason Dillaman <dillaman@redha... - 01:21 PM rbd Bug #18269: rbd info truncates block_name_prefix to 23 chars
- The issue is that the legacy API only supports 23 characters (plus an additional null byte) to represent the block na...
- 12:03 PM rbd Bug #18269: rbd info truncates block_name_prefix to 23 chars
- This has been changed when fixing this issue: http://tracker.ceph.com/issues/17310
I think we can return the old b... - 10:36 AM rbd Bug #18269 (Duplicate): rbd info truncates block_name_prefix to 23 chars
- Hi,
Since 10.2.4/5 rbd info truncates the block_name_prefix to 23 chars. Version 10.2.3 shows the prefix with 24 c... - 10:50 AM Revision 4c2659a0 (ceph): rbd: fix json formatting for image and journal status output
- Fixes: http://tracker.ceph.com/issues/18261
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 10:33 AM Bug #18268 (Closed): Cmake in jewel fails to detect C++11
- Invalid - the c++11 cmake check failed due to a missing libcurl dependency.
- 09:48 AM Bug #18268: Cmake in jewel fails to detect C++11
- close this, opened too early by accident.
- 09:46 AM Bug #18268 (Closed): Cmake in jewel fails to detect C++11
- 10:14 AM Revision 317100ad (ceph): osd/ECBackend: only need check missing_loc when doing recovery
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 09:56 AM Revision c5ce82e6 (ceph): rbd: make option --stripe-unit w/ B/K/M work.
- As 'man rbd' said: --stripe-unit size-in-B/K/M. But w/ B/K/M, the
command failed and said invalid options. So fix it... - 09:47 AM Revision 73fc2259 (ceph): osd/PrimaryLogPG: unify the access to primary pg
- Signed-off-by: huangjun <hjwsm1989@gmail.com>
- 09:33 AM Revision 7858f7e3 (ceph): osd/ECBackend: Send write message to peers first, then do local write
- Like ReplicatedBackend did, this will improve write performance.
Signed-off-by: huangjun <hjwsm1989@gmail.com> - 09:28 AM Revision 61d3e4f3 (ceph): osdmap: fix divide by zero error
- *** CID 1397255: Incorrect expression (DIVIDE_BY_ZERO)
/home/brad/working/src/ceph/src/osd/OSDMap.cc: 2995 in
OSDMa... - 09:03 AM Feature #18267 (New): ceph-disk may use blivet
- http://blivet.readthedocs.io/en/latest/intro.html seems a good python abstraction to deal with block devices
- 08:58 AM Revision 5915fb35 (ceph): osd/PG: simplify the logic of backfill_targets checking
- the final state is backfill_targets equals want_backfill,
and backfill shards should not included in stray_set.
S... - 08:38 AM Revision fd68cf1b (ceph): messages/MOSDPGTrim: add the missed HEAD_VERSION and COMPAT_VERSION
- Fixes: http://tracker.ceph.com/issues/18266
Signed-off-by: huangjun <hjwsm1989@gmail.com> - 08:32 AM Revision 51e41298 (ceph): client: don't need inode when request CEPH_MDS_OP_LOOKUPPARENT
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 08:32 AM Revision 9d925e0d (ceph): client: don't request lookup parent if ino is root
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 08:12 AM Revision 52deb168 (ceph): admin-socket: fix potential buffer overflow
- Add code to ensure cmd[pos] is valid memory.
Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com> - 08:08 AM Bug #18266 (Resolved): MOSDPGTrim wrongly decode during backfill
- I have pg 3.0 distribute on [1,2,4], and backfilling to osd.5
during the backfill, i saw the osd.1 receive the MOSDP... - 07:35 AM Revision 9897f0c6 (ceph): osd/PG: fix the unreadable log in choose_acting
- To avoid the log like: failed to fill position ^B
Signed-off-by: huangjun <hjwsm1989@gmail.com> - 07:08 AM Revision 162df9e4 (ceph): client: use new Trace interface
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 07:03 AM Revision c1aae140 (ceph): client: fix potential buffer overflow
- Trace::peek_string try to fill char *buf without any length check.
I think string buf is the better way to handle it.... - 06:43 AM Revision 1f2d5497 (ceph): JournalingObjectStore: remove misleading comments
- Prior to start journal commit, it always needs to wait the ongoing apply
operation to finish, not only needed during ... - 06:40 AM Revision 91b6d1da (ceph): JournalingObjectStore: remove unneeded variable
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 06:33 AM Revision 22ce0d91 (ceph): JournalingObjectStore: skip journal commit_start if commit_start does n...
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 12:33 AM Revision 711da4e2 (ceph): librbd: ignore error when object map is already locked by current client
- otherwise when using rbd cli to rollback image with object-map feature
enabled, the following error message will be p...
12/15/2016
- 11:59 PM Revision 078c513b (ceph): rgw: aws4: add rgw_s3_auth_aws4_force_boto2_compat conf option
- Runtime bugfix to handle presigned urls computed with canonical requests using
the port number once.
Boto2 computes ... - 10:41 PM Revision 8d7d5ae3 (ceph): Merge pull request #12463 from wjwithagen/wip-wjw-freebsd-osd-avoidports
- FreeBSD/OSD.cc: add client_messenger to the avoid_ports set.
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: ... - 10:11 PM Revision 9f04a7b3 (ceph): use dev option instead of dev-commit
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 10:00 PM Revision e2b30955 (ceph): Merge pull request #12500 from badone/wip-doc-PGPool
- doc/dev/osd_internals: add pgpool.rst
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:31 PM Documentation #18262 (Fix Under Review): rbdmap documentation is inadequate
- 05:27 PM Documentation #18262: rbdmap documentation is inadequate
- Working on it in https://github.com/ceph/ceph/pull/12509
- 02:44 PM Documentation #18262 (Resolved): rbdmap documentation is inadequate
- The only "official" documentation of rbdmap that I can find is the rbdmap manpage, which is just a stub.
- 09:02 PM Revision f6519509 (ceph): install-deps.sh: initial distro detection based on /etc/os-release
- This avoids initial distribution detection (before lsb_release is available)
based on the presence of a specific pack... - 09:02 PM Revision 240431be (ceph): build/ops: fix /etc/os-release parsing in install-deps.sh
- 85a370e35fc42031a7f7e24dea9e50a649c0f309 introduced the DISTRO variable whose
value was obtained by parsing /etc/os-r... - 08:32 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- Aaron Ten Clay wrote:
> I'm running an experiment against the current kraken branch, preventing the ceph_abort() cal... - 07:58 AM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- I'm running an experiment against the current kraken branch, preventing the ceph_abort() call which produces this err...
- 08:15 PM Revision 6bb3a037 (ceph): Merge pull request #12511 from liewegas/wip-workunits
- qa/workunits/rbd: fix
Reviewed-by: Jason Dillaman <dillaman@redhat.com>
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 08:10 PM Revision cf294777 (ceph): qa/workunits: use relative path instead of wget from git
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:53 PM Revision c6698c95 (ceph): Merge pull request #12508 from liewegas/wip-qa-admin-socket
- qa/tasks/admin_socket: subst in repo name
- 07:35 PM Revision 0f6be4c9 (ceph): doc/dev/osd_internals: add pgpool.rst
- Signed-off-by: Brad Hubbard <bhubbard@redhat.com>
- 07:20 PM Revision 9e41b4cf (ceph): os/bluestore: do not call commit_{start,finish}
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:20 PM Revision e0ec06ed (ceph): os/bluestore/BlueFS: defer releasing extents explicitly
- Don't rely on the Allocator to do this for us (that is
about to go away!).
Signed-off-by: Sage Weil <sage@redhat.com> - 07:20 PM Revision 9fad893f (ceph): os/bluestore/BlueFS: do not call commit_{start,finish}
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:20 PM Revision 5522dee8 (ceph): os/bluestore: remove commit_{start,finish} from Allocator
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:20 PM Revision a411f587 (ceph): os/bluestore: clone_range of len 0 creates but does not size object
- This mimics, roughly,
open(..., O_WRONLY|O_CREAT, ...)
seek(...)
if (len > 0)
write(...)
Signed-off-by: Sage ... - 07:20 PM Revision b605a14e (ceph): os/bluestore: release alloc directly into usable pool
- Wait until after the kv transaction commits, and then
release extents directly into the usable pool.
This will let u... - 07:20 PM Revision 65ead28a (ceph): os/bluestore: defer bluefs reclaimed extent release
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:52 PM Revision 4602884a (ceph): qa/tasks/workunit: leave workunits inside git checkout
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:52 PM Revision 27b8eac2 (ceph): qa/tasks/workunit.py: add CEPH_BASE env var
- Root of git checkout
Signed-off-by: Sage Weil <sage@redhat.com> - 06:51 PM Revision 5642e7e1 (ceph): PG: fix cached_removed_snaps bug in PGPool::update after map gap
- 5798fb3bf6d726d14a9c5cb99dc5902eba5b878a actually made 15943 worse
by always creating an out-of-date cached_removed_s... - 06:50 PM Revision aeb8fef9 (ceph): PG::handle_advance_map: add debugging option to verify cached_removed_s...
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 06:50 PM Revision d4b6615a (ceph): qa/config/rados.yaml: enable osd_debug_verify_cached_snaps
- Also, make map gaps more likely.
Signed-off-by: Samuel Just <sjust@redhat.com> - 06:35 PM Revision bcbe45d9 (ceph): qa/tasks/admin_socket: subst in repo name
- It is either ceph.git or ceph-ci.git.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:43 PM Revision 178d5bbe (ceph): test/rgw: add test for versioned object sync
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 05:27 PM rbd Bug #14535: rbd CLI does not validate pool and snapshot name optionals
- Jason Dillaman wrote:
> @Gaurav: the issue is that the "--pool" and "--snap" arguments are *not* validated but they ... - 05:22 PM Linux kernel client Bug #18041 (Resolved): periodically kernel crashes with CephFS
- in 4.8.15.
- 04:26 PM Revision 96e5d85d (ceph): os/bluestore: fix target_buffer value overflow in Cache::trim() when me...
- Signed-off-by: Igor Fedotov<ifedotov@mirantis.com>
- 04:04 PM rbd Bug #18247 (Fix Under Review): Changing 'rbd_default_features' to a string breaks Cinder
- *PR*: https://github.com/ceph/ceph/pull/12486
- 04:03 PM rbd Bug #18200 (Pending Backport): RBD diff got SIGABRT with "--whole-object" for RBD whose parent al...
- 04:03 PM Revision 31faa814 (ceph): Merge pull request #12396 from xiaoxichen/fix_diff
- librbd: use proper snapshot when computing diff parent overlap
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:02 PM rbd Feature #18123 (Pending Backport): Need CLI ability to add, edit and remove omap values with bina...
- 04:01 PM Bug #18252 (Pending Backport): Memory leaks in object_list_begin and object_list_end
- 04:01 PM Revision b473f235 (ceph): Merge pull request #12482 from badone/wip-librados-objectcursor-leak
- librados: Memory leaks in object_list_begin and object_list_end
Reviewed-by: Sage Weil <sage@redhat.com> - 04:00 PM Revision 61e592ad (ceph): Merge pull request #12286 from dillaman/wip-18123
- rados: optionally support reading omap key from file
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:00 PM Revision 1c8903f5 (ceph): Merge pull request #12462 from XinzeChi/wip-blk-link
- common/blkdev: use realpath instead of readlink to resolve the recurs…
Reviewed-by: Sage Weil <sage@redhat.com> - 03:49 PM rbd Bug #16179 (Fix Under Review): rbd-mirror: image sync object map reload logs message
- *PR*: https://github.com/ceph/ceph/pull/12484
- 03:40 PM Revision dd0a1b85 (ceph): Merge pull request #12488 from liewegas/wip-bluestore-enc
- os/bluestore: fix ondisk encoding for blobs
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com>
Reviewed-by: Varada Ka... - 02:44 PM rbd Bug #18261 (Resolved): rbd status: json format has duplicated/overwritten key
- Hi,
`rbd status <name> --format json` duplicates the watcher key if there are serveral watchers on a RBD. For exam... - 02:26 PM Revision acd44737 (ceph): os/bluestore/bluestore_types: bluestore_onode_t: varint encoding
- Changing the uint32_t encoding to varint encoding saves around 120 bytes
per onode.
Signed-off-by: Varada Kari <vara... - 12:55 PM rgw Bug #18260 (In Progress): When uploading a large number of objects constantly, the objects number...
- When finishing uploading a large number of objects constantly by cosbench, the objects number of bucket queried by @r...
- 12:01 PM Revision a8a2a8c3 (ceph): Revert "dummy: reduce run time, run user.yaml playbook"
- This reverts commit d4e3cec1851ae35889127b90912e133178085bc6.
Fixes: http://tracker.ceph.com/issues/18259
Signed-off... - 10:22 AM Revision be1a4a2a (ceph): Merge pull request #12502 from kylinstorage/wip-ctypos2
- fix typos
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 09:24 AM Revision c1dedf78 (ceph): rc/rgw/rgw_rados.cc : fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 09:24 AM Revision c6206776 (ceph): rc/rgw/rgw_coroutine.cc : fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 09:23 AM Revision 96258716 (ceph): rc/os/memstore/MemStore.h : fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 09:23 AM Revision 9b317f73 (ceph): rc/os/filestore/FileStore.cc : fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 09:22 AM Revision 8094bcaf (ceph): rc/os/bluestore/NVMEDevice.cc :fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 09:21 AM Revision 625ab010 (ceph): rc/mon/DumplingMonCommands.h :fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 08:30 AM rgw Bug #18258 (Duplicate): rgw: radosgw-admin orphan find goes into infinite loop
- The job is running 6 days already:
radosgw-admin orphans find --pool=.rgw.buckets --job-id=dev1
I think job is st... - 06:04 AM Revision fa0c5881 (ceph): Fix error in including all files in osd_tp
- osd_tp is the only variable that is a list and with current logic only
the last file of the list will be included in ... - 05:11 AM Bug #18250 (Resolved): Memory leak in ceph_test_rados_api_list
- 02:42 AM Revision 298d6190 (ceph): Merge pull request #12495 from kylinstorage/wip-ctypos
- Wip ctypos
Reviewed-by: Brad Hubbard <bhubbard@redhat.com>
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:24 AM Revision 15a5ace3 (ceph): librbd: remove consistency group rbd cli and API support
- Fixes: http://tracker.ceph.com/issues/18231
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:58 AM Revision 1fdbabad (ceph): Merge pull request #12479 from badone/wip-ceph_test_rados_api_list-leak
- test/rados/list.cc: Memory leak in ceph_test_rados_api_list
Reviewed-by: Sage Weil <sage@redhat.com> - 01:51 AM rbd Cleanup #18243: JournalMetadata flooding with errors when being blacklisted
- *Additional PR*: https://github.com/ceph/ceph/pull/12497
- 01:49 AM Revision 60f1b1a2 (ceph): journal: prevent repetitive error messages after being blacklisted
- Fixes: http://tracker.ceph.com/issues/18243
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:54 AM Revision c70e4c36 (ceph): src/os/bluestore/BlueStore.cc:fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 12:15 AM Bug #18257 (Resolved): rados/basic test fails due to 'Regular scrub request, losing deep-scrub de...
- 12:15 AM Bug #18256 (Resolved): Regular scrub request, losing deep-scrub details
- 12:07 AM Revision 96d30395 (ceph): Merge pull request #12493 from athanatos/wip-18113-qa
- Wip 18113 qa
- 12:05 AM Revision ae40602c (ceph): Merge remote-tracking branch 'ceph-qa-suite/master' into wip-18113-qa
12/14/2016
- 11:57 PM Revision 36481ff2 (ceph): Merge pull request #1310 from ceph/wip-18113
- test: Update for new error message when doing scrub with deep-scrub e…
Reviewed-by: Samuel Just <sjust@redhat.com> - 11:46 PM Bug #18257: rados/basic test fails due to 'Regular scrub request, losing deep-scrub details' in log
- http://pulpito.ceph.com/sage-2016-12-14_21:55:38-rados:basic-master---basic-smithi/634534
- 11:45 PM Bug #18257 (Resolved): rados/basic test fails due to 'Regular scrub request, losing deep-scrub de...
- I'm not sure whether the test is actually working properly now. Do we need to fix it, or just whitelist the error?
- 11:35 PM Bug #18256 (Resolved): Regular scrub request, losing deep-scrub details
- http://pulpito.ceph.com/sage-2016-12-14_21:55:38-rados:basic-master---basic-smithi/634534
- 11:21 PM Bug #16414 (Closed): scrub_test now failing, probably related to 9e2b455f45cca2f31b19c73d761661a9...
- Not seeing this anymore
- 10:52 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- The patch turns out to be pretty trivial:...
- 09:26 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- Revised test program here, in patch format so it can build in tree. We should probably roll this up into a regression...
- 08:56 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- Thanks Greg, I'll take a look at how all of that stuff gets set. FWIW, here's the log with the client debugging crank...
- 08:44 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- Did you check the client log to see where it's failing out at?
I'd check the code flow from Client::mount() to the M... - 08:28 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- The program logs this in the MDS logs when run. I'm definitely passing in a real path there:...
- 08:12 PM CephFS Bug #18254: path restricted cephx caps not working correctly
- Oh, and you will need to overwrite the key in the reproducer program with the one for "alice".
- 08:05 PM CephFS Bug #18254 (Resolved): path restricted cephx caps not working correctly
- Ramana noticed this first while testing my ganesha patches to allow restricting exports. It appears that attempting t...
- 10:20 PM Revision 1bfabc3d (ceph): test/rados/list.cc: Memory leak in ceph_test_rados_api_list
- Valgrind flags a memory leak when we create a temporary from
rados_object_list_end()
Fixes: http://tracker.ceph.com/... - 09:52 PM rgw Bug #17465 (Pending Backport): multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED errors
- 09:49 PM Revision 940b96a7 (ceph): Merge pull request #12438 from songbaisen/s6
- mon: make it more clearly to debug for paxos state
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:48 PM Revision 167b3e1d (ceph): Merge pull request #12461 from liupan1111/wip-replace-atomic
- osd: remove the lock heartbeat_update_lock, and change heatbeat_need_…
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:42 PM Revision a5bc1f48 (ceph): Merge pull request #12452 from ceph/wip-rgw-fix-cr-deadlock
- rgw: use explicit flag to cancel RGWCoroutinesManager::run()
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:27 PM Revision dff7077c (ceph): Merge pull request #12487 from athanatos/wip-rpg-rename
- src: rename ReplicatedPG to PrimaryLogPG
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:13 PM Revision d4e4e8b2 (ceph): os/bluestore/bluestore_types: bluestore_blob_t: varint encode csum_data...
- Signed-off-by: Sage Weil <sage@redhat.com>
- 08:09 PM Revision 90ba4ee6 (ceph): os/bluestore: version shard and spanning blob buffers, not each blob
- Instead of versioning every blob encoding, and adding a full byte
per blob, instead version the entire shard or spann... - 08:06 PM Revision 2af1b029 (ceph): include/denc: pass features through to decode() on featured objects
- This allows featured objects the *option* to do something
meaningful with the features. Generally the decoding is fe... - 07:45 PM CephFS Bug #18119 (Closed): mds: check and get latest current logsegment to avoid trimming logsegment cr...
- This does not seem to be an issue in either master nor Jewel.
- 07:39 PM Revision 9be7c540 (ceph): os/bluestore/bluestore_types: single byte for blob struct_v
- We forego decoding compatibility by older code by dropping
compat_v and len. We have to keep struct_v per blob here ... - 07:35 PM Revision 9b331f94 (ceph): Merge pull request #7639 from linuxbox2/wip-rgw-header
- rgw: add option to log custom HTTP headers (rgw_log_http_headers)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:34 PM Revision c2c5dace (ceph): Merge pull request #12268 from dzafman/wip-18113
- osd: When deep-scrub errors present upgrade regular scrubs
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:34 PM Revision ab9b8e73 (ceph): os/bluestore/bluestore_types: fix bluestore_pextent_t encoding
- Signed-off-by: Varada Kari <varada.kari@sandisk.com>
- 06:45 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- David Zafman wrote:
> Find all the "_failed_push: Read error" message in the logs of crashing OSDs and note the erro... - 06:18 PM Revision 6f8e4b38 (ceph): src: rename ReplicatedPG to PrimaryLogPG
- It's been confusing for a long time that EC pools are implemented by
ReplicatedPG. What PG/ReplicatedPG really imple... - 06:09 PM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- 05:40 PM Revision 8abf95af (ceph): Merge pull request #12456 from liewegas/qa-suite-firefly
- firefly: merge ceph-qa-suite
- 05:40 PM Revision e038662d (ceph): Merge pull request #12455 from liewegas/qa-suite-hammer
- hammer: merge ceph-qa-suite
- 05:39 PM Revision c067b589 (ceph): Merge pull request #12454 from liewegas/qa-suite-jewel
- jewel: merge ceph-qa-suite
- 05:39 PM Revision 025f777d (ceph): Merge pull request #12453 from liewegas/qa-suite-master
- master: merge ceph-qa-suite
- 05:30 PM Revision be713965 (ceph): merge ceph-qa-suite
- 05:30 PM Revision 59878b3b (ceph): merge ceph-qa-suite
- 05:29 PM Revision d2380d7d (ceph): merge ceph-qa-suite
- 05:29 PM Revision a1eaa3f0 (ceph): merge ceph-qa-suite
- 05:29 PM Revision c01f2ee0 (ceph): move ceph-qa-suite dirs into qa/
- 05:29 PM Revision 1c28e7f0 (ceph): move ceph-qa-suite dirs into qa/
- 05:29 PM Revision 7ed0dce3 (ceph): move ceph-qa-suite dirs into qa/
- 05:29 PM Revision 449ffc65 (ceph): move ceph-qa-suite dirs into qa/
- 05:28 PM Revision 0c061c14 (ceph): Revert "tasks/workunit.py: depth 1 clone"
- This reverts commit 4faf77a649cb3f8ddf497ca81937b3dbf63a18dc.
- 05:27 PM Revision 282451d8 (ceph): Revert "tasks/workunit.py: depth 1 clone"
- This reverts commit e6f61ea9f19d0f1fad4a6547775fa80616eeeb89.
- 05:27 PM Revision 08ce5441 (ceph): Revert "tasks/workunit.py: depth 1 clone"
- This reverts commit 12a707cb0f7b162e15c31915eb677bbd49b5e2cf.
- 05:24 PM rbd Bug #16176 (Pending Backport): objectmap does not show object existence correctly
- 05:23 PM Revision 4828ab63 (ceph): Merge pull request #12420 from dillaman/wip-16176
- librbd: properly order concurrent updates to the object map
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
Reviewed... - 05:21 PM Revision 12a707cb (ceph): tasks/workunit.py: depth 1 clone
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 4faf77a649cb3f8ddf497ca81937b3dbf63a18dc) - 05:21 PM Revision 6bdc3bb6 (ceph): tasks/workunit: remove kludge to use git.ceph.com
- This was hard-coded to ceph.git (almost) and breaks when
you specify --ceph-repo. Remove it entirely. We'll see if
... - 05:21 PM Revision e6f61ea9 (ceph): tasks/workunit.py: depth 1 clone
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 4faf77a649cb3f8ddf497ca81937b3dbf63a18dc) - 05:21 PM Revision 426f7cf2 (ceph): tasks/workunit: remove kludge to use git.ceph.com
- This was hard-coded to ceph.git (almost) and breaks when
you specify --ceph-repo. Remove it entirely. We'll see if
... - 05:21 PM Revision 124712a4 (ceph): Merge pull request #1307 from ceph/wip-workunit-repo
- tasks/workunit: use correct git mirror url
- 05:19 PM Revision 4faf77a6 (ceph): tasks/workunit.py: depth 1 clone
- Signed-off-by: Sage Weil <sage@redhat.com>
- 05:18 PM Revision 159c455a (ceph): tasks/workunit: remove kludge to use git.ceph.com
- This was hard-coded to ceph.git (almost) and breaks when
you specify --ceph-repo. Remove it entirely. We'll see if
... - 05:14 PM Linux kernel client Bug #17329 (Closed): modprobe test fails
- 04:40 PM rbd Bug #18242 (Pending Backport): rbd-nbd: invalid error code for "failed to read nbd request" messages
- 02:20 PM rbd Bug #18242 (Fix Under Review): rbd-nbd: invalid error code for "failed to read nbd request" messages
- PR: https://github.com/ceph/ceph/pull/12483
- 04:40 PM Revision 52e46fdf (ceph): Merge pull request #12483 from trociny/wip-18242
- rbd-nbd: invalid error code for "failed to read nbd request" messages
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:21 PM Revision c66977b0 (ceph): os/bluestore: remove redundant onode parameter in ExtentMap methods
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 04:21 PM Revision 693ee50c (ceph): os/bluestore: refactor ExtentMap::update to avoid preceeding db update ...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 04:14 PM rgw Bug #18241: rgw: the Multi-Object Delete operation of S3 API wrongly handles the "Code" response ...
- https://github.com/ceph/ceph/pull/12485
- 05:16 AM rgw Bug #18241: rgw: the Multi-Object Delete operation of S3 API wrongly handles the "Code" response ...
- I have found whole list about S3 code/message: http://docs.aws.amazon.com/AmazonS3/latest/API/s3-api.pdf Page25. I wo...
- 04:03 PM Bug #16800 (Resolved): SELinux denials found
- 11:17 AM Bug #16800: SELinux denials found
- https://github.com/ceph/ceph-qa-suite/pull/1309
- 02:45 AM Bug #16800: SELinux denials found
- in http://pulpito.ceph.com/kchai-2016-12-13_16:06:03-rados-master---basic-mira/630560/...
- 03:57 PM Revision 87e02994 (ceph): tasks/ceph: restore context of osd mount path before mkfs
- all newly created files and directories under the mount dir inherit the
SELinux type of their parent directory. so we... - 03:57 PM Revision 1ba5995b (ceph): tasks/ceph: restore context of osd mount path before mkfs
- all newly created files and directories under the mount dir inherit the
SELinux type of their parent directory. so we... - 03:56 PM Revision bd83719e (ceph): Merge pull request #1309 from ceph/wip-16800-kefu
- tasks/ceph: restore context of osd mount path before mkfs
- 03:23 PM Revision 49698d6e (ceph): Merge pull request #12476 from liewegas/wip-vstart-rados
- CMakeLists: add vstart-base target
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:59 PM Revision 04bf0f8c (ceph): rgw: add 'rgw log http headers' gloss to config-ref.rst
- Explain the option for upstream doc.
Signed-off-by: Matt Benjamin <mbenjamin@redhat.com> - 02:54 PM Bug #18036 (Resolved): unittest_throttle transient timeout
- 02:54 PM Revision 2b947021 (ceph): Merge pull request #12393 from dachary/wip-18036-throttle
- tests: unittest_throttle avoid ASSERT_DEATH
Reviewed-by: Sage Weil <sage@redhat.com> - 02:51 PM Revision a1a2f3a0 (ceph): Merge pull request #12473 from dillaman/wip-18243
- journal: avoid logging an error when a watch is blacklisted
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 02:09 PM Revision 2871374c (ceph): Merge pull request #1156 from ceph/wip-kclient-python
- Enable cephfs python tests on kclient
- 01:55 PM Revision 63ae8579 (ceph): Merge pull request #11542 from batrick/systemd-ceph-fuse
- systemd: add ceph-fuse service file
Reviewed-by: John Spray <john.spray@redhat.com> - 01:54 PM CephFS Feature #12132 (Resolved): cephfs-data-scan: Cleanup phase
- https://github.com/ceph/ceph/pull/12337#pullrequestreview-12909728...
- 01:52 PM Revision 3c7c65c6 (ceph): Merge pull request #12337 from vishalkanaujia/wip_12132
- tools: cleanup phase of cephfs-data-scan
Reviewed-by: John Spray <john.spray@redhat.com> - 01:49 PM Revision 69e03da1 (ceph): Merge pull request #12358 from tchaikov/wip-18157
- ceph-fuse: start up log on parent process before shutdown
Reviewed-by: Sage Weil <sage@redhat.com> - 12:57 PM Revision f0f552ca (ceph): Merge pull request #12384 from renhwztetecs/renhw-wip-libcephfs-addread...
- libcephfs: add readlink function in cephfs.pyx
Reviewed-by: John Spray <john.spray@redhat.com> - 12:56 PM CephFS Bug #18166 (Pending Backport): monitor cannot start because of "FAILED assert(info.state == MDSMa...
- 12:56 PM Revision cdbad50e (ceph): Merge pull request #12395 from jcsp/wip-18166
- mon/MDSMonitor: fix iterating over mutated map
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 12:56 PM Revision e25f060a (ceph): Merge pull request #12401 from kylinstorage/wip-typos
- client: fix mutex name typos
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:52 PM Revision 8d4a95d5 (ceph): Merge pull request #12443 from jcsp/wip-18225
- mds: release pool allocator memory after exceeding size limit
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:15 AM Revision 53225d52 (ceph): tasks/ceph: restore context of osd mount path before mkfs
- all newly created files and directories under the mount dir inherit the
SELinux type of their parent directory. so we... - 07:53 AM Revision 42c2514f (ceph): rbd-nbd: invalid error code for "failed to read nbd request" messages
- Fixes: http://tracker.ceph.com/issues/18242
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 07:32 AM Revision b26555a0 (ceph): src/kv/RocksDBStore.cc:fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 07:30 AM Revision 679292b9 (ceph): src/erasure-code/shec/ErasureCodeShec.cc:fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 07:28 AM Revision 46e79f48 (ceph): src/client/SyntheticClient.cc: fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 07:27 AM Revision 54d505d6 (ceph): src/rgw/rgw_cache.cc:fix typos
- Signed-off-by: xianxiaxiao <xianxia.xiao@kylin-cloud.com>
- 07:07 AM Revision 4e23550b (ceph): Merge pull request #12333 from xiexingguo/xxg-wip-bluestore-1206
- os/bluestore: fix potential csum_order overflow
Reviewed-by: Sage Weil <sage@redhat.com> - 07:07 AM Bug #18092 (Resolved): unittest_erasure_code_shec illegal instruction
- 07:06 AM Revision 6b6af6cf (ceph): Merge pull request #12382 from dachary/wip-18092-gf-complete
- erasure-code: synchronize with upstream gf-complete
- 06:51 AM Revision 3faf8b84 (ceph): CMakeLists: add vstart-base target
- No mds or radosgw. Add rados CLI.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:32 AM Bug #18252: Memory leaks in object_list_begin and object_list_end
- https://github.com/ceph/ceph/pull/12482
- 06:22 AM Bug #18252 (Resolved): Memory leaks in object_list_begin and object_list_end
- Clang Analyzer flags memory leaks in librados::IoCtx::object_list_begin and
librados::IoCtx::object_list_end and val... - 06:29 AM Revision 8d9d84bc (ceph): librados: Memory leaks in object_list_begin and object_list_end
- We allocate a cursor in the constructor but simply reassign it in these
functions without cleaning up the original. W... - 05:56 AM Bug #18250: Memory leak in ceph_test_rados_api_list
- https://github.com/ceph/ceph/pull/12479
- 03:58 AM Bug #18250 (Resolved): Memory leak in ceph_test_rados_api_list
- Valgrind reports the following leak in ceph_test_rados_api_list
==27742== 1,408 bytes in 11 blocks are definitely ... - 05:55 AM Bug #18251: There are some scrub errors after reset a node.
- I can repair the inconsistent pg by "ceph pg repair":
@[root@ceph177 ~]# ceph health detail
HEALTH_ERR 12 pgs inc... - 05:50 AM Bug #18251 (Closed): There are some scrub errors after reset a node.
- my ceph environment:
3 mons at tree nodes:192.7.7.177 192.7.7.180 192.7.7.181
27 osds.
ceph version: 10.2.3.... - 04:27 AM Revision 072c8b71 (ceph): cmake: fix hard coded boost python lib
- When using in tree boost build, linking will fail if boost is not installed.
Signed-off-by: John Coyle <dx9err@gmail... - 02:08 AM Revision 80ac7b12 (ceph): Merge pull request #12459 from runsisi/wip-ec-minor-cleanup
- osd/ECBackend: minor cleanup to remove duplicate code
Reviewed-by: Sage Weil <sage@redhat.com> - 12:23 AM rbd Tasks #18248 (Resolved): [teuthology] run gate-tempest-dsvm-full-devstack-plugin-ceph test
- This is a gating test case for the OpenStack project. We want to be able to detect Ceph regressions that impact OpenS...
12/13/2016
- 11:48 PM Revision 581a8c63 (ceph): Merge remote-tracking branch 'gh/kraken'
- 11:14 PM Revision 4092c97e (ceph): rgw: custom headers: use boost::container::flat_map
- Use this occasion of serialized map to implement encoders
for boost::container::flat_map, which is optimized for
in-o... - 11:13 PM Revision b82919a1 (ceph): rgw: add rgw_log_http_headers option
- Tracks headers that should be handled conditionally (currently,
can only log, so using minimal structure to represent... - 10:47 PM CephFS Bug #18151: Incorrect report of size when quotas are enabled.
- As commented in the users ML, we will be updating to 10.2.5 in early January. Will provide feedback once that is done.
- 07:58 PM CephFS Bug #18151: Incorrect report of size when quotas are enabled.
- In fact the quota tree changes already got backported so I think this is resolved. http://tracker.ceph.com/issues/16313
- 06:17 AM CephFS Bug #18151 (In Progress): Incorrect report of size when quotas are enabled.
- Well, this code changed a fair bit between Jewel and master, as Zheng ripped out the quota trees. However, there appe...
- 10:12 PM Bug #15368: "api_misc: [ FAILED ] LibRadosMiscConnectFailure.ConnectFailure"
- on master in smoke suite:
http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-13_05:00:02-smoke-master-testing-... - 09:57 PM Revision 378b810c (ceph): librbd: update in-memory object map after on-disk update committed
- Concurrent IO to the same object would previously result in the first
IO pausing to update the object map while the o... - 09:57 PM Revision 477ae54a (ceph): librbd: clean up object map update interface
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:57 PM Revision ea7b30a4 (ceph): librbd: convert ObjectMap to template for unit testing
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:57 PM Revision b1d624b4 (ceph): librbd: new block guard helper to prevent concurrent IO to blocks
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:57 PM Revision 7d743bfc (ceph): librbd: block concurrent in-flight object map updates for the same object
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:40 PM rbd Bug #18247: Changing 'rbd_default_features' to a string breaks Cinder
- ... and most likely Nova and Glance as well since they have the same copy-pasted code.
- 09:40 PM rbd Bug #18247 (Resolved): Changing 'rbd_default_features' to a string breaks Cinder
- https://github.com/openstack/cinder/blob/master/cinder/volume/drivers/rbd.py#L152
The Cinder driver casts the now ... - 09:05 PM rbd Cleanup #18231 (Fix Under Review): Remove rbd CLI + API support for consistency groups from Kraken
- *PR*: https://github.com/ceph/ceph/pull/12475
- 07:42 PM rbd Cleanup #18243 (Fix Under Review): JournalMetadata flooding with errors when being blacklisted
- *PR*: https://github.com/ceph/ceph/pull/12473
- 07:36 PM rbd Cleanup #18243 (In Progress): JournalMetadata flooding with errors when being blacklisted
- 05:09 PM rbd Cleanup #18243 (Resolved): JournalMetadata flooding with errors when being blacklisted
- When a client is blacklisted the log is flooded with error messages like below:
2016-12-12 08:17:17.550844 7f2165f... - 07:40 PM Revision b82a1c1d (ceph): journal: avoid logging an error when a watch is blacklisted
- Fixes: http://tracker.ceph.com/issues/18243
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 07:23 PM rbd Bug #18244 (Fix Under Review): librbd::ResizeRequest: failed to update image header: (16) Device ...
- *PR*: https://github.com/ceph/ceph/pull/12472
- 06:37 PM rbd Bug #18244 (In Progress): librbd::ResizeRequest: failed to update image header: (16) Device or re...
- 05:24 PM rbd Bug #18244: librbd::ResizeRequest: failed to update image header: (16) Device or resource busy
- http://qa-proxy.ceph.com/teuthology/trociny-2016-12-12_21:20:55-rbd-wip-mgolub-testing---basic-vps/628603/...
- 05:13 PM rbd Bug #18244 (Resolved): librbd::ResizeRequest: failed to update image header: (16) Device or resou...
- From Jason:
The operations that use "assert_header_locked" should be modified to handle -EBUSY and retry -- or jus... - 07:12 PM rgw Bug #18230: rgw: ERROR: got unexpected error when trying to read object: -2
- I will upload detailed logs as soon as I can reproduce the problem.
- 07:10 PM Revision ce4f2a52 (ceph): librbd: remove image header lock assertions
- This assertions can sporadically fail if the watch is lost and
recovered in the background. Upon a true loss of the l... - 07:09 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- Sepia smithis running Xenial now have valgrind 3.12.0~svn20160714-1ubuntu2 installed....
- 07:07 PM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
teuthology:/a/dzafman-2016-12-13_08:27:18-rados-master-distro-basic-smithi/630584...- 06:48 PM rbd Bug #14535: rbd CLI does not validate pool and snapshot name optionals
- @Gaurav: the issue is that the "--pool" and "--snap" arguments are *not* validated but they should be for ops that cr...
- 06:40 PM rbd Bug #14535: rbd CLI does not validate pool and snapshot name optionals
- This bug is not reproducible with jewel."--pool" and "--snap" optionals are not validating to ensure they don't cont...
- 06:08 PM Linux kernel client Bug #18148: Fix unsafe d_parent handling in kcephfs
- Patches posted to ceph-devel:
http://marc.info/?l=ceph-devel&m=148165227231455&w=2 - 06:06 PM Bug #18246 (Resolved): trusty kernel loses aios
- Trusty kernel (3.13 + stuff) suffers from an old aio bug that loses aio completions, leading to stalls in bluestore. ...
- 05:59 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- I'll lower the priority to Normal now.
Ok, this should be fixed in mainline kernels and coming to stable series ke... - 05:47 PM Revision c6198c3e (ceph): Merge pull request #12447 from ifed01/wip-bluestore-fix-reshard2
- os/bluestore: avoid resharding if the last shard size fall below shar…
Reviewed-by: xie xingguo <xie.xingguo@zte.com... - 05:14 PM rgw-testing Documentation #18245 (Closed): civetweb documentation setup missing
- hello all,
i had a working setup of ceph on ubuntu 16.04 on 05 Dec 2016 using civetweb that comes with ceph.
tr... - 05:05 PM rbd Bug #16889 (Can't reproduce): Ceph 10.2.2 meet a Segmentation fault after rename a image with for...
- Closing this due to lack of activity -- please feel free to re-open if this is still an issue on the latest Jewel rel...
- 04:52 PM rbd Bug #18242 (Resolved): rbd-nbd: invalid error code for "failed to read nbd request" messages
- 2016-12-12 08:01:49.385411 7f8209ffb700 -1 rbd-nbd: failed to read nbd request header: (0) Success
(It should use ... - 04:39 PM Revision bdf4db8c (ceph): cmake: simplify find_package jemalloc
- simplified the package to find jemalloc. this one matches
the one in src/rocksdb/cmake/modules. The existing one
was ... - 04:19 PM Revision 8406083f (ceph): rgw: dump s3_code as the Code response element in RGWDeleteMultiObj_Obj...
- Fixes: http://tracker.ceph.com/issues/18241
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 04:19 PM rgw Bug #18241 (In Progress): rgw: the Multi-Object Delete operation of S3 API wrongly handles the "C...
- 04:18 PM rgw Bug #18241 (Resolved): rgw: the Multi-Object Delete operation of S3 API wrongly handles the "Code...
- According to "the AWS documentation":http://docs.aws.amazon.com/AmazonS3/latest/API/multiobjectdeleteapi.html the *Co...
- 03:35 PM Bug #16783: Build fails if you disable radosgw (--without-radosgw) during linking
- Will put this on my queue. I see this on the master branch too (cmake -DWITH_RADOSGW=0), be it with a different undef...
- 02:58 PM Revision 5d02fda1 (ceph): cmake: disable mallinfo for jemalloc
- jemalloc does not implement mallinfo. Only check for existence
of mallinfo when the allocator is not jemalloc.
Signe... - 02:46 PM Revision 0be3f5f7 (ceph): Merge pull request #12289 from liewegas/wip-pg-down
- osd/PG: add "down" pg state (distinct from down+peering)
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:44 PM Revision c0e6171c (ceph): Merge pull request #12389 from ovh/wip-rework-recovery-priorities
- osd: Increase priority for inactive PGs backfill
Reviewed-by: Sage Weil <sage@redhat.com> - 02:44 PM Revision 11733614 (ceph): Merge pull request #12352 from kylinstorage/wip-cleanup-mark-queued
- osd: mark queued flag for op
Reviewed-by: Sage Weil <sage@redhat.com> - 02:24 PM CephFS Bug #18159 (Fix Under Review): "Unknown mount option mds_namespace"
- https://github.com/ceph/ceph/pull/12465
- 02:21 PM CephFS Bug #16691 (Resolved): sepia LRC lost directories
- 02:21 PM CephFS Feature #17853 (Resolved): More deterministic timing for directory fragmentation
- 02:14 PM Revision 0d1e9aab (ceph): common/blkdev: use realpath instead of readlink to resolve the recursio...
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 02:09 PM Revision f80022dd (ceph): os/bluestore: add a debug option to bypass block device writes for blue...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 02:07 PM RADOS Bug #18240 (Can't reproduce): Deep scrub errors running cephfs kernel client on jewel
I have no idea why this is showing up in kcephfs and knfs tests but not on rados tests. The good news is that at l...- 02:05 PM RADOS Bug #18239 (Duplicate): nan in ceph osd df again
- This bug is back: http://tracker.ceph.com/issues/10695
With jewel 10.2.5 an out osd will show up with -nan in osd ... - 01:59 PM Linux kernel client Bug #18161 (Resolved): kernel client failing to look up mds_namespace gives ENOENT (but it exists)
- Yep, that was it, I've added the norequire_active_mds option.
- 01:47 PM CephFS Bug #18238 (Can't reproduce): TestDataScan failing due to log "unmatched rstat on 100"
This is almost certainly just something where we need to update the log whitelist, but I'm curious about how we got...- 01:41 PM Revision 35306063 (ceph): os/bluestore: avoid resharding if the last shard size fall below shard ...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:46 AM Revision 70e7969e (ceph): client: drop extra "="
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 11:02 AM Revision 517a77f5 (ceph): FreeBSD/OSD.cc: add client_messenger to the avoid_ports set.
- Observed "feature":
During rebind due to a "wrongly marked down" log message, FreeBSD is
able to bind to the port... - 10:58 AM rbd Bug #18115 (Pending Backport): partition func should be enabled When load nbd.ko for rbd-nbd
- 10:40 AM Bug #17645 (Need More Info): "terminate called after throwing an instance of 'std::out_of_range'"...
- 10:40 AM Stable releases Tasks #17151: hammer v0.94.10
- ...
- 10:15 AM rbd Backport #18237: hammer: rbd import-diff does not complain when image-name not given
- $SUBJ says it all
hammer PR: https://github.com/ceph/ceph/pull/12312
The rbd CLI code was refactored post-hamme... - 10:04 AM rbd Backport #18237 (In Progress): hammer: rbd import-diff does not complain when image-name not given
- 10:04 AM rbd Backport #18237 (Resolved): hammer: rbd import-diff does not complain when image-name not given
- https://github.com/ceph/ceph/pull/12312
- 10:14 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- @Henrik: The fix appears to be to revert https://github.com/ceph/ceph/commit/1a48a8a2b222e41236341cb1241f0885a1b0b9d8...
- 09:39 AM CephFS Bug #17270: [cephfs] fuse client crash when adding a new osd
- Is there are chance to get this backported to hammer too? We had same ceph-fuse crashes recently (0.94.9 ceph-fuse an...
- 08:50 AM Backport #18220 (New): hammer: msg: upper 32-bits of message sequence get lost
- 08:27 AM Revision fe7d0681 (ceph): ECBackend: minor cleanup to remove duplicate code
- Signed-off-by: runsisi <runsisi@zte.com.cn>
- 08:27 AM Revision ff718c8b (ceph): osd: remove the lock heartbeat_update_lock, and change heatbeat_need_up...
- Signed-off-by: Pan Liu <pan.liu@istuary.com>
- 08:17 AM CephFS Bug #18211: test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data pool empty ...
- 08:17 AM CephFS Bug #18211: test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data pool empty ...
- https://github.com/ceph/ceph-client/commit/6899bb08e4173b7dfc0aa232e589541da869411f
- 03:23 AM Revision 98e7a9b9 (ceph): rgw/rgw_rest_conn.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:22 AM Revision 4ba18ef6 (ceph): rgw/rgw_lib.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:21 AM Revision 057d100f (ceph): osd/OSD.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:21 AM Revision 37c8d10a (ceph): msg/simple/Pipe.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:20 AM Revision a5e5eec0 (ceph): msg/async/dpdk/TCP-Stack.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:19 AM Revision c64fafed (ceph): mon/Monitor.h: remove unused declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 03:18 AM Revision 74ad126e (ceph): mon/MonClient.h: remove unused declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:16 AM Revision 52910740 (ceph): mon/AuthMonitor.h: remove unused declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:15 AM Revision b7bfb1f3 (ceph): mds/snap.h: remove unused declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 02:56 AM Revision a3bf3418 (ceph): Merge pull request #12294 from dx9/test-ecp-uname
- test: use uname -m vs. uname -p in test-erasure-code-plugins.sh
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:53 AM Revision a88ceff2 (ceph): librbd/diff_iterator: use proper snap to query parent overlap
- If no snapshot has been made, we will use CEPH_NOSNAP instead of 0,
to query the parent overlap.
Fixes bug http://tr... - 01:31 AM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
Find all the "_failed_push: Read error" message in the logs of crashing OSDs and note the errors={osd#(shard#)=-5}....- 01:05 AM Revision 8fdae47f (ceph): tasks/cephfs: set norequire_active_mds on kclient
- The kernel client's cluster availability test is
more primitive than the fuse client, so we need
to switch it off to ...
12/12/2016
- 11:53 PM Revision 85e0774a (ceph): test: Update for new error message when doing scrub with deep-scrub errors
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 11:01 PM Bug #18058 (Resolved): librados: new setxattr overload breaks c++ ABI
- 10:42 PM Revision ca933160 (ceph): Merge pull request #1278 from ceph/wip-16225-min
- hammer: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- 10:16 PM rgw Bug #18230: rgw: ERROR: got unexpected error when trying to read object: -2
- the log provided shows that the multipart upload failed to complete for some reason, but can't really say what happen...
- 08:35 PM rgw Bug #18230: rgw: ERROR: got unexpected error when trying to read object: -2
- object stat :...
- 05:30 PM rgw Bug #18230: rgw: ERROR: got unexpected error when trying to read object: -2
- Uploaded wrong logfile, this is the right file.
- 05:14 PM rgw Bug #18230: rgw: ERROR: got unexpected error when trying to read object: -2
- I attached a log with the end of the multipart upload and the gc process removing files 3 hours later.
Following t... - 04:19 PM rgw Bug #18230 (Need More Info): rgw: ERROR: got unexpected error when trying to read object: -2
- I'm getting this error in the rgw log (client gets 404) when trying to GET some files (HEAD / bucket listing works pr...
- 09:47 PM rgw Bug #17465 (Fix Under Review): multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED errors
- https://github.com/ceph/ceph/pull/12452
- 09:42 PM Revision 73cd8df8 (ceph): rgw: use explicit flag to cancel RGWCoroutinesManager::run()
- RGWCoroutinesManager::run() was setting ret = -ECANCELED to break out of
the loop when it sees going_down. coroutines... - 09:29 PM Revision 857dfee9 (ceph): Merge pull request #1304 from vshankar/wip-15028
- cram: support fetching from sha1 branch, tag, commit hash
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 09:06 PM Feature #18235 (Fix Under Review): os/filestore/HashIndex: be loud about splits
- 08:29 PM Feature #18235 (Resolved): os/filestore/HashIndex: be loud about splits
- This ML thread "[ceph-users] filestore_split_multiple hardcoded maximum" has coincided with ~1 week of slow requests ...
- 08:32 PM Revision 61c47acd (ceph): os/filestore/HashIndex: be loud about splits
- Filestore splits are a rare yet important enough event that an
OSD should visibly report when they happen.
Without t... - 08:22 PM Bug #17988 (Resolved): tests: osd-scrub-repair.sh fails when stty reports 0 columns
Part of this pull request
https://github.com/ceph/ceph/pull/12146
in commit
b425290a927e46601e93e0af17d2b378b734...- 08:20 PM Bug #18180 (Resolved): ReplicatedPG::execute_ctx rarely leaking ctx->reply
- 08:20 PM Bug #18172 (Resolved): osd: leaked MOSDOpReply
- 08:20 PM Revision df052e79 (ceph): Merge pull request #12450 from athanatos/wip-18180
- osd/ReplicatedPG::record_write_error: don't leak orig_reply on cancel
Reviewed-by: Sage Weil <sage@redhat.com> - 07:48 PM Bug #18139 (Resolved): LibRadosList.EnumerateObjects failure
- 07:41 PM Bug #18233 (Resolved): tasks/rados_python.yaml: test_rados.TestIoctx.test_aio_execute
- fixed by https://github.com/ceph/ceph/pull/12439
- 07:22 PM Bug #18233 (Resolved): tasks/rados_python.yaml: test_rados.TestIoctx.test_aio_execute
- samuelj@teuthology:/a/samuelj-2016-12-10_00:43:47-rados-wip-sam-testing2---basic-smithi/621100,621231
- 07:30 PM Revision 3b07638c (ceph): Merge pull request #12402 from liewegas/wip-scrub-recovery
- osd: default osd_scrub_during_recovery=false
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:25 PM Revision ec3d62b6 (ceph): Merge pull request #12448 from theanalyst/doc/11.1.0-rc
- doc: final additions to 11.1.0-rc release notes
Reviewed-by: Sage Weil <sage@redhat.com> - 07:25 PM Bug #18234 (Can't reproduce): bluestore: rocksdb crash in memory allocation
- 2016-12-10T01:39:42.352 INFO:tasks.ceph.osd.0.smithi023.stderr:tcmalloc: large alloc 140391412334592 bytes == (nil) @...
- 07:03 PM rbd Backport #18137: jewel: rbd-mirror: image sync should send NOCACHE advise flag
- Please see my comment in https://github.com/ceph/ceph/pull/12043 how it could be resolved without conflicts.
- 06:33 PM Revision 1e31aee4 (ceph): doc: final additions to 11.1.0-rc release notes
- Signed-off-by: Abhishek Lekshmanan <alekshmanan@suse.com>
- 06:27 PM Revision 91421d8d (ceph): 11.1.0
- 06:20 PM Bug #15943 (In Progress): crash adding snap to purged_snaps in ReplicatedPG::WaitingOnReplicas
- Bah, I don't think my fix was right.
- 05:37 PM Revision 63249312 (ceph): Merge pull request #1305 from ceph/wip-h-j-x
- upgrade/hammer-jewel-x: whitelist quota
- 05:29 PM Revision 9c318011 (ceph): upgrade/hammer-jewel-x: whitelist quota
- This is from teh librados api test.
Signed-off-by: Sage Weil <sage@redhat.com> - 05:10 PM rgw Feature #18232 (New): Saving a backpack of zoneparams configuration for multisite/DR
- Currently the zoneparams is stored locally in the cluster, the only way is to backup the json output of zone get comm...
- 04:59 PM Revision c4f1b428 (ceph): librbd: diffs to clone's first snapshot should include parent diffs
- If the clone has a backing object created after the snapshot that
overwrites an extent of the parent, the parent diff... - 04:58 PM rbd Backport #18111 (Fix Under Review): hammer: diff calculate can hide parent extents when examining...
- 04:58 PM rbd Backport #18111 (In Progress): hammer: diff calculate can hide parent extents when examining firs...
- 04:29 PM rbd Cleanup #18231 (Resolved): Remove rbd CLI + API support for consistency groups from Kraken
- 04:21 PM Revision 51342e87 (ceph): Merge pull request #10209 from runsisi/sisi-wip-remove-redundant-check
- osd/ReplicatedPG: remove redundant check for balance/localize read
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>... - 04:18 PM Revision 2bdf5930 (ceph): Merge pull request #12190 from liupan1111/wip-speed-up-acting-ods
- osd/OSDMap: improve the performance of pg_to_acting_osds
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu ... - 04:08 PM Revision 6af0c8fc (ceph): Merge pull request #12279 from wjwithagen/wip-wjw-freebsd-ENODATA-2
- os/filestore/chain_xattr.h:uses ENODATA, so include compat.h
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:07 PM Bug #18175 (Pending Backport): mon: osd flag health message is misleading
- 04:06 PM Revision d89e2fca (ceph): Merge pull request #12365 from liewegas/wip-mon-flag-warning
- mon/OSDMonitor: only show interesting flags in health warning
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed... - 04:05 PM Revision 1b533f8e (ceph): Merge pull request #12439 from tchaikov/wip-pybind-requires
- pybind/rados: add missing "length" requires for aio_execute()
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:03 PM Revision 9418e070 (ceph): Merge pull request #12390 from tchaikov/wip-start-after-setting-nonce
- msg/async: set nonce before starting the workers
Reviewed-by: Haomai Wang <haomai@xsky.com> - 04:02 PM Revision 106115da (ceph): Merge pull request #12309 from wjwithagen/wip-wjw-freebsd-CLOCK_MONOTONE
- rgw/rgw_file.cc: Add compat.h to allow CLOCK_MONOTONE
Reviewed-by: Matt Benjamin <mbenjamin@redhat.com> - 04:01 PM Revision 55e18d2e (ceph): Merge pull request #12257 from kylinstorage/wip-remove-unneeded-forward...
- remove unneeded forward declaration
Reviewed-by: Sage Weil <sage@redhat.com> - 04:00 PM Revision 405e94ab (ceph): Merge pull request #12301 from wjwithagen/wip-wjw-freebsd-blkid
- src/test/CMakeLists.txt: Exclude test on HAVE_BLKID
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:59 PM rbd Backport #18215 (Fix Under Review): jewel: TestImageSync.SnapshotStress fails on bluestore
- Waiting for review on the PR : https://github.com/ceph/ceph/pull/12043
- 03:56 PM Revision 836d8968 (ceph): Merge pull request #12378 from dzafman/wip-18139
- test: Don't write to a poolid that this test might not have created
Reviewed-by: Sage Weil <sage@redhat.com> - 03:54 PM rgw Feature #18229 (Resolved): multisite: trim bilogs as data sync peer zones catch up
- 03:53 PM rgw Feature #18228 (In Progress): multisite: trim mdlog as all zones catch up to master zone
- Metadata master zone should trim its mdlog as peer zones make progress.
Peer zones should trim their mdlogs to mat... - 03:47 PM rbd Bug #11502: "[ FAILED ] TestLibRBD.LockingPP" in rbd-next-distro-basic-mult run
- OSD logs of interest: http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-11_02:01:21-rbd-master-distro-basic-smit...
- 02:25 PM rbd Bug #11502 (In Progress): "[ FAILED ] TestLibRBD.LockingPP" in rbd-next-distro-basic-mult run
- http://qa-proxy.ceph.com/teuthology/teuthology-2016-12-11_02:01:21-rbd-master-distro-basic-smithi/624047/teuthology.log
- 03:42 PM rgw Feature #18227 (Resolved): multisite: trim data changes log as peers zones catch up
- https://github.com/ceph/ceph/pull/10372
https://github.com/ceph/ceph/pull/10546 - 02:48 PM CephFS Bug #18157: ceph-fuse segfaults on daemonize
- We worked around this somewhat badly in master/kraken, but Kefu's Preforker change is a better option.
- 02:48 PM CephFS Bug #18159: "Unknown mount option mds_namespace"
- Let's just make it silent on this case (unkonwn option) and let kernel reject it
- 02:47 PM Linux kernel client Bug #2439 (In Progress): ceph-client: auth: handle null verify_authorizer_reply method
- 02:32 PM Linux kernel client Bug #12224 (Resolved): libceph: support cls_lock operations
- in 4.9
- 02:29 PM Linux kernel client Bug #18041 (Pending Backport): periodically kernel crashes with CephFS
- https://git.kernel.org/cgit/linux/kernel/git/torvalds/linux.git/commit/?id=c3f4688a08fd86f1bf8e055724c84b7a40a09733 i...
- 02:21 PM Revision 2d8aafb9 (ceph): rgw: complete versioning enablement after sending it to meta master
- Fixes: http://tracker.ceph.com/issues/18003
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 02:18 PM rbd Bug #18149 (Resolved): teuthology: qemu-iotests on xenial fails with unexpected console output
- 02:17 PM Revision b1181c70 (ceph): Merge pull request #12371 from ceph/wip-18149
- qa/workunits/rbd: use more recent qemu-iotests that support Xenial
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 02:15 PM CephFS Bug #17193 (Pending Backport): truncate can cause unflushed snapshot data lose
- 02:07 PM CephFS Bug #9935 (In Progress): client: segfault on ceph_rmdir path "/"
- 01:24 PM Bug #17814 (Resolved): coredump in ceph-osd
- I haven't seen this in quite some time now, so I think it's now resolved by moving to later kernels.
- 01:09 PM Bug #18226 (Resolved): assert in bluestore_extent_ref_map_t::record_t::bound_encode with debug build
- ./bin/ceph_test_objectstore --gtest_filter=ObjectStore/StoreTest.SyntheticMatrixCsumVsCompression/2
fails with
... - 01:05 PM rgw Bug #18003 (Fix Under Review): slave zonegroup cannot enable the bucket versioning
- https://github.com/ceph/ceph/pull/12444
- 12:42 PM rbd Subtask #17019 (In Progress): rbd-mirror HA: create pool locker / leader class
- 12:42 PM rbd Subtask #17020 (In Progress): rbd-mirror HA: pool replayer should be started/stopped when lock ac...
- 12:03 PM CephFS Bug #18225 (Fix Under Review): MDS doesn't release memory after exceeding its cache size limit
- https://github.com/ceph/ceph/pull/12443
- 11:37 AM CephFS Bug #18225 (Resolved): MDS doesn't release memory after exceeding its cache size limit
In some circumstances the MDS may fail to enforce its own cache size limits. Because boost::pools are used for all...- 12:02 PM Revision 57ac1af8 (ceph): mds: make cache size health warning factor configurable
- ...now that it's used more than once place, copying around
the fraction was bad.
Signed-off-by: John Spray <john.spr... - 12:02 PM Revision 6b578e7f (ceph): mds: release pool allocator memory after exceeding size limit
- Usually we like keeping the memory in our pools, but in circumstances
where we have violated our self-imposed inode c... - 11:32 AM Bug #18224 (Can't reproduce): Mass OSD failure with Bluestore
- Hello,
We've been testing Ceph Kraken + bluestore recently on our 4-node cluster with 96 OSDs. Suddenly we noticed... - 11:32 AM Revision f0b861c0 (ceph): libcephfs: move ceph_fstatx() for readability
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 05:53 AM Revision 722a9a7f (ceph): include/fs_types: fix unsigned integer overflow
- stats image has (stripe_count * object_size) > UINT32_MAX results following exception:
...
5: (()+0xc3391) [0x7f7... - 04:41 AM Revision ba421b57 (ceph): Merge pull request #12436 from badone/wip-cov1395747
- crush: Silence coverity warnings for test/crush/crush.cc
Reviewed-by: xiexingguo <xie.xingguo@zte.com.cn> - 04:39 AM Revision 2bb42d9c (ceph): Merge pull request #12409 from tchaikov/wip-doc-releases
- doc/releases: add links to kraken and v10.2.4
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 03:44 AM Bug #18223 (Can't reproduce): osd: leaked MOSDMap::incremental_maps
- ...
- 03:24 AM Revision 21264362 (ceph): pybind/rados: add missing "length" requires for aio_execute()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 01:25 AM rgw Bug #18210: rgw: multisite: commit period issue when creating multiple zonegroups
- Please rados gateway multisite how to configure multiple zonegroup, realize share the same user and bucket namespace?
- 01:10 AM Revision a3fda1d7 (ceph): mon: make it more clearly to debug for paxos state
- Signed-off-by:song baisen <song.baisen@zte.com.cn>
- 12:39 AM Revision 4e7a3467 (ceph): rgw: remove duplicate flush formatter
- Signed-off-by: Guo Zhandong <guozhandong@cmss.chinamobile.com>
12/11/2016
- 11:16 PM Revision efbe45fe (ceph): crush: Silence coverity warnings for test/crush/crush.cc
- Coverity 1395747 reports that "c" leaks. Switching to smart pointers should
resolve that.
Signed-off-by: Brad Hubbar... - 11:16 AM Revision d2f0d745 (ceph): cram: support fetching from sha1 branch, tag, commit hash
- Signed-off-by: Venky Shankar <vshankar@redhat.com>
- 01:42 AM Revision 4314cb94 (ceph): qa/workunits/rbd: use more recent qemu-iotests that support Xenial
- Fixes: http://tracker.ceph.com/issues/18149
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
12/10/2016
- 11:29 PM Revision a5c5ba6b (ceph): Merge pull request #12410 from dachary/wip-10-2-5
- doc: release notes for 10.2.5
Reviewed-by: Sage Weil <sage@redhat.com> - 12:26 PM Revision e0dfb98f (ceph): cleanup: use string & to avoid unnecessary copy
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:20 AM Stable releases Tasks #17487: jewel v10.2.4
- @Sergey: That issue will be fixed in 10.2.5, see #18207
- 09:14 AM Revision 966d4256 (ceph): doc: release notes for 10.2.5
- Fixes: http://tracker.ceph.com/issues/18207
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:36 AM Bug #16800 (Fix Under Review): SELinux denials found
- -https://github.com/ceph/ceph-qa-suite/pull/1303-
-an alternative fix at https://github.com/ceph/ceph/pull/12430- - 12:51 AM Revision c8dc9452 (ceph): osd: Add "trigger_scrub" admin socket command
- This allows testing to fake a schedule scrub (must_scrub not set)
Signed-off-by: David Zafman <dzafman@redhat.com> - 12:51 AM Revision 64a7012e (ceph): test: Add test for keeping deep-scrub information
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:04 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Sorry to hear that Sean. The backport is in progress so hopefully will make it into the next Jewel release.
12/09/2016
- 11:53 PM Stable releases Tasks #17487: jewel v10.2.4
- Sergey Jerusalimov wrote:
> Guys's please tell about https://www.spinics.net/lists/ceph-devel/msg33968.html
- 11:52 PM Stable releases Tasks #17487: jewel v10.2.4
- Gay's please tell about https://www.spinics.net/lists/ceph-devel/msg33968.html
- 11:15 PM Revision 26c87fd1 (ceph): rbd: --max_part and --nbds_max options for nbd map
- Fixes: http://tracker.ceph.com/issues/18186
Signed-off-by: Pan Liu <pan.liu@istuary.com>
(cherry picked from commit 4... - 10:57 PM Revision ddb54036 (ceph): radosgw-admin: 'zone placement modify' doesnt require pool names
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit b59afea4dbb06454b1e14f03dd65ba2449674a15)... - 10:56 PM Revision 7cfc346c (ceph): radosgw-admin: add 'zonegroup placement default' command
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit 711cc132528f2dfeb6c1f8defb19493ffe7cb9be) - 10:56 PM Revision dbc1b614 (ceph): radosgw-admin: fix 'placment' typos
- Fixes: http://tracker.ceph.com/issues/18078
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 10:44 PM rgw Backport #18216 (In Progress): jewel: rgw-admin: missing command to modify placement targets
- 01:25 PM rgw Backport #18216 (Resolved): jewel: rgw-admin: missing command to modify placement targets
- https://github.com/ceph/ceph/pull/12428
- 10:43 PM Revision 4f7147cb (ceph): rgw_admin: commands to manage placement targets
- Fixes: http://tracker.ceph.com/issues/18078
added the following commands:
radosgw-admin zone placement add
radosg... - 10:40 PM Revision 155641f9 (ceph): rgw-admin: add commands to manage zonegroup placement fields
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit a91c7b5cc699b2c37d449974d2ebf2eece9506a0)
... - 10:30 PM Revision bb9678bf (ceph): rgw: use set for zonegroup placement target tags
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 12162d654ce24db0617e4bc3de24aebc28b50996) - 10:29 PM rbd Backport #18215 (New): jewel: TestImageSync.SnapshotStress fails on bluestore
- Non-trivial backport (conflict in src/tools/rbd_mirror/image_sync/ObjectCopyRequest.cc)
- 10:29 PM rbd Backport #18215 (In Progress): jewel: TestImageSync.SnapshotStress fails on bluestore
- 01:25 PM rbd Backport #18215 (Closed): jewel: TestImageSync.SnapshotStress fails on bluestore
- https://github.com/ceph/ceph/pull/12043
- 10:26 PM rbd Backport #18214 (In Progress): jewel: add max_part and nbds_max options in rbd nbd map, in order ...
- 01:25 PM rbd Backport #18214 (Resolved): jewel: add max_part and nbds_max options in rbd nbd map, in order to ...
- https://github.com/ceph/ceph/pull/12426
- 10:21 PM rbd Backport #18194 (In Progress): jewel: rbd-mirror split-brain issues should be clearly visible in ...
- 10:16 PM rbd Backport #18191 (In Progress): jewel: "rbd mirror image resync" does not force resync after split...
- 10:11 PM rbd Backport #18111 (New): hammer: diff calculate can hide parent extents when examining first snapsh...
- 09:24 PM rbd Backport #18111 (Fix Under Review): hammer: diff calculate can hide parent extents when examining...
- 09:22 PM rbd Backport #18111 (In Progress): hammer: diff calculate can hide parent extents when examining firs...
- 08:28 PM rbd Backport #18111: hammer: diff calculate can hide parent extents when examining first snapshot in ...
- @Nathan: the code was refactored in Infernalis, so it cannot be a direct cherry pick. You can assign to me and I'll t...
- 02:27 PM rbd Backport #18111 (Need More Info): hammer: diff calculate can hide parent extents when examining f...
- Jason, I looked at the hammer backport but the whole file src/librbd/DiffIterate.cc appears to be missing in hammer.
- 09:58 PM rbd Backport #18190 (In Progress): jewel: rbd-mirror: gmock warnings in bootstrap request unit tests
- 09:51 PM rbd Backport #18221 (In Progress): jewel: dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- 09:11 PM rbd Backport #18221 (Resolved): jewel: dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- https://github.com/ceph/ceph/pull/13103
- 09:33 PM rbd Backport #18222 (In Progress): hammer: dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- 09:11 PM rbd Backport #18222 (Resolved): hammer: dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- https://github.com/ceph/ceph/pull/12423
- 09:33 PM Revision 996fc257 (ceph): qa/workunits/rbd: removed qemu-iotest case 077
- The test case is not stable due to racing console output. This
results in spurious failures.
Fixes: http://tracker.c... - 08:43 PM rbd Bug #16176 (Fix Under Review): objectmap does not show object existence correctly
- *PR*: https://github.com/ceph/ceph/pull/12420
- 08:08 PM Revision c461ee19 (ceph): 10.2.5
- 08:07 PM rbd Bug #10773 (Pending Backport): dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- 08:07 PM Revision b40603f6 (ceph): Merge pull request #12366 from dillaman/wip-10773
- qa/workunits/rbd: removed qemu-iotest case 077
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:30 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- In the last 24hrs there was corruption in the metadata pool, It resulted in an assert loop on the MDS until the corru...
- 05:59 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- David Zafman wrote:
> Another commit has been added to PR12088 to fix a problem. The scenario in this bug might not... - 05:08 PM Revision 6d7b384c (ceph): Merge pull request #12253 from aclamk/fix-copy-object-compression
- Fixed problem with PUT with x-amz-copy-source when source object is compressed.
Reviewed-by: Casey Bodley <cbodley@r... - 05:05 PM Revision ff152935 (ceph): Merge pull request #12283 from ceph/wip-rgw-18106
- rgw: make RGWLocalAuthApplier::is_admin_of() aware about system users.
Reviewed-by: Orit Wasserman <owassrm@redhat.c... - 04:09 PM Revision 79c2db9b (ceph): Merge remote-tracking branch 'upstream/pull/1302/head'
- * upstream/pull/1302/head:
fsx-mpi: fsx-mpi expects a file name not a dir
fsx-mpi: remove chef task
Fix mpi calls - 03:46 PM rgw Bug #18187: rgw:radosgw server abort when accept a CORS request with short origin
- Red Hat's security team assigned CVE-2016-9579 to this issue.
- 02:45 PM Bug #15260: ceph-disk and ceph-detect-init builds do check-only things on every build
- I don't know how to fix this, someone else will have to work on it.
- 02:25 PM rgw Backport #18212 (In Progress): jewel: rgw:radosgw server abort when accept a CORS request with sh...
- 01:25 PM rgw Backport #18212 (Resolved): jewel: rgw:radosgw server abort when accept a CORS request with short...
- https://github.com/ceph/ceph/pull/12397
- 02:24 PM rgw Backport #18213 (In Progress): hammer: rgw:radosgw server abort when accept a CORS request with s...
- 01:25 PM rgw Backport #18213 (Resolved): hammer: rgw:radosgw server abort when accept a CORS request with shor...
- https://github.com/ceph/ceph/pull/12398
- 02:23 PM rgw Backport #18217 (In Progress): jewel: rgw sends omap_getvals with (u64)-1 limit
- 01:26 PM rgw Backport #18217 (Resolved): jewel: rgw sends omap_getvals with (u64)-1 limit
- https://github.com/ceph/ceph/pull/12419
- 02:21 PM Revision 8b10d3ba (ceph): rgw: omap_get_all() fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 99e866feb3f8aa0ff768d6253979b6b4fc0fa452) - 02:21 PM Revision df9d929b (ceph): rgw/rgw_rados: do not omap_getvals with (u64)-1 max
- Fixes: http://tracker.ceph.com/issues/17985
This will make the OSD fall over if the object is big
and the OSD doesn'... - 02:20 PM rgw Backport #18218 (In Progress): hammer: rgw sends omap_getvals with (u64)-1 limit
- 01:26 PM rgw Backport #18218 (Resolved): hammer: rgw sends omap_getvals with (u64)-1 limit
- https://github.com/ceph/ceph/pull/12418
- 02:20 PM Revision e97ceb13 (ceph): rgw: omap_get_all() fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from commit 99e866feb3f8aa0ff768d6253979b6b4fc0fa452) - 02:20 PM Revision 38ab8922 (ceph): rgw/rgw_rados: do not omap_getvals with (u64)-1 max
- Fixes: http://tracker.ceph.com/issues/17985
This will make the OSD fall over if the object is big
and the OSD doesn'... - 02:13 PM Messengers Bug #18184: SimpleMessenger Pipe threads are spinning when idle
- Thank you Nathan for information. I have removed 'kraken' from backport field.
- 01:24 PM Messengers Bug #18184: SimpleMessenger Pipe threads are spinning when idle
- Kraken backports have not started yet. Master is still being merged into kraken.
- 02:05 PM CephFS Bug #18211: test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data pool empty ...
- the object is from pool permission check. it's kernel version of http://tracker.ceph.com/issues/13782
- 09:51 AM CephFS Bug #18211 (Resolved): test_snapshot_remove (tasks.cephfs.test_strays.TestStrays) failed at data ...
- http://pulpito.ceph.com/jspray-2016-12-06_12:37:38-kcephfs:recovery-master-testing-basic-smithi/611141/...
- 01:45 PM Backport #18132 (In Progress): hammer: ReplicatedBackend::build_push_op: add a second config to l...
- 01:44 PM Revision fe77c9a9 (ceph): osd: limit omap data in push op
- We already have the config osd_recovery_max_chunk to limit the total
size of omap entries and omap data. But we need ... - 01:39 PM Bug #16125 (Resolved): ceph-disk should not spit out a traceback when a subprocess.call errors
- 01:09 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- I have made the requested changes on the branch, and opened a new PR at https://github.com/ceph/ceph/pull/12414
- 01:39 PM Revision 0a99c92e (ceph): Merge pull request #12414 from ceph/wip-16125
- ceph-disk: prevent unnecessary tracebacks from subprocess.check_call
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:39 PM Backport #18219 (In Progress): jewel: msg: upper 32-bits of message sequence get lost
- 01:28 PM Backport #18219 (Resolved): jewel: msg: upper 32-bits of message sequence get lost
- https://github.com/ceph/ceph/pull/12416
- 01:37 PM Revision ad869dec (ceph): msg: don't truncate message sequence to 32-bits
- Message sequence is 64-bits number, but the upper 32-bits get lost
when setting/getting message sequence. This causes... - 01:34 PM Backport #18220 (In Progress): hammer: msg: upper 32-bits of message sequence get lost
- 01:28 PM Backport #18220 (Rejected): hammer: msg: upper 32-bits of message sequence get lost
- 01:16 PM rbd Backport #17879: jewel: rbd-mirror: use sparse read during image sync
- It is better to backport this together with this fix http://tracker.ceph.com/issues/18146
- 12:59 PM rbd Bug #18146 (Pending Backport): TestImageSync.SnapshotStress fails on bluestore
- 12:59 PM Revision cb798835 (ceph): Merge pull request #12368 from trociny/wip-18146
- rbd-mirror: fix sparse read optimization in image sync
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:57 PM devops Backport #18199 (In Progress): jewel: build/ops: install-deps.sh based on /etc/os-release
- 12:52 PM Revision 8e524d14 (ceph): ceph-disk: allow to exit nicely when using command_check_call
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 12:52 PM Revision 9be64fb0 (ceph): ceph-disk: remove try/except for CalledProcessError to use new exit fla...
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 12:52 PM Revision 2cb9bfe6 (ceph): ceph-disk: update tests to use the new exit flag
- Signed-off-by: Alfredo Deza <adeza@redhat.com>
- 12:30 PM Revision 6a76adcd (ceph): osd: Increase priority for inactive PGs backfill
- This change does prioritize backfill of PGs which don't
have min_size active copies. Such PGs would cause IO stalls
f... - 09:49 AM CephFS Bug #17193: truncate can cause unflushed snapshot data lose
- 2016-12-06T13:28:03.559 INFO:tasks.cephfs_test_runner: self.assertTrue(self.fs.data_objects_absent(file_a_ino, siz...
- 09:28 AM rgw Bug #18210 (In Progress): rgw: multisite: commit period issue when creating multiple zonegroups
root@B-80-11:~/multisite# rados lspools
rbd
openstack
cn-sy-south.rgw.root
cn-sy-south.rgw.control
cn-sy-south...- 09:20 AM Revision 483969fc (ceph): Merge pull request #12408 from badone/wip-mon_osd_down_out_interval-docfix
- doc: Modify documentation for mon_osd_down_out_interval
Reviewed-by: xiexingguo <xie.xingguo@zte.com.cn> - 09:16 AM Bug #16800: SELinux denials found
- 09:14 AM Bug #16800: SELinux denials found
- SELinux denials found on ubuntu@mira061.front.sepia.ceph.com: ['type=AVC msg=audit(1481273299.192:4526):
avc: deni... - 09:06 AM Linux kernel client Bug #11585 (Can't reproduce): kdb crash around __ceph_remove_cap() while dirfrag.sh
- 09:01 AM Linux kernel client Bug #17191 (Resolved): kclient accesses "/" when mounting a subpath
- 08:48 AM Revision 26c68646 (ceph): doc/releases: add links to kraken and v10.2.4
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 08:02 AM Revision e793376d (ceph): doc: Modify documentation for mon_osd_down_out_interval
- Update docs to reflect the new default of 600 set by 817d65bd4
Signed-off-by: Brad Hubbard <bhubbard@redhat.com> - 07:21 AM RADOS Bug #18209 (Duplicate): src/common/LogClient.cc: 310: FAILED assert(num_unsent <= log_queue.size())
- ...
- 07:20 AM rgw Bug #18208 (Resolved): rgw: when uploading the objects continuesly in the versioned bucket, some ...
- when uploading the objects continuesly in the versioned bucket, some objects will not sync on another zone in the sam...
- 07:13 AM devops Bug #18198 (Pending Backport): build/ops: install-deps.sh based on /etc/os-release
- 07:11 AM devops Bug #18198 (In Progress): build/ops: install-deps.sh based on /etc/os-release
- PR: https://github.com/ceph/ceph/pull/12405
- 07:13 AM rgw Bug #17971: bucket acl all user write
- https://github.com/ceph/ceph/pull/12157
- 06:58 AM rbd Cleanup #18186 (Pending Backport): add max_part and nbds_max options in rbd nbd map, in order to ...
- 06:57 AM Revision 21c0c595 (ceph): Merge pull request #12379 from liupan1111/wip-fix-rbd-params
- rbd: --max_part and --nbds_max options for nbd map
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 06:55 AM Revision dff52060 (ceph): libcephfs: fixup spelling mistakes
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 06:50 AM Stable releases Tasks #18207: jewel v10.2.5
- h3. rados...
- 06:48 AM Stable releases Tasks #18207: jewel v10.2.5
- ...
- 06:45 AM Stable releases Tasks #18207 (Resolved): jewel v10.2.5
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 06:14 AM Bug #18153: No space cause osd crash (bluestore)
- Addtion: This issue is for bluestore
- 05:46 AM Revision c36ffb7f (ceph): log: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:46 AM Revision 1f2da40d (ceph): filestore: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:45 AM Revision 4d7fc018 (ceph): rgw: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:45 AM Revision ba7250c6 (ceph): compressor: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:45 AM Revision 1f155619 (ceph): mon: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 05:45 AM Revision 1a187cbb (ceph): mds: use std::make_shared to replace new
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:34 AM Revision 90c7e345 (ceph): mds: don't use Server::finish_force_open_sessions during log replay
- Server::finish_force_open_sessions() send session open message to
clients. It's wrong to use it during log replay.
S... - 03:33 AM Revision a49726e1 (ceph): mds: fix sessionmap version increasement when replaying ESessions
- SessionMap::open_sessions() is used by ESessions::replay() to open
sessions that were opened by Server::prepare_force... - 03:31 AM Revision 0ec25575 (ceph): mds: properly wake up scatter_nudge waiters after clearing scatter dirty
- LogSegment::try_to_expire() calls Locker::scatter_nudge() for dirty
scatter locks. If lock's parent is non-auth, Lock... - 02:33 AM Revision 317c9b98 (ceph): Merge pull request #12400 from gregsfortytwo/wip-fix-pg-unsigned-warning
- osd: fix signed/unsigned comparison warning
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:19 AM rbd Feature #13465 (New): librbd: internal way to write multiple extents to an object at once
- 02:15 AM Revision e519a454 (ceph): Merge pull request #12211 from leseb/doc-openstack
- doc: update cinder key permissions for mitaka
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:05 AM Bug #18145: pgs stuck in remapped after recovery on cluster with many osds down
- pg_stat state up up_primary acting acting_primary
13.0 remapped [214,224,120] 214 [214,120] 214
... - 01:31 AM RADOS Feature #18206 (Resolved): osd: osd_scrub_during_recovery only considers primary, not replicas
- We should also avoid scrubbing if the replica is busy doing recovery. That means the scrub scheduler should decline t...
- 01:25 AM Revision 8dca17c0 (ceph): osd: default osd_scrub_during_recovery=false
- This is a more friendly behavior. Tell users in the release notes how to
get the old behavior.
Signed-off-by: Sage ... - 01:14 AM Bug #18205 (Resolved): jewel: valgrind error
- teuthology commit 25e496922b1c56193b40acae75e970cb2dd2c249
- 12:11 AM Bug #18205 (Resolved): jewel: valgrind error
- <error>
<unique>0x0</unique>
<tid>1</tid>
<kind>SyscallParam</kind>
<what>Syscall param msync(start) poin... - 12:51 AM Revision c5f0658a (ceph): client: fix typos
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 12:13 AM RADOS Bug #18204: jewel: finish_promote unexpected promote error (34) Numerical result out of range
- samuelj@teuthology:/a/loic-2016-12-08_18:04:28-rados-jewel-distro-basic-smithi/617789/remote
- 12:12 AM RADOS Bug #18204: jewel: finish_promote unexpected promote error (34) Numerical result out of range
- samuelj@teuthology:/a/loic-2016-12-08_18:04:28-rados-jewel-distro-basic-smithi/617794
- 12:05 AM RADOS Bug #18204 (Can't reproduce): jewel: finish_promote unexpected promote error (34) Numerical resul...
- This caused the run to fail with an incorrect read return.
12/08/2016
- 11:50 PM Revision ef1df97b (ceph): osd: fix signed/unsigned comparison warning
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 11:19 PM Bug #18203 (Closed): Additional Ceph Monitors failed verifying authorize reply
- Using ceph-deploy, I add two additional ceph monitors to my ceph cluster:
ceph-deploy mon add server2
ceph-deploy... - 10:25 PM Revision 532a759d (ceph): osd: When deep-scrub errors present upgrade regular scrubs
- Previously, if a weekly deep-scrub found errors the next daily scrub
would cause the deep-scrub information to be rem... - 10:04 PM rgw Bug #18187: rgw:radosgw server abort when accept a CORS request with short origin
- https://github.com/ceph/ceph/pull/12397 (jewel)
https://github.com/ceph/ceph/pull/12398 (hammer)
- 09:03 PM rgw Bug #18187: rgw:radosgw server abort when accept a CORS request with short origin
- I've requested that the Red Hat security team assign a CVE to this issue.
- 08:53 PM rgw Bug #18187 (Pending Backport): rgw:radosgw server abort when accept a CORS request with short origin
- 08:17 PM rgw Bug #18187: rgw:radosgw server abort when accept a CORS request with short origin
- Bug verified.
- 06:27 AM rgw Bug #18187: rgw:radosgw server abort when accept a CORS request with short origin
- patches have been pushed:
https://github.com/ceph/ceph/pull/12381 - 06:21 AM rgw Bug #18187 (Resolved): rgw:radosgw server abort when accept a CORS request with short origin
- set public-acl to a rgw object.
set cors rule to the bucket(eg: <AllowedOrigin>*.verylongdomain.com</AllowedOrigin... - 09:34 PM Revision 0f83bb7d (ceph): rgw: do not abort when accept a CORS request with short origin
- Fixed: #18187
when accept a CROS request, the request http origin shorter than the bucket's corsrule
(eg. origin: ht... - 09:31 PM Revision 4eb7c731 (ceph): rgw: do not abort when accept a CORS request with short origin
- Fixed: #18187
when accept a CROS request, the request http origin shorter than the bucket's corsrule
(eg. origin: ht... - 09:17 PM Revision 03076a69 (ceph): client: set CEPH_SETATTR_KILL_SGUID on truncate
- On a size change, try to clobber the S_ISUID and S_ISGID bits if we
have Ax caps. If we don't have them, then ask the... - 09:07 PM Revision 69169cb2 (ceph): Merge pull request #12367 from liewegas/wip-bluestore-sync-submit
- os/bluestore: bluestore_sync_submit_transaction = false
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 09:04 PM Revision 3f6219ca (ceph): Merge pull request #12356 from xiexingguo/xxg-wip-bluestore-commit-latency
- os/bluestore: fix global commit latency
Reviewed-by: Sage Weil <sage@redhat.com> - 08:34 PM Revision e4107337 (ceph): Merge pull request #12381 from ly798/fix-rgw-crush-due-to-bad-cors
- rgw: do not abort when accept a CORS request with short origin
- 08:34 PM rbd Bug #18200 (Fix Under Review): RBD diff got SIGABRT with "--whole-object" for RBD whose parent al...
- *PR*: https://github.com/ceph/ceph/pull/12396
- 06:36 PM rbd Bug #18200 (Resolved): RBD diff got SIGABRT with "--whole-object" for RBD whose parent also have ...
- ...
- 08:26 PM Bug #18202 (Can't reproduce): rados list-inconsistent-obj can hang
Running:
while : ; do bin/rados list-inconsistent-obj 1.0 | jq '.' || break; done
hangs after not too long. ...- 07:41 PM Bug #17910 (Duplicate): rgw: threads were stuck by discarded osd_op_reply message
- http://tracker.ceph.com/issues/16122
- 07:40 PM Messengers Bug #16122 (Pending Backport): msg: upper 32-bits of message sequence get lost
- 07:35 PM Messengers Bug #18184: SimpleMessenger Pipe threads are spinning when idle
- We discussed yesterday and this needs to go to kraken.
- 04:07 PM Messengers Bug #18184 (Resolved): SimpleMessenger Pipe threads are spinning when idle
- 12:07 AM Messengers Bug #18184: SimpleMessenger Pipe threads are spinning when idle
- Sage's fix PR: -https://github.com/ceph/ceph/pull/12372- https://github.com/ceph/ceph/pull/12375
- 12:00 AM Messengers Bug #18184 (Resolved): SimpleMessenger Pipe threads are spinning when idle
- See the ceph-users thread at https://www.mail-archive.com/ceph-users@lists.ceph.com/msg34275.html
On upgrading, user... - 07:30 PM rgw Bug #18078 (Pending Backport): rgw-admin: missing command to modify placement targets
- 07:24 PM Revision 18e3f9c1 (ceph): test: add missing ceph_ll_close calls
- There's a noticable up to tick-length hang that occurs when you call
ceph_shutdown with open files still in play. Ens... - 07:24 PM Revision 6b7e39e4 (ceph): client: drop correct caps when setting btime
- btime lives under auth caps, but the client drops file caps when setting
it. Change it to drop auth caps instead.
Si... - 07:24 PM Revision 8338b944 (ceph): test: flesh out the setuid/setgit clearing test
- Add tests for write and truncate and switch to symbolic constants.
Signed-off-by: Jeff Layton <jlayton@redhat.com> - 07:24 PM Revision 2d1c91f4 (ceph): client/mds: have write codepath clear the setuid/setgid bits if they're...
- Declare a new CEPH_SETATTR_KILL_SGUID flag. When that bit is set in
the mask, then that tells the server to clear out... - 07:22 PM Revision 3dbf0c90 (ceph): Merge pull request #11865 from dachary/wip-17710-jewel
- jewel: multisite: race between ReadSyncStatus and InitSyncStatus leads to EIO errors
Reviewed-by: Yehuda Sadeh <yehu... - 07:15 PM rgw Bug #17465: multisite: coroutine deadlock in RGWMetaSyncCR after ECANCELED errors
- see special handling for ECANCELED in RGWCoroutinesManager::run()
- 07:03 PM rgw Bug #17872 (Resolved): all swift tests fail with '[Errno 111] Connection refused' because radosgw...
- resolved by changes to the qa suite
- 07:03 PM Revision aac1a3ed (ceph): msg/async: set nonce before starting the workers
- otherwise workers will respond with difference nonces to peers.
and remove nonce from Processor. as there is only one... - 07:01 PM rgw Bug #17239: radosgw-admin period update reverts deleted zonegroup
- @orit ping
- 06:52 PM rgw Bug #17930 (Rejected): failure to run any task in rgw suite on vps
- 06:51 PM rgw-testing Bug #18201 (New): rgw: create a test to validate bucket index is clean
- - in the case of multipart object creation and removal on versioned bucket
- 06:44 PM rgw Bug #17625 (Resolved): set_acl fails for object beginning and ending in underscore
- 06:43 PM rgw Bug #17822 (Resolved): multisite requests failing with '400 Bad Request' with civetweb 1.8
- 06:41 PM rgw Bug #16408: Creating Bucket failed and can't be deleted.
- @orit any progress here?
- 06:37 PM rgw Bug #17985 (Pending Backport): rgw sends omap_getvals with (u64)-1 limit
- 05:50 PM Revision db3deb80 (ceph): mon/MDSMonitor: fix iterating over mutated map
- If a standby is promoted, this was modifying the
standby_daemons map that we were iterating over
in maybe_promote_sta... - 05:38 PM CephFS Bug #18166 (Fix Under Review): monitor cannot start because of "FAILED assert(info.state == MDSMa...
- https://github.com/ceph/ceph/pull/12395
- 04:23 PM CephFS Bug #18166: monitor cannot start because of "FAILED assert(info.state == MDSMap::STATE_STANDBY)"
- It looks like MDSMonitor::maybe_promote_standby is iterating over pending_fsmap.standby_daemons, but inside the loop ...
- 06:01 AM CephFS Bug #18166: monitor cannot start because of "FAILED assert(info.state == MDSMap::STATE_STANDBY)"
- The attachment is the log of crash monitor.
Thanks! - 05:16 PM Revision fe814e78 (ceph): Merge pull request #12369 from tchaikov/wip-c99
- cmake: compile C code with c99
Reviewed-by: Willem Jan Withagen <wjw@digiware.nl>
Reviewed-by: Casey Bodley <cbodley... - 04:26 PM devops Backport #18199 (Resolved): jewel: build/ops: install-deps.sh based on /etc/os-release
- https://github.com/ceph/ceph/pull/12405
- 04:25 PM devops Bug #18198 (Pending Backport): build/ops: install-deps.sh based on /etc/os-release
- 04:23 PM devops Bug #18198 (Resolved): build/ops: install-deps.sh based on /etc/os-release
- Avoid shaky distro detection by package manager. Use /etc/os-release instead.
Fixed by commits
85a370e35fc42031a7... - 04:06 PM Revision ecc36faa (ceph): Merge pull request #12375 from liewegas/wip-msgr-eagain-loop
- msg/simple/Pipe: avoid returning 0 on poll timeout
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:56 PM Backport #18185 (Resolved): jewel: SimpleMessenger Pipe threads are spinning when idle
- 12:30 AM Backport #18185: jewel: SimpleMessenger Pipe threads are spinning when idle
- https://github.com/ceph/ceph/pull/12376
- 12:02 AM Backport #18185 (Resolved): jewel: SimpleMessenger Pipe threads are spinning when idle
- https://github.com/ceph/ceph/pull/12376
- 03:55 PM Revision 2c7d2b99 (ceph): Merge pull request #12376 from liewegas/wip-msgr-eagain-loop-jewel
- msg/simple/Pipe: avoid returning 0 on poll timeout
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:37 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- Merged the chown part of this, and I think I have sorted out the problems I was having with the truncate and write co...
- 02:45 PM RADOS Bug #17743 (Need More Info): ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa r...
- 02:44 PM Bug #17526 (Resolved): rados bench seq must verify the hostname
- 02:43 PM Bug #18018 (Can't reproduce): tests: ceph-helpers.sh races when killing daemons
- 02:42 PM Bug #17919 (Can't reproduce): tests: test/mon/osd-crush.sh is racy
- 02:42 PM Bug #18022 (Can't reproduce): tests: osd-crush.sh sometime fails
- 02:35 PM Revision 07fd958b (ceph): Merge pull request #12331 from ceph/wip-jlayton-suid
- Have ceph clear setuid/setgid bits on chown
- 02:35 PM Bug #18036 (Fix Under Review): unittest_throttle transient timeout
- https://github.com/ceph/ceph/pull/12393
- 02:33 PM Revision cfb2305f (ceph): tests: unittest_throttle avoid ASSERT_DEATH
- Combined with threads it may cause intermittent failures.
Fixes: http://tracker.ceph.com/issues/18036
Signed-off-by... - 02:21 PM Revision 9af76d26 (ceph): doc: update cinder key permissions for mitaka
- OpenStack Mitaka introduced the support of RBD snapshots while taking a
snapshot of a Nova instance. For this to work... - 02:09 PM rbd Documentation #18197 (Resolved): Remove any pre-OpenStack Liberty references from the RBD documen...
- Liberty is the oldest (non-EOLed) version of OpenStack. This will help clear up the documentation which lists configu...
- 01:58 PM Bug #15260: ceph-disk and ceph-detect-init builds do check-only things on every build
- 01:56 PM Revision 92adebc1 (ceph): Merge pull request #12388 from kylinstorage/wip-remove-librbd-unused-va...
- librbd: remove unused local variable
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:55 PM rbd Cleanup #18186 (Fix Under Review): add max_part and nbds_max options in rbd nbd map, in order to ...
- PR: https://github.com/ceph/ceph/pull/12379
- 02:22 AM rbd Cleanup #18186 (Resolved): add max_part and nbds_max options in rbd nbd map, in order to keep con...
- 01:20 PM Feature #18188 (Resolved): tests: verify k=2, m=2 erasure code data consistency
- 06:50 AM Feature #18188 (Fix Under Review): tests: verify k=2, m=2 erasure code data consistency
- https://github.com/ceph/ceph/pull/12383
- 06:46 AM Feature #18188 (Resolved): tests: verify k=2, m=2 erasure code data consistency
- It is a commonly used setting
- 01:19 PM Revision 27f6b032 (ceph): Merge pull request #12383 from dachary/wip-18188-k-2-m-2
- tests: erasure-code: add k=2, m=2 for isa & jerasure
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:09 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Thanks for testing it. The slowdown sounds like a different problem entirely and I'd suggest opening a separate bug f...
- 12:03 PM Revision 45ceb389 (ceph): rbd: --max_part and --nbds_max options for nbd map
- Fixes: http://tracker.ceph.com/issues/18186
Signed-off-by: Pan Liu <pan.liu@istuary.com> - 11:44 AM Revision efa1e543 (ceph): tests: fix erasure-code premature deallocation of cct
- The setup function returns before the run function, the cct variable
must be a data member, not a local variable that... - 11:44 AM Revision 5d367402 (ceph): tests: erasure-code: add k=2, m=2 for isa & jerasure
- Fixes: http://tracker.ceph.com/issues/18188
Signed-off-by: Loic Dachary <loic@dachary.org> - 10:43 AM Messengers Bug #14120: Pipe::do_recv() may loop infinitely
- Greg Farnum wrote:
> That makes it a little more explicit than the Linux manpage does that we shouldn't get EAGAIN... - 03:55 AM Messengers Bug #14120: Pipe::do_recv() may loop infinitely
- Greg Farnum wrote:
> So, I think this patch was a mistake and we need to revert it wherever it's appeared.
>
> Fr... - 12:20 AM Messengers Bug #14120: Pipe::do_recv() may loop infinitely
- Revert PR at https://github.com/ceph/ceph/pull/12374 may get more discussion of options.
- 12:18 AM Messengers Bug #14120: Pipe::do_recv() may loop infinitely
- According to http://pubs.opengroup.org/onlinepubs/009695399/functions/recv.html,...
- 12:05 AM Messengers Bug #14120 (In Progress): Pipe::do_recv() may loop infinitely
- So, I think this patch was a mistake and we need to revert it wherever it's appeared.
From "man 2 recv":... - 10:13 AM Bug #17807 (New): async messenger should rebind using the new nonce
- not able to reproduce it on linux. reassigning from me.
- 08:15 AM Bug #17807: async messenger should rebind using the new nonce
- @tchaikov
The command failing is:
`ceph tell osd.0 version`
whilest running:
`src/test/cephtool-test-... - 09:54 AM Revision 7f5685e8 (ceph): Merge pull request #12387 from tchaikov/wip-remove-unused-var
- msg/async: remove unused member variable
Reviewed-by: Haomai Wang <haomai@xsky.com> - 09:43 AM Revision a2cfc17d (ceph): rbd-mirror: fix sparse read optimization in image sync
- Issue truncate or zero ops for the subtracted extents between the
diff and the sparse read.
Fixes: http://tracker.ce... - 09:05 AM Revision 985738bc (ceph): librbd: remove unused local variable
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 08:46 AM Revision f0e4b693 (ceph): msg/async: remove unused member variable
- PosixServerSocketImpl::sa is not referenced anywhere, so remove it.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 08:16 AM Bug #18196 (Resolved): fail to build ceph-11.0.2 if yasm installed
- I haven't checked if this issue still exist at master branch..
but, we've got this build err at ceph-11.0.2
it ha... - 07:25 AM Revision 4adb3c13 (ceph): explictly call find_package(PythonInterp) first to fix build err
- this is an un-modified message from dev-util/cmake-3.7.1
/usr/share/cmake/Modules/FindPythonLibs.cmake
call ``find_p... - 07:08 AM CephFS Backport #18195 (Resolved): jewel: cephfs: fix missing ll_get for ll_walk
- https://github.com/ceph/ceph/pull/13125
- 07:07 AM rbd Backport #18194 (Resolved): jewel: rbd-mirror split-brain issues should be clearly visible in mir...
- https://github.com/ceph/ceph/pull/12425
- 07:05 AM Backport #18193 (Resolved): jewel: transient jerasure unit test failures
- https://github.com/ceph/ceph/pull/14701
- 07:05 AM CephFS Backport #18192 (Resolved): jewel: standby-replay daemons can sometimes miss events
- https://github.com/ceph/ceph/pull/13126
- 07:05 AM rbd Backport #18191 (Resolved): jewel: "rbd mirror image resync" does not force resync after split-brain
- https://github.com/ceph/ceph/pull/12425
- 07:04 AM rbd Backport #18190 (Resolved): jewel: rbd-mirror: gmock warnings in bootstrap request unit tests
- https://github.com/ceph/ceph/pull/12425
- 06:52 AM Revision 67d4d9e6 (ceph): rgw: do not abort when accept a CORS request with short origin
- Fixed: #18187
when accept a CROS request, the request http origin shorter than the bucket's corsrule
(eg. origin: ht... - 06:35 AM Bug #18092 (Fix Under Review): unittest_erasure_code_shec illegal instruction
- https://github.com/ceph/ceph/pull/12382
For the record there is no need for backport because the root cause was in... - 06:14 AM Bug #18092: unittest_erasure_code_shec illegal instruction
- http://lab.jerasure.org/jerasure/gf-complete/merge_requests/20/diffs merged, submodule needs to be synchronized
- 06:30 AM Revision 4d7b81ae (ceph): erasure-code: synchronize with upstream gf-complete
- Fixes: http://tracker.ceph.com/issues/18092
Signed-off-by: Loic Dachary <loic@dachary.org> - 06:00 AM Backport #18183 (In Progress): jewel: cephfs metadata pool: deep-scrub error "omap_digest != best...
- 05:59 AM Revision 36ff7580 (ceph): os/ObjectStore: properly clone object map when replaying OP_COLL_MOVE_R...
- FileStore::_close_replay_guard does not sync the object map. If OSD
crashes while executing FileStore::_collection_mo... - 05:59 AM Revision 7f94c7bf (ceph): os/ObjectStore: properly clear object map when replaying OP_REMOVE
- To remove an object, filestore needs to unlink corresponding object
file from filesystem and removes corresponding ob... - 02:26 AM Revision 83aaa55d (ceph): ceph-fuse: rewrite the fork hackery using Prefork
- in this change we use global_init_postfork_start() to restart the
log after it is stopped by Preforker.
* ceph_fuse.... - 02:13 AM Revision a488c5d8 (ceph): cmake: compile C code with c99
- so the functions like snprintf() available in C99 are available without
defining _XOPEN_SOURCE. and "asm()" is used t... - 02:13 AM Revision dfa7de61 (ceph): cmake: should detect c++11 before enabling it
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:06 AM Bug #18139: LibRadosList.EnumerateObjects failure
- https://github.com/ceph/ceph/pull/12378
- 12:09 AM Bug #18139: LibRadosList.EnumerateObjects failure
Caused by new PoolCreationRace test in ceph_test_rados_api_misc added by c0fb48331213e6934d19b7dbeeb83afeed5d7f7a
...- 01:27 AM Revision cde687ba (ceph): test: Don't write to a poolid that this test might not have created
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 12:31 AM Revision 96cf8a1b (ceph): Merge pull request #12354 from umullan/correction
- doc: correcting the object name
- 12:27 AM Revision f7abffec (ceph): msg/simple/Pipe: avoid returning 0 on poll timeout
- If poll times out it will return 0 (no data to read on socket). In
165e5abdbf6311974d4001e43982b83d06f9e0cc we chang... - 12:25 AM Revision 6c3d015c (ceph): msg/simple/Pipe: avoid returning 0 on poll timeout
- If poll times out it will return 0 (no data to read on socket). In
165e5abdbf6311974d4001e43982b83d06f9e0cc we chang... - 12:12 AM Revision 0924e63b (ceph): mds: use projected linkage in StrayManager::migrate_stray()
- Its caller StrayManager::eval_remote_stray uses projected linkage.
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 12:12 AM Revision ab49eaeb (ceph): mds: fix indent in StrayManager::eval_remote_stray
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 12:12 AM Revision 99c91474 (ceph): mds: only send slave rmdir prepare to auth mds of subtree
- This avoid trigger the assertion of path traverse return value
in Server::handle_slave_rmdir_prep. (Other witness md... - 12:12 AM Revision 672b4463 (ceph): mds: don't revoke/resume stale caps while exporting caps
- The revoke/resume cycle increases capability's sequence, which
confuses clients. The caps get removed if exporting su... - 12:12 AM Revision 57c00133 (ceph): mds: don't kill request that has started slave operations
- Rollback slave operations is tricky. Make MDcache::request_kill
ignores request that has started slave operations.
S... - 12:10 AM Backport #18155: Pipe::do_recv() may loop infinitely
- http://tracker.ceph.com/issues/14120#note-6
- 12:10 AM Backport #18155 (Rejected): Pipe::do_recv() may loop infinitely
- Zapping this after further investigation.
- 12:07 AM Backport #18155: Pipe::do_recv() may loop infinitely
- targeting jewel instead of jewel-next at https://github.com/ceph/ceph/pull/12373
12/07/2016
- 11:49 PM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- I have also seen this error during my testing. During a 4KB random write test using libRBD FIO, OSDs start to fail. I...
- 06:30 AM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- In one of the core, We see here that gift is around 2GB and same is reserved in the allocator:
In the loop below:
... - 11:39 PM Bug #18180: ReplicatedPG::execute_ctx rarely leaking ctx->reply
- 09:47 PM Bug #18180 (Resolved): ReplicatedPG::execute_ctx rarely leaking ctx->reply
- http://pulpito.ceph.com/jspray-2016-12-07_00:24:14-fs-wip-jcsp-testing-20161206-distro-basic-smithi/612548
http:... - 11:29 PM Backport #18183 (Resolved): jewel: cephfs metadata pool: deep-scrub error "omap_digest != best gu...
- https://github.com/ceph/ceph/pull/12380
- 11:27 PM Bug #18139: LibRadosList.EnumerateObjects failure
ceph_test_rados_api_misc with pid 15487 wrote 4 bytes to "foo" to pool 14 which belongs to the other test!- 02:13 AM Bug #18139: LibRadosList.EnumerateObjects failure
Still need to investigate rollforward which I think caused an object "foo" to be created then deleted, but not befo...- 11:25 PM Bug #17177 (Pending Backport): cephfs metadata pool: deep-scrub error "omap_digest != best guess ...
- Sure, I see no problem with that.
- 11:23 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- According to Zheng's comments in the users ML, this is a bug that causes data corruption (although I have not explici...
- 11:25 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- It would be very useful to see this in jewel as I prefer to use the LTS releases over the 'stable' releases
- 10:51 PM Bug #18153: No space cause osd crash (bluestore)
- Related to (possibly duplicate of) #16878
- 07:32 AM Bug #18153: No space cause osd crash (bluestore)
- @sage
- 10:29 PM Revision fe456b80 (ceph): ReplicatedPG::record_write_error: don't leak orig_reply on cancel
- The submit_log_entries machinery depends on the destructor for the
functor cleaning up after itself to handle cancela... - 10:17 PM rbd Bug #18149 (Fix Under Review): teuthology: qemu-iotests on xenial fails with unexpected console o...
- *PR*: https://github.com/ceph/ceph/pull/12371
- 09:45 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- David Zafman wrote:
> Another commit has been added to PR12088 to fix a problem. The scenario in this bug might not... - 09:02 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
- Another commit has been added to PR12088 to fix a problem. The scenario in this bug might not be impacted, but I tho...
- 08:53 PM RADOS Bug #18162: osd/ReplicatedPG.cc: recover_replicas: object added to missing set for backfill, but ...
There is an object with peer missing:
peer osd.20(0) missing {2:d0cc2acb:::10000080236.0000007d:head=0'0}
An ...- 12:16 AM RADOS Bug #18162 (Resolved): osd/ReplicatedPG.cc: recover_replicas: object added to missing set for bac...
- I encountered the bug in #13937. I wanted to help test PR12088, and may have encountered an unrelated bug as a result...
- 08:59 PM Revision cd56396a (ceph): Merge pull request #12347 from gregsfortytwo/wip-18157-fix
- ceph-fuse: start up log on parent process before shutdown
Reviewed-by: Sage Weil <sage@redhat.com> - 08:06 PM CephFS Bug #18179 (Resolved): MDS crashes on missing metadata object
- Saw this crash happening on a Jewel 10.2.3 MDS when it was missing a object in the metadata pool:...
- 07:56 PM Revision e0554f97 (ceph): POSIX/src/common/module.c: do not use strerror_r the GNU way.
- From the manpage:
char *strerror(int errnum);
int strerror_r(int errnum, char *buf, size_t buflen);
... - 07:08 PM Revision 0a6d76f2 (ceph): fsx-mpi: fsx-mpi expects a file name not a dir
- The test still fails even after being enabled:
2016-12-07T18:00:44.337 INFO:teuthology.orchestra.run.mira105:Runnin... - 07:07 PM Revision c70ec42d (ceph): fsx-mpi: remove chef task
- Per Sage's comment: https://github.com/ceph/ceph-qa-suite/pull/284#issuecomment-141463034
Signed-off-by: Patrick Don... - 05:28 PM RADOS Bug #18178 (Won't Fix): Unfound objects lost after OSD daemons restarted
- Steps to reproduce in both Hammer and Jewel:
1. Create an EC pool, in my case, named ecpool-01, in k3+m2;
2. Fill... - 05:18 PM Revision 02e7e839 (ceph): Merge pull request #977 from ceph/wip-rgw-compression
- rgw/verify: use rgw_compression_type = "random"
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Orit Wass... - 05:10 PM Revision 6da72500 (ceph): mds: clear setuid/setgid bits on ownership changes
- If we get a ownership change, POSIX mandates that you clear the
setuid and setgid bits unless you are "appropriately ... - 05:10 PM Revision 18d2499d (ceph): client: drop setuid/setgid bits on ownership change
- When we hold exclusive auth caps, then the client is responsible for
handling changes to the mode. Make sure we remov... - 05:10 PM Revision 3d7fa898 (ceph): test: add new testcase for clearing setuid/setgid bits on chown/chgrp
- Signed-off-by: Jeff Layton <jlayton@redhat.com>
- 05:09 PM Revision 58345df3 (ceph): test: remove improper casts from SetSize test
- Signed-off-by: Jeff Layton <jlayton@redhat.com>
- 05:01 PM CephFS Bug #18166: monitor cannot start because of "FAILED assert(info.state == MDSMap::STATE_STANDBY)"
- So this cluster is freshly-created with version 10.2.3?
Can you upload the monitor log with ceph-post-file? (Prefera... - 09:43 AM CephFS Bug #18166 (Resolved): monitor cannot start because of "FAILED assert(info.state == MDSMap::STATE...
ceph version: v10.2.3
operation system: ubuntu 14.04
linux kernel version: 3.13.0
Description:
I test for c...- 04:24 PM rbd Bug #18146 (Fix Under Review): TestImageSync.SnapshotStress fails on bluestore
- PR: https://github.com/ceph/ceph/pull/12368
- 04:07 PM Revision 9b965f9d (ceph): Merge pull request #12259 from liupan1111/wip-fix-nbd-max-part
- rbd-nbd: support partition for rbd-nbd mapped raw block device
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by... - 03:41 PM Bug #13594: osd/PG.cc: 2856: FAILED assert(values.size() == 1)
- I tried an adapted version of https://github.com/ceph/ceph/pull/6444 which gets the OSD started, but it is getting a ...
- 08:09 AM Bug #13594: osd/PG.cc: 2856: FAILED assert(values.size() == 1)
- We are seeing a similar backtrace on a Hammer OSD, is this the same issue? Looks like the fix wasn't backported?
<... - 03:37 PM Revision 508e81ea (ceph): os/bluestore: bluestore_sync_submit_transaction = false
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:28 PM Bug #18140 (Resolved): get_onode oid #2:afcea40e:::benchmark_data_smithi099_10837_object2430:head...
- 03:27 PM Revision 8fa08e96 (ceph): upgrade/hammer-jewel-x/stress-split: no xenial
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:09 PM Revision 899e650f (ceph): Merge pull request #12359 from tchaikov/wip-cmake
- cmake: detect keyutils if WITH_LIBCEPHFS OR WITH_RBD
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:02 PM rbd Bug #10773 (Fix Under Review): dumpling, hammer, jewel: qemu/tests/qemu-iotests/077 fails
- *PR*: https://github.com/ceph/ceph/pull/12366
- 02:59 PM Revision 2c70df97 (ceph): qa/workunits/rbd: removed qemu-iotest case 077
- The test case is not stable due to racing console output. This
results in spurious failures.
Fixes: http://tracker.c... - 02:57 PM Revision 286ceb1e (ceph): rados: optionally support reading omap key from file
- Fixes: http://tracker.ceph.com/issues/18123
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 02:54 PM Revision 577cf95d (ceph): Merge pull request #1211 from ceph/wip-15753-master
- upgrade/hammer-jewel-x suite
- 02:53 PM Revision 8ee41c6f (ceph): upgrade/hammer-jewel-x: redo stress-split
- Make this easy: write a singel yaml that does the hammer install,
some limited work, then upgardes to jewel. Copy it... - 02:53 PM Revision 03427961 (ceph): Added new hammer-jewel-x suite
- Removed rbd/test_librbd_python.sh for now
Removed all `sudo` from exec lines
Signed-off-by: Yuri Weinstein <yweinste... - 02:53 PM Revision e3c3c67b (ceph): upgrade/hammer-jewel-x/parallel: update
- Merger hammer-x (jewel branch) and jewel-x (master branch).
Signed-off-by: Sage Weil <sage@redhat.com> - 02:53 PM Revision f774097a (ceph): exclude ceph-mgr
- 02:53 PM Revision 3ea7610d (ceph): upgrade/hammer-jewel-x: no mds, no fs tests
- 02:53 PM Revision e9b06667 (ceph): upgrade/hammer-jewel-x: no xenial
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 PM Revision c6a0564a (ceph): upgrade/hammer-jewel-x: fix upgrade order
- 02:53 PM Revision 836921e0 (ceph): upgrade/hammer-jewel-x: misc fixes
- 02:51 PM Bug #18175: mon: osd flag health message is misleading
- https://github.com/ceph/ceph/pull/12365
- 02:45 PM Bug #18175 (Resolved): mon: osd flag health message is misleading
- If any flags of interest are set it issues a warning like
HEALTH_WARN noout,noin,noscrub,nodeep-scrub,sortbitwise,... - 02:50 PM Revision 26220f06 (ceph): mon/OSDMonitor: only show interesting flags in health warning
- Also add PAUSEREC flag into the list.
Fixes: http://tracker.ceph.com/issues/18175
Signed-off-by: Sage Weil <sage@red... - 02:49 PM Bug #18030 (Resolved): tests: unittest_pglog timeout
- 09:54 AM Bug #18030: tests: unittest_pglog timeout
- https://github.com/ceph/ceph/pull/12361 removing EXPECT_DEATH tests as per Sam advice
- 09:45 AM Bug #18030: tests: unittest_pglog timeout
- https://jenkins.ceph.com/job/ceph-pull-requests/15424/ (master)...
- 02:42 PM Revision 329846a3 (ceph): Merge pull request #12361 from dachary/wip-18030-pglog
- tests: remove TestPGLog EXPECT_DEATH tests
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:31 PM rgw Documentation #18174 (Resolved): document steps to disable metadata_heap on existing zones
- In Jewel, the option was added to disable use of the metadata_heap pool to archive metadata. New clusters/zones will ...
- 02:27 PM Bug #18173 (Resolved): selinux denial on /var/lib/ceph/osd/ceph-1/type
- ['type=AVC msg=audit(1481075825.792:4517): avc: denied { open } for
pid=24997 comm="ceph-osd" path="/var/lib/ceph/... - 02:27 PM Bug #18172 (Resolved): osd: leaked MOSDOpReply
- ...
- 02:26 PM Linux kernel client Bug #18161: kernel client failing to look up mds_namespace gives ENOENT (but it exists)
- Ah, that could be it. I'll look again.
- 02:17 PM Linux kernel client Bug #18161: kernel client failing to look up mds_namespace gives ENOENT (but it exists)
- can't reproduce this manually. maybe the -ENOENT was from mds up check, please try adding 'norequire_active_mds' moun...
- 12:10 AM Linux kernel client Bug #18161 (Resolved): kernel client failing to look up mds_namespace gives ENOENT (but it exists)
- See this failure:
http://pulpito.ceph.com/jspray-2016-12-06_12:37:38-kcephfs:recovery-master-testing-basic-smithi/61... - 02:17 PM rbd Cleanup #18171 (Resolved): rbd-mirror: remove the need for a polling loop within the pool replayer
- The image deleter should have a callback to the pool replayer to alert it when the image has been deleted (so it can ...
- 02:15 PM Revision aa0a0e22 (ceph): Merge pull request #12208 from ukernel/wip-18047
- mds: don't access mdsmap from log submit thread
Reviewed-by: John Spray <john.spray@redhat.com> - 02:14 PM CephFS Bug #17954 (Pending Backport): standby-replay daemons can sometimes miss events
- 02:14 PM CephFS Bug #16924 (Resolved): Crash replaying EExport
- Not backporting because it's multi-mds
- 02:13 PM Revision d6b991a3 (ceph): Merge pull request #12077 from jcsp/wip-17954
- mds: fix dropping events in standby replay
Reviewed-by: Yan, Zheng <zyan@redhat.com> - 02:13 PM rbd Cleanup #18170 (Resolved): rbd-mirror: pool replayer should re-use pool watcher
- The pool replayer creates its own watch and scraps the local pool for images. This functionality already exists withi...
- 02:12 PM Revision 4ed42243 (ceph): Merge pull request #12133 from jcsp/wip-16924
- mds: don't maintain bloom filters in standby replay
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 02:11 PM rbd Subtask #15029 (Fix Under Review): Use watch/notify to alert to specific changes in the rbd_mirro...
- *PR*: https://github.com/ceph/ceph/pull/12364
- 02:11 PM CephFS Bug #18016 (Duplicate): cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- Will assume this is duplicate of https://github.com/ceph/ceph/pull/12234 unless we can see evidence otherwise -- this...
- 02:11 PM rbd Bug #17993 (Fix Under Review): rbd-mirror: potential race mirroring cloned image
- *PR*: https://github.com/ceph/ceph/pull/12839
- 01:40 PM Revision 5a5a2b3f (ceph): tasks/cephfs: use kill in test_reconnect_eviction
- Previously relied on client being able to unmount
while the MDS was offline, which is not necessarily
so. Use kill i... - 01:09 PM Feature #18168 (New): readline isn't configured or installed in ceph cli
- readline isn't configured or installed in ceph cli, example:
~~~~
ceph> help ^H^H^H^[[A^[[A^[[B^H
~~~
I can't... - 12:56 PM Feature #18167 (New): ceph df should show correct pool usage
- at the moment the output of "ceph df" does not take the crush ruleset into account to calculate the usage in percent ...
- 12:53 PM CephFS Feature #17980: MDS should reject connections from OSD-blacklisted clients
- Yes, these two should work together: 9754 to blacklist things, and then this ticket to enforce that blacklist on the ...
- 12:50 PM Revision 4006cdeb (ceph): Merge pull request #12360 from wido/docs-cephfs-datascan-workers
- doc: Fix for worker arguments to cephfs-data-scan tool
Reviewed-by: John Spray <john.spray@redhat.com> - 12:19 PM Revision 063d61d8 (ceph): Merge pull request #1300 from batrick/multimds-merge
- suites/multimds: sync with fs suites
Reviewed-by: John Spray <john.spray@redhat.com> - 12:06 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- Hmm, still nothing's jumping out at me.
It is noteworthy that mds_gid_t is a BOOST_STRONG_TYPEDEF (unlike other th... - 11:56 AM Bug #17645: "terminate called after throwing an instance of 'std::out_of_range'" in upgrade:jewel...
- Running 50 times the job to verify how frequently it happens....
- 11:38 AM Bug #18163: platform.linux_distribution() is deprecated; stop using it
- lsb-release is no longer a Ceph runtime dependency, but is still a Ceph build dependency - see #17425
Getting rid ... - 04:10 AM Bug #18163 (Resolved): platform.linux_distribution() is deprecated; stop using it
- platform.linux_distribution() is deprecated, so we should stop using it. Notably it uses /etc/SuSE-release on SUSE s...
- 09:58 AM CephFS Feature #17835 (In Progress): mds: enable killpoint tests for MDS-MDS subtree export
- 09:50 AM Revision f1b457ff (ceph): tests: remove TestPGLog EXPECT_DEATH tests
- As per Sam Just advice, remove the EXPECT_DEATH tests to avoid
intermittent hang because they do not play well with t... - 09:26 AM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- https://jenkins.ceph.com/job/ceph-pull-requests/15414/
- 09:19 AM Revision 6a601eba (ceph): test/cephfs: add readlink test
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 09:11 AM Revision 1217ef55 (ceph): libcephfs: add readlink function in cephfs.pyx
- Signed-off-by: huanwen ren <ren.huanwen@zte.com.cn>
- 08:55 AM Revision 8f4d3ce1 (ceph): Merge pull request #12327 from iain-buclaw-sociomantic/pybind-validate-...
- pybind/rados: Add @requires for all aio methods
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Reviewed-by: Kefu Chai... - 08:49 AM Revision 82c2f840 (ceph): doc: Fix for worker arguments to cephfs-data-scan tool
- The docs were incorrect and these arguments should work.
Signed-off-by: Wido den Hollander <wido@42on.com> - 08:28 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Tested this patch (https://github.com/ceph/ceph-client/commit/06ae6a76e4570cba948084f6a1c0d206485d1706) on two server...
- 08:16 AM CephFS Bug #18157: ceph-fuse segfaults on daemonize
- an alternative fix at https://github.com/ceph/ceph/pull/12358
- 08:09 AM Revision b805505d (ceph): cmake: find keyutils if rbd or libcephfs is enabled
- * find_package(keyutils REQUIRED) if (WITH_LIBCEPHFS OR WITH_RBD)
prior to this change, we detect keyutils if the b... - 08:09 AM Revision 321691d8 (ceph): cmake: turn krbd into a static lib
- * simplify the link dependencies.
* s/keyutils/${KEYUTILS_LIBRARIES}/
Signed-off-by: Kefu Chai <kchai@redhat.com> - 07:37 AM Revision bf3f57af (ceph): os/bluestore: fix global commit latency
- "start" is used to calculate the global bluestore commit latency
and hence shall not be updated at each internal stat... - 07:23 AM Bug #10405: osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill_targets(peer))
- Created as #18165
- 07:21 AM RADOS Bug #18165 (Resolved): OSD crash with osd/ReplicatedPG.cc: 8485: FAILED assert(is_backfill_target...
- ...
- 06:17 AM Revision 5af46009 (ceph): doc: correcting the object name
- Signed-off-by: umullangi@walmartlabs.com
- 03:53 AM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- ...
- 03:38 AM Revision dc648a79 (ceph): suites/multimds: add kclient disable override
- The libcephfs tests are negatively affected by other mounts. This commit
adds a kclient disable in addition to the ce... - 03:38 AM Revision 9be89e58 (ceph): suites/multimds: sync with fs suites
- This commit synchronizes the multimds suite with the fs suite. The
basic/verify sub-suites now do the same tests exce... - 03:36 AM Revision 69bbff23 (ceph): os/bluestore: don't implicitly create the source object for clone
- We shall implicitly create the destination object instead and
missing source object usually indicates an error.
Sign... - 02:27 AM Revision ba6a43aa (ceph): os/bluestore: cleanup Cache::_audit
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 02:04 AM Revision 66953e32 (ceph): Merge pull request #12350 from chanyoung/struct-OSDOp-typos
- osd: fix typos in "struct OSDOp" comments
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:54 AM Revision 411b7324 (ceph): os/bluestore: clear omap flag if parent has none
- As clone shall be a perfect duplicate of parent.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:03 AM Revision 5f1abf9c (ceph): suites/kcephfs: disable broken python tests
- Disabling strays because of:
http://tracker.ceph.com/issues/17193
Disabling test_failover because of:
http://tracker... - 01:02 AM CephFS Documentation #18040 (Resolved): Documentation says not to run multiple MDS, but we can do that now
- 12:56 AM Revision f9fc3548 (ceph): osd: mark queued flag for op
- queue_op will check the op epoch with current osdmap epoch,
and then, the op will be push into waiting_for_map or mar... - 12:46 AM Revision 98842b7c (ceph): suites/kcephfs: run python tests with 4 MDSs
- For the benefit of test_failover
Signed-off-by: John Spray <john.spray@redhat.com> - 12:46 AM Revision d86b67ef (ceph): tasks/cephfs: make test_journal_repair work with more daemons
- Previously this assumed it was running with exactly two MDS
daemons. When there were more, it would fail to execute
... - 12:46 AM Revision 370ad523 (ceph): suites/kcephfs: remove task for cap flush test
- This test skips all if not running against
fuse.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:46 AM Revision 14f3a688 (ceph): tasks/cephfs: fix race in TestStrays.test_dirfrag_limit
- With the kernel client, this was proceeding to attempt
a split before the directory had persisted, because
there was ... - 12:46 AM Revision 989ecd6b (ceph): suites/kcephfs: disable test_full for kcephfs
- Until http://tracker.ceph.com/issues/17204 is done.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:46 AM Revision 1eabbbda (ceph): tasks/cephfs: skip TestVolumeClient.test_evict on kcephfs
- This test was probably buggy and only happened to work
with ceph-fuse, because it expects the MDS to immediately
resp... - 12:46 AM Revision 45eb4bf7 (ceph): tasks/cephfs: special case for kcephfs behaviour
- It does not generate EIOs in all the cases that
the fuse client does.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:46 AM Revision 0bd95f72 (ceph): tasks/cephfs: fix unmount call in volumeclient test
- Should have been to umount_wait, not umount (i.e.
the blocking foreground version). This happened
to matter because ... - 12:46 AM Revision d6d9715d (ceph): tasks/cephfs: skip volumeclient client test on kcephfs
- This relies on quota-ish stuff that doesn't exist
in kclient. We can still run the outer part
of the test though.
S... - 12:46 AM Revision 1aa7ad6a (ceph): tasks/cephfs: skip test_client_abort on kclient
- This tests a fuse-only feature, ticket for adding
it in kclient is:
http://tracker.ceph.com/issues/17805
Signed-off-... - 12:45 AM Revision 318aa226 (ceph): suites/kcephfs: s/yam/yaml/
- Oops!
Signed-off-by: John Spray <john.spray@redhat.com> - 12:45 AM Revision 2e99bd10 (ceph): suites/fs: s/yam/yaml/
- Oops!
Signed-off-by: John Spray <john.spray@redhat.com> - 12:45 AM Revision 2f6b034d (ceph): tasks/cephfs: add a skip for non-fuse
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 AM Revision c5f6dfc1 (ceph): suites/kcephfs: put clients on dedicated nodes
- Some tests want to use power cycling to reset stuck
mounts, and that needs to not kill OSDs as collateral
damage.
Ne... - 12:45 AM Revision 28aed558 (ceph): tasks/cephfs: skip ENOSPC testing on kclient
- Ticket #17204 exists to revive the old patchset, until then
we skip the tests.
Signed-off-by: John Spray <john.spray... - 12:45 AM Revision 1f7d2ef7 (ceph): tasks/ceph: handle down nodes in log rotation
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 AM Revision 507cfebb (ceph): tasks/cephfs: update test_journal_repair for kclient
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 AM Revision d1277afd (ceph): tasks/cephfs: fix eviction test for volumeclient
- It was not correct to expect a client to block after
eviction unless it was also deauthorised. I guess
this was work... - 12:45 AM Revision bc680e7a (ceph): tasks/cephfs: support multi-fs in kernel client
- Change the Mount interface to take it as an
argument to mount() instead of setting it
out of band in a config file as... - 12:45 AM Revision cd084c7d (ceph): suites/kcephfs: add python tests
- Let's see which of these is happy running with a kernel client!
Signed-off-by: John Spray <john.spray@redhat.com> - 12:45 AM Revision b21b825d (ceph): tasks/cephfs: make KernelMount.umount_wait idempotent
- Some places (notably CephFSTestCase.setUp) don't check
for mountedness before calling this.
Signed-off-by: John Spra... - 12:45 AM Revision 04951c8a (ceph): tasks/cephfs: skip test_session_reject cleanly
- Instead of asserting in configure_auth (which in fact
works fine with KernelMount.write_secret_file), raise
a SkipTes... - 12:45 AM Revision e5264ec5 (ceph): tasks/kclient: unmount conditionally
- Don't assume the workload left the mount up and
running.
Signed-off-by: John Spray <john.spray@redhat.com> - 12:45 AM Revision 62d51777 (ceph): suites/kcephfs: add TestFailover
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:45 AM Revision 3ac80a35 (ceph): suites/kcephfs: tolerate skipping tests
- With fuse client we expect everything to be
runnable so treat SkipTest as a failure because
it indicates something ba... - 12:44 AM Revision 0676444e (ceph): Merge pull request #1282 from batrick/fs-reorg
- fs: unify common parts of sub-suites
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 12:36 AM Bug #18127 (Resolved): osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- 12:33 AM Bug #18152 (Duplicate): segfault in ceph-fuse when quota is enabled
- #16066
- 12:25 AM Revision 8b2c896d (ceph): osd: fix typos in "struct OSDOp" comments
- "nembers" -> "members"
Signed-off-by: Chanyoung Park <park910113@gmail.com> - 12:18 AM rbd Bug #18156 (Pending Backport): rbd-mirror: gmock warnings in bootstrap request unit tests
- 12:18 AM Revision d3f224b3 (ceph): Merge pull request #12344 from trociny/wip-resync-fixup
- rbd-mirror: fix gmock warnings in bootstrap request unit tests
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:17 AM Backport #17970: jewel: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- Loic Dachary wrote:
> @Aaron could you please open a bug report for this ? In the bug report make sure you add every... - 12:17 AM Revision a3c3e784 (ceph): Merge pull request #1275 from jcsp/wip-17853
- Directory fragmentation tests
Reviewed-by: Patrick Donnelly <pdonnell@redhat.com> - 12:04 AM Feature #18160 (New): support shared ccache dirs across users
- Right now, every user on a machine building Ceph has their own ccache dir — approximately 32GB!
It would be nice if ...
12/06/2016
- 11:45 PM Bug #18036: unittest_throttle transient timeout
- https://jenkins.ceph.com/job/ceph-pull-requests/15403/...
- 11:39 PM Revision 86dcfd8d (ceph): Merge pull request #11369 from theanalyst/kraken-release-notes
- doc: release notes for 11.0.2
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:39 PM CephFS Bug #18159 (Resolved): "Unknown mount option mds_namespace"
- I think this is just a spurious message coming from src/mount/mount.ceph.c because it was not updated when mds_namesp...
- 11:34 PM Revision 399617be (ceph): tasks/cephfs: add test_standby_for_invalid_fscid
- Signed-off-by: Ramakrishnan Periyasamy <rperiyas@redhat.com>
- 11:24 PM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hey Sean,
This is the fix.
$ git describe 73a1b45ec01a7debe0520015a11afdaa11dfd269
v11.0.2-652-g73a1b45
It ... - 09:17 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi Brad,
This has been upgraded some time back:
root@ceph-mon1:~# ceph -v
ceph version 10.2.3 (ecc23778eb545d8... - 03:39 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi Sean,
What version are you currently running? Still 10.2.2? - 11:23 PM Revision 61d00784 (ceph): doc: add salient features of kraken 11.1.0 rc
- Reordering to add Sage's release note comments on top
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 11:20 PM Revision 230406e3 (ceph): doc: add release notes for 11.1.0
- Release notes as of 7b1293e70db51f620210332bde1f83ade15bd9d3
Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com> - 11:20 PM Revision a0704058 (ceph): doc: release notes for 11.0.1
- Signed-off-by: Abhishek Lekshmanan <alekshmanan@suse.com>
- 11:20 PM Revision f8467c0d (ceph): doc: bump release notes to 11.0.2
- bumping release notes to 11.0.2 kraken and adding the single commit that
differs between the changes
Signed-off-by: ... - 11:16 PM CephFS Bug #18157 (Fix Under Review): ceph-fuse segfaults on daemonize
- https://github.com/ceph/ceph/pull/12347
- 10:20 PM CephFS Bug #18157: ceph-fuse segfaults on daemonize
- Not detected in nightlies because of #18158
- 10:16 PM CephFS Bug #18157 (Resolved): ceph-fuse segfaults on daemonize
- ...
- 11:11 PM Revision 48d5f133 (ceph): Merge pull request #12346 from theanalyst/doc/changelog/v10.2.4
- doc: adding changelog for v10.2.4
Reviewed-by: Sage Weil <sage@redhat.com> - 11:07 PM Revision cbf18b1d (ceph): ceph-fuse: start up log on parent process before shutdown
- Otherwise, we hit an assert in the Ceph context and logging teardown.
Fixes: http://tracker.ceph.com/issues/18157
S... - 11:06 PM Revision 08289228 (ceph): doc: adding changelog for v10.2.4
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 11:02 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- https://bugs.launchpad.net/ubuntu/+source/google-perftools/+bug/1647864
- 10:13 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- Just saw this on xenial! oh goodie....
- 10:27 PM Revision 2340a7b9 (ceph): Merge pull request #12328 from liewegas/wip-bluestore-flush
- os/bluestore: flush before enumerating omap values
- 10:27 PM Revision 8981c1c7 (ceph): Merge pull request #12265 from liewegas/wip-bluestore-precondition
- os/bluestore: drop old bluestore preconditioning; replace with wal preextension of file size
- 10:21 PM Revision 4eca628f (ceph): Merge pull request #12281 from dachary/wip-17743-memstore
- tests: do not use memstore.test_temp_dir in two tests
Reviewed-by: David Zafman <dzafman@redhat.com> - 10:21 PM Revision 38964b98 (ceph): Merge pull request #12298 from chhabaramesh/bit_alloc_mempool
- os/bluestore: bitmap allocator dump functionality
Reviewed-by: Sage Weil <sage@redhat.com> - 09:40 PM Revision 376026d7 (ceph): rbd-mirror: fix gmock warnings in bootstrap request unit tests
- Fixes: http://tracker.ceph.com/issues/18156
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 09:40 PM rbd Bug #18051: "rbd mirror image resync" does not force resync after split-brain
- Should be backported together with the fix for #18156
- 09:40 PM rbd Cleanup #16991: rbd-mirror split-brain issues should be clearly visible in mirror status
- Should be backported together with the fix for #18156
- 09:39 PM rbd Bug #18156 (Fix Under Review): rbd-mirror: gmock warnings in bootstrap request unit tests
- PR: https://github.com/ceph/ceph/pull/12344
- 09:38 PM rbd Bug #18156 (Resolved): rbd-mirror: gmock warnings in bootstrap request unit tests
- ...
- 08:54 PM rbd Bug #17993 (In Progress): rbd-mirror: potential race mirroring cloned image
- 07:35 PM Revision b5458f77 (ceph): Merge pull request #12338 from liewegas/wip-kraken-notes
- doc/release-notes: kraken release notes (draft)
Reviewed-by: Abhishek Lekshmanan <abhishek.lekshmanan@gmail.com> - 07:34 PM Revision 4607cb5f (ceph): doc/release-notes: kraken release notes (draft)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:31 PM Backport #18155 (In Progress): Pipe::do_recv() may loop infinitely
- 07:30 PM Backport #18155 (Rejected): Pipe::do_recv() may loop infinitely
- https://github.com/ceph/ceph/pull/12349
- 07:07 PM Bug #17998 (Closed): ceph-osd oom killed during rados bench teuthology run
- I think sage fixed this.
- 07:06 PM Bug #10405 (Can't reproduce): osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill...
- Actually, neither of those crashes is related to this bug, please open a new one.
- 06:52 PM CephFS Bug #17193: truncate can cause unflushed snapshot data lose
- It looks like the patch hasn't eliminated the failure:
http://pulpito.ceph.com/jspray-2016-12-06_12:37:38-kcephfs:re... - 06:38 PM Revision 377f239f (ceph): Merge pull request #532 from ceph/wip-12378
- Adds task to wrap the aver utility
- 06:38 PM Revision 9068dc37 (ceph): Merge pull request #734 from dachary/wip-rados-thrash
- openstack: rados/thrash...cache-pool-snaps.yaml: need 15GB
- 06:37 PM Revision 19f39ac8 (ceph): Merge pull request #1019 from ceph/wip-rgw-fix-longpath
- rgw: split osd's in 2 nodes
- 06:27 PM Messengers Bug #14120 (Pending Backport): Pipe::do_recv() may loop infinitely
- 06:05 PM Revision 9f82d0f8 (ceph): Merge pull request #980 from ceph/wip-fix-infinit
- Fix infinite wait during monitor quorum check
- 05:45 PM Revision a77cfe6b (ceph): Merge pull request #12340 from athanatos/wip-18127
- osd/PGLog::proc_replica_log,merge_log: fix bound for last_update
Reviewed-by: Sage Weil <sage@redhat.com> - 05:01 PM Revision a9da6054 (ceph): FileStore::_do_fiemap: do not reference fiemap after it is freed
- `last` points to fiemap::fm_extends[n], and if fiemap gets freed, we can
not reference any of its fieldis. so we coul... - 03:58 PM Revision ebb9f094 (ceph): Merge pull request #12339 from kylinstorage/wip-optimize-assert
- msg/async: assert(0) -> ceph_abort()
Reviewed-by: Sage Weil <sage@redhat.com> - 03:52 PM Revision 2f3e75e8 (ceph): Merge pull request #12329 from ktdreyer/wip-doc-spelling
- doc: fix grammar/spelling in RGW sections
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com>
Reviewed-by: Casey Bo... - 03:46 PM Revision fe25c45b (ceph): rgw/verify: set compression type=random
- instead of adding each compression type to the matrix for the rgw/verify
suite, use the new 'random' compression type... - 03:46 PM Revision f39cafe5 (ceph): rgw: configure compression in default zone when not multisite
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 03:34 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- Testing a PR now that fixes the setattr codepaths. That's pretty simple to do from those codepaths since we're sendin...
- 02:58 PM CephFS Feature #18154 (Fix Under Review): qa: enable mds thrash exports tests
Currently:...- 02:54 PM Revision afda23ae (ceph): Merge pull request #12033 from dachary/wip-17926-jewel
- jewel: ceph-disk --dmcrypt create must not require admin key
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:54 PM Revision b357eddd (ceph): msg/async/rdma/RDMAStack.cc: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 02:52 PM Revision 0e387afb (ceph): msg/async/rdma/Infiniband.h: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 02:50 PM Revision 3591b3fe (ceph): msg/async/rdma/Infiniband.cc: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 01:13 PM Revision 8e8f8dd2 (ceph): tools: cleanup phase of cephfs-data-scan
- cephfs-data-scan has a new optional phase to delete xattrs generated
during recovery.
Signed-off-by: Vishal Kanaujia... - 01:10 PM devops Backport #18133 (Resolved): jewel: undefined references when building unit tests with --with-xio
- 01:04 PM Revision 42645a30 (ceph): rbd-nbd: support partition for rbd-nbd mapped raw block device.
- Fixes: http://tracker.ceph.com/issues/18115
Signed-off-by: Pan Liu pan.liu@istuary.com - 12:38 PM Bug #18153 (Resolved): No space cause osd crash (bluestore)
- Ceph cluster will only one monitor and one osd, the disk size is 50GB
mon_osd_full_ratio is 95% mon_osd_nearfull_r... - 12:37 PM rgw Bug #17996: rgw: ECANCELED in rgw_get_system_obj() leads to infinite loop
- new fix: -https://github.com/ceph/ceph/pull/12225-
- 12:18 PM Revision 6c5958c1 (ceph): Merge pull request #12125 from ukernel/wip-17990
- mds: properly commit new dirfrag before splitting it
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:06 AM Revision 6e69b580 (ceph): Merge pull request #12334 from Adirl/fix_log_level
- msg/async/rdma: change log level: 0 -> 1
Reviewed-by: Haomai Wang <haomai@xsky.com> - 10:54 AM Revision 03bb8964 (ceph): msg/async/rdma: change log level: 0 -> 1
- this will avoid irrelevant messages to console in case of "ceph -s"
issue: 914828
Change-Id: Ia220c62ff7a9f80fbe606... - 09:46 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. rbd...
- 09:45 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. rgw...
- 09:43 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. rados...
- 09:42 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. fs...
- 09:40 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. powercycle...
- 09:39 AM Stable releases Tasks #17851: jewel v10.2.6
- ...
- 09:36 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. ceph-disk...
- 08:47 AM Revision bbafd7f8 (ceph): Merge pull request #11968 from ddiss/jewel_next_flush_evict_snaps
- jewel: tools: snapshotted RBD extent objects can't be manually evicted from a cache tier
Reviewed-by: Kefu Chai <kch... - 08:46 AM Revision 0aa44189 (ceph): Merge pull request #12151 from dachary/wip-18011-jewel
- jewel: test fails due to The UNIX domain socket path
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:45 AM Revision f898b18a (ceph): Merge pull request #12296 from SUSE/wip-18133-jewel
- jewel: build/ops: fix undefined crypto references with --with-xio
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:44 AM Revision 8498ed34 (ceph): os/bluestore: merge find() & erase()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 08:41 AM Backport #17970: jewel: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- @Aaron could you please open a bug report for this ? In the bug report make sure you add every details, including acc...
- 08:35 AM Revision 6dc85ca9 (ceph): msg/async/dpdk/TCP.h: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:32 AM Revision fbfc5483 (ceph): msg/async/dpdk/DPDKStack.cc: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:30 AM Revision 7d13dd5c (ceph): msg/async/dpdk/DPDK.cc: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:29 AM Revision ac2cc227 (ceph): common/map_cacher.hpp: assert(0) -> ceph_abort()
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:17 AM Bug #18092 (In Progress): unittest_erasure_code_shec illegal instruction
- 08:12 AM Revision 2711dac3 (ceph): tests: do not use memstore.test_temp_dir in two tests
- unittest_memstore_clone and test_objectstore_memstore.sh both
use memstore.test_temp_dir and when running in parallel... - 05:50 AM Revision a371aa51 (ceph): os/bluestore: readability improvements to _do_clone_range()
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 05:48 AM Revision e8450e54 (ceph): os/bluestore: kill unreachable code
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 05:40 AM CephFS Bug #18086 (Pending Backport): cephfs: fix missing ll_get for ll_walk
- 05:16 AM Bug #18113: Don't lose deep-scrub information
- The only issue that became obvious when modifying the code is what to do if nodeep-scrub flag is set.
Sam Just:
... - 05:16 AM rbd Bug #15028 (Fix Under Review): Deep-flatten incorrectly updates fast-diff stats
- PR https://github.com/ceph/ceph/pull/12326
- 04:34 AM CephFS Bug #18151: Incorrect report of size when quotas are enabled.
- Due to other bug / issue, I've run ceph-fuse in debug mode with 'debug client = 20'. Right after launching ceph-fuse,...
- 01:21 AM CephFS Bug #18151: Incorrect report of size when quotas are enabled.
- 1) My environment:
- ceph/cephfs in 10.2.2.
- All infrastructure is in the same version (rados cluster, mons, m... - 01:15 AM CephFS Bug #18151 (Resolved): Incorrect report of size when quotas are enabled.
- 04:29 AM Bug #18152: segfault in ceph-fuse when quota is enabled
- The full log, running ceph-fuse in debug mode, and with 'debug client = 20' is gzipped, and available for download in...
- 04:09 AM Bug #18152 (Duplicate): segfault in ceph-fuse when quota is enabled
- When quotas are enabled, by mounting cephfs using ceph-fuse, as
ceph-fuse --id mount_user -k /etc/ceph/ceph.client... - 04:00 AM Revision ef7fdc0a (ceph): os/bluestore: fix potential csum_order overflow
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 01:32 AM Revision 0f7a2766 (ceph): tool: add some ceph relate processes to ps-ceph.pl
- add ceph-mgr,ceph-disk,rbd-mirror,radosgw to ps-ceph.pl,because
these processes may run long time.so we need to kno... - 01:04 AM Revision 71ef0cbd (ceph): Merge pull request #9837 from zhjwpku/typos
- doc: network-protocol typos
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:29 AM Bug #18139: LibRadosList.EnumerateObjects failure
This test verifies 3 things. First, as objects are returned it makes sure there are no duplicates AND inserts the ...
12/05/2016
- 11:42 PM Revision 16144d8e (ceph): Fix infinite wait during monitor quorum check
- Signed-off-by: Vasu Kulkarni <vasu@redhat.com>
- 11:35 PM Revision fac276b9 (ceph): Split osd's into 2 nodes
- http://tracker.ceph.com/issues/15612
Not all test machines(mira, vps) have 4 osd's and without this
change it will fa... - 10:53 PM Revision 68e08c7a (ceph): Merge pull request #535 from ceph/wip-12376
- tasks/radosbenchsweep task
- 10:53 PM Revision d06a5fed (ceph): Merge pull request #1024 from ceph/wip-default-fs
- tasks/ceph: default to xfs instead of root dir
- 10:49 PM Revision 46c6b13a (ceph): Merge pull request #1087 from sponce/master
- rados: Added tests for the striper layer of rados
- 10:49 PM Bug #18145: pgs stuck in remapped after recovery on cluster with many osds down
- Correction: Issue was resolved not through restarting the primary but merely by marking them down to force peering to...
- 04:09 AM Bug #18145 (Can't reproduce): pgs stuck in remapped after recovery on cluster with many osds down
- During a maintenance event in which many osds were removed and some existing osds were down the cluster went into rec...
- 10:42 PM Revision 1cd5be72 (ceph): Merge pull request #956 from ceph/wip-rm-ext4
- Remove ext4 option from rados:thrash tests
Reviewed-by: Samuel Just <sjust@redhat.com> - 10:15 PM Revision 9411351c (ceph): 10.2.4
- 09:38 PM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- https://jenkins.ceph.com/job/ceph-pull-requests/15371/console fails despite https://github.com/ceph/ceph/pull/12281
- 09:14 PM Bug #10405: osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill_targets(peer))
- Yeah, this has all been rewritten in Jewel. I may be able to look into this at some point if I have time, but there'...
- 08:58 PM Backport #17970: jewel: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- I compiled this pull request earlier today and started an OSD (17) with the new code. Then I started the OSDs which w...
- 08:47 PM Bug #17789 (Resolved): osd: update_log_missing does not order correctly with osd_ops
- 08:46 PM Backport #17881 (Resolved): jewel: Add config option to disable new scrubs during recovery
- 08:08 PM Revision b03c9501 (ceph): PGLog::proc_replica_log,merge_log: fix bound for last_update
- If olog.tail > log.tail, olog.tail is also a bound on last_update.
See the changed comment in the commit for details.... - 07:36 PM Revision 811ace2f (ceph): Merge pull request #1301 from ceph/wip-valgrind-centos
- do all valgrind runs on centos
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:21 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- In the meantime, we can force valgrind runs onto centos.
https://github.com/ceph/ceph-qa-suite/pull/1301 - 07:17 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- It's a valgrind bug: http://stackoverflow.com/questions/37032339/valgrind-unrecognised-instruction
https://github.... - 07:07 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- bf7d77a84b144ffdc92efd7d19d3038b75911b54 looks like it could maybe be the culprit? it moved a global static to a fun...
- 07:21 PM Revision 693bd238 (ceph): do all valgrind runs on centos
- The xenial valgrind has a bug with generating random
numbers; see http://tracker.ceph.com/issues/18126
Revert this w... - 07:06 PM RADOS Bug #18054 (Need More Info): os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed...
- 07:02 PM Backport #17876 (Resolved): jewel: osd: update_log_missing does not order correctly with osd_ops
- 07:01 PM Revision 2ff4cc9b (ceph): Merge pull request #11997 from Abhishekvrshny/wip-17876-jewel
- jewel: osd: update_log_missing does not order correctly with osd_ops
Reviewed-by: Sage Weil <sage@redhat.com> - 07:01 PM Feature #17866 (Resolved): Add config option to disable new scrubs during recovery
- 07:01 PM Revision a9539648 (ceph): Merge pull request #11944 from SUSE/wip-17866-jewel
- jewel: osd: Add config option to disable new scrubs during recovery
Reviewed-by: Sage Weil <sage@redhat.com> - 06:59 PM Revision dded3de9 (ceph): Merge pull request #12053 from theanalyst/v10.2.4/release-notes
- doc: release notes for 10.2.4
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:59 PM Revision 7b0ba9d3 (ceph): doc: fix capitalization in RGW admin ops
- lower-case second word in this sentence.
Signed-off-by: Ken Dreyer <kdreyer@redhat.com> - 06:59 PM Revision 7db4def8 (ceph): doc: fix spelling in RGW s3 compliance
- mentionned -> mentioned
Signed-off-by: Ken Dreyer <kdreyer@redhat.com> - 06:52 PM Revision 1e042a9b (ceph): os/bluestore: flush before enumerating omap values
- For a few update ops we enumerate omap keys (to remove them).
Make sure we flush the pipeline before doing so or else... - 06:47 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- So the upshot here is that I don't think this is anything that has broken in ceph, per-se. FUSE changed its behavior,...
- 06:12 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- Ahh, I think I see the problem:...
- 04:25 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- Definitely a kernel problem. Works correctly on v4.8.0, broken on v4.8.6 kernel for sure. I haven't bisected to be su...
- 03:45 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- Sorry, I mean this patch in my v4.8.10 kernel:...
- 03:38 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- First evidence I see of this test failing is here:
http://pulpito.ceph.com/teuthology-2016-11-30_10:10:02-fs-j... - 06:46 PM Revision 9ae9e641 (ceph): os/bluestore/BlueFS: pre-extend file size for WAL (.log) files
- When rocksdb has log recycling on (this is required!), it will
do robust checksums on log records and change playback... - 06:46 PM Revision 73ffab4f (ceph): os/bluestore: remove kludgey rocksdb preconditioning
- This doesn't work, it's slow, and it's hacky.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:44 PM Bug #18140 (Fix Under Review): get_onode oid #2:afcea40e:::benchmark_data_smithi099_10837_object2...
- https://github.com/ceph/ceph/pull/12328
- 06:44 PM rbd Bug #18149 (In Progress): teuthology: qemu-iotests on xenial fails with unexpected console output
- 05:34 PM rbd Bug #18149 (Resolved): teuthology: qemu-iotests on xenial fails with unexpected console output
- ...
- 06:36 PM Bug #18127: osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- 05:58 PM Bug #18127 (In Progress): osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- 06:09 PM Revision 13d68c9c (ceph): Merge pull request #11672 from linuxbox2/jewel-17663
- jewel: rgw_rest_s3: apply missed base64 try-catch
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:06 PM Revision 5f0bc2ac (ceph): pybind/rados: Add @requires for all aio methods
- Signed-off-by: Iain Buclaw <iain.buclaw@sociomantic.com>
- 05:58 PM Bug #18042 (Resolved): SimpleMessenger debug delay injection deadlock
- 05:57 PM Bug #17999 (Resolved): ec scrub mismatch during teuthology run
- 05:47 PM Revision 03ad410e (ceph): Merge pull request #11953 from SUSE/wip-17885-jewel
- jewel: test: temporarily disable fork()'ing tests
Reviewed-by: John Spray <john.spray@redhat.com> - 05:32 PM Stable releases Tasks #17851: jewel v10.2.6
- ...
- 04:47 PM Revision 7b1293e7 (ceph): Merge pull request #12275 from xiexingguo/xxg-wip-bluestore-1202
- os/bluestore: dedup omap_head, reuse nid instead
Reviewed-by: Sage Weil <sage@redhat.com> - 04:45 PM Revision 3f2298ee (ceph): Merge pull request #1299 from athanatos/wip-enable-hacky-flag
- ec-data-pool: enable the hacky_overwrites flag
- 04:45 PM Revision 2041a187 (ceph): Merge pull request #12305 from athanatos/wip-ec-rbd-fixes
- osd: fixes to make rbd on ec work
Reviewed-by: Sage Weil <sage@redhat.com> - 04:39 PM Revision 01e8960e (ceph): Merge pull request #11884 from SUSE/wip-17754-jewel
- jewel: ceph-create-keys loops forever
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:38 PM Revision 73f65329 (ceph): Merge pull request #11529 from SUSE/wip-17600-jewel
- jewel: common: Improve linux dcache hash algorithm
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:32 PM Revision 645119e7 (ceph): Merge pull request #12306 from athanatos/wip-ec-scrub
- osd: fix ec scrub errors
Reviewed-by: Sage Weil <sage@redhat.com> - 04:20 PM rbd Bug #18051 (Pending Backport): "rbd mirror image resync" does not force resync after split-brain
- 04:20 PM rbd Cleanup #16991 (Pending Backport): rbd-mirror split-brain issues should be clearly visible in mir...
- 04:20 PM Revision 566d01bf (ceph): Merge pull request #12212 from trociny/wip-16991
- rbd-mirror: recovering after split-brain
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:18 PM Revision d75ffa43 (ceph): Merge pull request #12307 from athanatos/wip-18042
- msg/simple/Pipe::stop_and_wait: unlock pipe_lock for stop_fast_dispatching()
Reviewed-by: Haomai Wang <haomai@xsky.c... - 03:38 PM CephFS Backport #18026 (In Progress): jewel: ceph_volume_client.py : Error: Can't handle arrays of non-s...
- 03:38 PM Revision e7256056 (ceph): ceph_volume_client: set an existing auth ID's default mon caps
- ... as 'allow r' (the minimum mon caps required to access a share)
when:
* authorizing the auth ID to access a volum... - 03:36 PM CephFS Backport #18100: jewel: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- @John https://github.com/ceph/ceph/pull/12097/files conflicts in a non trivial way, could you take a look when you ha...
- 03:33 PM CephFS Backport #18103 (In Progress): jewel: truncate can cause unflushed snapshot data lose
- 03:32 PM Revision e1af4902 (ceph): mds: force client flush snap data before truncating objects
- Snapshot data get lost if following sequence of events happen
- client writes data to a file
- make a snapshot
- tru... - 03:30 PM rbd Backport #18024 (In Progress): jewel: "FAILED assert(m_processing == 0)" while running test_lock_...
- 03:30 PM Revision 900f2acd (ceph): librbd: account m_processing when failing request after refresh
- AioImageRequestWQ::_void_process() dequeues an item from the
work queue by invoking ThreadPool::_void_process() which... - 03:29 PM rbd Backport #18110 (In Progress): jewel: diff calculate can hide parent extents when examining first...
- 03:29 PM Revision 4a157ea3 (ceph): librbd: diffs to clone's first snapshot should include parent diffs
- If the clone has a backing object created after the snapshot that
overwrites an extent of the parent, the parent diff... - 03:27 PM rbd Backport #18136 (In Progress): jewel: qa: rbd-mirror workunit false negative when waiting for ima...
- 02:57 PM rgw Backport #18061 (In Progress): jewel: rgw:fix for deleting objects name beginning and ending with...
- 02:56 PM Revision 820ab7d8 (ceph): rgw: fix for versioned delete_multi_object
- Fixes: http://tracker.ceph.com/issues/17888
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 02:56 PM Revision 514a31fd (ceph): rgw:fix for deleting objects name beginning and ending with underscores...
- Fixes: http://tracker.ceph.com/issues/17888
Signed-off-by: zhouruisong 236131368@qq.com
(cherry picked from commit 2... - 02:53 PM Bug #17561 (Resolved): transient jerasure unit test failures
- this is rare enough that a backport is not necessary
- 02:30 PM Revision d89df9df (ceph): bitmap allocator dump functionality
- Signed-off-by: Ramesh Chander <Ramesh.Chander@sandisk.com>
- 02:19 PM rbd Cleanup #18125 (Fix Under Review): rbd-cli: no warning message when enable/disable mirroring opti...
- PR: https://github.com/ceph/ceph/pull/12319
- 02:14 PM Revision 232271bb (ceph): doc: release notes: add the last 5 prs making it in 10.2.4
- Signed-off-by: Abhishek Lekshmanan <abhishek@suse.com>
- 02:06 PM Bug #18036: unittest_throttle transient timeout
- In jewel https://jenkins.ceph.com/job/ceph-pull-requests/15336/console...
- 02:03 PM Revision 55df834e (ceph): Merge pull request #12310 from wjin/change_info
- mailmap: change personal info
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:52 PM Backport #18015 (Resolved): jewel: osd: condition OSDMap encoding on features
- 01:50 PM Revision a9444915 (ceph): Merge pull request #12167 from liewegas/wip-osdmap-encoding-jewel
- jewel: osd: condition OSDMap encoding on features
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:48 PM Bug #18128 (Resolved): unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- 12:29 PM Bug #18128 (Fix Under Review): unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- https://github.com/ceph/ceph/pull/12318
- 01:47 PM Revision 09d2d6f7 (ceph): Merge pull request #12318 from tchaikov/wip-18128
- test/ceph_crypto: do not read ceph.conf in global_init()
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:01 PM Bug #16804 (Resolved): Leak_StillReachable in mon
- 12:28 PM Revision bbe1952e (ceph): Merge pull request #12317 from xiexingguo/xxg-wip-dedup-perfnotes
- doc/dev/perf: fix dittography
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:27 PM Backport #17679 (Resolved): jewel: monitor should send monmap updates when the monmap is updated
- 12:26 PM Revision c72a2271 (ceph): test/ceph_crypto: do not read ceph.conf in global_init()
- ForkDeathTest.MD5 expect an empty output while global_init() complains
if ceph.conf is missing if 0 is passed in as t... - 12:09 PM Linux kernel client Bug #18041 (In Progress): periodically kernel crashes with CephFS
- Patch posted to mailing list and merged into ceph-client/testing branch.
- 11:58 AM Revision 1fcef74b (ceph): os/bluestore: move empty-check of osr-queue out of loop
- which is optimal.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 11:57 AM Linux kernel client Bug #18148 (Resolved): Fix unsafe d_parent handling in kcephfs
- As Zheng points out, there are several places in the kernel client that access d_parent without proper locking:
> ... - 11:45 AM Bug #17177: cephfs metadata pool: deep-scrub error "omap_digest != best guess omap_digest"
- Hi,
Not sure if it helps but I hit what I think is this issue today, not caused by fstrim this time or anything ha... - 11:10 AM Revision d9b8ebc8 (ceph): doc/dev/perf: fix dittography
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 09:47 AM rbd Backport #18137: jewel: rbd-mirror: image sync should send NOCACHE advise flag
- @Radoslaw https://github.com/ceph/ceph/pull/12280/commits/1167865e3b4c5284938cb1797ebeff15974f7260 conflicts in a way...
- 09:35 AM rgw Backport #18101 (In Progress): jewel: Add workaround for upgrade issues for older jewel versions
- 09:35 AM Revision 7db6d1d1 (ceph): rgw: add recovery procedure for upgrade to older version of jewel
- Fixes: http://tracker.ceph.com/issues/17820
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
(cherry picked from c... - 09:34 AM rgw Backport #18102 (In Progress): jewel: rgw: Unable to commit period zonegroup change
- 09:34 AM Revision 478e40a6 (ceph): rgw: fix missing master zone for a single zone zonegroup
- Fixes: http://tracker.ceph.com/issues/17364
Signed-off-by: Orit Wasserman <owasserm@redhat.com>
(cherry picked from c... - 09:09 AM rgw Backport #18107 (In Progress): jewel: multisite: failed assertion in 'radosgw-admin bucket sync s...
- 09:09 AM Revision b502b96a (ceph): rgw: RGWBucketSyncStatusManager uses existing async_rados
- RGWBucketSyncStatusManager was creating its own RGWAsyncRadosProcessor
and failing to clean it up on destruction. A r... - 09:01 AM Revision ece622db (ceph): rgw: only set CURLOPT_UPLOAD for PUT/POST requests
- when set on GET requests, curl sends a 'Transfer-encoding: chunked'
header, but doesn't do the actual encoding to ter... - 09:00 AM rgw Backport #18112 (In Progress): jewel: multisite requests failing with '400 Bad Request' with cive...
- 08:54 AM Backport #18059 (Resolved): librados: new setxattr overload breaks c++ ABI
- 08:51 AM Revision 93e67198 (ceph): ceph-disk: systemd unit must run after local-fs.target
- A ceph udev action may be triggered before the local file systems are
mounted because there is no ordering in udev. T... - 08:51 AM Revision e16d756f (ceph): ceph-disk: trigger must ensure device ownership
- The udev rules that set the owner/group of the OSD devices are racing
with 50-udev-default.rules and depending on whi... - 08:51 AM Revision e3f65937 (ceph): build/ops: restart ceph-osd@.service after 20s instead of 100ms
- Instead of the default 100ms pause before trying to restart an OSD, wait
20 seconds instead and retry 30 times instea... - 08:51 AM Revision bee7e3a9 (ceph): ceph-disk: enable --runtime ceph-osd systemd units
- If ceph-osd@.service is enabled for a given device (say /dev/sdb1 for
osd.3) the ceph-osd@3.service will race with ce... - 08:47 AM Bug #17425 (Resolved): Remove the runtime dependency on lsb_release
- 08:04 AM rgw Bug #17971: bucket acl all user write
- test Methods:
1.set a bucket to all user write permissions
2.use the postman to send a put request, in the bucket t... - 07:54 AM rbd Bug #18146 (Resolved): TestImageSync.SnapshotStress fails on bluestore
- http://qa-proxy.ceph.com/teuthology/trociny-2016-12-04_21:40:12-rbd-master---basic-mira/603854/teuthology.log
Repr... - 07:20 AM Bug #17645: "terminate called after throwing an instance of 'std::out_of_range'" in upgrade:jewel...
- The burst of "not found" in the log, right before the osd crashes suggests the file system was damaged. There is no i...
- 07:07 AM Bug #17645: "terminate called after throwing an instance of 'std::out_of_range'" in upgrade:jewel...
- ...
- 06:39 AM Revision 47e72024 (ceph): rbd: fix parameter check
- using import-diff command, the imagename must be specified.
Signed-off-by: Yankun Li <lioveni99@gmail.com> - 06:29 AM Bug #18030 (Fix Under Review): tests: unittest_pglog timeout
- https://github.com/ceph/ceph/pull/12304 abandonned because too complicated
- 05:33 AM Revision 76dfbc7b (ceph): Merge pull request #12311 from wjin/fix
- src/common: remove nonused config option
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Kefu Chai <k... - 04:49 AM Revision d68ee830 (ceph): os/bluestore: dedup omap_head, reuse nid instead
- This is faster and save us some memory as well as space.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 04:49 AM Revision 4339b426 (ceph): os/bluestore: kill deprecated get_preferred_csum_order() method
- Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn>
- 03:47 AM Bug #18092: unittest_erasure_code_shec illegal instruction
- Caused by a pclmul mis detect
gf_cpu_identify() output:
#gf_cpu_supports_intel_pclmul
#gf_cpu_supports_intel_s... - 03:45 AM Revision b8aaf697 (ceph): Merge pull request #12260 from tchaikov/wip-dh-python
- debian: apply dh_python to python-rgw also
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:01 AM Revision 4f42efbb (ceph): mailmap: change personal info
- Signed-off-by: Wei Jin <wjin.cn@gmail.com>
- 02:46 AM Revision 1b8d33dd (ceph): mon: add warn info for osds were removed from osdmap,but still kept in ...
- if the osd were removed from osdmap but still kept in crushmap.This will result in
the pg can not change to active+c... - 02:05 AM Revision 7af2e043 (ceph): src/common: remove nonused config option
- Signed-off-by: Wei Jin <wjin.cn@gmail.com>
12/04/2016
- 10:26 PM Revision ebccc3ff (ceph): rgw/rgw_file.cc: Add compat.h to allow CLOCK_MONOTONE
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 09:16 PM Backport #18144 (In Progress): hammer: make check fails when hostname not properly set, but run-m...
- 09:14 PM Backport #18144 (Rejected): hammer: make check fails when hostname not properly set, but run-make...
- https://github.com/ceph/ceph/pull/12308
- 09:03 PM devops Backport #18143 (In Progress): hammer: run-make-check.sh fails on SUSE
- 08:25 PM devops Backport #18143 (Rejected): hammer: run-make-check.sh fails on SUSE
- https://github.com/ceph/ceph/pull/12308
- 08:48 PM Bug #18127: osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- Will take another look tomorrow if no one else gets to it.
- 08:44 PM Bug #18127 (New): osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- Hmm, now I'm not so sure.
- 08:38 PM Bug #18127: osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- Simple typo, I think.
- 08:23 PM devops Bug #18142 (Resolved): run-make-check.sh fails on SUSE
- On SUSE, the run-make-check.sh script (1) tries to use yum instead of zypper and (2) fails to load rbd module.
Thi... - 03:11 PM Revision c3d35896 (ceph): Merge pull request #12163 from ovh/wip-throttle-get-started-perf-counter
- common: Add throttle_get_started perf counter
Reviewed-by: Sage Weil <sage@redhat.com> - 03:11 PM Revision 6d4ad15b (ceph): Merge pull request #12285 from liewegas/wip-bluestore-allocator
- os/bluestore: use bitmap allocator for bluefs
Reviewed-by: Varada Kari <varada.kari@sandisk.com> - 03:10 PM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- /a/sage-2016-12-03_19:34:03-rados-wip-sage-testing---basic-smithi/599494
- 02:53 PM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- /a/sage-2016-12-03_19:33:05-rados-master---basic-smithi/599285
- 03:09 PM Bug #18140 (Resolved): get_onode oid #2:afcea40e:::benchmark_data_smithi099_10837_object2430:head...
- ...
- 03:08 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- /a/sage-2016-12-03_19:34:03-rados-wip-sage-testing---basic-smithi/599343
- 02:49 PM Bug #18126: Illegal instruction from Messenger::create -> std::random_device::_M_getval
- /a/sage-2016-12-03_19:33:05-rados-master---basic-smithi/599046
- 03:07 PM Bug #18139 (Resolved): LibRadosList.EnumerateObjects failure
- ...
- 03:01 PM Bug #18138 (Can't reproduce): OSD hits EAGAIN on pthread_create
- /a/sage-2016-12-03_19:34:03-rados-wip-sage-testing---basic-smithi/599254...
- 02:58 PM Revision c55396a9 (ceph): Merge pull request #9714 from wido/mirror-docs-fix
- doc: Small styling fix to mirror documentation
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:56 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- quick way to tell if this is (probably) the root cause:
grep ceph-objectstore-tool teuthology.log
verify that the... - 02:55 PM Revision 471e6294 (ceph): Merge pull request #12299 from Adirl/fix_max_values
- msg/async/rdma: set correct value to memory manager
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:24 PM Backport #18135 (In Progress): jewel: make check fails when hostname not properly set, but run-ma...
- 02:10 PM Backport #18135 (Resolved): jewel: make check fails when hostname not properly set, but run-make-...
- https://github.com/ceph/ceph/pull/12302
- 02:15 PM Revision 5400673d (ceph): tests: check hostname --fqdn sanity before running cmake check
- References: http://tracker.ceph.com/issues/18135
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 02:13 PM Revision bd96c31c (ceph): tests: check hostname --fqdn sanity before running make check
- Fixes: http://tracker.ceph.com/issues/18134
Signed-off-by: Nathan Cutler <ncutler@suse.com>
(cherry picked from commi... - 02:12 PM rbd Backport #18137 (Resolved): jewel: rbd-mirror: image sync should send NOCACHE advise flag
- https://github.com/ceph/ceph/pull/16285
- 02:10 PM rbd Backport #18136 (Resolved): jewel: qa: rbd-mirror workunit false negative when waiting for image ...
- https://github.com/ceph/ceph/pull/12425
- 02:09 PM Bug #18134 (Pending Backport): make check fails when hostname not properly set, but run-make-chec...
- 01:38 PM Revision 37ec0e14 (ceph): msg/async/rdma: set correct value to memory manager
- set the correct max_send_wr and max_recv_wr
print log messages accordingly
Change-Id: I97a562bc994f14b87724fcf84baca... - 01:28 PM Revision fdc593e3 (ceph): src/test/CMakeLists.txt: Exclude test on HAVE_BLKID
- - Since ceph_test_get_blkdev_size really depends on blkid stuff.
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 12:24 PM Revision f502763d (ceph): Merge pull request #12270 from yuyuyu101/wip-rdma-polling
- msg/async/rdma: event polling thread can block on event
Reviewed-by: Adir lev <adirl@mellanox.com> - 12:21 PM Revision 78b03e3a (ceph): Merge pull request #11987 from Liuchang0812/patch-2
- doc: Update layout.rst, move commands to CODE block
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Alfredo D... - 10:46 AM Revision 4f2f9199 (ceph): Merge pull request #1290 from SUSE/wip-18014-jewel
- thrashosds: try ceph-objectstore-tool for 10 minutes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:33 AM Bug #18030 (In Progress): tests: unittest_pglog timeout
- 08:55 AM Revision cec7441e (ceph): thrashosds: try ceph-objectstore-tool for 10 minutes
- If ceph-objectstore-tool binary is not present, it's likely because we're in
the middle of an upgrade. Do not try to ... - 02:27 AM Revision 9bf51f9f (ceph): ReplicatedPG: add return value to RepGather
- Now that repops can represent an error, we need to remember
the error code so that we can reply to waiting_for_* mess... - 02:08 AM Revision 5c5c117a (ceph): ReplicatedPG::record_write_error: send only the flags requested by the op
- This isn't really important, but it's nice to be consistent with
OSD::reply_op_error. Yet another reason to do away ... - 12:34 AM Revision d73be200 (ceph): Merge pull request #12297 from SUSE/wip-18134
- tests: check hostname --fqdn sanity before running make check
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:05 AM Revision 6b89fac4 (ceph): ReplicatedPG: always send the ack with the commit
- This was always a pretty silly concept and it has gotten in
the way of something else.
Signed-off-by: Samuel Just <s... - 12:05 AM Revision 7c97cd21 (ceph): ReplicatedPG: allow repops to apply with commit
- Up to now, the repop machinery depended on all repops commiting and
applying in order. For MOSDPGUpdateLogMissing op... - 12:05 AM Revision c0c7f926 (ceph): ReplicatedPG: add debugging to EINVAL returns
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 12:05 AM Revision ef376c97 (ceph): ReplicatedPG::submit_log_entries: fill in repop->v
- This way, we can deal with waiting_for_commit appropriately.
Also, add more debugging to new_repop and already_*.
Si... - 12:05 AM Revision 89fd030b (ceph): OSD::init_op_flags: don't consider PING to be a write
- Signed-off-by: Samuel Just <sjust@redhat.com>
12/03/2016
- 10:37 PM Bug #18134 (Fix Under Review): make check fails when hostname not properly set, but run-make-chec...
- https://github.com/ceph/ceph/pull/12297
- 10:28 PM Bug #18134 (Resolved): make check fails when hostname not properly set, but run-make-check.sh doe...
- On a machine where "hostname --fqdn" fails, several tests in "make check" also fail.
This is easily fixed by addin... - 10:37 PM Revision dcfff612 (ceph): tests: check hostname --fqdn sanity before running make check
- Fixes: http://tracker.ceph.com/issues/18134
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 09:59 PM devops Backport #18133: jewel: undefined references when building unit tests with --with-xio
- h3. description
This kind of thing happens when linking several of the unit tests. As far as I can tell, it only h... - 09:53 PM devops Backport #18133 (Resolved): jewel: undefined references when building unit tests with --with-xio
- https://github.com/ceph/ceph/pull/12296
(Note that this backport is not a cherry-pick because master uses cmake an... - 09:57 PM Revision f47213cb (ceph): build/ops: fix undefined crypto references with --with-xio
- Only with --with-xio, RPM build fails due to undefined references to various
symbols starting with "PK11_" in ./.libs... - 07:07 PM Revision 6776fab0 (ceph): rgw/rgw_main.cc: fix parenteses and function result
- - The function in the macro parameter is expected to return -1 i
on error and not type(bool).
So reorganize the... - 06:47 PM Revision dc68f2fa (ceph): test: use uname -m vs. uname -p in test-erasure-code-plugins.sh
- uname -p is not portable and returns unknown on Alpine
Signed-off-by: John Coyle <dx9err@gmail.com> - 05:50 PM Revision 6cb1ed48 (ceph): rbd-mirror: make 'rbd mirror image resync' work after split-brain
- Fixes: http://tracker.ceph.com/issues/18051
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 05:37 PM Revision 7c078eda (ceph): qa/workunits/rbd: test_status_in_pool_dir: explicitly check grep return...
- Otherwise, it does not work as supposed to work in statements like below:
set -e
test_status_in_pool_dir ... && ..... - 05:37 PM Revision cccca67d (ceph): rbd-mirror: split-brain issues should be clearly visible in mirror status
- Fixed: http://tracker.ceph.com/issues/16991
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 12:52 PM Backport #18132: hammer: ReplicatedBackend::build_push_op: add a second config to limit omap entr...
- h3. original description
In ceph deployments with large numbers of objects (typically generated by use of radosgw ... - 12:52 PM Backport #18132 (New): hammer: ReplicatedBackend::build_push_op: add a second config to limit oma...
- 07:51 AM Backport #18132 (Resolved): hammer: ReplicatedBackend::build_push_op: add a second config to limi...
- https://github.com/ceph/ceph/pull/12417
- 12:50 PM Revision 8a774cc2 (ceph): msg/simple/Pipe: handle addr decode error
- Fixes: http://tracker.ceph.com/issues/18072
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 2f5... - 12:49 PM Bug #15368: "api_misc: [ FAILED ] LibRadosMiscConnectFailure.ConnectFailure"
- Sage, are you saying that http://tracker.ceph.com/issues/16091 should be backported to jewel? (The description of thi...
- 10:24 AM Backport #18108 (In Progress): jewel: msg/simple/Pipe: error decoding addr
- 09:57 AM Revision 4d9a28d2 (ceph): Merge pull request #12067 from SUSE/wip-17953-jewel
- jewel: mon: OSDMonitor: only reject MOSDBoot based on up_from if inst matches
Reviewed-by: Samuel Just <sjust@redhat... - 07:03 AM Revision 237bedb3 (ceph): ec-data-pool: enable the hacky_overwrites flag
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 02:39 AM Revision 177bae75 (ceph): Merge pull request #12282 from liewegas/wip-bluestore-dump
- os/bluestore: clean up Allocator::dump
- 02:29 AM Revision 263cbc29 (ceph): Merge pull request #12287 from liewegas/wip-store-kv-stats
- kv: dump rocksdb stats
- 12:38 AM Linux kernel client Bug #18130: soft lockups in ceph.ko
- looks like our code can't handle iov_iter of type ITER_PIPE
12/02/2016
- 11:56 PM Revision 6f0dafcb (ceph): ReplicatedPG::do_op: wait_for_commit even for results < 0 entries
- This way, the replies come back in order and we don't expose
uncommitted results.
Signed-off-by: Samuel Just <sjust@... - 11:56 PM Revision 32bd4562 (ceph): ECBackend::try_state_to_reads: fix debug spacing
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 11:56 PM Revision 77506161 (ceph): ECBackend: ops must consistently use or not use the cache
- If the state is flipped, ops already in the pipeline need to
continue to maintain it.
Signed-off-by: Samuel Just <sj... - 09:40 PM Revision e00fe48b (ceph): ReplicatedPG::_scrub_finish: check stats for ec overwrites pools
- This should work fine now that we are doing an update-in-place
with rollback information off to the side.
Signed-off... - 09:40 PM Revision 4d371cc2 (ceph): ECBackend::try_state_to_reads: assert that rmw ops require hacky_overwr...
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:40 PM Revision 90011543 (ceph): ECTransaction: fix projected_size for delete->create in get_write_plan
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:40 PM Revision 9ee54723 (ceph): ECTransaction::get_write_plan: don't create empty to_read entries
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:40 PM Revision 0597309d (ceph): ReplicatedPG: merge apply_ctx_scrub_stats into apply_stats
- The only way the two aren't called essentially atomically is when the
ECBackend needs to delay a write for rmw. In s... - 09:39 PM Revision e2a820e6 (ceph): Merge pull request #12284 from ceph/wip-cmake-args
- build: dump env during build
Reviewed-by: Dan Mick <dmick@redhat.com> - 09:16 PM Revision 3a6f73e9 (ceph): osd/PG: distinct down state instead of down+peering
- When we declare a PG down, move to a distinct down state
(!= down+peering) so that we know peering completed (and
con... - 08:48 PM Revision 4b8b0c08 (ceph): Merge pull request #12224 from yehudasa/wip-rgw-list-all
- rgw/rgw_rados: do not omap_getvals with (u64)-1 max (updated)
also approve, passed teuthology (many false positives i... - 08:30 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- BTW as you might have guessed, the crash occurred for me when I added a metadata server to a fresh cluster. Then ceph...
- 08:28 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- I'm a bit puzzled why the last insert fails:...
- 07:24 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- I see MDSMonitor::prepare_beacon() proceed through the:...
- 07:05 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- Valgrind:...
- 07:00 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- w/ debugging symbols:...
- 06:52 PM CephFS Bug #16771: mon crash in MDSMonitor::prepare_beacon on ARM
- Hi,
I can confirm this issue on armhf; I was initially having it with 10.1.2-0ubuntu1 from xenial on a scaleway C1... - 08:29 PM Bug #15628 (Can't reproduce): segfault at 0 ip sp error 4 in libtcmalloc.so.4.1.2
- 08:28 PM Bug #15368: "api_misc: [ FAILED ] LibRadosMiscConnectFailure.ConnectFailure"
- https://github.com/ceph/ceph/pull/11128 should help
- 08:25 PM Revision 20439242 (ceph): Merge pull request #1297 from ceph/wip-14.04
- suites/rados: s/trusty/"14.04"/
- 08:13 PM Revision fd022882 (ceph): Merge pull request #12187 from Jing-Scott/dev/slave-master-sync-info
- rgw: metadata sync info should be shown at master zone of slave zoneg…
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 08:09 PM Revision bbb26153 (ceph): Merge pull request #1276 from ceph/no-btrfs-on-hammer
- rados: remove btrfs tests; use xfs instead
- 07:55 PM Revision 2cee58a4 (ceph): Merge pull request #1298 from ceph/wip-pre-single-major-branch
- krbd/unmap: pre-single-major is now 3.12.z
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 07:22 PM Revision d194db82 (ceph): OSDMonitor: only reject MOSDBoot based on up_from if inst matches
- If the osd actually restarts, there is no guarrantee that the epoch will
advance past up_from. If the inst is differ... - 07:10 PM Revision 9fda9ce0 (ceph): kv/RocksDBStore: dump extended stats
- Signed-off-by: Varada Kari <varada.kari@sandisk.com>
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 07:10 PM Revision 43c59902 (ceph): osd: dump kv stats for ObjectStores (if any)
- Signed-off-by: Sage Weil <sage@redhat.com>
Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com> - 07:10 PM Revision e292905e (ceph): os/bluestore: dump kv stats
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:05 PM Revision b97393cf (ceph): ceph.spec: dump env during build
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:05 PM Revision 06321714 (ceph): debian/rules: dump env during build
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:57 PM rbd Feature #18123 (Fix Under Review): Need CLI ability to add, edit and remove omap values with bina...
- *PR*: https://github.com/ceph/ceph/pull/12286
- 01:59 PM rbd Feature #18123 (Resolved): Need CLI ability to add, edit and remove omap values with binary keys
- RBD stores several omap keys with embedded null characters due to encoding string lengths within the key. When one or...
- 06:33 PM CephFS Bug #18131: ceph-fuse not clearing setuid/setgid bits on chown
- The tests I'm mainly concered with are the pjd.sh tests in those. The rest seem to be transient failures of one sort ...
- 06:29 PM CephFS Bug #18131 (Resolved): ceph-fuse not clearing setuid/setgid bits on chown
- I had some test failures that showed up in my most recent fs suite run here:
http://pulpito.ceph.com/jlayton-... - 06:21 PM Revision a9c99fd1 (ceph): kv: make kvdb can print itself statistics.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 06:20 PM Linux kernel client Bug #18130 (Resolved): soft lockups in ceph.ko
- While running xfstests vs. a ceph vstart cluster, I hitting softlockups in test generic/095. Looks like a we're cycli...
- 05:36 PM Bug #18022: tests: osd-crush.sh sometime fails
- This is *different* from http://tracker.ceph.com/issues/17919 because it happens in a context where retrying should n...
- 05:35 PM Bug #18022: tests: osd-crush.sh sometime fails
- https://jenkins.ceph.com/job/ceph-pull-requests/15255/...
- 05:30 PM Bug #18022 (Duplicate): tests: osd-crush.sh sometime fails
- 05:33 PM Bug #17919: tests: test/mon/osd-crush.sh is racy
- https://github.com/ceph/ceph/pull/12016
- 05:28 PM Bug #17919: tests: test/mon/osd-crush.sh is racy
- 05:14 PM Revision 0a60d358 (ceph): Merge pull request #12245 from ifed01/wip-fix-global-init-refcount
- test/fio: fix global CephContext life cycle
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 05:13 PM Bug #17889 (Pending Backport): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- wait two weeks before merging the backport
- 05:12 PM Revision bbd97ce3 (ceph): Merge pull request #12241 from dachary/wip-17889-systemd-order
- ceph-disk: enable --runtime ceph-osd systemd units
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Nathan Cutl... - 05:04 PM Revision bb186f24 (ceph): os/bluestore/BlueFS: default to bitmap allocator
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:52 PM Revision 462110a0 (ceph): os/bluestore: dump allocator state on allocation failure
- This is probably noisy for an *actual* ENOSPC, but the OSD should
actually prevent those from happening in general, a... - 04:51 PM CephFS Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- @jcsp did you run into this before ?
- 04:51 PM CephFS Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- 04:50 PM CephFS Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- https://jenkins.ceph.com/job/ceph-pull-requests/14992/console
exact same error - 04:28 PM Bug #18128: unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- It can easily be repeated with...
- 04:28 PM Bug #18128: unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- @Kefu could these intermittent failures be a side effect of the following ? Maybe not directly but it could have ampl...
- 04:19 PM Bug #18128: unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- https://jenkins.ceph.com/job/ceph-pull-requests/15202
- 04:16 PM Bug #18128: unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- https://jenkins.ceph.com/job/ceph-pull-requests/15158/console
- 04:07 PM Bug #18128 (Resolved): unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
https://jenkins.ceph.com/job/ceph-pull-requests/15152/...- 04:24 PM rgw Bug #18106 (Fix Under Review): radosgw-admin-data-sync task fails with "object not deleted from d...
- PR: https://github.com/ceph/ceph/pull/12283.
- 11:58 AM rgw Bug #18106 (In Progress): radosgw-admin-data-sync task fails with "object not deleted from destin...
- 04:20 PM Bug #18121 (Duplicate): unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- 12:09 PM Bug #18121 (Duplicate): unittest_ceph_crypto fails ForkDeathTest.MD5 (intermitent)
- https://jenkins.ceph.com/job/ceph-pull-requests/15202/consoleText...
- 04:16 PM Revision 6d171887 (ceph): Merge pull request #12207 from jdurgin/wip-librados-setxattr-overload-j...
- librados: remove new setxattr overload to avoid breaking the C++ ABI
Reviewed-by: Sage Weil <sage@redhat.com> - 04:10 PM Revision d009a6cb (ceph): Merge pull request #12075 from ceph/wip-rgw-zonegroup-config
- rgw: fix for unsafe change of rgw_zonegroup
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:05 PM rbd Cleanup #17127 (Pending Backport): rbd-mirror: image sync should send NOCACHE advise flag
- 02:54 PM rbd Cleanup #17127 (Fix Under Review): rbd-mirror: image sync should send NOCACHE advise flag
- 02:54 PM rbd Cleanup #17127: rbd-mirror: image sync should send NOCACHE advise flag
- PR: https://github.com/ceph/ceph/pull/12280
- 11:41 AM rbd Cleanup #17127 (In Progress): rbd-mirror: image sync should send NOCACHE advise flag
- 04:05 PM rbd Bug #18048 (Pending Backport): qa: rbd-mirror workunit false negative when waiting for image dele...
- 04:04 PM Revision 98709d9f (ceph): Merge pull request #12280 from trociny/wip-17127
- rbd-mirror: set SEQUENTIAL and NOCACHE advise flags on image sync
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:01 PM Revision 3121892e (ceph): os/bluestore: dump allocator state at lowest debug level
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:00 PM Revision 9911f9f6 (ceph): os/bluestore: drop unused ostream arg to Allocator::dump
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:54 PM RADOS Bug #17743 (Fix Under Review): ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa...
- https://github.com/ceph/ceph/pull/12281
- 03:21 PM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- https://jenkins.ceph.com/job/ceph-pull-requests/15166/console...
- 02:15 PM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- https://jenkins.ceph.com/job/ceph-pull-requests/15167/console...
- 01:40 PM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- repeating the failure as instructed by Kefu and trying to get a core but cannot (3a9bcaa4aa6042587886c0eaae0ce4eeeb8f...
- 10:58 AM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- Updating the title so that it matches when looking for test_objectstore_memstore.sh failures
- 03:36 PM rbd Cleanup #18125 (In Progress): rbd-cli: no warning message when enable/disable mirroring option th...
- 02:10 PM rbd Cleanup #18125 (Resolved): rbd-cli: no warning message when enable/disable mirroring option that ...
- 1. rbd mirror pool enable <PoolName> pool :- Doesn't throw a warning message when the pool is already enabled
2. ... - 03:36 PM rgw Bug #17888 (Pending Backport): rgw:fix for deleting objects name beginning and ending with unders...
- please backport both:
https://github.com/ceph/ceph/pull/11982
https://github.com/ceph/ceph/pull/12262 - 03:35 PM Revision 4951fbc5 (ceph): Merge pull request #12262 from cbodley/wip-17888
- rgw: fix for versioned delete_multi_object
ftw - 03:28 PM Revision 054fafad (ceph): rgw: make RGWLocalAuthApplier::is_admin_of() aware about system users.
- Fixes: http://tracker.ceph.com/issues/18106
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com> - 03:11 PM Bug #18030: tests: unittest_pglog timeout
- ...
- 01:45 PM Bug #18030: tests: unittest_pglog timeout
- https://jenkins.ceph.com/job/ceph-pull-requests/15177/console...
- 02:58 PM rbd Bug #18115: partition func should be enabled When load nbd.ko for rbd-nbd
- PR: https://github.com/ceph/ceph/pull/12259
- 01:00 AM rbd Bug #18115 (Resolved): partition func should be enabled When load nbd.ko for rbd-nbd
- We are using rbd-nbd as our raw block device function. For different kernel versions, some set max_part as 0(kernel 4...
- 02:57 PM Bug #18093 (Resolved): osd enomem with bluestore
- 02:57 PM Revision 2630df76 (ceph): Merge pull request #12256 from liewegas/wip-18093
- osd: fix memory leak from EC write workload
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:56 PM Revision 835e755a (ceph): rados/thrash/workloads: shorten rados bench a bit
- I hit ENOSPC during thrashing on one run.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:53 PM Bug #18127 (Resolved): osd/osd_types.h: 2978: FAILED assert(newhead >= tail
- ...
- 02:49 PM Bug #18126 (Resolved): Illegal instruction from Messenger::create -> std::random_device::_M_getval
- ...
- 02:37 PM Revision 890692d0 (ceph): suites/rados: s/trusty/"14.04"/
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:06 PM rbd Cleanup #16985 (Resolved): Improve error reporting from "rbd feature enable/disable"
- 02:05 PM Revision 350a6601 (ceph): Merge pull request #12238 from gaurav36/bug-rbd-feature-enable-error
- librbd: enabling/disabling rbd feature should report missing dependency
Reviewed-by: Jason Dillaman <dillaman@redhat... - 02:01 PM Revision fbccd1e8 (ceph): Merge pull request #12195 from trociny/wip-qa-rbd-wait_for_image_present
- qa/workunits/rbd: use image id when probing for image presence
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:59 PM Bug #18124: osd-scrub-snaps.sh intermittent failures
- @David did you see that one before ?
- 01:59 PM Bug #18124 (Can't reproduce): osd-scrub-snaps.sh intermittent failures
- https://jenkins.ceph.com/job/ceph-pull-requests/15174/console...
- 01:18 PM CephFS Bug #18118 (Duplicate): multimds: mds stuck in up:creating
- seems like dup of http://tracker.ceph.com/issues/18066. MDSRank::creating_done did not get called. Osd op with tid ==...
- 03:05 AM CephFS Bug #18118 (Duplicate): multimds: mds stuck in up:creating
- Seen here:
http://pulpito.ceph.com/pdonnell-2016-12-02_01:20:51-multimds-master-testing-basic-mira/594001/
mds ... - 12:34 PM rgw Bug #17076: AWS S3 Version 4 signatures fail sometimes.
- Hi, is the fix (https://github.com/ceph/ceph/pull/10919) going to be backported for 10.2.4 point release?
- 12:34 PM Revision cf93b482 (ceph): Merge pull request #11942 from wjwithagen/wip-wjw-freebsd-boost
- do_freebsd.sh: Build with SYSTEM Boost on FreeBSD
Reviewed-by: Kefu Chai <kchai@redhat.com> - 12:32 PM Revision 8c935170 (ceph): common: Add throttle_get_started perf counter
- This change adds 'get_started' performance counter which
is increased at the beginning of Throttle::get() call,
befor... - 12:27 PM Backport #18116 (In Progress): jewel: common osd: Improve scrub analysis, list-inconsistent-obj o...
- 01:24 AM Backport #18116 (Resolved): jewel: common osd: Improve scrub analysis, list-inconsistent-obj outp...
- https://github.com/ceph/ceph/pull/13146
- 12:13 PM rbd Bug #18122 (Can't reproduce): unittest_journal TestJournalTrimmer.RemoveObjectsWithOtherClient (i...
- Running make check manually...
- 11:55 AM Bug #10405: osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill_targets(peer))
- 11:13 AM Bug #10405: osd crashes on osd/ReplicatedPG.cc: 9025: FAILED assert(is_backfill_targets(peer))
- I just had this assert on Hammer, 0.94.6. It was reproducible on every _mark_unfound_lost revert_. Due to revert not ...
- 11:53 AM Revision e476b80a (ceph): os/filestore/chain_xattr.h:uses ENODATA, so include compat.h
- - Trying to be able to build without ENODATA in /usr/include/errno.h
And here we use ENODATA for testing attribute... - 11:38 AM Revision 1167865e (ceph): rbd-mirror: set SEQUENTIAL and NOCACHE advise flags on image sync
- Fixes: http://tracker.ceph.com/issues/17127
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 11:10 AM Backport #18120 (Resolved): jewel: fixed the issue when --disable-server, compilation fails
- https://github.com/ceph/ceph/pull/12239
- 10:56 AM Bug #16014: test fails due to "The UNIX domain socket path"
- The source of the problem is http://tracker.ceph.com/issues/15249
- 10:42 AM Revision a4b141db (ceph): Merge pull request #1296 from dachary/wip-ceph-coverage-jewel
- upgrade: ceph-test is needed for ceph-coverage
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com> - 10:42 AM Revision aae55224 (ceph): Merge pull request #1295 from dachary/wip-16506-ceph-coverage
- upgrade: ceph-test is needed for ceph-coverage
Reviewed-by: Abhishek Lekshmanan <abhishek@suse.com> - 10:20 AM Revision 89248e19 (ceph): jewel: fixed the issue when --disable-server, compilation fails.
- If cannot disable-server, the user has to always compile backend storage part,
even only want to compile the client. ... - 10:11 AM Revision f1b9618b (ceph): Cmake/FreeBSD: use the SYSTEM_BOOST
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
- 10:07 AM Bug #18046: filestore: sync_entry timed out cause osd crash
- we change vm.zone_reclaim_mode=0, and do the same tests, it doesn't turn up until now
- 09:33 AM Revision 78848fef (ceph): upgrade/infernalis-client-x: ceph-test is needed for ceph-coverage
- Do not exclude the ceph-test package otherwise the ceph-coverage
executable is not installed.
Fixes: http://tracker.... - 09:32 AM CephFS Bug #18119: mds: check and get latest current logsegment to avoid trimming logsegment crashing
- https://github.com/ceph/ceph/pull/12277
The fix here is to check whether mdr->ls/mut->ls is expired or not in call... - 09:27 AM CephFS Bug #18119 (Closed): mds: check and get latest current logsegment to avoid trimming logsegment cr...
- ...
- 09:31 AM Revision 791de76c (ceph): upgrade: ceph-test is needed for ceph-coverage
- Do not exclude the ceph-test package otherwise the ceph-coverage
executable is not installed.
Fixes: http://tracker.... - 09:29 AM Bug #16506: "line 16: exec: ceph-coverage: not found" in upgrade:client-upgrade-jewel-distro-basi...
- https://github.com/ceph/ceph-qa-suite/pull/1295 fixes it for real in master and the corresponding jewel backport is h...
- 09:27 AM Revision 81224945 (ceph): upgrade: ceph-test is needed for ceph-coverage
- Do not exclude the ceph-test package otherwise the ceph-coverage
executable is not installed.
Fixes: http://tracker.... - 09:01 AM Revision b168c262 (ceph): Merge pull request #12267 from dachary/wip-17904-jewel
- jewel: Error EINVAL: removing mon.a at 172.21.15.16:6789/0, there will be 1 monitors
Reviewed-by: Samuel Just <sjust... - 08:54 AM Backport #17904: jewel: Error EINVAL: removing mon.a at 172.21.15.16:6789/0, there will be 1 moni...
- https://github.com/ceph/ceph/pull/11999 was merged into jewel-next by accident. This will lead to duplicate commits w...
- 08:26 AM Revision 7106f426 (ceph): FileStore::_do_fiemap: do not reference fiemap after it is freed
- `last` points to fiemap::fm_extends[n], and if fiemap gets freed, we can
not reference any of its fieldis. so we coul... - 06:48 AM Revision 3a9bcaa4 (ceph): Merge pull request #12209 from tchaikov/wip-enable-unittest_dns_resolve
- test: enable unittest_dns_resolve
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:33 AM Revision 311869f2 (ceph): msg/async/rdma: make rdma dispatcher can sleep if inactive enough
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 06:23 AM rbd Bug #18068: diff calculate can hide parent extents when examining first snapshot in clone
- Jason, I looked at the hammer backport but the whole file src/librbd/DiffIterate.cc appears to be missing in hammer.
- 05:51 AM Revision f4b635f0 (ceph): test: enable unittest_dns_resolve
- guess this test was missed when we were moving to cmake. let's re-enable
it!
Signed-off-by: Kefu Chai <kchai@redhat.... - 03:39 AM Revision d6417f4c (ceph): PGTransaction,ReplicatedPG: clarify handling of noop operations
- The offending transaction was [call rbd.copyup,delete] on a non-existent
object. PGTransaction incorrectly ended up ... - 02:57 AM rbd Bug #18117 (Won't Fix): hammer: attempting to remove a protected snapshot from a clone will disso...
- Given a clone with a single protected snapshot, flatten the clone to dissociate the HEAD revision from the parent ima...
- 01:46 AM Revision d2f8fb4a (ceph): Merge pull request #12263 from Adirl/fix_max_buffers
- msg/async/rdma: don't use more buffers than what device capabilities …
Reviewed-by: Haomai Wang <haomai@xsky.com> - 01:23 AM Bug #18114 (Pending Backport): common osd: Improve scrub analysis, list-inconsistent-obj output a...
- 12:55 AM Bug #18114 (Resolved): common osd: Improve scrub analysis, list-inconsistent-obj output and osd-s...
- https://github.com/ceph/ceph/pull/9613
- 12:51 AM Revision d32d70b7 (ceph): systemd: add ceph-fuse service file
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
- 12:51 AM Bug #18113: Don't lose deep-scrub information
- https://github.com/ceph/ceph/pull/12268
- 12:37 AM Bug #18113 (Resolved): Don't lose deep-scrub information
We'd like to not lose deep-scrub information when more frequent scrub happens.- 12:39 AM Revision 1515bd0e (ceph): Merge pull request #12140 from iain-buclaw-sociomantic:pybind-aioexec
- python-rados: implement new aio_execute
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:32 AM Revision fd432fee (ceph): test/pybind: Add tests for aio_execute
- Signed-off-by: Iain Buclaw <iain.buclaw@sociomantic.com>
- 12:32 AM Revision 7aa80fd0 (ceph): pybind: Fix comment for exec in Ioctx
- Signed-off-by: Iain Buclaw <iain.buclaw@sociomantic.com>
- 12:14 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> Zheng Yan wrote:
>
> >
> > If we only want inode, it's better to use getattr to validate d...
12/01/2016
- 11:58 PM CephFS Bug #17656: cephfs: high concurrent causing slow request
- william sheng wrote:
> Greg Farnum wrote:
> > Just from the description it sounds like we're backing up while the M... - 11:30 PM Bug #18002 (Resolved): kstore failed in rados run
- 11:29 PM Bug #18105 (Fix Under Review): bluestore: rocksdb preconditioning does not seem to work
- https://github.com/ceph/ceph/pull/12265
- 05:36 PM Bug #18105 (Resolved): bluestore: rocksdb preconditioning does not seem to work
- I think the problem is that we do it on mkfs, but rocksdb doesn't populate the recycle list on restart.
- 10:21 PM Revision c362ed28 (ceph): Merge pull request #1294 from ceph/wip-17960-master
- Removed xenial + Excluded librgw2
- 10:21 PM Revision 57e0a674 (ceph): upgrade/jewel-x/point-to-point: avoid xenial
- Xenial has newer packages in the distro and we want to
avoid fragile install instructions to avoid them.
Signed-off-... - 10:10 PM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- For the record, the pull requests that need backporting are:
* https://github.com/ceph/ceph/pull/12136
* https://... - 07:17 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- Instead of removing the enable/disable from ceph-disk, it is enough to **enable --runtime** so that it "does not star...
- 06:31 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- The problem is exactly the opposite of what I thought: since ceph-disk@.service already starts the matching ceph-osd@...
- 10:02 PM Bug #17960 (Resolved): Unresolved dependency (radosgw : Depends: librgw2 (= 10.2.0-1xenial))
- https://github.com/ceph/ceph-qa-suite/pull/1294
- 05:00 PM Bug #17960: Unresolved dependency (radosgw : Depends: librgw2 (= 10.2.0-1xenial))
- also in http://qa-proxy.ceph.com/teuthology/yuriw-2016-12-01_16:39:40-upgrade:jewel-x-master-distro-basic-vps/593558/...
- 09:57 PM Revision a0d183bc (ceph): Merge pull request #1284 from ceph/jewel-name-limits
- drop broken name length config args
- 09:56 PM Revision 5fa23a3b (ceph): Merge pull request #1292 from ceph/jewel-avoid-xenial
- rados: avoid xenial for upgrade tests
- 09:45 PM Revision 00de0140 (ceph): mon: MonmapMonitor: drop unnecessary 'goto' statements
- Signed-off-by: Joao Eduardo Luis <joao@suse.de>
(cherry picked from commit 20dcb597e35e6961db81831facefbe22cecddec3) - 09:45 PM Revision 25f1b390 (ceph): mon: MonmapMonitor: return success when monitor will be removed
- Fixes: http://tracker.ceph.com/issues/17725
Signed-off-by: Joao Eduardo Luis <joao@suse.de>
(cherry picked from comm... - 09:19 PM Backport #18109 (In Progress): hammer: msg/simple/Pipe: error decoding addr
- 09:17 PM Backport #18109 (Resolved): hammer: msg/simple/Pipe: error decoding addr
- https://github.com/ceph/ceph/pull/12266
- 09:19 PM Revision 92de2fd9 (ceph): msg/simple/Pipe: handle addr decode error
- Fixes: http://tracker.ceph.com/issues/18072
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 2f5... - 09:18 PM rgw Backport #18112 (Resolved): jewel: multisite requests failing with '400 Bad Request' with civetwe...
- https://github.com/ceph/ceph/pull/12313
- 09:18 PM rbd Backport #18111 (Resolved): hammer: diff calculate can hide parent extents when examining first s...
- https://github.com/ceph/ceph/pull/12446
- 09:18 PM rbd Backport #18110 (Resolved): jewel: diff calculate can hide parent extents when examining first sn...
- https://github.com/ceph/ceph/pull/12322
- 09:17 PM Backport #18108 (Resolved): jewel: msg/simple/Pipe: error decoding addr
- https://github.com/ceph/ceph/pull/12291
- 09:17 PM rgw Backport #18107 (Resolved): jewel: multisite: failed assertion in 'radosgw-admin bucket sync status'
- https://github.com/ceph/ceph/pull/12314
- 08:46 PM rgw Bug #18106: radosgw-admin-data-sync task fails with "object not deleted from destination zone"
- from the 'destination zone', rgw.client.1.log:...
- 07:16 PM rgw Bug #18106 (Resolved): radosgw-admin-data-sync task fails with "object not deleted from destinati...
- From http://qa-proxy.ceph.com/teuthology/teuthology-2016-11-28_17:05:19-rgw-master---basic-smithi/583185/teuthology.l...
- 08:12 PM CephFS Feature #17980: MDS should reject connections from OSD-blacklisted clients
- Related to http://tracker.ceph.com/issues/9754?
- 07:50 PM Revision 828ac749 (ceph): Merge pull request #11999 from Abhishekvrshny/wip-17904-jewel
- jewel: Error EINVAL: removing mon.a at 172.21.15.16:6789/0, there will be 1 monitors
Reviewed-by: Samuel Just <sjust... - 07:42 PM Bug #17859 (Resolved): filestore: can get stuck in an unbounded loop during scrub
- 07:42 PM Backport #17915 (Resolved): jewel: filestore: can get stuck in an unbounded loop during scrub
- 07:25 PM Revision 9a478a8d (ceph): rgw: print is_admin as int instead of __u8
- RGWUserInfo::admin is a __u8, so printing it directly results in output
like '\00'. this causes some tools to interpr... - 07:19 PM Revision dc5a8df7 (ceph): msg/async/rdma: don't use more buffers than what device capabilities allow
- Change-Id: I6df7dd1a4d871b4dca55e784969ff459bebc6a86
Signed-off-by: Avner BenHanoch <avnerb@mellanox.com> - 07:13 PM Revision 53b3f6bf (ceph): Merge pull request #12261 from liewegas/wip-store-rename-test
- ceph_test_objectstore: fix Rename test
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 07:08 PM Revision be5c8282 (ceph): Merge pull request #12001 from dachary/wip-17915-jewel
- jewel: filestore: can get stuck in an unbounded loop during scrub
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:05 PM rgw Bug #17965 (Resolved): rgw: lifecycle worker thread does not set lock duration
- 06:57 PM rgw Bug #17965: rgw: lifecycle worker thread does not set lock duration
- https://github.com/ceph/ceph/pull/12231
- 07:00 PM Revision 59022a21 (ceph): Merge pull request #12231 from yehudasa/wip-17965
- rgw: set duration for lifecycle lease
- 06:57 PM rgw Bug #17888 (Fix Under Review): rgw:fix for deleting objects name beginning and ending with unders...
- 06:57 PM rgw Bug #17888: rgw:fix for deleting objects name beginning and ending with underscores of one bucket...
- this broke a couple s3tests: s3tests.functional.test_s3.test_versioning_multi_object_delete and test_versioning_multi...
- 06:55 PM Revision fa8e4838 (ceph): Merge pull request #12174 from SUSE/wip-18025-jewel
- rgw: don't store empty chains in gc
- 06:53 PM Revision cc2d1e61 (ceph): rgw: fix for versioned delete_multi_object
- Fixes: http://tracker.ceph.com/issues/17888
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:52 PM rgw Bug #16408 (In Progress): Creating Bucket failed and can't be deleted.
- 04:34 PM rgw Bug #16408: Creating Bucket failed and can't be deleted.
- kraken backporting will not start for some time - this patch will get into kraken via manual merge
- 09:59 AM rgw Bug #16408 (Fix Under Review): Creating Bucket failed and can't be deleted.
- https://github.com/ceph/ceph/pull/12250
- 06:49 PM rgw Bug #17822 (Pending Backport): multisite requests failing with '400 Bad Request' with civetweb 1.8
- 06:46 PM Revision 785e87c8 (ceph): Merge pull request #11758 from Abhishekvrshny/wip-17784-jewel
- jewel: osd crashes when radosgw-admin bi list --max-entries=1 command runing
- 06:39 PM rgw Bug #18083 (Pending Backport): multisite: failed assertion in 'radosgw-admin bucket sync status'
- 06:39 PM rgw Bug #17985: rgw sends omap_getvals with (u64)-1 limit
- This issue has a new associated upstream PR https://github.com/ceph/ceph/pull/12224
- 06:25 PM rbd Bug #18068 (Pending Backport): diff calculate can hide parent extents when examining first snapsh...
- 06:18 PM Bug #18072 (Pending Backport): msg/simple/Pipe: error decoding addr
- 06:18 PM Revision 3c8392f7 (ceph): Merge pull request #12221 from liewegas/wip-18072
- msg/simple/Pipe: handle addr decode error
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Greg Farnum <gfarnu... - 05:49 PM Revision d9bf1243 (ceph): Merge pull request #12218 from dillaman/wip-18068
- librbd: diffs to clone's first snapshot should include parent diffs
Reviewed-by: Mykola Golub <mgolub@mirantis.com> - 05:41 PM Revision 212294ac (ceph): test/fio: fix global CephContext life cycle in fio pobjectstore plugin
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 05:29 PM Revision ee19ced0 (ceph): Excluded librgw2
- Fixes http://tracker.ceph.com/issues/17960
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> - 04:58 PM Revision cef5b35e (ceph): ceph_test_objectstore: fix Rename test
- We were doing a no-op setattr here, even though the intenral
ENOENT used to be ignored, because it previously trigger... - 04:55 PM Revision 4e409285 (ceph): Merge pull request #10086 from Yan-waller/yj-wip-rgwrests3ccstringfind
- rgw: conform to the standard usage of string::find
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 04:31 PM Revision c80613f9 (ceph): debian: apply dh_python to python-rgw also
- so the subvar of ${python:Depends} and ${python3:Depends} can be set
properly. also this silences the warnings like
... - 04:22 PM Backport #16225 (Fix Under Review): hammer: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- 04:22 PM Backport #16225 (In Progress): hammer: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- 04:15 PM Backport #18095: jewel: Improve deep-scrub performance with many snapshots
- h3. original description
This is accomplished by improving the scrub boundary requirements, so that we don't hav... - 04:05 PM Revision 539385b1 (ceph): ceph-disk: enable --runtime ceph-osd systemd units
- If ceph-osd@.service is enabled for a given device (say /dev/sdb1 for
osd.3) the ceph-osd@3.service will race with ce... - 03:46 PM Revision ae3dedad (ceph): rgw: fix for unsafe change of rgw_zonegroup
- Fixes: http://tracker.ceph.com/issues/17962
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 03:41 PM Revision dbe22614 (ceph): Merge pull request #12229 from cbodley/wip-rgw-bucket-sync-status-assert
- rgw: RGWBucketSyncStatusManager uses existing async_rados
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by:... - 03:29 PM Backport #18104 (Resolved): jewel: ceph osd down detection behaviour
- https://github.com/ceph/ceph/pull/12677
- 03:20 PM Revision 6d752bd8 (ceph): Merge pull request #12254 from Adirl/disconnect_log
- msg/async/rdma: fix disconnect log line
Reviewed-by: Haomai Wang <haomai@xsky.com> - 03:18 PM Revision 96cced44 (ceph): Merge pull request #9846 from stiopaa1/msg_asyncmess_removeUnneededInclude
- msg/AsyncMessenger: remove unneeded include
Reviewed-by: Haomai Wang <haomai@xsky.com> - 03:17 PM Bug #17809 (Resolved): "symbol lookup error: ceph_test_librbd_api: undefined symbol" in upgrade:c...
- 03:08 AM Bug #17809 (Fix Under Review): "symbol lookup error: ceph_test_librbd_api: undefined symbol" in u...
- https://github.com/ceph/ceph/pull/12246
- 03:17 PM Revision 4b1d7432 (ceph): Merge pull request #12246 from tchaikov/wip-17809
- buffer: add copy(unsigned, ptr) back
Reviewed-by: Sage Weil <sage@redhat.com> - 03:17 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Zheng Yan wrote:
>
> If we only want inode, it's better to use getattr to validate dentry (getattr is basically ... - 09:05 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> Actually, I think we want this patch. Now that we're not manipulating the dcache with this call... - 03:17 PM Revision bd023cfe (ceph): rbd: enabling/disabling rbd feature should report missing dependency
- Currently while enabling or disabling rbd feature command does not
give missing dependency for eg: attempting to enab... - 03:15 PM Bug #18058 (Pending Backport): librados: new setxattr overload breaks c++ ABI
- 03:15 PM Revision d91790f2 (ceph): Merge pull request #12206 from jdurgin/wip-librados-setxattr-overload
- librados: remove new setxattr overload to avoid breaking the C++ ABI
Reviewed-by: Sage Weil <sage@redhat.com> - 03:15 PM CephFS Bug #18066 (Resolved): objecter dropped op submitted before pool existed
- https://github.com/ceph/ceph/pull/12234
- 03:14 PM Bug #17942 (Resolved): osdc: osdmap update may race with retaking exclusive lock
- 03:14 PM Revision 5c750892 (ceph): Merge pull request #12234 from liewegas/wip-17942-again
- osdc/Objecter: fix relock race
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:05 PM CephFS Backport #18103 (Resolved): jewel: truncate can cause unflushed snapshot data lose
- https://github.com/ceph/ceph/pull/12324
- 03:05 PM rgw Backport #18102 (Resolved): jewel: rgw: Unable to commit period zonegroup change
- https://github.com/ceph/ceph/pull/12315
- 03:04 PM CephFS Bug #17982 (Resolved): fuse client failing to trim disconnected inode on unmount
- Fix is merged -- commit 2d02d2c95af9aed31a8579a2245b759f57b3a193.
- 03:04 PM rgw Backport #18101 (Resolved): jewel: Add workaround for upgrade issues for older jewel versions
- https://github.com/ceph/ceph/pull/12316
- 03:03 PM CephFS Backport #18100 (Resolved): jewel: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- https://github.com/ceph/ceph/pull/13139
- 03:03 PM Revision 3f4a6362 (ceph): upgrade/client-upgrade: correct distros/ location
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:03 PM CephFS Bug #18013 (Resolved): ceph_test_libcephfs access failures when run without ceph-fuse mount in te...
- Fixed in commit 8a887edaffeed66f02f605ee78b9999ffd629a60.
- 03:02 PM rgw Backport #18098: jewel: rgw: Swift's "prefix" parameter is not supported on account listing
- h3. original description
RadosGW doesn't support the _prefix_ parameter on account listing through the Swift API. ... - 02:20 PM rgw Backport #18098 (In Progress): jewel: rgw: Swift's "prefix" parameter is not supported on account...
- 02:19 PM rgw Backport #18098 (Resolved): jewel: rgw: Swift's "prefix" parameter is not supported on account li...
- https://github.com/ceph/ceph/pull/12258
- 03:00 PM Revision 942565ef (ceph): Merge pull request #12228 from ceph/wip-jlayton-umount
- libcephfs and test suite fixes
- 02:53 PM Revision 27067c7a (ceph): upgrade/client-upgrade: fix distro symlinks
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:46 PM Revision f143438d (ceph): krbd/unmap: pre-single-major is now 3.12.z
- 3.13 won't build on newer distros, due to lack of gcc5 support.
nightly/pre-single-major (with a slash) is now gone.
... - 02:39 PM Revision 198db468 (ceph): osd/osd_types: avoid pinning memory with pg_log_entry_t::snaps
- The pg_log_entry_t may stay in memory for a long time;
avoid pinning a larger buffer in memory.
See: http://tracker.... - 02:38 PM Revision 896644d5 (ceph): osd/osd_types: prevent ObjectModDesc::bl from pinning memory
- We may decode this from a large buffer (e.g., an
ECSubWrite payload) and the ObjectModDesc is part of
the pg_log_entr... - 02:38 PM Revision 30b0575a (ceph): msg/async/rdma: fix disconnect log line
- issue: none
Change-Id: I29e2a6ae78dda3cf4a1817b9ab41bea0f636bda5
Signed-off-by: Adir Lev <adirl@mellanox.com> - 02:08 PM rgw Feature #17931 (Pending Backport): rgw: Swift's "prefix" parameter is not supported on account li...
- 02:06 PM Revision d9c1d868 (ceph): rgw: add support for the prefix parameter in account listing of Swift API.
- Fixes: http://tracker.ceph.com/issues/17931
Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
(cherry picke... - 02:05 PM CephFS Bug #8405 (Duplicate): multimds: FAILED assert(dir->is_frozen_tree_root())
- dup of http://tracker.ceph.com/issues/17606
- 02:05 PM Revision 6ead4cc7 (ceph): rgw: optimize out ctor-copy in RGWListBuckets_ObjStore_SWIFT.
- This commit has been backported to Jewel as a dependency for
0e0a14a70f688e29c1993b723d64ec99a55f3677.
Signed-off-by... - 01:47 PM Bug #18097: osd fails after upgrade to kraken (v11.0.2) when using bluestore
- Forgot to mention perhaps the most important part: due to hitting a lot of various bluefs bugs in Jewel we were using...
- 10:53 AM Bug #18097: osd fails after upgrade to kraken (v11.0.2) when using bluestore
- More loggs from the affected OSD:...
- 10:29 AM Bug #18097 (Won't Fix): osd fails after upgrade to kraken (v11.0.2) when using bluestore
- Hi.
This week we have upgraded Ceph on our test cluster to the latest Kraken release (v11.0.2). After the upgrade ... - 01:32 PM Revision cce94b9f (ceph): Fixed problem with PUT with x-amz-copy-source when source object is com...
- Signed-off-by: Adam Kupczyk <akupczyk@mirantis.com>
- 01:20 PM rbd Bug #18070 (Resolved): rbd-nbd: immediate seg fault starting the daemon
- 01:19 PM Revision 0c078b05 (ceph): Merge pull request #12222 from dillaman/wip-18070
- rbd-nbd: restart parent process logger after forking
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Mykola G... - 11:50 AM rbd Bug #17993: rbd-mirror: potential race mirroring cloned image
- Yang Dongsheng wrote:
> Jason Dillaman wrote:
> > We track this state already -- it's just being enabled too soon s... - 10:27 AM Bug #18096: osd fails after upgrade to kraken (v11.0.2) when using bluestore
- Please close this as duplicate, I forgot to add all the needed bug attributes before I hit submit :(
- 10:26 AM Bug #18096 (Won't Fix): osd fails after upgrade to kraken (v11.0.2) when using bluestore
- Hi.
This week we have upgraded Ceph on our test cluster to the latest Kraken release (v11.0.2). After the upgrade ... - 10:12 AM rgw Bug #17975 (Fix Under Review): rgw:can get bucket's location in slave zonegroup,not returned 301
- https://github.com/ceph/ceph/pull/11700
- 10:10 AM rgw Bug #17364 (Pending Backport): rgw: Unable to commit period zonegroup change
- 10:10 AM rgw Documentation #17820 (Pending Backport): Add workaround for upgrade issues for older jewel versions
- 10:09 AM rgw Bug #17976 (Won't Fix): multisite upgrade from hammer->jewel still doesn't handle different rgw_r...
- 10:08 AM rgw Bug #17788 (Resolved): rgw: failing to authenticate aws4 with boto and with port specified
- 10:06 AM rgw-testing Bug #18023 (Fix Under Review): Add s3test for multiple object delete with object names the begin ...
- https://github.com/ceph/s3-tests/pull/137
- 10:02 AM rgw Bug #18063 (Resolved): radosgw-admin -n client.0 user rm --uid foo.client.0 --purge-data fails
- 10:02 AM rgw Bug #18063 (Closed): radosgw-admin -n client.0 user rm --uid foo.client.0 --purge-data fails
- seems to be a bad backport, reverted the problematic commit and fixed compilation.
new backport of resharding:
ht... - 09:11 AM Revision 8e1066e6 (ceph): bufferlist: cleanup semantical wrong for bufferlist::append
- this is just semantically wrong. as append_buffer.set_offset() was
called, so append_buffer._off is always 0. in othe... - 09:06 AM Revision 82c4680e (ceph): rgw/rgw_data_sync.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:06 AM Revision f43252a3 (ceph): msg/async/dpdk/stream.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:06 AM Revision 5dad2b34 (ceph): msg/async/dpdk/ARP.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:06 AM Revision 35048024 (ceph): msg/async/dpdk/shared_ptr.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:05 AM Revision 43c72fbf (ceph): librbd/ImageCtx: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:04 AM Revision 957a7e72 (ceph): msg/DispatchQueue.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:03 AM Revision 1531da2e (ceph): mon/Paxos.h: remove unneeded forward declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:02 AM Revision 582ff3bb (ceph): include/Context.h: remove unneeded forward declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:02 AM Revision dbdb6d3a (ceph): include/mempool.h: remove unneeded farward declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:02 AM Revision c269c9bb (ceph): common/perf_counters.h: remove unneeded forward declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:02 AM Revision 7db7c050 (ceph): common/TrackedOp.h: remove unneeded forward declaration
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 09:01 AM Revision cdc0930a (ceph): auth/Crypto.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:01 AM Revision aebe7464 (ceph): auth/AuthClientHandler.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:33 AM Bug #17916: osd/PGLog.cc: 1047: FAILED assert(oi.version == i->first)
- Hi, since a few days we have similar behaviour in Hammer (0.94.6) -- I don't see
above "unexpected io error" anywhe... - 07:28 AM Revision b3887379 (ceph): build/ops: restart ceph-osd@.service after 20s instead of 100ms
- Instead of the default 100ms pause before trying to restart an OSD, wait
20 seconds instead and retry 30 times instea... - 04:42 AM RADOS Bug #17949: make check: unittest_bit_alloc get_used_blocks() >= 0
- Seen again on master branch trying to reproduce other make check issues on rex001.
- 03:14 AM RADOS Bug #18054: os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- /a/sage-2016-11-30_17:15:54-rados-wip-sage-testing---basic-smithi/589941
- 03:13 AM RADOS Bug #14115: crypto: race in nss init
- /a/sage-2016-11-30_17:15:54-rados-wip-sage-testing---basic-smithi/590025
- 03:05 AM Revision f8a8b4f0 (ceph): buffer: add copy(unsigned, ptr) back
- to be ABI-compatible with prior versions.
copy(unsigned, ptr) was renamed to copy_deep() in 6d7f748
Fixes: http://t... - 02:31 AM Revision 4dadd8db (ceph): Merge pull request #12244 from ceph/wip-rgw-compression-doc
- doc: add docs for raw compression
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 02:29 AM Revision 8e5bb761 (ceph): Merge pull request #12113 from ceph/wip-rgw-zone-compression
- rgw: move compression config into zone placement
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 02:16 AM Revision aed8692e (ceph): Merge pull request #12232 from liewegas/wip-rgw-lclist
- rgw: need to close_section in lc list op
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 01:06 AM Revision ec0d5dfe (ceph): radosgw-admin: add --compression for zone placement add/modify
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 01:06 AM Revision b6abe642 (ceph): rgw: ops use zone placement's compression type
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 01:06 AM Revision ceeb4427 (ceph): rgw: remove config option rgw_compression_type
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 01:06 AM Revision b31d0699 (ceph): rgw: add compression_type field to RGWZonePlacementInfo
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 12:05 AM Backport #16917 (Rejected): Hammer leaves pg_TEMP directories when PG gets removed
- Decided that this wasn't a necessary backport. Jewel can handle the upgrade with extra pg_TEMP directories, so this ...
- 12:02 AM Backport #17970 (Fix Under Review): jewel: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- https://github.com/ceph/ceph/pull/12088
11/30/2016
- 11:57 PM Backport #16225 (Fix Under Review): hammer: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- https://github.com/ceph/ceph/pull/12121
- 11:53 PM Bug #8885: SIGABRT in TrackedOp::dump() via dump_ops_in_flight()
- bc3dcd22bb2c6ce0370632baf99f644636afb05b
https://github.com/ceph/ceph/pull/8044
- 11:42 PM Feature #17470 (Resolved): Improve deep-scrub performance with many snapshots
- 11:39 PM Feature #17470: Improve deep-scrub performance with many snapshots
- Pull request merged at 3cc40d769b0578f9dd982b6f786da6ad9fd02a07
https://github.com/ceph/ceph/pull/11255 - 10:00 PM Feature #17470 (Pending Backport): Improve deep-scrub performance with many snapshots
- 27bdc8ce6d0a7d8ae47f29540f281ba417e16b4c was the master sha1
- 11:41 PM Backport #18095 (Resolved): jewel: Improve deep-scrub performance with many snapshots
- 16f9d95204f3eca6908ae241e5bacc48b006cb23
https://github.com/ceph/ceph/pull/11311 - 11:40 PM Backport #18095 (Resolved): jewel: Improve deep-scrub performance with many snapshots
- https://github.com/ceph/ceph/pull/11311
- 11:15 PM Revision 47cd4f46 (ceph): Merge pull request #1293 from ceph/wip-17977-fix
- qemu: Set permissions on /dev/kvm
Reviewed-by: Dan Mick <dmick@redhat.com> - 11:05 PM Revision 7abc7689 (ceph): qemu: Set permissions on /dev/kvm
- Hack until fix in https://bugzilla.redhat.com/show_bug.cgi?id=1333159
makes it into CentOS repos.
Fixes: http://trac... - 10:36 PM Revision 0a5dae77 (ceph): os/bluestore: not fadvise flags in log
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:35 PM Revision 8d144f94 (ceph): os/bluestore: deep copy on partial bufferptrs on setattr
- Otherwise we may inadvertantly pin larger buffers in
memory.
Fixes: http://tracker.ceph.com/issues/18093
Signed-off-... - 10:33 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- David copied CentOS CR's gperftools packages to lab-extras today in order to test. (see ticket #18094)
- 09:58 PM Revision 098cbc4b (ceph): buffer: put aligned buffers in buffer_data mempool
- Oops!
Signed-off-by: Sage Weil <sage@redhat.com> - 09:39 PM Revision 426c910f (ceph): Merge pull request #12105 from cbodley/wip-rgw-curl-upload
- rgw: dont set CURLOPT_UPLOAD for GET requests
- 09:38 PM Revision 890eb3da (ceph): Merge pull request #12242 from cbodley/wip-rgw-admin-placement
- radosgw-admin: more on placement configuration
- 09:26 PM Revision 6869cf1c (ceph): doc: add docs for rgw compression
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 09:06 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Actually, I think we want this patch. Now that we're not manipulating the dcache with this call, we must handle the d...
- 07:38 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Did some basic testing (with a doctored kernel that always revalidates dentries) and this seems to do the right thing...
- 03:58 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Ok, I think this patch will probably do the right thing. Only tested for compilation so far, but I'll see if I can gi...
- 02:49 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> >
> > I think we can do this (maybe need minor modification to the code). But I don't underst... - 02:37 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- got it. the whole point is avoid d_invalidated
- 02:26 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Zheng Yan wrote:
> Jeff Layton wrote:
> > Zheng Yan wrote:
> >
> > >
> > > I'm little worry about that d_reval... - 01:51 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> I think the thing we want to do here is to not set r_locked_dir, and pass a reference to the in... - 01:49 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> Zheng Yan wrote:
>
> >
> > I'm little worry about that d_revalidate does sleep lookup whil... - 01:39 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- I think the thing we want to do here is to not set r_locked_dir, and pass a reference to the inode that was the resul...
- 01:22 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Aurimas, If you can compile kernel from source. The detach patch (for 4.8.x kernel) workaround this issue.
- 08:22 PM Bug #18093 (Resolved): osd enomem with bluestore
- http://pulpito.ceph.com/sage-2016-11-30_17:15:54-rados-wip-sage-testing---basic-smithi/589862 is a recent example:
<... - 08:19 PM Revision c161f649 (ceph): Merge pull request #12185 from xiexingguo/xxg-wip-bluestore-1125
- os/bluestore: drop member "space" from Onode
Reviewed-by: Sage Weil <sage@redhat.com> - 07:56 PM Revision 711cc132 (ceph): radosgw-admin: add 'zonegroup placement default' command
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:56 PM Revision b59afea4 (ceph): radosgw-admin: 'zone placement modify' doesnt require pool names
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
- 07:06 PM CephFS Bug #18066: objecter dropped op submitted before pool existed
- 07:06 PM Bug #18085 (Resolved): osd thrashing deadlock: copy-from vs max-backfills
- 07:04 PM Revision e7e8c03a (ceph): pybind: Add binding for aio_exec
- This exposes to the python API for the following C methods:
* rados_aio_exec
Signed-off-by: Iain Buclaw <iain.buclaw... - 06:56 PM rgw Bug #18078 (Fix Under Review): rgw-admin: missing command to modify placement targets
- added followup pr https://github.com/ceph/ceph/pull/12242 that should be backported at the same time
- 05:22 PM rgw Bug #18078 (Pending Backport): rgw-admin: missing command to modify placement targets
- https://github.com/ceph/ceph/pull/12230
- 06:54 PM Revision 0cf08985 (ceph): radosgw-admin: fix 'placment' typos
- Fixes: http://tracker.ceph.com/issues/18078
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 05:21 PM Revision c40b60ba (ceph): Merge pull request #12230 from yehudasa/wip-18078
- rgw-admin: new commands to control placement
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 05:20 PM Revision 08801a0e (ceph): Merge pull request #1291 from ceph/wip-18085
- rados/thrash*: do no set osd_max_backfills=1
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:13 PM Revision 9717bc34 (ceph): rados/thrash*: vary osd_max_backfills, always >1
- This can lead to a copy-from vs backfill deadlock; see
http://tracker.ceph.com/issues/18085
This effectively reverts... - 04:55 PM Revision 9832332b (ceph): upgrade/client-upgrade: specify centos or trusty (not xenial)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:42 PM Bug #17889 (Fix Under Review): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- Working on a fix assuming ceph-disk@.service must be Before= ceph-osd@.service at https://github.com/ceph/ceph/pull/...
- 04:07 PM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- The logs of osd.32 show 3 failed attempts to start at 13:18:15...
- 06:03 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- ceph-disk@.service should be Before= ceph-osd@.service but this relationship does not exist. It usually is not a prob...
- 04:34 PM Revision a91c7b5c (ceph): rgw-admin: add commands to manage zonegroup placement fields
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 04:34 PM Revision ead132ae (ceph): rgw_admin: commands to manage placement targets
- Fixes: http://tracker.ceph.com/issues/18078
added the following commands:
radosgw-admin zone placement add
radosg... - 04:18 PM Revision c12d0af2 (ceph): rgw: metadata sync info should be shown at master zone of slave zonegroup
- When executing 'radosgw-admin sync status', the metadata sync info should be shown on the srceen at master zone of sl...
- 04:00 PM Revision f95ed3e7 (ceph): rados: avoid ubuntu xenial on upgrade tests
- Not all of the older package builds are present for xenial.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:51 PM Bug #18092 (Resolved): unittest_erasure_code_shec illegal instruction
- build@247e7c628ef2:~/ceph-ubuntu-14.04-build/build$ ./bin/unittest_erasure_code_shec
[==========] Running 71 tests f... - 03:35 PM Revision ea019fba (ceph): Merge pull request #12236 from gongchuang/gc-wip-1130
- msg/async/rdma: fixup memory free
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:50 PM Revision b3e2719a (ceph): Merge pull request #12138 from oritwas/wip-rgw-doc-upgrade-region-pool
- rgw: add documentation for upgrading with rgw_region_root_pool
Reviewed-by: Casey Bodley <cbodley@redhat.com>
Review... - 02:42 PM Bug #17824 (Resolved): bluestore: multiple aios allocated at same address?
- 02:35 PM rgw Bug #18091 (Resolved): 'radosgw-admin sync status' on master zone of non-master zonegroup
- The sync status incorrectly reports "no sync (zone is master)" when run from the master zone of a non-master zonegrou...
- 02:10 PM Stable releases Tasks #17487: jewel v10.2.4
- Running a suite for the last 2 prs which will make it to 10.2.4
This is the current jewel branch as of 427f357f0ee... - 01:36 PM Revision c891971d (ceph): Merge pull request #12061 from guihecheng/my-fix
- cephfs: fix missing ll_get for ll_walk
Reviewed-by: John Spray <john.spray@redhat.com> - 12:37 PM Revision 2d02d2c9 (ceph): client: fix some potential locking problems in InodeRef handling
- As Zheng points out, declaring an InodeRef before you take the mutex
means that its destructor gets called after the ... - 12:37 PM Revision 8a887eda (ceph): test/libcephfs: ensure that we set the mode of the libcephfs root befor...
- Patrick noticed that the libcephfs tests failed to run unless they were
run after the ceph-fuse tests had run. The ce... - 12:34 PM rgw Bug #18090 (New): bootstrap-rgw does not allow creation of keys without write permissions to mons
- Keys created with the boostrap-rgw profile only allow the creation of keys which are mon 'allow rw' and osd 'allow rw...
- 10:36 AM rbd Cleanup #16985 (Fix Under Review): Improve error reporting from "rbd feature enable/disable"
- PR https://github.com/ceph/ceph/pull/12238
- 08:13 AM Bug #16026 (Rejected): ceph-disk activate on devices not owned by the ceph user fails
- the *var/lib/ceph/tmp/mnt.J7lWtb: (13) Permission denied mount_activate: Failed to activate* error message reflects w...
- 08:06 AM Revision 45fc1868 (ceph): msg/async/rdma: fixup memory free
- Signed-off-by: gongchuang <gong.chuang@zte.com.cn>
- 07:51 AM Revision 63b42dd3 (ceph): Merge pull request #12235 from tchaikov/wip-osd_stat_t-decode
- osd/osd_types: fix the osd_stat_t::decode()
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:43 AM devops Bug #18065: kraken aarch64 build fails, complains about -march=native
- I tested Kefu's suggestion to build latest master on aarch64 and it succeeds. The real fix, then, will be to backport...
- 07:05 AM Revision 433efe0c (ceph): osd/osd_types: fix the osd_stat_t::decode()
- should decode the deprecated num_hb_out as vector<int> instead of uint32_t.
it's a regression introduced by 85f22ec
... - 05:31 AM rbd Bug #17993: rbd-mirror: potential race mirroring cloned image
- Jason Dillaman wrote:
> We track this state already -- it's just being enabled too soon since clone is re-using the ... - 04:09 AM Bug #18088 (Can't reproduce): mon: segment fault when starts mon first
- whole log as following, It seems that jerasure loading has bug. My ceph's version is 0.94:
2016-11-30 11:31:41.118... - 03:56 AM Bug #17942: osdc: osdmap update may race with retaking exclusive lock
- https://github.com/ceph/ceph/pull/12234
- 03:55 AM Revision c0fb4833 (ceph): osdc/Objecter: fix relock race
- In commit a863ae1c0fab636eabced0979889cbb3be74bf74 we tried
to fix a race but failed because we didn't update the
ses... - 03:21 AM Revision 823551ae (ceph): osd/PG: bound the portion of the log we request in PG::RecoveryState::G...
- Signed-off-by: Jie Wang <jie.wang@kylin-cloud.com>
- 02:58 AM Revision abbf21e8 (ceph): rgw: need to close_section in lc list op
- Signed-off-by: weiqiaomiao <wei.qiaomiao@zte.com.cn>
- 02:55 AM Revision 49fdc370 (ceph): Merge pull request #894 from ceph/wip-bluestore
- rados: test bluestore too
- 02:55 AM Revision 0fa0fa9c (ceph): rados/objectstore/objectstore.yaml: do not test kstore
- It's flaky.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:54 AM Revision c2466294 (ceph): Merge pull request #1152 from ceph/wip-objecstore
- rados/objectstore/objectstore.yaml: skip bluestore tests
- 02:53 AM Revision 1a1ba44d (ceph): rados: test bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 AM Revision e7f6e5a0 (ceph): rgw: test bluestore and filestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 AM Revision a7e183d4 (ceph): fs: test bluestore and filestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 AM Revision 2ac9ad02 (ceph): rbd: test on filestore and bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 AM Revision 87175c1a (ceph): rados/objectstore/objectstore.yaml: test bluestore
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:50 AM Revision 2f5cfbc0 (ceph): msg/simple/Pipe: handle addr decode error
- Fixes: http://tracker.ceph.com/issues/18072
Signed-off-by: Sage Weil <sage@redhat.com> - 02:22 AM Revision 2af20585 (ceph): osdmaptool: show all the pg map to osds info
- Signed-off-by:song baisen <song.baisen@zte.com.cn>
- 02:07 AM Revision a491710d (ceph): rgw: Fix a bug that LCWorker's worktime is not the same as config
- rgw_lifecycle_work_time.
Fixes: http://tracker.ceph.com/issues/18087
Signed-off-by: Zhang Shaowen <zhangshaowen@cms... - 02:04 AM rgw Bug #18087 (Resolved): rgw: LCWorker's worktime is not the same as config rgw_lifecycle_work_time.
- https://github.com/ceph/ceph/pull/11963
- 02:01 AM Revision bc27d933 (ceph): Merge pull request #12194 from tchaikov/wip-unit.cc
- test,cmake: turn unit.h into unit.cc to speed up compilation
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 02:00 AM Revision ad846d10 (ceph): cephfs: fix missing ll_get for ll_walk
- Fixs: http://tracker.ceph.com/issues/18086
Signed-off-by: Gui Hecheng <guihecheng@cmss.chinamobile.com> - 01:24 AM CephFS Bug #18086: cephfs: fix missing ll_get for ll_walk
- fixed by : https://github.com/ceph/ceph/pull/12061
- 01:24 AM CephFS Bug #18086 (Resolved): cephfs: fix missing ll_get for ll_walk
- When exporting a cephfs with nfs-ganesha, segfault is encountered upon releasing file handles using 'systemctl stop n...
- 01:21 AM Revision 65ef596c (ceph): rgw: lock is not released when set sync marker is failed.
- Fixes: http://tracker.ceph.com/issues/18077
Signed-off-by: Zhang Shaowen <zhangshaowen@cmss.chinamobile.com> - 01:06 AM Revision ef489208 (ceph): Merge pull request #1289 from ceph/wip-16397-workaround
- suites/knfs: pin to ubuntu
Reviewed-by: Jeff Layton <jlayton@redhat.com> - 12:49 AM Bug #18046: filestore: sync_entry timed out cause osd crash
- it maybe related to our configuration, we set vm.zone_reclaim_mode=3, which will block the memory allocation if there...
- 12:44 AM Revision c407e41e (ceph): rgw: set duration for lifecycle lease
- Fixes: http://tracker.ceph.com/issues/17965
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com> - 12:43 AM Revision 1d9f12da (ceph): rgw: remove a use of g_ceph_context
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
11/29/2016
- 11:54 PM Bug #18001 (Rejected): "Error: error calling conf_read_file: error code 22"
- This was a bug in the suite, which was already fixed - it was missing the ceph task when this was run, so no ceph.con...
- 11:44 PM Bug #13522: Apparent deadlock between tcmalloc getting a stacktrace and dlopen allocating memory
- This appears to trigger very frequently with ceph-objectstore-tool. :(
- 11:42 PM Bug #18074 (Duplicate): "saw valgrind issues" "Syscall param msync(start) points to uninitialised...
- this is a dup of http://tracker.ceph.com/issues/18084
- 05:44 PM Bug #18074 (Duplicate): "saw valgrind issues" "Syscall param msync(start) points to uninitialised...
- Run: http://pulpito.ceph.com/yuriw-2016-11-28_20:50:22-rados-wip-yuri-testing_2016_11_28-distro-basic-smithi/#
Jobs:... - 11:36 PM Bug #18085 (Fix Under Review): osd thrashing deadlock: copy-from vs max-backfills
- https://github.com/ceph/ceph-qa-suite/pull/1291
- 11:31 PM Bug #18085: osd thrashing deadlock: copy-from vs max-backfills
- /a/sage-2016-11-29_20:05:25-rados:thrash-master---basic-smithi/586464
osd logs are in the test dir
- 11:28 PM Bug #18085 (Resolved): osd thrashing deadlock: copy-from vs max-backfills
- one pg is backfilling. backfilling blocks on a copy-from operation, which blocks on the read (copy-get) because the ...
- 11:12 PM Bug #17999: ec scrub mismatch during teuthology run
- 09:53 PM Bug #17999 (In Progress): ec scrub mismatch during teuthology run
- 08:50 PM Bug #17999: ec scrub mismatch during teuthology run
- I was wrong, the errors seem to be on the ec base tier.
- 05:05 PM Bug #17999: ec scrub mismatch during teuthology run
- http://pulpito.ceph.com/sage-2016-11-29_03:30:55-rados-wip-sage-testing---basic-smithi/584558
cache tier (base poo... - 04:06 PM Bug #17999: ec scrub mismatch during teuthology run
- Kefu's weren't on ec pools.
- 11:09 PM Revision 99e866fe (ceph): rgw: omap_get_all() fixes
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 10:57 PM Bug #15368: "api_misc: [ FAILED ] LibRadosMiscConnectFailure.ConnectFailure"
- /a/sage-2016-11-29_20:05:25-rados:thrash-master---basic-smithi/586352
- 10:26 PM Revision e76d6ef4 (ceph): Merge pull request #12178 from liupan1111/wip-fix-bug-hb-out
- osd: replace hb_out and hb_in with a single hb_peers
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Wei... - 10:19 PM rgw Bug #18083 (Fix Under Review): multisite: failed assertion in 'radosgw-admin bucket sync status'
- https://github.com/ceph/ceph/pull/12229
- 10:09 PM rgw Bug #18083 (Resolved): multisite: failed assertion in 'radosgw-admin bucket sync status'
- When the CephContext destructor is called, HeartbeatMap hits the assertion: FAILED assert(m_workers.empty()).
The ... - 10:17 PM Revision 3ad2c2a8 (ceph): rgw: RGWBucketSyncStatusManager uses existing async_rados
- RGWBucketSyncStatusManager was creating its own RGWAsyncRadosProcessor
and failing to clean it up on destruction. A r... - 10:05 PM Revision 12162d65 (ceph): rgw: use set for zonegroup placement target tags
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 09:20 PM rgw Bug #17572 (Resolved): swift: Problems with DLO containing 0 length segments
- 09:20 PM rgw Backport #17677 (Resolved): hammer: swift: Problems with DLO containing 0 length segments
- 09:20 PM rgw Documentation #18082 (New): documentation still contains region configuration from old multisite
- 09:19 PM rgw Documentation #18081 (Resolved): documentation for compression configuration and statistics
- 09:17 PM Backport #17678 (Resolved): hammer: monitor should send monmap updates when the monmap is updated
- 09:16 PM Revision 12d67814 (ceph): Merge pull request #11457 from tchaikov/wip-17558-hammer
- hammer: mon: send updated monmap to its subscribers
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Kefu Ch... - 09:12 PM Revision 8406ee58 (ceph): Merge pull request #11628 from ceph/wip-hammer-11567
- hammer: rgw: Don't loop forever when reading data from 0 sized segment.
Reviewed-by: Orit Wasserman <owasserm@redhat... - 09:02 PM Revision f3a0c40f (ceph): rgw: only set CURLOPT_UPLOAD for PUT/POST requests
- when set on GET requests, curl sends a 'Transfer-encoding: chunked'
header, but doesn't do the actual encoding to ter... - 08:55 PM Revision 190bd385 (ceph): rgw: fix break inside of yield in RGWFetchAllMetaCR
- the yield macro is implemented with for/switch, so the breaks in
RGWFetchAllMetaCR weren't being applied to the for l... - 08:47 PM Revision a1c6017a (ceph): Merge pull request #12220 from liewegas/wip-coverity
- librbd/ImageCtx: no need for virtual dtor
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:31 PM Bug #15628: segfault at 0 ip sp error 4 in libtcmalloc.so.4.1.2
- I'm now on jewel 10.2.3.
Problem not reproduce.
Sank,you - 08:30 PM Revision a56b4b29 (ceph): Pipe::stop_and_wait: unlock pipe_lock for stop_fast_dispatching()
- OSD::ms_fast_dispatch may need the pipe_lock to finish what it's
doing and avoid a deadlock.
Fixes: http://tracker.c... - 08:28 PM Bug #18042: SimpleMessenger debug delay injection deadlock
- I think I can just unlock the pipe_lock there since we unlock it waiting on a cond just below there.
- 08:24 PM Bug #18042: SimpleMessenger debug delay injection deadlock
- The same conditions appear to be present in master.
- 08:18 PM Bug #18042: SimpleMessenger debug delay injection deadlock
- I don't think this is a recent regression, demoting to high for now.
- 07:04 PM Bug #18042: SimpleMessenger debug delay injection deadlock
- Thread 45 (Thread 0x7fbadab63700 (LWP 21310)):
#0 0x00007fbb03e206d5 in pthread_cond_wait@@GLIBC_2.3.2 () from /lib... - 08:14 PM Revision 8f2ccff3 (ceph): Merge pull request #12219 from zealoussnow/wip-1130
- osdc: pass a string reference type to "osdmap->lookup_pg_pool_name"
Reviewed-by: Sage Weil <sage@redhat.com> - 08:10 PM Revision b44032f3 (ceph): Merge pull request #12166 from liewegas/wip-osdmap-encoding
- osd: condition OSDMap encoding on features
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:06 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- Thanks. Potential fix is up here:
https://github.com/ceph/ceph/pull/12228
Waiting for build now so I can get a ... - 02:15 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- Jeff Layton wrote:
> Thanks. To make sure i understand...
>
> Since the inode is released after the mutex is drop... - 12:44 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- Thanks. To make sure i understand...
Since the inode is released after the mutex is dropped, then the refcount dec... - 09:13 AM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- This looks like inode reference leak. I found something suspicious ...
- 08:05 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- Potential fix up here. Still needs testing, but it seems to do the right thing on my box:
https://github.com/ceph/... - 06:05 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- Sounds reasonable to me Jeff.
- 04:25 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- Actually, now that I look further, it turns out that access.cc looks like it has just the function we need:...
- 03:15 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- I think the right solution is to add a new function for setting the default UserPerm for the cmount, and have those j...
- 08:01 PM Revision 5f00e1d4 (ceph): osd: Add func has_flag in MOSDOp.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(manually cherry picked just one line from d9a2ca5c5ae50dc34e184d5... - 07:50 PM rgw Bug #18079 (Resolved): rgw: need to stream metadata full sync init
- 07:44 PM Revision dd5845c5 (ceph): Merge pull request #12202 from liewegas/wip-bluestore-coverity
- os/bluestore: misc coverity fixes/cleanups
- 07:27 PM Revision 27c1462d (ceph): Merge pull request #12047 from rzarzynski/wip-rgw-17931
- rgw: add support for the prefix parameter in account listing of Swift API
- 06:56 PM Revision 7cd123ec (ceph): rgw/rgw_rados: do not omap_getvals with (u64)-1 max
- Fixes: http://tracker.ceph.com/issues/17985
This will make the OSD fall over if the object is big
and the OSD doesn'... - 06:46 PM rgw Bug #18078 (Resolved): rgw-admin: missing command to modify placement targets
- 06:42 PM Revision 515c14c0 (ceph): Merge pull request #11671 from linuxbox2/rgw_file-17663
- rgw_file: apply missed base64 try-catch
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:41 PM Revision 750d8cf7 (ceph): Merge pull request #11751 from yehudasa/wip-17788
- rgw: extract host name from host:port string
- 06:40 PM rgw Bug #18077 (Resolved): multisite: lock is not released when RGWMetaSyncShardCR::full_sync() fails...
- https://github.com/ceph/ceph/pull/12197
- 06:29 PM Revision e62d48a9 (ceph): rgw: fix for broken yields in RGWMetaSyncShardCR
- Fixes: http://tracker.ceph.com/issues/18076
Signed-off-by: Casey Bodley <cbodley@redhat.com> - 06:26 PM rgw Bug #18076 (Resolved): multisite: some yields in RGWMetaSyncShardCR::full_sync() resume in increm...
- When RGWMetaSyncShardCR::full_sync() is done, it updates the sync_marker and writes it to rados. But after it changes...
- 06:13 PM Revision 2a233bda (ceph): Merge pull request #12217 from dzafman/wip-tests-off
- Turn off tests again due to Jenkins failures
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:37 PM rbd Bug #18070 (Fix Under Review): rbd-nbd: immediate seg fault starting the daemon
- *PR*: https://github.com/ceph/ceph/pull/12222
- 04:35 PM rbd Bug #18070 (Resolved): rbd-nbd: immediate seg fault starting the daemon
- 0> 2016-11-29 11:33:38.618620 7fb14363d100 -1 /home/jdillaman/ceph/src/log/Log.cc: In function 'void ceph::loggi...
- 05:36 PM Revision 29baf254 (ceph): rbd-nbd: restart parent process logger after forking
- Fixes: http://tracker.ceph.com/issues/18070
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 05:20 PM Revision b67df1eb (ceph): Merge pull request #12204 from liewegas/wip-bluestore-17824
- os/bluestore/KernelDevice: fix race in aio_thread vs aio_wait
- 05:15 PM Revision d6a6b03a (ceph): client: simplify remove_cap interface
- All this complexity only existed to handle the
case where trim wanted to iterate over an xlist
without getting distur... - 05:15 PM Revision 89fc88ef (ceph): Revert "client: trim_caps() do not dereference cap if it's removed"
- We will simplify this another way.
This reverts commit e9fbe39f0f91b7f6551d911f1a2519f5b35175a2.
Signed-off-by: Joh... - 05:13 PM Revision b42dfca0 (ceph): Merge pull request #12130 from liupan1111/wip-osd-hearteat
- osd: remove redudant call of heartbeat_check
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Haomai Wang <hao... - 05:11 PM Revision d5596026 (ceph): Merge pull request #12169 from liewegas/wip-rados-bench-hints
- rados: add hints to rados bench
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:10 PM Bug #18073 (Can't reproduce): LibRadosIo.ReadTimeout segv
- ...
- 05:09 PM CephFS Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- RPMs here: http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/wip-17837-jewel/x86_64/
- 12:01 PM CephFS Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- Alexander: I've pushed a backport of this to jewel to a branch called wip-17837-jewel. It will build in an hour or t...
- 11:50 AM CephFS Bug #17837 (Pending Backport): ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- 07:12 AM CephFS Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- I could test the changes, do I have to compile this project?
- 05:06 PM Bug #17989 (Closed): bluestore CEPH osd disk overloaded by reads periodically by rocksdb tables g...
- Hi,
Thanks for the report! Unfortunately this is a side effect of using rocksdb for metadata. If you look at the... - 05:01 PM Bug #18072: msg/simple/Pipe: error decoding addr
- https://github.com/ceph/ceph/pull/12221
- 05:00 PM Bug #18072 (Resolved): msg/simple/Pipe: error decoding addr
- ...
- 04:41 PM rgw Bug #18071 (Resolved): radosgw valgrind "invalid read size 4" RGWGetObj
- Found reviewing output for PR #11751. This doesn't look conditioned by that 1-liner change, perhaps has been around ...
- 04:32 PM RADOS Bug #17968 (Need More Info): Ceph:OSD can't finish recovery+backfill process due to assertion fai...
- This is due to the BALANCE_READS option, right?
- 04:32 PM Revision b660630f (ceph): osdc: pass a string reference type to "osdmap->lookup_pg_pool_name"
- Signed-off-by: Leo Zhang <nguzcf@gmail.com>
- 04:31 PM Bug #9308: EBUSY on umount of osd volume after ceph-osd shutdown
- http://tracker.ceph.com/issues/17944 is probably the root cause
- 04:28 PM rbd Bug #18068 (Fix Under Review): diff calculate can hide parent extents when examining first snapsh...
- *PR*: https://github.com/ceph/ceph/pull/12218
- 03:01 PM rbd Bug #18068 (Resolved): diff calculate can hide parent extents when examining first snapshot in clone
- Create a clone from a parent image, create a snapshot on the clone, and write some data to the clone's HEAD revision....
- 04:27 PM Revision 45eda01f (ceph): librbd: diffs to clone's first snapshot should include parent diffs
- If the clone has a backing object created after the snapshot that
overwrites an extent of the parent, the parent diff... - 04:27 PM Bug #18004 (Resolved): heartbeat peers need to be updated when a new OSD added into an existed cl...
- https://github.com/ceph/ceph/pull/12069
- 04:20 PM Bug #18027 (Duplicate): test_objectstore_memstore.sh transient failure
- 04:16 PM Bug #18046: filestore: sync_entry timed out cause osd crash
- Hmm, I'm not sure about that. Why would align_bl take that long to begin with? Is this reproducible? If so, can yo...
- 04:09 PM Bug #17867 (Can't reproduce): jewel: omap deep scrub error during power cycle run
- 04:07 PM Revision 59bc5ffe (ceph): Merge pull request #1283 from SUSE/wip-18014
- thrashosds: try ceph-objectstore-tool for one minute
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:04 PM Revision be718458 (ceph): osd: reject PARALLELEXEC ops with EINVAL
- Errors are better than crashing.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 407495197dd87... - 04:04 PM Revision 982af4af (ceph): test: Turn off test-erasure-eio.sh due to Jenkins failures
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 04:03 PM Revision 8d352358 (ceph): ceph_test_rados_api_misc: test rados op with bad flas
- Pass the bad PARALLELEXEC flag to remove(), which takes a flags arg.
Signed-off-by: Sage Weil <sage@redhat.com>
(che... - 04:02 PM Revision a405e442 (ceph): test: Turn off osd-scrub-repair.sh due to Jenkins failures
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 03:36 PM Revision 7c3babb8 (ceph): Merge pull request #1288 from dachary/wip-shec-upgrade-jewel
- upgrade/hammer-x: verify shec before the full upgrade
Reviewed-by: Sage Weil <sage@redhat.com> - 02:44 PM Revision 96e3d592 (ceph): mds: don't access mdsmap from log submit thread
- the log submit thread does not hold the big mds_lock.
Fixes: http://tracker.ceph.com/issues/18047
Signed-off-by: Yan... - 02:29 PM CephFS Bug #16397: nfsd selinux denials causing knfs tests to fail
- From a recent run I see this is only happening on centos NFS servers, so I'm going to pin these tests to ubuntu (but ...
- 02:28 PM Revision b6ba7c01 (ceph): suites/knfs: pin to ubuntu
- Workaround for http://tracker.ceph.com/issues/16397, which
manifests when we run bleeding edge kernels against the ve... - 02:24 PM rgw Bug #18064 (In Progress): multisite: sync status reports master is on a different period
- 02:24 PM rgw Bug #18064: multisite: sync status reports master is on a different period
- Looking further into this I see that we're actually storing master_period as the first period from master instead of ...
- 12:02 PM rgw Bug #18064 (Resolved): multisite: sync status reports master is on a different period
- On current master, sync status on secondary reports that the master is on a different period, though the master and t...
- 02:18 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Zheng Yan wrote:
>
> I'm little worry about that d_revalidate does sleep lookup while parent is not locked. I th... - 01:04 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- With kernel v4.5.4 there's no kernel panics, but CPUs started to soft lockup on one node every few hours (one node so...
- 02:38 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> Ok, thanks. I see that you had written that in the original description too. If you have the ti... - 02:17 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Jeff Layton wrote:
> From ceph_d_revalidate:
>
> [...]
>
> The result handling after ceph_mdsc_do_request look... - 02:14 PM devops Bug #18065 (Fix Under Review): kraken aarch64 build fails, complains about -march=native
- -*master PR*: https://github.com/ceph/ceph/pull/12214-
- 12:38 PM devops Bug #18065 (Resolved): kraken aarch64 build fails, complains about -march=native
- When building 11.0.2 for aarch64 we are getting the following FTBFS:
/home/abuild/rpmbuild/BUILD/ceph-11.0.2+git.1... - 01:54 PM rbd Bug #17993: rbd-mirror: potential race mirroring cloned image
- We track this state already -- it's just being enabled too soon since clone is re-using the create image state machin...
- 06:08 AM rbd Bug #17993: rbd-mirror: potential race mirroring cloned image
- Hi Jason,
What about add a key-value in header object to mark this image is ready for mirror or not? such as "mi... - 01:45 PM CephFS Bug #18066 (Resolved): objecter dropped op submitted before pool existed
http://pulpito.ceph.com/teuthology-2016-11-28_17:15:02-fs-master---basic-smithi/583404/
This is manifesting as a...- 12:59 PM rgw Bug #17888: rgw:fix for deleting objects name beginning and ending with underscores of one bucket...
- https://github.com/ceph/ceph/pull/11982
- 12:54 PM CephFS Bug #17193 (Pending Backport): truncate can cause unflushed snapshot data lose
- 12:47 PM rbd Cleanup #16991 (Fix Under Review): rbd-mirror split-brain issues should be clearly visible in mir...
- PR: https://github.com/ceph/ceph/pull/12212
- 12:46 PM rbd Bug #18051 (Fix Under Review): "rbd mirror image resync" does not force resync after split-brain
- PR: https://github.com/ceph/ceph/pull/12212
- 12:40 PM CephFS Feature #12552 (Rejected): qa: test cephfs over cache tier in fs suite
- Cache tiers are deprecated.
- 11:53 AM Revision bfa66be2 (ceph): Merge pull request #11764 from bassamtabbara/wip-embedded
- cmake: Support for embedding Ceph Daemons
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@red... - 11:50 AM Revision 4bb05b98 (ceph): Merge pull request #12097 from ceph/wip-17837
- src/mds: fix MDSMap upgrade decoding
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:45 AM Revision 6a155a84 (ceph): Merge pull request #12090 from wjwithagen/wip-wjw-do_freebsd.sh
- FreeBSD: do_freebsd.sh
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:24 AM Backport #18060 (In Progress): jewel: timeout during ceph-disk trigger due to /var/lock/ceph-disk...
- 10:19 AM Backport #18060: jewel: timeout during ceph-disk trigger due to /var/lock/ceph-disk flock contention
- Backport submitted (against jewel-next) via:
https://github.com/ceph/ceph/pull/12210 - 08:09 AM Backport #18060 (Resolved): jewel: timeout during ceph-disk trigger due to /var/lock/ceph-disk fl...
- https://github.com/ceph/ceph/pull/12210
- 10:14 AM Revision 0ab5b7a7 (ceph): systemd/ceph-disk: reduce ceph-disk flock contention
- "ceph-disk trigger" invocation is currently performed in a mutually
exclusive fashion, with each call first taking an... - 10:07 AM rgw Bug #18063: radosgw-admin -n client.0 user rm --uid foo.client.0 --purge-data fails
- Only with the resharding code
- 10:06 AM rgw Bug #18063 (Resolved): radosgw-admin -n client.0 user rm --uid foo.client.0 --purge-data fails
- Failute in smoke suite http://qa-proxy.ceph.com/teuthology/owasserm-2016-11-07_16:44:38-smoke-wip-rgw-resharding-hamm...
- 09:39 AM Revision 85f22ec8 (ceph): osd: replace hb_out and hb_in with a single hb_peers
- Signed-off-by: Pan Liu <pan.liu@istuary.com>
- 09:33 AM Revision 79b90a26 (ceph): osd/OSDMap: improve the performance of pg_to_acting_osds.
- Signed-off-by: Pan Liu <pan.liu@istuary.com>
- 08:49 AM Revision 2c1df81e (ceph): upgrade/hammer-x: verify shec before the full upgrade
- The hammer-x/stress-split-erasure-code upgrade sequence comes from
hammer-x/stress-split and was modified to fully up... - 08:23 AM CephFS Bug #18047 (Fix Under Review): assertion in MDSMap::get_up_features()
- https://github.com/ceph/ceph/pull/12208
- 08:09 AM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- i am able to reproduce the above failure using "ctest -R test_objectstore_memstore.sh -V --repeat-until-fail 400".
... - 08:09 AM rgw Backport #18061 (Resolved): jewel: rgw:fix for deleting objects name beginning and ending with un...
- https://github.com/ceph/ceph/pull/12320
- 08:09 AM Bug #18049 (Pending Backport): timeout during ceph-disk trigger due to /var/lock/ceph-disk flock ...
- 08:08 AM Revision e69430c4 (ceph): Merge pull request #12200 from ddiss/tracker18049_ceph_disk_trigger_flo...
- systemd/ceph-disk: reduce ceph-disk flock contention
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Ke... - 08:06 AM Revision d5d7e366 (ceph): Merge pull request #12180 from tchaikov/wip-silence-get_timeout_delays
- tests: disable the echo when running get_timeout_delays()
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:04 AM Revision c23f56b9 (ceph): qa/workunits/rbd: use image id when probing for image presence
- This fixes a race in resync tests leading to false negative results.
Fixes: http://tracker.ceph.com/issues/18048
Sig... - 07:48 AM Revision c6067f48 (ceph): embedded: Add a skeleton libcephd library
- libcephd is a library that contains ceph daemon code
that can be statically linked in other applications.
Added Merg... - 07:48 AM Revision b5d57c97 (ceph): embedded: add compression and EC plugins to libcephd
- Compression and erasure coding plugins are now statically compiled
into libcephd. A new method is added to load them ... - 07:48 AM Revision 06647591 (ceph): embedded: Support for running MON and OSD from libcephd
- Added supported for running MON and OSD daemon code almost
untouched directly from libcephd.
Also added two API func... - 07:48 AM Revision 9e8519cd (ceph): embedded: Add librbd and librados to embedded ceph
- This commit add librados, librbd to the embedded ceph static library. This is needed to support daemons built with li...
- 07:48 AM Revision d447a808 (ceph): embedded: Add RADOS classes to embedded cephd library
- RADOS classes can now be statically compiled and added to
the embedded cephd library.
The RADOS ClassHandler now has... - 06:22 AM Bug #18058 (Fix Under Review): librados: new setxattr overload breaks c++ ABI
- https://github.com/ceph/ceph/pull/12206
- 06:13 AM Bug #18058 (Resolved): librados: new setxattr overload breaks c++ ABI
- Overloading a function that was not overloaded before breaks the ABI
- 06:22 AM Backport #18059 (Fix Under Review): librados: new setxattr overload breaks c++ ABI
- 06:21 AM Backport #18059 (Resolved): librados: new setxattr overload breaks c++ ABI
- https://github.com/ceph/ceph/pull/12207
- 06:14 AM Revision 79be070a (ceph): librados: remove new setxattr overload to avoid breaking the C++ ABI
- Fixes: http://tracker.ceph.com/issues/18058
Signed-off-by: Josh Durgin <jdurgin@redhat.com>
(cherry picked from commi... - 06:08 AM Revision b8ff781d (ceph): librados: remove new setxattr overload to avoid breaking the C++ ABI
- Fixes: http://tracker.ceph.com/issues/18058
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 03:47 AM Revision d368069e (ceph): librbd/ImageCtx: no need for virtual dtor
- CID 1396232 (#1 of 1): Non-virtual destructor (VIRTUAL_DTOR)
1. nonvirtual_dtor: Class librbd::<unnamed>::SafeTimerSi... - 03:47 AM Revision 79b08ef2 (ceph): Merge pull request #12170 from dzafman/wip-ec-error-tests
- test: test-erasure-eio.sh fix recovery testing and enable it
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:02 AM Bug #18057 (Resolved): shoud output hb_peers, not hb_in
- HB_IN should be replaced with HB_PEERS
11/28/2016
- 11:06 PM Revision 7d0f9776 (ceph): Merge pull request #10672 from ceph/wip-rgw-http-getcmd
- RGWHTTPArgs::get_str() - return argument string that was set.
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 11:04 PM Revision 77b7e30a (ceph): Merge pull request #10546 from cbodley/wip-rgw-log-trim-lease
- rgw multisite: use a rados lock to coordinate data log trimming
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 11:00 PM rgw-testing Bug #18055 (New): rgw: framework to test extended rest api
- test the extended apis that consist of:
user:
get_user_info
create_user
modify_user
remove_user
create_subuse... - 10:06 PM Revision 6ecb44f0 (ceph): Merge pull request #12114 from liewegas/wip-bluestore-failops
- os/bluestore: mark ops that can't tolerate ENOENT
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:59 PM Revision 7c7adc0f (ceph): Merge pull request #1287 from ceph/jewel-failed-to-encode
- upgrade/hammer-x: encoding fixes (jewel)
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:28 PM Revision 0e60bf85 (ceph): Merge pull request #12022 from jcsp/wip-17853
- mds: more deterministic timing on frag split/join
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Patrick... - 09:21 PM Revision 6c7e628c (ceph): Merge pull request #12094 from 363921219/cleanup_C_CompleteSplits
- osd: cleanup C_CompleteSplits::finish()
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:21 PM Revision 03e87016 (ceph): Merge pull request #12148 from tchaikov/wip-scan-build-fixes
- scan build fixes
Reviewed-by: Sage Weil <sage@redhat.com> - 09:18 PM Revision ccf6da4f (ceph): Merge pull request #12099 from wjin/fix_filestore_perfcounter
- os/filestore: fix journal logger
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:57 PM Bug #17824 (Fix Under Review): bluestore: multiple aios allocated at same address?
- https://github.com/ceph/ceph/pull/12204
- 08:35 PM Bug #17824 (In Progress): bluestore: multiple aios allocated at same address?
- It looks like this is the fault of aio_wait not actually waiting? Looking at logs from /a/sage-2016-11-23_20:05:59-r...
- 08:56 PM Revision 6ffaa54c (ceph): os/bluestore/KernelDevice: fix race in aio_thread vs aio_wait
- The caller is free to destroy the aio vector contents
once aio_wait completes. This is exactly what
BlueFS::_fsync()... - 08:22 PM RADOS Bug #18054 (Resolved): os/bluestore/BlueStore.cc: 3576: FAILED assert(0 == "allocate failed, wtf")
- plenty of space, but bitmap allocator fails......
- 08:01 PM Feature #18053 (Resolved): Minimize log-based recovery in the acting set
- In general, we maintain pretty long logs (3k by default) to ensure that we detect duplicate ops correctly. This has ...
- 07:35 PM Revision 4d6f8481 (ceph): crush: condition latest tunable encoding on features
- This avoids throwing hammer OSDMap encodings off.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from com... - 07:35 PM Revision bf96b30e (ceph): crush/CrushWrapper: encode with features
- No behavior change yet; just fixing callers.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit b... - 07:35 PM Revision c5f5b94f (ceph): crush/CrushWrapper: drop unused 'lean' encode() argument
- No callers, no users.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 638a38bbb55c07ad0358a35a... - 07:32 PM Feature #18052 (New): Replace past_intervals with more compact structure
- Currently, we maintain one record for every interval back to the last interval in which the pg went clean. This is p...
- 07:29 PM Revision 65c61565 (ceph): os/ObjectStore: pass by ref to clone
- CID 1395658 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter noid of type gh... - 07:29 PM Revision 4a60eadd (ceph): os/Transaction: add missing break
- CID 1395137 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: The case for value ObjectStore::Tra... - 07:29 PM Revision 08bcc85a (ceph): os/bluestore: init all fields
- 9. uninit_member: Non-static class member block_size is not initialized in this constructor nor in any functions that...
- 07:29 PM Revision 614e955d (ceph): os/bluestore: be pedantic about kv_stop locking
- Makes coverity happy.
CID 1395346 (#1 of 1): Data race condition (MISSING_LOCK)
1. missing_lock: Accessing this->kv_... - 07:29 PM Revision ac72b776 (ceph): os/ObjectStore: add missing break
- CID 1394998 (#1 of 1): Missing break in switch (MISSING_BREAK)
unterminated_case: The case for value ObjectStore::Tra... - 07:29 PM Revision 047bb40a (ceph): os/ObjectStore: pass by ref to clone_range
- CID 1395650 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter noid of type gh... - 07:29 PM Revision ff0abab8 (ceph): os/bluestore/BlueFS: init iocv
- CID 1396119 (#1 of 1): Uninitialized pointer field (UNINIT_CTOR)
2. uninit_member: Non-static class member field iocv... - 07:29 PM Revision 29847b2b (ceph): os/bluestore/BlueRocksEnv: fix strerror args
- CID 1395399 (#1 of 1): Argument cannot be negative (NEGATIVE_RETURNS)
negative_returns: A negative constant -2 is pas... - 07:29 PM Revision 5b7dc941 (ceph): os/bluestore: pass by ref to _collection_list
- CID 1395617 (#1 of 1): Big parameter passed by value (PASS_BY_VALUE)
pass_by_value: Passing parameter end of type gho... - 07:29 PM Revision 9795cea1 (ceph): os/ObjectStore: pass by ref to collection_list
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:29 PM Revision 81de672a (ceph): os/bluestore/BlueFS: check flush result
- CID 1394759 (#1 of 1): Unchecked return value (CHECKED_RETURN)
20. check_return: Calling _flush without checking retu... - 07:19 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- From ceph_d_revalidate:...
- 05:07 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Ok, thanks. I see that you had written that in the original description too. If you have the time, then it might be g...
- 03:51 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- There are 6 nodes that have mounted the same cephfs directory and 4 of them doing active R/W requests on same paths (...
- 03:44 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- That BUG_ON also looks suspicious. We may need to hold the rcu_read_lock there to ensure that dn->d_parent doesn't va...
- 03:31 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Sure...
First, does this kernel have any patches beyond what went into v4.8.4 ? There are some other BUG_ONs in th... - 12:59 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- fs/ceph/inode.c:1272 is BUG_ON(d_inode(dn->d_parent) != dir); For cephfs case, I think only thing that can change d_p...
- 11:52 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- could you please check if this issue exists in 4.5 kernel
- 09:03 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- It was quite regular load. Graphs attached.
- 02:46 AM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- what workloads trigger this bug?
- 07:15 PM Feature #17741 (Resolved): Fix but with recovery read marker and get_rw_locks assumptions
- 07:15 PM Feature #17668 (Resolved): bug with last_backfill = head when snapdir exists and a write removes ...
- 07:15 PM Feature #14040 (Resolved): ECBackend support for RMW
- 07:15 PM Feature #17690 (Resolved): workload which generates write errors (like ceph_test_rados) very occa...
- 06:44 PM Revision c844efe0 (ceph): os/bluestore/BlockDevice: init rotational
- CID 1396126 (#1 of 1): Uninitialized scalar field (UNINIT_CTOR)
2. uninit_member: Non-static class member rotational ... - 05:08 PM Revision 308c4ec9 (ceph): Merge pull request #12201 from tchaikov/wip-memstore-leak
- os/memstore: fix a mem leak in MemStore::Collection::create_object()
Reviewed-by: Casey Bodley <cbodley@redhat.com>
... - 04:56 PM Revision 2eba6252 (ceph): upgrade/hammer-x/stress-split-*: disable sighup injection
- We already did this for stress-split; do the same
here. It triggers a File closed exception when the greenlet
is joi... - 04:55 PM Revision 8a62cbc0 (ceph): systemd/ceph-disk: reduce ceph-disk flock contention
- "ceph-disk trigger" invocation is currently performed in a mutually
exclusive fashion, with each call first taking an... - 04:12 PM Revision a52a21b6 (ceph): os/memstore: fix a mem leak in MemStore::Collection::create_object()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:34 PM Revision 3c8711e6 (ceph): rgw: add documentation for upgrading with rgw_region_root_pool
- Signed-off-by: Orit Wasserman <owasserm@redhat.com>
- 03:29 PM Revision 5ff2680c (ceph): upgrade/hammer-x/parallel: white 'failed to encode'
- The problem here has nothing to do with osdmap
encoding, but that hammer -> jewel makes the systemd
transition and in... - 02:48 PM rgw Bug #16355: radosgw-admin command, adding the tenants can not view the user usage
- I have the same error when trying to see user stats for a user which is not in the default tenant. Syncing stats thro...
- 02:37 PM Linux kernel client Feature #17524: krbd: support disabling auto-exclusive lock transition logic
- Reference: https://github.com/kubernetes/kubernetes/issues/33013
- 02:29 PM CephFS Feature #11950 (In Progress): Strays enqueued for purge cause MDCache to exceed size limit
- 02:25 PM rbd Bug #18051 (Resolved): "rbd mirror image resync" does not force resync after split-brain
- If split-brain is detected for a mirroring image, running "rbd mirror image resync" command for this image is expecte...
- 02:21 PM Bug #18049: timeout during ceph-disk trigger due to /var/lock/ceph-disk flock contention
- 01:08 PM Bug #18049 (Resolved): timeout during ceph-disk trigger due to /var/lock/ceph-disk flock contention
- ceph-disk@.service handles udev device events by calling "ceph-disk trigger", which in turn handles service restart f...
- 02:09 PM Revision 60a83242 (ceph): rados: add hints to rados bench
- By default, hint with the rados bench IO size and with sequential read
and write flags. Unless the --no-hints option... - 01:25 PM CephFS Feature #18050 (New): Enable mounting a .snap directory from libcephfs/ceph-fuse
Manila is adding a "mountable snapshots" feature:
https://github.com/openstack/manila-specs/blob/master/specs/ocat...- 11:23 AM rbd Cleanup #16991 (In Progress): rbd-mirror split-brain issues should be clearly visible in mirror s...
- 11:20 AM Revision 7f6f9ac5 (ceph): pybind: conditional compile the linux specific constant
- FreeBSD does not have ENODATA, let's follow the example in compat.h,
map ENOATTR to NoData.
Signed-off-by: Kefu Chai... - 11:06 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- It looks like var-lib-ceph.mount does not depend on lvm2-monitor.service even indirectly although it should. Not sure...
- 11:00 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- After setting up the environment as described at http://tracker.ceph.com/issues/17889#note-2 the dependencies are aut...
- 10:52 AM Bug #17889 (In Progress): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 10:52 AM Bug #17889: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- It turns out this may not be fixed after all : https://github.com/ceph/ceph/pull/12136#issuecomment-263007276
May... - 09:36 AM Bug #17889 (Pending Backport): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 09:34 AM Bug #17889 (In Progress): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 10:54 AM Bug #17813 (Pending Backport): ceph-disk: udev permission race with dm
- 10:54 AM Bug #17813: ceph-disk: udev permission race with dm
- https://github.com/ceph/ceph/pull/12136 is the right thing to do to deal with this problem but depends on #17889 bein...
- 10:06 AM rbd Bug #18048 (Fix Under Review): qa: rbd-mirror workunit false negative when waiting for image dele...
- PR: https://github.com/ceph/ceph/pull/12195
- 10:05 AM rbd Bug #18048 (Resolved): qa: rbd-mirror workunit false negative when waiting for image deleted afte...
- In qa/workunits/rbd/rbd_mirror.sh, when testing resync, we wait first for the image to be deleted and then check that...
- 09:43 AM CephFS Bug #18047 (Resolved): assertion in MDSMap::get_up_features()
- ...
- 07:27 AM Revision 5233aa0b (ceph): Merge pull request #12168 from liewegas/doc-perf
- doc/dev/perf: a few notes on perf
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:03 AM CephFS Feature #12132 (In Progress): cephfs-data-scan: Cleanup phase
- The following xattrs are added to zeroth object:
#define XATTR_CEILING "scan_ceiling"
#define XATTR_MAX_MTIME "... - 04:33 AM Revision 5af29540 (ceph): test,cmake: turn unit.h into unit.cc to speed up compilation
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 04:33 AM Revision ce4f641b (ceph): cmake: disable -fvar-tracking-assignments for osdcap.cc
- this silences the warning of
/home/jenkins-build/build/workspace/ceph-pull-requests/src/test/osd/osdcap.cc:
In membe... - 03:46 AM Revision 557231e0 (ceph): ceph_argparse: simplify argv_to_vec() using vector::insert()
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:40 AM Revision da9be4ce (ceph): Merge pull request #12176 from ovh/wip-doc-osd-scrub-during-recovery-ch...
- doc: Add doc about osd scrub {during recovery|chunk {min|max}| sleep}
Reviewed-by: Abhishek Lekshmanan <abhishek@sus... - 03:07 AM Revision c2782aaa (ceph): Merge pull request #10297 from Yan-waller/yj-wip-msgsimple-0714
- msg/simple: save the errno in case being changed by subsequent codes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:07 AM Revision af080303 (ceph): Merge pull request #11154 from stiopaa1/osd_pg_useMoveOnSharedPtr
- osd/PG.h: move shared ptr instead of copying it
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:01 AM Revision 8db48a32 (ceph): Merge pull request #12186 from chrone81/patch-1
- doc: Remove duplicate command for Ubuntu
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:55 AM Bug #17999: ec scrub mismatch during teuthology run
- * http://pulpito.ceph.com/kchai-2016-11-27_12:44:55-rados-wip-kefu-testing2---basic-mira/581643/
* http://pulpito.ce... - 01:58 AM Bug #18046: filestore: sync_entry timed out cause osd crash
- can we do this?...
- 01:52 AM Bug #18046 (Closed): filestore: sync_entry timed out cause osd crash
- hello, i got filestore sync_entry thread hung, and crashed osd after 600s
here is the sync_entry thread backtrace:
... - 01:46 AM Revision d0a6f017 (ceph): rgw: fix slave zonegroup cannot enable the bucket versioning
- Signed-off-by: lvshuhua <lvshuhua@cmss.chinamobile.com>
- 01:24 AM CephFS Bug #17911 (Resolved): ensure that we vet the ceph_statx flags masks in libcephfs API
- Merged in https://github.com/ceph/ceph/pull/12106
- 12:00 AM Revision 49eafeb5 (ceph): Merge pull request #12106 from ceph/wip-jlayton-libcephfs
- API cleanup for libcephfs interfaces
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
11/27/2016
- 07:06 PM Revision 2a9a80b6 (ceph): Merge pull request #1285 from ceph/jewel-failed-to-encode
- upgrade/hammer-x: do not whitelist 'failed to encode map'
- 06:02 PM Revision 2ba74089 (ceph): doc: Remove duplicate command for Ubuntu
- Remove duplicate "sudo service radosgw restart id=rgw.<short-hostname>" command for Ubuntu in Configure Bucket Shardi...
- 04:19 PM RADOS Bug #17743: ceph_test_objectstore & test_objectstore_memstore.sh crashes in qa run (kraken)
- "ceph_test_objectstore --gtest_filter=\*/0" also, see
https://jenkins.ceph.com/job/ceph-pull-requests/14959/consol... - 12:46 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- ...
- 12:42 PM Linux kernel client Bug #18045 (Duplicate): BUG_ON(d_inode(dn->d_parent) != dir) in fs/ceph/inode.c
- Dup of #18041, moved from the fs project.
- 12:21 PM Linux kernel client Bug #18045 (Duplicate): BUG_ON(d_inode(dn->d_parent) != dir) in fs/ceph/inode.c
- On IRC:
< donatas> kernel panics ~3-5 every day...
11/26/2016
- 11:37 PM Revision a97f1bec (ceph): upgrade/hammer-x/parallel: upgrade osds first
- Signed-off-by: Sage Weil <sage@redhat.com>
- 11:37 PM Revision ca212479 (ceph): upgrade/hammer-x: do not whitelist 'failed to encode map'
- Well, on parallel. For the others, keep it in
place because we don't upgrade osds first (we are testing
other things... - 09:56 PM Revision 2b2510e1 (ceph): FreeBSD/radosgw-admin can be build
- Signed-off-by: Willem Jan Withagen <wjw@digiware.nl>
11/25/2016
- 09:50 PM Revision 862b47fa (ceph): thrashosds: try ceph-objectstore-tool for 10 minutes
- If ceph-objectstore-tool binary is not present, it's likely because we're in
the middle of an upgrade. Do not try to ... - 07:24 PM Bug #17813 (In Progress): ceph-disk: udev permission race with dm
- 06:23 PM Stable releases Tasks #17151: hammer v0.94.10
- h3. fs
Pushed hammer-backports-14716 with revert of http://github.com/ceph/ceph/commit/4a36933 which was recently ... - 04:30 PM rgw Bug #17888 (Pending Backport): rgw:fix for deleting objects name beginning and ending with unders...
- 04:30 PM Revision a8e359f1 (ceph): Merge pull request #11982 from zhouruisong/master
- rgw:bugfix for deleting objects name beginning and ending with underscores of one bucket using POST method of AWS's j...
- 03:16 PM Revision e2c848d5 (ceph): Merge pull request #9859 from x11562/OSDMap
- mon: osdmap's epoch should be more than 0
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Joao Eduardo Luis <... - 03:12 PM Revision 4862a0e1 (ceph): Merge pull request #9172 from majianpeng/librados-add-fullforce
- librados: For C-API, expose LIBRADOS_OPERATION_FULL_FORCE flag
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Revi... - 03:10 PM Revision 92f1e89b (ceph): Merge pull request #10553 from songbaisen/c3
- osd: remove the redundant clear method in consume_map function
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:07 PM Revision 9139bba9 (ceph): Merge pull request #12117 from 363921219/cleanup_PeeringWQ_dequeue
- osd: clean up PeeringWQ::_dequeue(), remove unnecessary variable
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:05 PM Revision 8a19d185 (ceph): Merge pull request #11841 from hjwsm1989/filestore
- os/filestore: avoid to get the wrong hardlink number.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:03 PM Revision 2e3ea2ee (ceph): Merge pull request #11913 from wjwithagen/wip-wjw-freebsd-aio-inline
- os/fs/FS.cc: condition on WITH_AIO for FreeBSD
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:01 PM Revision 42a126e3 (ceph): Merge pull request #9062 from majianpeng/aio-pwritev
- os/fs/FS: optimize aio::pwritev which make caller provide length.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:44 PM RADOS Bug #18043 (Closed): ceph-mon prioritizes public_network over mon_host address
- Problem description:
Not using sections to declare ceph monitors results in monitors listening on the public_clust... - 02:36 PM Bug #18042 (Resolved): SimpleMessenger debug delay injection deadlock
- ...
- 02:30 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- More info about the incident.
Topology:
2 osd nodes with 24 total osds
3 monitor/mds nodes
6 cephfs kernel clie... - 01:56 PM Linux kernel client Bug #18041: periodically kernel crashes with CephFS
- Any more clues about what else might have changed in the last few days?
- 01:11 PM Linux kernel client Bug #18041 (Resolved): periodically kernel crashes with CephFS
- Hi,
last few days we are having ~5-15 kernel crashes according to:... - 02:23 PM Revision 65874846 (ceph): drop broken name length config args
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 2a44c3d20de9a75065c271e9ad8dfceeed1186d9) - 09:51 AM Bug #18037: leveldb corruption leads to "Operation not permitted not handled" and assert
- > This OSD had XFS corruption which was repaired. Maybe the xfs_repair restored a file, but left it owned by root? I'...
- 09:50 AM rgw Bug #17996: rgw: ECANCELED in rgw_get_system_obj() leads to infinite loop
- master pr: -https://github.com/ceph/ceph/pull/12179-
- 08:39 AM Revision 708e6405 (ceph): os/bluestore: drop member "space" from Onode
- We can assess it through collection instead, which can therefore
save us some memory.
Signed-off-by: xie xingguo <xi... - 05:55 AM Revision d274df74 (ceph): mon: PGMonitor add check only concern our self cluster command
- we only concern the command send to our self cluster
Signed-off-by:song baisen <song.baisen@zte.com.cn> - 03:20 AM Revision fbb0987d (ceph): Merge pull request #12183 from dachary/wip-17830-eio
- tests: facilitate background process debug in ceph-helpers.sh
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:15 AM Revision 36cc8c48 (ceph): mon: avoid start election twice when quorum enter
- when quorum enter it is no meaning to start election twice
Signed-off-by: song baisen <song.baisen@zte.com.cn> - 03:07 AM Revision ebea0ac8 (ceph): mon: OSDMonitor preprocess_pool_op add check only concern our self clus...
- we only concern the commands send to ourself cluster
Signed-off-by:song baisen <song.baisen@zte.com.cn>
11/24/2016
- 08:35 PM CephFS Documentation #18040: Documentation says not to run multiple MDS, but we can do that now
- Merged to master -- I leave it up to you whether you want to backport (I don't usually do that for documentation)
- 07:31 PM CephFS Documentation #18040 (Fix Under Review): Documentation says not to run multiple MDS, but we can d...
- https://github.com/ceph/ceph/pull/12184
- 07:28 PM CephFS Documentation #18040 (Resolved): Documentation says not to run multiple MDS, but we can do that now
- http://docs.ceph.com/docs/master/rados/deployment/ceph-deploy-mds/ has a red box that says "Do not run multiple metad...
- 08:35 PM Revision b569c8df (ceph): Merge pull request #12184 from SUSE/wip-18040
- doc: we can now run multiple MDS, so qualify warning
Reviewed-by: John Spray <john.spray@redhat.com> - 07:29 PM Revision effc36c0 (ceph): doc: we can now run multiple MDS, so qualify warning
- Fixes: http://tracker.ceph.com/issues/18040
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 06:52 PM Revision f491ea06 (ceph): tests: facilitate background process debug in ceph-helpers.sh
- When displaying the output of a background process, do it on stderr so
that it is not bufferized. Otherwise the outpu... - 05:29 PM Bug #17762 (Pending Backport): transient jerasure unit test failures
- 05:28 PM Bug #18037 (Fix Under Review): leveldb corruption leads to "Operation not permitted not handled" ...
- This PR improves the error message: https://github.com/ceph/ceph/pull/12181
- 05:18 PM Bug #18037 (In Progress): leveldb corruption leads to "Operation not permitted not handled" and a...
- 05:07 PM Bug #18037: leveldb corruption leads to "Operation not permitted not handled" and assert
- Here is the code: https://github.com/ceph/ceph/blob/jewel/src/os/filestore/FileStore.cc#L2880-L2899
- 05:01 PM Bug #18037: leveldb corruption leads to "Operation not permitted not handled" and assert
- ...
- 04:42 PM Bug #18037: leveldb corruption leads to "Operation not permitted not handled" and assert
- ceph version 10.2.2
- 04:41 PM Bug #18037 (Resolved): leveldb corruption leads to "Operation not permitted not handled" and assert
- we have a jewel OSD that doesn't start due to leveldb corruption (looks like). We upped the debug levels and can see ...
- 05:27 PM Revision 44aaeb7f (ceph): Merge pull request #11733 from tchaikov/wip-17762
- common: release g_ceph_context before returns
Reviewed-by: Loic Dachary <ldachary@redhat.com>
Reviewed-by: Sage Weil... - 05:24 PM Revision b06557ec (ceph): Merge pull request #12172 from dachary/wip-17830-eio
- tests: osd-scrub-repair.sh abort if add_something fails
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:54 PM RADOS Bug #17830: osd-scrub-repair.sh is failing (intermittently?) on Jenkins
- https://jenkins.ceph.com/job/ceph-pull-requests/14911/console from https://github.com/ceph/ceph/pull/12081
timesou... - 03:52 PM RADOS Bug #17830: osd-scrub-repair.sh is failing (intermittently?) on Jenkins
- https://jenkins.ceph.com/job/ceph-pull-requests/14906/console from https://github.com/ceph/ceph/pull/12061
It time... - 06:47 AM RADOS Bug #17830 (Resolved): osd-scrub-repair.sh is failing (intermittently?) on Jenkins
- 06:27 AM RADOS Bug #17830: osd-scrub-repair.sh is failing (intermittently?) on Jenkins
- 04:44 PM Bug #17757: test-erasure-eio.sh failing in jenkins tests on PRs
- https://jenkins.ceph.com/job/ceph-pull-requests/14909/console from https://github.com/ceph/ceph/pull/12177
- 04:21 PM Bug #18027: test_objectstore_memstore.sh transient failure
- *Assertion `bl_eq(state->contents[hoid].data, r2)' failed.* is also found in http://tracker.ceph.com/issues/17743#note-2
- 04:13 PM Bug #18027: test_objectstore_memstore.sh transient failure
- https://jenkins.ceph.com/job/ceph-pull-requests/14910/console...
- 01:51 PM Bug #18027 (Duplicate): test_objectstore_memstore.sh transient failure
- https://jenkins.ceph.com/job/ceph-pull-requests/14858/console timeout after 1h and the tail is...
- 04:17 PM Revision 1b9bc050 (ceph): tests: disable the echo when running get_timeout_delays()
- this function is very distracting when one is looking at the log
Signed-off-by: Kefu Chai <kchai@redhat.com> - 03:00 PM Bug #18036 (Resolved): unittest_throttle transient timeout
- https://jenkins.ceph.com/job/ceph-pull-requests/14895/console...
- 02:44 PM rgw Bug #17996 (In Progress): rgw: ECANCELED in rgw_get_system_obj() leads to infinite loop
- 01:10 PM rgw Bug #17996: rgw: ECANCELED in rgw_get_system_obj() leads to infinite loop
- What is the number of retries we should be attempting here?
- 02:38 PM Revision cb1cda96 (ceph): common,test: g_ceph_context->put() upon return
- prior to this change, global_init() could create a new CephContext
and assign it to g_ceph_context. it's our responsi... - 02:38 PM Revision d305cc51 (ceph): crushtool: do not release g_ceph_context at exit
- it is but a work around of occasionally timeout.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 02:13 PM Revision 71c03bc6 (ceph): doc: Add doc about osd scrub {during recovery|chunk {min|max}| sleep}
- Signed-off-by: Paweł Sadowski <pawel.sadowski@corp.ovh.com>
- 01:57 PM Bug #18030 (Resolved): tests: unittest_pglog timeout
- 01:32 PM rgw Bug #17215 (Fix Under Review): Unable to suspend a user that is part of a tenant
- 01:27 PM Revision 073240c8 (ceph): Merge pull request #10296 from songbaisen/b4
- mon: small change on the HealthMonitor start_epoch function
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-... - 01:25 PM CephFS Bug #18016 (Need More Info): cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- I'll keep posting on this issue whenever I find such an error. If nothing happens in a month or two we can probably f...
- 10:52 AM CephFS Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- Can't tell what was going on here without logs from the services (which afaik we don't gather in these situations?)
... - 08:10 AM CephFS Bug #18016: cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- https://jenkins.ceph.com/job/ceph-pull-requests/14881/console
- 06:07 AM CephFS Bug #18016 (Duplicate): cephtool-test-mds.sh waiting for an active MDS daemon (intermittent)
- ...
- 10:57 AM Stable releases Tasks #17151: hammer v0.94.10
- h3. fs...
- 10:55 AM Stable releases Tasks #17151: hammer v0.94.10
- h3. rgw...
- 10:50 AM rgw Backport #18025 (In Progress): jewel: rgw: gc records empty entries
- 10:47 AM rgw Backport #18025 (Resolved): jewel: rgw: gc records empty entries
- https://github.com/ceph/ceph/pull/12174
- 10:49 AM Revision d4a28eba (ceph): rgw: don't store empty chains in gc
- Fixes: http://tracker.ceph.com/issues/17897
Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
(cherry picked from comm... - 10:47 AM CephFS Backport #18026 (Resolved): jewel: ceph_volume_client.py : Error: Can't handle arrays of non-strings
- https://github.com/ceph/ceph/pull/12325
- 10:47 AM rbd Backport #18024 (Resolved): jewel: "FAILED assert(m_processing == 0)" while running test_lock_fen...
- https://github.com/ceph/ceph/pull/12323
- 10:45 AM Revision 15c6147f (ceph): doc: explain directory fragmenation settings
- ...and update the config ref.
Includes the new mds_bal_fragment_fast_factor setting.
Signed-off-by: John Spray <joh... - 10:37 AM Revision 3210ee77 (ceph): mds: try fragmenting new fragments during split
- In case insertions have occurred during the split that would
immediately take the new fragments over the split thresh... - 10:36 AM Revision 241b49fd (ceph): mds/MDBalancer: separate out fragmentation from hit_dir
- In _fragment_finish we would like to try splitting
the new frags without applying a spurious hit to their
temperature... - 10:36 AM Revision ed134e7d (ceph): mds: maybe_fragment earlier in openc
- Check it during the initial request, not just
on completion, so that when doing lots of creates
we get a chance to sp... - 10:36 AM Revision 819d34e9 (ceph): mds: more deterministic timing on frag split/join
- ...by using timer instead of tick()
Fixes: http://tracker.ceph.com/issues/17853
Signed-off-by: John Spray <john.spra... - 10:33 AM Revision a8d55b09 (ceph): mds/MDBalancer: remove stale show_imports fn
- This was just dropping its argument and
calling through to show_subtrees.
Signed-off-by: John Spray <john.spray@redh... - 10:32 AM Revision 1e94794b (ceph): common: remove unused mds_bal_merge_[rd|wr]
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:32 AM Revision aba7aa6a (ceph): mds: fix fragment thrasher
- The allows_dirfrags() test was in the wrong place, causing
in some cases a root fragment to be passed into queue_merg... - 10:29 AM rgw-testing Bug #18023 (Resolved): Add s3test for multiple object delete with object names the begin and end ...
- testing issue: http://tracker.ceph.com/issues/17888
- 10:26 AM Revision 6c1439bc (ceph): mds: include fragmenting in state print
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:26 AM Revision 8d5cb931 (ceph): mds: tweak merge/split counters
- Increment these when we have finished splitting
or merging, not partway through the process.
This makes testing more... - 10:22 AM Revision aef133d5 (ceph): mds: add a performance counter for dirfrag merge
- Signed-off-by: John Spray <john.spray@redhat.com>
- 08:55 AM RADOS Bug #18021: Assertion "needs_recovery" fails when balance_read reaches a replica OSD where the ta...
- In my test, when encountering a large number of "balance_reads", the OSDs can be so busy that they can't send heartbe...
- 08:43 AM RADOS Bug #18021 (Duplicate): Assertion "needs_recovery" fails when balance_read reaches a replica OSD ...
- 2016-10-25 19:00:00.626567 7f9a63bff700 -1 error_msg osd/ReplicatedPG.cc: In function 'void ReplicatedPG::wait_for_un...
- 08:53 AM CephFS Bug #17656: cephfs: high concurrent causing slow request
- Greg Farnum wrote:
> Just from the description it sounds like we're backing up while the MDS purges deleted files fr... - 08:47 AM Bug #18022 (Can't reproduce): tests: osd-crush.sh sometime fails
- https://jenkins.ceph.com/job/ceph-pull-requests/14894/console...
- 08:35 AM Revision 61e01f06 (ceph): mon: small change on the HealthMonitor start_epoch function
- No need to call start_epoch function each time in the loop.
Signed-off-by: songbaisen <song.baisen@zte.com.cn> - 08:27 AM RADOS Bug #17949: make check: unittest_bit_alloc get_used_blocks() >= 0
- https://jenkins.ceph.com/job/ceph-pull-requests/14894/console
- 08:25 AM rgw Bug #17897: rgw: gc records empty entries
- realized its been fixed already
- 05:52 AM rgw Bug #17897: rgw: gc records empty entries
- https://github.com/ceph/ceph/pull/11969
- 08:15 AM Revision bfda134f (ceph): Merge pull request #10437 from odivlad/fix-doc
- hammer: docs: Bucket object versions
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 08:07 AM Bug #18018: tests: ceph-helpers.sh races when killing daemons
- I thought maybe it was jenkins being rebooted or something, but both osd-crush.sh and osd-scrub-repair.sh happened ho...
- 08:05 AM Bug #18018: tests: ceph-helpers.sh races when killing daemons
- osd-crush.sh experienced a similar and unexplained termination (see logs)
- 08:00 AM Bug #18018: tests: ceph-helpers.sh races when killing daemons
- Blocked by http://tracker.ceph.com/issues/18019, wait for it to be resolved to restore something stable.
- 06:49 AM Bug #18018 (Can't reproduce): tests: ceph-helpers.sh races when killing daemons
https://jenkins.ceph.com/job/ceph-pull-requests/14885/console...- 07:36 AM Revision 03af4aae (ceph): Don't loop forever when reading data from 0 sized segment.
- The 0 sized segment can arise depending on how
the client uploads the object in the first place.
The cpu loop then ha... - 07:32 AM Revision d585e92e (ceph): Merge pull request #9513 from songbaisen/a5
- mon: Forbidden copy and assignment function in monoprequest
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:01 AM Revision cca0f591 (ceph): Merge pull request #12085 from wjwithagen/wip-freebsd-ceph-helpers-2
- workunits/ceph-helpers.sh: Fixes for FreeBSD
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:52 AM Revision 9ad8ce28 (ceph): tests: osd-scrub-repair.sh abort if add_something fails
- If the script keeps going after this function fails, it will be non
trivial to find the root cause of the problem.
S... - 06:18 AM Revision 9731121f (ceph): osd: remove the redundant clear method in consume_map function
- In the above loop before this to_remove to clear,we have remove all
the element.So this clear method is redundant.
... - 04:20 AM rgw Bug #17995: rgw: zonegroup add cmd didn't update zone's realm_id
- https://github.com/ceph/ceph/pull/12139
- 03:53 AM Revision 20c445c8 (ceph): Merge pull request #11943 from wido/docs-pool-remove
- doc: Add documentation about mon_allow_pool_delete before pool remove
Reviewed-by: Loic Dachary <ldachary@redhat.com... - 03:48 AM Revision 2dda81d1 (ceph): rgw:fix for deleting objects name beginning and ending with underscores...
- Fixes: http://tracker.ceph.com/issues/17888
Signed-off-by: zhouruisong 236131368@qq.com - 03:47 AM Revision 4f592255 (ceph): test: test-erasure-eio.sh fix recovery testing and enable it
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 01:43 AM Revision ed583d39 (ceph): OSD: remove redudant call of heartbeat_check. Heartbeat_check is alread...
- Signed-off-by: Pan Liu <pan.liu@istuary.com>
- 12:57 AM Revision e4629b33 (ceph): workunits/ceph-helpers.sh: Fixes for FreeBSD
- - stat(1) does not have '%T'
Signed-off-by: Willem Jan Withagen <wjw@digiware.nl> - 12:47 AM Revision 9e2645a8 (ceph): ECTransaction: adjacent extents might have unaligned boundaries
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 12:40 AM Revision dd7a58b4 (ceph): msg/simple/Pipe:the returned value for do_recv unequal to zero
- the returned value for do_recv unequal to zero:
ssize_t Pipe::do_recv(char *buf, size_t len, int flags)
{
again:
s...
11/23/2016
- 11:51 PM Bug #17916: osd/PGLog.cc: 1047: FAILED assert(oi.version == i->first)
- Hmm, that might be able to cause inconsistently applied transactions (though I don't think so...)
- 11:43 PM Bug #17831 (In Progress): osd: ENOENT on clone
- https://github.com/athanatos/ceph/tree/wip-17831 -- it'll be a little bit before I have time to test and debug it.
- 11:40 PM Bug #17831: osd: ENOENT on clone
- 10:13 PM Bug #17831: osd: ENOENT on clone
- Xinze Chi's diagnosis is entirely correct. This is actually pretty simple, just need to modify ReplicatedBackend to ...
- 10:41 PM Revision ae772b8d (ceph): os/bluestore: set csum order based on alloc hints
- If the users hints that this object is sequentially read and written we
can use a larger csum order.
Signed-off-by: ... - 10:29 PM Stable releases Tasks #17151: hammer v0.94.10
- h3. rados...
- 10:28 PM Stable releases Tasks #17151: hammer v0.94.10
- ...
- 10:13 PM Revision 88fcf658 (ceph): include/rados: fix ALLOC_HINT_FLAG_{SEQUENTIAL_WRITE,RANDOM_WRITE} names
- Oops.
Signed-off-by: Sage Weil <sage@redhat.com> - 10:12 PM Revision c7220ccc (ceph): common/TrackedOp: Handle dump racing with constructor
- Use is_tracked to prevent TrackedOp::dump() from trying to call
virtual function while still in OpRequest constructor... - 10:12 PM Revision 8312dc61 (ceph): common/TrackedOp: Move tracking_enabled check into register_inflight_op()
- Make tracking_enabled (and the lock private.)*
Signed-off-by: David Zafman <dzafman@redhat.com>
(Partial cherry pick... - 10:12 PM Revision 656d0c9f (ceph): common/TrackedOp: Should lock ops_history_lock when access shutdown.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
(cherry picked from commit 7fe72a2e7d116093ccff6683666e6289f5f12421) - 10:12 PM Revision 3e00ee5c (ceph): osd: add dump_blocked_ops asok command.
- From ceph health we can see there are blocked ops and from 'ceph health
detai' we can see which osd has blocked ops. ... - 10:12 PM Revision 6a7fbf42 (ceph): osd: cleanup: Specify both template types for create_request()
- Code consistency
Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit cecdc49e6d2f38d5eb9f852... - 10:12 PM Revision 5717eb00 (ceph): mds, osd: Fix missing locking for "dump_blocked_ops"
- Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit be5bed840f21da998be3b8374a8e33f208258e1b)... - 10:12 PM Revision ce586885 (ceph): CLEANUP: Move locking into dump_ops_in_flight()/dump_historic_ops()
- Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 17c645f70708134f50374cadb5505b0babe2265a)... - 10:12 PM Revision e8e76642 (ceph): common/TrackedOp: Missed locking when examining "events"
- Another crash caused by a dump_ops_in_flight similar to #8885
Signed-off-by: David Zafman <dzafman@redhat.com>
(cher... - 10:05 PM Revision f5a15f04 (ceph): doc/dev/perf: a few notes on perf and flame graphs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:57 PM devops Fix #16440 (Resolved): [initscripts]: systemd-run is not needed in initscripts
- 09:55 PM devops Backport #16441 (Resolved): jewel: [initscripts] systemd-run is not needed in initscripts
- 09:51 PM devops Backport #16442 (Resolved): hammer: [initscripts]: systemd-run is not needed in initscripts
- 09:50 PM Revision 9bf08ddc (ceph): Merge pull request #9873 from odivlad/fix-init-el7-hammer
- hammer: build/ops: remove SYSTEMD_RUN from initscript
Reviewed-by: Orit Wasserman <owasserm@redhat.com>
Reviewed-by:... - 09:49 PM CephFS Backport #17285 (Resolved): ceph-mon leaks in MDSMonitor when ceph-mds process is running but MDS...
- 09:49 PM Revision 9655228d (ceph): Merge pull request #10238 from aiicore/hammer
- hammer: mon: fix memory leak in prepare_beacon
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: John Spray <jo... - 09:45 PM Revision cc90274d (ceph): crush: condition latest tunable encoding on features
- This avoids throwing hammer OSDMap encodings off.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:45 PM Revision b7c9e055 (ceph): crush/CrushWrapper: encode with features
- No behavior change yet; just fixing callers.
Signed-off-by: Sage Weil <sage@redhat.com> - 09:44 PM Backport #16918 (Resolved): hammer: making stop.sh more portable
- 09:44 PM Revision e2c3e21a (ceph): Merge pull request #10569 from jschmid1/wip-16918-hammer
- hammer: build/ops: make stop.sh more portable
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 09:42 PM Revision 4af4ef09 (ceph): Merge pull request #10402 from ceph/wip-openstack-wusui
- qa: Add ceph-ansible installer.
- 09:41 PM Bug #16525 (Resolved): mon crash: crush/CrushWrapper.h: 940: FAILED assert(successful_detach)
- 09:41 PM Backport #16584 (Resolved): hammer: mon crash: crush/CrushWrapper.h: 940: FAILED assert(successfu...
- 09:40 PM Revision 8f3548cc (ceph): upgrade/hammer-x: fix symlinks
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:40 PM Revision 637d348a (ceph): Merge pull request #10724 from Vicente-Cheng/wip-16584-hammer
- hammer: crush: reset bucket->h.items[i] when removing tree item
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:39 PM Stable releases Tasks #17851: jewel v10.2.6
- h3. ceph-disk...
- 09:38 PM Stable releases Tasks #17851: jewel v10.2.6
- h3. Upgrade...
- 09:37 PM Stable releases Tasks #17851: jewel v10.2.6
- h3. powercycle...
- 09:36 PM Stable releases Tasks #17851: jewel v10.2.6
- h3. fs...
- 09:35 PM Stable releases Tasks #17851: jewel v10.2.6
- h3. rados...
- 08:42 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. rgw...
- 08:41 AM Stable releases Tasks #17851: jewel v10.2.6
- h3. rbd...
- 08:39 AM Stable releases Tasks #17851: jewel v10.2.6
- ...
- 09:34 PM Bug #17966 (Resolved): test-erasure-eio.sh can crash osd
- 09:20 PM Revision 84df525e (ceph): Merge pull request #10904 from tchaikov/wip-14470-hammer
- hammer: mon: return size_t from MonitorDBStore::Transaction::size()
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Re... - 09:19 PM Bug #11101 (Resolved): ceph tell: broken error message / misleading hinting
- 09:18 PM Revision a7c8c511 (ceph): Merge pull request #10905 from SUSE/wip-11101-hammer
- hammer: build/ops: improve ceph.in error message
Reviewed-by: Sage Weil <sage@redhat.com> - 09:17 PM rbd Bug #16887 (Resolved): ceph 10.2.2 rbd status on image format 2 returns "(2) No such file or dire...
- 09:17 PM rbd Backport #16952 (Resolved): hammer: ceph 10.2.2 rbd status on image format 2 returns "(2) No such...
- 09:16 PM Revision c8f54c84 (ceph): Merge pull request #10987 from Vicente-Cheng/wip-16592-hammer
- hammer: librbd: ceph 10.2.2 rbd status on image format 2 returns "(2) No such file or directory"
Reviewed-by: Jason ... - 09:14 PM Bug #17400 (Resolved): mon/tool: PGMonitor::check_osd_map assert fail when the rebuild mon store
- 09:14 PM Backport #17602 (Resolved): hammer: mon/tool: PGMonitor::check_osd_map assert fail when the rebui...
- 09:13 PM Feature #17179 (Resolved): add a tool to rebuild mon store from OSD
- 09:13 PM Backport #17291 (Resolved): hammer: add a tool to rebuild mon store from OSD
- 09:13 PM Revision 48b6054a (ceph): Merge pull request #11125 from tchaikov/wip-17179-hammer
- hammer: tools: add a tool to rebuild mon store from OSD
Reviewed-by: Nathan Cutler <ncutler@suse.com> - 09:11 PM Bug #17390 (Resolved): OSDMonitor: Missing nearfull flag set
- 09:11 PM Backport #17403 (Resolved): hammer: OSDMonitor: Missing nearfull flag set
- 09:10 PM Revision a97c81c3 (ceph): Merge pull request #11273 from aiicore/wip-17403-hammer
- hammer: mon: OSDMonitor: Missing nearfull flag set
Reviewed-by: Sage Weil <sage@redhat.com> - 09:07 PM Bug #16002 (Resolved): ObjctCacher: doesn't correctly handle read replies on split BufferHeads
- 09:06 PM Backport #16546 (Resolved): hammer: ObjectCacher doesn't correctly handle read replies on split B...
- 09:06 PM Revision c4cee499 (ceph): Merge pull request #11618 from asheplyakov/hammer-16546
- hammer: rbd: fix possible rbd data corruption
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:58 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- For the record I added *Author: Loic Dachary* in files where the contribution I made was covered by copyright (i.e. n...
- 07:41 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- I am not removing anyone's name: Loic's name is still in the Authors file.
This is not something I am doing withou... - 07:19 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- But removing other people's names without asking is always going to be controversial, right?
- 02:36 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- I didn't think a whole-project change was the right thing to do. I worked on ceph-disk for this ticket, so I updated ...
- 02:33 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- Not to diminish anyone's contribution, but Loic did author over half of the lines:...
- 02:27 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- I just did "egrep -r 'Author:' src/" in a ceph/ceph clone and saw that there are many lines similar to this one in th...
- 01:26 PM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- I think there was a discussion on what 'authors' should be at some point. I don't remember all the details (this tick...
- 11:02 AM Bug #16125: ceph-disk should not spit out a traceback when a subprocess.call errors
- @alfredo could you explain the purpose of this change in this context:...
- 08:57 PM Bug #15943 (Resolved): crash adding snap to purged_snaps in ReplicatedPG::WaitingOnReplicas
- 08:56 PM Backport #16151 (Resolved): hammer: crash adding snap to purged_snaps in ReplicatedPG::WaitingOnR...
- 08:56 PM Revision 94955846 (ceph): Merge pull request #11676 from asheplyakov/hammer-16151
- hammer: osd: update PGPool to detect map gaps and reset cached_removed_snaps
Reviewed-by: Samuel Just <sjust@redhat.... - 08:54 PM rgw Backport #17840 (Resolved): hammer: rgw: the value of total_time is wrong in the result of 'rados...
- 08:54 PM Revision 1fda4a0f (ceph): Merge pull request #11899 from SUSE/wip-17840-hammer
- hammer: rgw: the value of total_time is wrong in the result of 'radosgw-admin log show' opt
Reviewed-by: Orit Wasser... - 08:54 PM Backport #17764 (Resolved): hammer: collection_list shadow return value #
- 08:53 PM Revision 11886bd5 (ceph): Merge pull request #11927 from SUSE/wip-17764-hammer
- hammer: osd: fix collection_list shadow return value
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Samuel ... - 08:50 PM Bug #15345 (Resolved): "RWLock.h: 124: FAILED assert(r == 0)" in rados-jewel-distro-basic-smithi
- 08:50 PM Backport #17957 (Resolved): hammer: "RWLock.h: 124: FAILED assert(r == 0)" in rados-jewel-distro-...
- 08:50 PM Revision 21dc0ec9 (ceph): Merge pull request #12071 from SUSE/wip-17957-hammer
- hammer: RWLock.h: 124: FAILED assert(r == 0) in rados-jewel-distro-basic-smithi
Reviewed-by: Samuel Just <sjust@redh... - 08:49 PM Bug #17307 (Resolved): ceph-objectstore-tool crashes if --journal-path <a-directory>
- 08:47 PM Backport #17359 (Resolved): hammer: ceph-objectstore-tool crashes if --journal-path <a-directory>
- 08:47 PM Revision 8f19eca5 (ceph): Merge pull request #11929 from SUSE/wip-17359-hammer
- hammer: tools: ceph-objectstore-tool crashes if --journal-path <a-directory>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:46 PM Bug #16266 (Resolved): Ceph Status - Segmentation Fault
- 08:46 PM Backport #17346 (Resolved): hammer: Ceph Status - Segmentation Fault
- 08:46 PM Revision af6e2080 (ceph): Merge pull request #11930 from SUSE/wip-17346-hammer
- hammer: cephx: Fix multiple segfaults due to attempts to encrypt or decrypt
Reviewed-by: Brad Hubbard <bhubbard@redh... - 08:44 PM Backport #17333 (Resolved): hammer: crushtool --compile is create output despite of missing item
- 08:44 PM Revision 655e9041 (ceph): Merge pull request #11931 from SUSE/wip-17333-hammer
- hammer: tools: crushtool --compile generates output despite missing item
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:44 PM Bug #13967 (Resolved): PG::choose_acting valgrind error or ./common/hobject.h: 182: FAILED assert...
- 08:43 PM Backport #17146 (Resolved): hammer: PG::choose_acting valgrind error or ./common/hobject.h: 182: ...
- 08:43 PM Revision c118c0af (ceph): Merge pull request #11932 from SUSE/wip-17146-hammer
- hammer: PG::choose_acting valgrind error or ./common/hobject.h: 182: FAILED assert(!max || (*this == hobject_t(hobjec...
- 08:42 PM Bug #16998 (Resolved): PG::_update_calc_stats wrong for CRUSH_ITEM_NONE up set items
- 08:42 PM Backport #17142 (Resolved): hammer: osd: PG::_update_calc_stats wrong for CRUSH_ITEM_NONE up set ...
- 08:42 PM Revision e4ea9452 (ceph): Merge pull request #11933 from SUSE/wip-17142-hammer
- hammer: osd: PG::_update_calc_stats wrong for CRUSH_ITEM_NONE up set items
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:41 PM Bug #16933 (Resolved): the %USED of "ceph df" is wrong
- 08:41 PM Backport #17120 (Resolved): hammer: the %USED of "ceph df" is wrong
- 08:40 PM Revision 92e0a471 (ceph): Merge pull request #11934 from SUSE/wip-17120-hammer
- hammer: mon: %USED of ceph df is wrong
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:39 PM Bug #16034 (Resolved): OSD: crash on EIO during deep-scrubing
- 08:39 PM Backport #16870 (Resolved): hammer: OSD: crash on EIO during deep-scrubing
- 08:39 PM Revision d7fc569f (ceph): Merge pull request #11935 from SUSE/wip-16870-hammer
- hammer: osd: crash on EIO during deep-scrubbing
Reviewed-by: Samuel Just <sjust@redhat.com> - 08:36 PM Bug #16185 (Resolved): prepare_pgtemp needs to only update up_thru if newer than the existing one
- 08:33 PM Backport #16428 (Resolved): hammer: prepare_pgtemp needs to only update up_thru if newer than the...
- 08:33 PM Revision 8a15ac77 (ceph): Merge pull request #11937 from SUSE/wip-16428-hammer
- hammer: mon: prepare_pgtemp needs to only update up_thru if newer than the existing one
Reviewed-by: Samuel Just <sj... - 08:32 PM Bug #14248 (Resolved): OpTracker needs to release the message throttle in _unregistered
- 08:31 PM Backport #14323 (Resolved): hammer: OpTracker needs to release the message throttle in _unregistered
- 08:31 PM Revision 44588f27 (ceph): Merge pull request #11938 from SUSE/wip-14323-hammer
- hammer: msg: OpTracker needs to release the message throttle in _unregistered
Reviewed-by: Samuel Just <sjust@redhat... - 08:30 PM CephFS Bug #11258 (Resolved): cephfs-java ftruncate unit test failure
- 08:30 PM CephFS Backport #13927 (Resolved): hammer: cephfs-java ftruncate unit test failure
- 08:29 PM Revision 8c901706 (ceph): Merge pull request #11939 from SUSE/wip-13927-hammer
- hammer: mds: fix cephfs-java ftruncate unit test failure
Reviewed-by: John Spray <john.spray@redhat.com> - 08:27 PM Backport #18015 (Resolved): jewel: osd: condition OSDMap encoding on features
- https://github.com/ceph/ceph/pull/12167
- 07:47 PM Revision 02bf3ba7 (ceph): Merge pull request #11673 from zhangsw/fix-rgw-initbucketshardsync-bug
- rgw: Class member cookie is not initialized correctly in some coroutine's constructor.
Reviewed-by: Orit Wasserman <o... - 07:47 PM rgw Bug #17897 (Pending Backport): rgw: gc records empty entries
- 11:20 AM rgw Bug #17897 (In Progress): rgw: gc records empty entries
- Would like to propose a PR for this unless someone else already did.
- 07:46 PM Revision ce85112d (ceph): test: CLEANUP make test clearer by using "fail" as argument
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:46 PM Revision 8eb59955 (ceph): Merge pull request #11969 from yehudasa/wip-17897
- rgw: don't store empty chains in gc
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 07:45 PM Revision fdc92eb1 (ceph): Merge pull request #11815 from ceph/wip-17792
- rgw: remove circular reference in RGWAsyncRadosRequest
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 07:38 PM Revision c66c5568 (ceph): osd/osd_types: encode pg_pool_t like hammer if features indicate hammer
- If the target features are missing the new OSDOp encoding, the
first feature we added post-hammer, encode like hammer... - 07:38 PM Revision 85caf349 (ceph): osd/osd_types: conditional pg_pool_t encoding
- Align this with decode.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 01d9e8a20bbc3c039f67b0... - 07:24 PM Revision 94bfb853 (ceph): Merge pull request #12142 from athanatos/wip-17966
- osd: Fix read error propogation in ECBackend
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: David Zafman <dza... - 07:21 PM Revision 4fa099e4 (ceph): Merge pull request #1273 from ceph/wip-whitelist-crc
- whitelist CRC mismatch
- 07:09 PM Revision 638a38bb (ceph): crush/CrushWrapper: drop unused 'lean' encode() argument
- No callers, no users.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:54 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- http://pulpito.ceph.com/teuthology-2016-11-21_17:15:01-fs-master---basic-smithi/567231/
- 06:22 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
Another instance
jspray-2016-11-23_14:06:32-fs-wip-jcsp-testing-20161122-distro-basic-smithi/572367- 06:51 PM Revision 2f8cfb63 (ceph): osd/osd_types: encode pg_pool_t like hammer if features indicate hammer
- If the target features are missing the new OSDOp encoding, the
first feature we added post-hammer, encode like hammer... - 06:48 PM Revision 01d9e8a2 (ceph): osd/osd_types: conditional pg_pool_t encoding
- Align this with decode.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:36 PM Revision e3f2fa35 (ceph): mds: fix dropping events in standby replay
- Ensure that we never drop the last segment during
standby replay -- this avoids the case where we
start ignoring even... - 06:31 PM Revision 59666c9e (ceph): Merge pull request #11994 from ukernel/wip-17193
- mds: force client flush snap data before truncating objects
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 06:29 PM Revision ca421e11 (ceph): Merge pull request #11635 from batrick/mds-unique-ptr-20161024
- mds: more unique_pointer changes
Reviewed-by: John Spray <john.spray@redhat.com> - 06:25 PM CephFS Bug #17800 (Pending Backport): ceph_volume_client.py : Error: Can't handle arrays of non-strings
- 06:25 PM Revision 1604d1e4 (ceph): Merge pull request #11917 from ajarr/wip-17800
- ceph_volume_client: set an existing auth ID's default mon caps
Reviewed-by: John Spray <john.spray@redhat.com> - 06:13 PM Revision df97766c (ceph): Merge pull request #11983 from liewegas/wip-bluestore-release
- os/bluestore: fix alloc release timing on sync submits
Reviewed-by: Igor Fedotov <ifedotov@mirantis.com> - 05:27 PM rbd Feature #17409 (Resolved): Optional separate data pool support for v2 images
- 05:27 PM rbd Subtask #17529 (Resolved): [data pool] new teuthology test cases to utilize separate data pool
- 05:26 PM Revision 0e5653fe (ceph): Merge pull request #1235 from vshankar/wip-rbd-data-pool
- suites/rbd: add data pool test cases
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:44 PM Revision 2150fe7f (ceph): Merge pull request #12129 from wjin/fix_backoffthrottle_comment
- common/Throttle: fix typo for BackoffThrottle
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:37 PM Revision bd8554a7 (ceph): Merge pull request #9643 from wjin/mon
- mon: clean legacy code
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:52 PM Revision c475ebda (ceph): src/test: reenable test-erasure-eio.sh
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 03:43 PM rbd Bug #16176 (In Progress): objectmap does not show object existence correctly
- 03:42 PM rbd Bug #16176: objectmap does not show object existence correctly
- OK, I see the issue now. In the face of a crash during in-flight IO, where more than one in-flight IO maps to the sam...
- 03:34 PM Revision 366e9305 (ceph): Merge pull request #12000 from jcsp/wip-doc-exports
- src/doc: fix class names in exports.txt
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Sage Weil <sage@r... - 03:34 PM Revision 15433bf1 (ceph): Merge pull request #10474 from songbaisen/b5
- mon: remove the redudant jugement in LogMonitor tick function
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 03:28 PM Revision f1b7a061 (ceph): Merge pull request #11631 from wolsen/issues/17689
- upstart: start ceph-all after static-network-up
Reviewed-by: James Page <james.page@ubuntu.com> - 03:21 PM Revision fa5bf9ce (ceph): Merge pull request #12128 from tchaikov/wip-cmake
- cmake: add -Wno-unknown-pragmas to CMAKE_CXX_FLAGS
Reviewed-by: Casey Bodley <cbodley@redhat.com> - 03:09 PM rgw Bug #16597 (Pending Backport): the response element "X-Timestamp" of swift stat bucket api is zero
- 03:05 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- This chmod may be the bit we're missing:
https://github.com/ceph/ceph-qa-suite/blob/master/tasks/cephfs/fuse_mount.p... - 02:56 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- Looks like these tests don't specify a UserPerm on the ceph function invocations, nor set up a "global" one. I imagin...
- 02:49 PM CephFS Bug #18013: ceph_test_libcephfs access failures when run without ceph-fuse mount in teuthology (n...
- BTW, the only material difference between this test run and a normal FS suite run is that ceph-fuse is turned off. Co...
- 02:46 PM CephFS Bug #18013 (Resolved): ceph_test_libcephfs access failures when run without ceph-fuse mount in te...
- When ceph-fuse is turned off for the libcephfs_interface_tests task, we see access control failures:...
- 03:00 PM Revision c4623710 (ceph): Merge pull request #12126 from branch-predictor/bp-doc-async-opts
- doc/rados/configuration/ms-ref.rst: document a few async msgr options
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:58 PM Revision 603ad766 (ceph): Merge pull request #12135 from kylinstorage/wip-remove-unneeded-forward...
- osd/PG.h: remove unneeded forward declaration
Reviewed-by: Sage Weil <sage@redhat.com> - 02:55 PM Revision 0d2f431b (ceph): rgw: doc: Mark S3 object version API as supported
- S3 object version is already in since Hammer.
Ref: http://marc.info/?l=ceph-devel&m=143715290627682
Signed-off-by: Y... - 02:55 PM Revision 8ca16052 (ceph): doc: add bucket object version description.
- bucket object version has been supported, but do not have description in the docs,
so add this part.
Signed-off-by: ... - 02:41 PM CephFS Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
- http://pulpito.ceph.com/sage-2016-11-23_14:40:24-upgrade:hammer-x-master---basic-smithi/
- 02:37 PM CephFS Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
- https://github.com/ceph/ceph-qa-suite/pull/1280
added debugging. the mon connection looks fine, but it isn't doin... - 02:18 PM CephFS Bug #17847: "Fuse mount failed to populate /sys/ after 31 seconds" in jewel 10.2.4
- It's a hammer ceph-fuse trying to mount.. my guess is a compat issue
- 02:38 PM Revision 04911e5e (ceph): Merge pull request #1281 from ceph/wip-jewel-debug-fuse
- upgrade/hammer-x: debug mds
- 02:37 PM Revision b84c1a2d (ceph): upgrade/hammer-x: debug mds
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:37 PM Revision 4394478b (ceph): Merge pull request #1280 from ceph/wip-jewel-debug-fuse
- upgrade/hammer-x: debug client
- 02:36 PM Revision 3f7ad755 (ceph): upgrade/hammer-x: debug client
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:25 PM Bug #14934: common/config_opts.h: audit OPT_INT/OPT_UINT and handle incorrect signed uint
- http://tracker.ceph.com/issues/14934
- 02:17 PM Revision f45e9723 (ceph): vstart: cleaner multi-mds startup with standbys
- The daemons will get assigned to roles in the
order they start otherwise. The trick is
to let them all go into the F... - 02:17 PM Revision 5ad7c44e (ceph): mds: don't maintain bloom filters in standby replay
- ...and thereby avoid needing to clear them when
replaying an EExport
Fixes: http://tracker.ceph.com/issues/16924
Sig... - 02:15 PM Revision 0525250a (ceph): Merge pull request #12162 from liewegas/wip-coverity
- script/run-coverity: update
- 02:11 PM Revision d0356893 (ceph): script/run-coverity: -x
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:05 PM Revision 6f4efc12 (ceph): Merge pull request #11848 from javeme/case-CEPH_MSG_POOLOP
- mon: move case CEPH_MSG_POOLOP to OSDs group
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 01:22 PM rbd Bug #17973 (Pending Backport): "FAILED assert(m_processing == 0)" while running test_lock_fence.sh
- 11:00 AM rbd Bug #17973 (Fix Under Review): "FAILED assert(m_processing == 0)" while running test_lock_fence.sh
- https://github.com/ceph/ceph/pull/12160
- 01:22 PM Revision c3910309 (ceph): Merge pull request #12160 from vshankar/wip-17973
- librbd: mark request as finished after failed refresh
- 01:03 PM Revision 8f9ee150 (ceph): doc/rados/configuration/ms-ref.rst: document a few async msgr options
- Documentation of a few of Async Messenger configuration options.
Signed-off-by: Piotr Dałek <git@predictor.org.pl> - 11:49 AM Revision d7a479c4 (ceph): rgw: TempURL properly handles accounts created with the implicit tenant.
- This is because in Jewel in the TempURL implementation we aren't trying
to rgw_get_user_info_by_uid() on rgw_user wit... - 11:18 AM Revision 95ed04a5 (ceph): doc: Add documentation about mon_allow_pool_delete before pool remove
- Tell users they need to set this to true before Monitors will allow
pools to be removed.
Also update the Pending Rel... - 11:05 AM Revision db7533dd (ceph): Merge pull request #12055 from liewegas/wip-17942
- osdc/Objecter: handle race between calc_target and handle_osd_map
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 11:02 AM Revision feefd5ed (ceph): Merge pull request #11178 from stiopaa1/osd_pg_changeStructPGRecoverySt...
- osd/PG.h: change PGRecoveryStats struct to class
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:01 AM Revision 354e5bfb (ceph): Merge pull request #12009 from 363921219/master
- osd: clean up process_peering_events
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:00 AM Revision 0e540531 (ceph): Merge pull request #12031 from liewegas/wip-ceph-abort
- common: assert(0) -> ceph_abort()
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Kefu Chai <kchai@re... - 10:55 AM Revision cc2f222a (ceph): librbd: account m_processing when failing request after refresh
- AioImageRequestWQ::_void_process() dequeues an item from the
work queue by invoking ThreadPool::_void_process() which... - 10:48 AM Revision 6332a201 (ceph): Merge pull request #12034 from wjwithagen/wip-wjw-freebsd-strtoll
- common/strtol.cc: Get error testing also to work on FreeBSD
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:44 AM rbd Backport #18012 (Resolved): jewel: qa/workunits/rbd: improvements for rbd-mirror tests
- https://github.com/ceph/ceph/pull/12425
- 09:53 AM Backport #17883 (Resolved): hammer: OSDs marked OUT wrongly after monitor failover
- 09:52 AM Revision 49964b01 (ceph): Merge pull request #11946 from SUSE/wip-17883-hammer
- hammer: mon: OSDs marked OUT wrongly after monitor failover
Reviewed-by: Kefu Chai <kchai@redhat.com> - 09:52 AM rbd Backport #17671 (Resolved): Fix coding mistake in pre-refactor rbd shell
- 09:51 AM Revision 6e1ae86e (ceph): Merge pull request #11948 from SUSE/wip-17671-hammer
- hammer: rbd: export diff should open image as read-only
Reviewed-by: Mykola Golub <mgolub@mirantis.com>
Reviewed-by:... - 09:48 AM rbd Bug #17310 (Resolved): image.stat() call in librbdpy fails sometimes
- 09:48 AM rbd Backport #17374 (Resolved): hammer: image.stat() call in librbdpy fails sometimes
- 09:48 AM Revision 2f9869c1 (ceph): Merge pull request #11949 from SUSE/wip-17374-hammer
- hammer: librbd: image.stat() call in librbdpy fails sometimes
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 09:41 AM rgw Bug #16435 (Resolved): COPY broke multipart files uploaded under dumpling
- 09:41 AM rgw Backport #17123 (Resolved): hammer: COPY broke multipart files uploaded under dumpling
- 09:41 AM Revision 2dac8848 (ceph): Merge pull request #11950 from SUSE/wip-17123-hammer
- hammer: rgw: COPY broke multipart files uploaded under dumpling
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 09:40 AM rgw Bug #13452 (Resolved): RGW Swift API: ranged request on a DLO provides wrong values in Content-Ra...
- 09:40 AM rgw Backport #16594 (Resolved): hammer: RGW Swift API: ranged request on a DLO provides wrong values ...
- 09:39 AM Revision 1503c2ba (ceph): Merge pull request #11951 from SUSE/wip-16594-hammer
- hammer: rgw: swift: ranged request on a DLO provides wrong values in Content-Range HTTP header
Reviewed-by: Orit Was... - 09:17 AM rgw Bug #13598 (Resolved): radosgw-admin: inconsistency in uid/email handling
- 09:17 AM rgw Backport #16318 (Resolved): hammer: radosgw-admin: inconsistency in uid/email handling
- 09:17 AM Revision 118beb9a (ceph): Merge pull request #11952 from SUSE/wip-16318-hammer
- hammer: rgw: fix inconsistent uid/email handling in radosgw-admin
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 09:14 AM rbd Feature #16171 (Resolved): Request exclusive lock if owner sends -ENOTSUPP for proxied maintenanc...
- 09:14 AM rbd Backport #17068 (Resolved): hammer: Request exclusive lock if owner sends -ENOTSUPP for proxied m...
- 09:14 AM Revision 3b226b82 (ceph): Merge pull request #12018 from trociny/wip-17068-hammer
- hammer: librbd: request exclusive lock if current owner cannot execute op
Reviewed-by: Jason Dillaman <dillaman@redh... - 09:08 AM rgw Bug #17987: incorrect entry is removed when a part is upload more than once during multipart-upload
- https://github.com/ceph/ceph/pull/12152
- 09:03 AM Revision 2921d8d5 (ceph): Merge pull request #12150 from tchaikov/wip-kill-gf-complete-warnings
- erasure-code: fix gf-complete warning
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:45 AM Revision 43f15c61 (ceph): cmake: regroup CMAKE_CXX_FLAGS and CMAKE_C_FLAGS
- - some options are only meaningful for C++, so move them into
CMAKE_CXX_FLAGS.
- regroup CMAKE_CXX_FLAGS and CMAKE_... - 08:27 AM Revision b49b6a9e (ceph): Merge pull request #11855 from dachary/wip-17472-jewel
- jewel: rpm: /etc/ceph/rbdmap is packaged with executable access rights
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:25 AM Revision 43878546 (ceph): Merge pull request #11660 from Abhishekvrshny/wip-17601-jewel
- jewel: mon: health does not report pgs stuck in more than one state
Reviewed-by: Sage Weil <sage@redhat.com> - 08:16 AM rgw Backport #17969 (In Progress): jewel: multisite upgrade from hammer -> jewel ignores rgw_region_r...
- 08:16 AM Revision a0b4e60c (ceph): rgw: look for region_map in rgw_region_root_pool
- Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from commit b81d88008443cbc1b43ea93a7058284dbc44538f) - 08:16 AM Revision af10e571 (ceph): rgw: region conversion respects pre-existing rgw_region_root_pool
- Fixes: http://tracker.ceph.com/issues/17963
Signed-off-by: Casey Bodley <cbodley@redhat.com>
(cherry picked from com... - 08:05 AM CephFS Backport #17956 (In Progress): jewel: Clients without pool-changing caps shouldn't be allowed to ...
- 08:05 AM Revision 05e5a5a2 (ceph): mds: require MAY_SET_POOL to set pool_ns
- The intent of that flag is to enable admins to limit a client
to setting layouts to put objects within the OSD auth c... - 08:04 AM CephFS Backport #18008 (In Progress): jewel: Cannot create deep directories when caps contain "path=/som...
- 06:43 AM CephFS Backport #18008 (Resolved): jewel: Cannot create deep directories when caps contain "path=/somepath"
- https://github.com/ceph/ceph/pull/12154
- 08:03 AM Revision 6efad699 (ceph): mds: use projected path construction for access
- A new CDentry will not have a parent until its projected parent is
flushed to journal. During path construction a giv... - 07:57 AM CephFS Backport #18010 (In Progress): jewel: Cleanly reject "session evict" command when in replay
- 06:43 AM CephFS Backport #18010 (Resolved): jewel: Cleanly reject "session evict" command when in replay
- https://github.com/ceph/ceph/pull/12153
- 07:57 AM Revision edac06fd (ceph): mds: ignore 'session evict' when mds is replaying log
- Fixes: http://tracker.ceph.com/issues/17801
Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 31... - 07:55 AM Revision 6e8f3b40 (ceph): cmake: add -Wno-unknown-pragmas to CMAKE_C_FLAGS
- this silences warnings like:
warning: ignoring #pragma clang diagnostic [-Wunknown-pragmas]
and recent clang (3.9 a... - 07:54 AM Backport #18011 (In Progress): jewel: test fails due to "The UNIX domain socket path"
- 06:46 AM Backport #18011 (Resolved): jewel: test fails due to "The UNIX domain socket path"
- https://github.com/ceph/ceph/pull/12151
- 07:53 AM Revision 4df1b9c5 (ceph): tests: save 9 characters for asok paths
- For vstart.sh powered tests, save 9 characters in the path name
by replacing testdir/test- with td/t-
60 characters ... - 07:47 AM Bug #17923 (Resolved): tests: ceph-disk.sh fails on py34
- the problem was introduced in master, it does not exist in jewel
- 07:38 AM Revision b9d4fac7 (ceph): erasure-code: fix gf-complete warning
- pick up latest gf-complete submodule
$ git log --no-merges --pretty=%s \
a6847973cba329ae079d3bd26341a4ec2906f012.... - 07:35 AM rgw Backport #17961 (In Progress): rgw, jewel: TempURL fails if rgw_keystone_implicit_tenants is enabled
- h3. initial description
This is because in Jewel in the TempURL implementation we aren't trying to _rgw_get_user_i... - 07:12 AM Revision 8e83ddb3 (ceph): mds: properly commit new dirfrag before splitting it
- CDir::is_new() check is invalid before the new directory gets
journaled. Besides, it's not good to commit a directory... - 07:00 AM Revision 97eb2ad7 (ceph): osd_types: pg_t::is_split(): use unsigned for bits operations
- this silences the warning of
The result of the '<<' expression is undefined
quote from n3337, §5.8 expr.shift:
If ... - 07:00 AM Revision a7a39a20 (ceph): hobject: better left-shift an unsigned
- this silences the warning of
The result of the '<<' expression is undefined
quote from n3337, §5.8 expr.shift:
If ... - 07:00 AM Revision c3748fa7 (ceph): FileStore::_do_fiemap: do not reference fiemap after it is freed
- `last` points to fiemap::fm_extends[n], and if fiemap gets freed, we can
not reference any of its fieldis. so we coul... - 07:00 AM Revision 4d2eb9a2 (ceph): ReplicatedPG: check retcode before verifying trailing hole
- this silences the warning of
Value stored to 'r' is never used.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:54 AM Backport #18009 (In Progress): jewel: ceph-disk: udev permission race with dm
- 06:43 AM Backport #18009 (Resolved): jewel: ceph-disk: udev permission race with dm
- https://github.com/ceph/ceph/pull/12147
- 06:53 AM Backport #18007 (In Progress): jewel: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 06:42 AM Backport #18007 (Resolved): jewel: ceph-disk: ceph-disk@.service races with ceph-osd@.service
- https://github.com/ceph/ceph/pull/12147
- 06:52 AM Revision 1f0abeff (ceph): global/signal_handler: retry if read() returns with EINTR
- this silences the warning of
Value stored to 'r' is never used.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:52 AM Revision 995ac943 (ceph): common/blkdev: get_device_by_uuid() silence clang warning
- early return if blkid_get_cache() fails. this chance is but cosmetic,
it pleases clang static analyzer which thinks t... - 06:52 AM Revision 8e933189 (ceph): tools/ceph_radosacl: print out return code of "acl set"
- this silences the warning of
Value stored to 'r' is never read.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 06:39 AM Revision 335d50f1 (ceph): Merge pull request #12146 from dzafman/wip-dz-delays
- tests: minor make check cleanup
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:37 AM Bug #17889 (Pending Backport): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 06:37 AM Bug #17813 (Pending Backport): ceph-disk: udev permission race with dm
- 06:36 AM Revision bd1eb7aa (ceph): Merge pull request #12136 from dachary/wip-17889-systemd-order
- ceph-disk: resolve race conditions
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:07 AM Revision e16c6456 (ceph): Merge pull request #12145 from tchaikov/wip-client-use-after-freed
- client: trim_caps() do not dereference cap if it's removed
Reviewed-by: Brad Hubbard <bhubbard@redhat.com> - 05:42 AM rgw Bug #13207 (Resolved): CVE-2016-7031 rgw: Anonymous user is able to read bucket with authenticate...
- 05:42 AM rgw Backport #17150 (Resolved): hammer: rgw: Anonymous user is able to read bucket with authenticated...
- 05:42 AM Revision 9ad73698 (ceph): Merge pull request #11045 from SUSE/wip-17150-hammer
- hammer: rgw: Anonymous user is able to read bucket with authenticated read ACL
Reviewed-by: Orit Wasserman <owasserm... - 05:41 AM Revision b425290a (ceph): test: Handle terminal width 0 case for running test in emacs
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:38 AM Revision dcb5fb9b (ceph): test: CLEANUP: Make wait_for_clean() clearer changing variable name
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:36 AM Revision c1eb8746 (ceph): test: Return wait_for_clean() to start sleeping at .1
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:34 AM rgw Bug #17635 (Resolved): rgw crash when client post object with null conditions
- 05:33 AM rgw Backport #17631 (Resolved): hammer: Fix rgw crash when client post object with null condition
- 05:32 AM Revision 45394294 (ceph): test: Enhance get_timeout_delays()
- Do all math using bc so we can have fractions
Allow caller to specify the first step (default 1)
Add testing of fract... - 05:32 AM Revision 3ca73177 (ceph): Merge pull request #11809 from SUSE/wip-17631-hammer
- hammer: rgw: fix crash when client posts object with null condition
Reviewed-by: Orit Wasserman <owasserm@redhat.com> - 05:04 AM Revision e9fbe39f (ceph): client: trim_caps() do not dereference cap if it's removed
- this silences the warning of "Use of memory after it is freed" reported
by clang static analyzer.
Reported-by: Brad ... - 01:53 AM Bug #18005 (Closed): osd crushed in processing deep scrub
- osd crushed in processing deep scrub
this is the log
ceph version 0.94.6 (e832001feaf8c176593e0325c8298e3f16dfb403... - 01:44 AM Bug #18004 (Resolved): heartbeat peers need to be updated when a new OSD added into an existed cl...
- The case is:
There is a storage node which has two osds. nearly one min later, a new OSD joins in. Monitor sees it a... - 01:43 AM rgw Bug #18003 (Resolved): slave zonegroup cannot enable the bucket versioning
- The master zone in slave zonegroup cannot enable the bucket versioning, created in slave zonegroup, and it will retur...
- 12:54 AM Revision 28c73c60 (ceph): os/filestore: blacklist same ENOENT failures as bluestore
- FileStore doesn't care per se, but they indicate buggy calling code, and
we want to catch all bad callers!
Signed-of... - 12:48 AM Revision 4fe43499 (ceph): Merge pull request #1277 from ceph/wip-exclude-upgrade-clients
- Excluded 'libcephfs2','libcephfs-devel','libcephfs-dev'
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:40 AM Revision 3d4c3583 (ceph): Excluded 'libcephfs2','libcephfs-devel','libcephfs-dev'
- Removed firefly and infernalis paths
Removed mds role from hammer (per chat with Jason)
Add "fs: xfs" override
Signe... - 12:36 AM Revision b08df131 (ceph): os/bluestore: mark ops that can't tolerate ENOENT
- If we get errors on these we screw up the transaction
data_bl decoding cursor; assert they don't happen. In
general,... - 12:35 AM Revision 58f9387a (ceph): Merge pull request #12127 from renhwztetecs/renhw-wip-doc-mds
- doc/mds: fixup "mds bal mode" Description
Reviewed-by: John Spray <john.spray@redhat.com> - 12:35 AM Revision 60941ae2 (ceph): Merge pull request #12052 from liewegas/wip-osd-fast-dispatch
- osd: a few fast dispatch optimizations
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Kefu Chai <kchai@red... - 12:34 AM Revision 0b616961 (ceph): Merge pull request #12059 from liewegas/wip-osd-omap-limits
- osd: set server-side limits on omap get operations
Reviewed-by: xie xingguo <xie.xingguo@zte.com.cn>
Reviewed-by: Ke... - 12:33 AM Revision 9953fdf7 (ceph): Merge pull request #12064 from majianpeng/rocksdb-perf
- kv/RocksDBStore: Don't update rocksdb perf_context if rocksdb_perf di…
Reviewed-by: Sage Weil <sage@redhat.com> - 12:32 AM Revision 129dce48 (ceph): Merge pull request #12068 from yuyuyu101/wip-rdma-cct
- msg/async/rdma: ensure CephContext existed
Reviewed-by: Sage Weil <sage@redhat.com> - 12:29 AM Revision 2c3cda2d (ceph): Merge pull request #12069 from liupan1111/wip-osd-up-heartbeat-peers
- osd: heartbeat peers need to be updated when a new OSD added into an existed cluster
Reviewed-by: Sage Weil <sage@re... - 12:25 AM Revision 2cc8994e (ceph): mds: use unique_ptr unstable_bits_t in SimpleLock
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
- 12:25 AM Revision 128ac29c (ceph): mds: use unique_ptr in MDCache
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
- 12:03 AM Revision ed0d099a (ceph): mds: use unique_ptr bufferlist in inline_data_t
- Signed-off-by: Patrick Donnelly <pdonnell@redhat.com>
11/22/2016
- 11:52 PM Revision 66feecc2 (ceph): Merge pull request #11959 from batrick/mds-header-prot-org
- Partial organization of mds/ header sections
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:48 PM Bug #17997 (Closed): ceph-fuse causing OS crash or hang
- Known issue in upstream kernel.
See http://tracker.ceph.com/issues/17984 - 08:44 PM Bug #17997: ceph-fuse causing OS crash or hang
- Nathan Cutler wrote:
> Are these tests being run with "-k testing" by any chance?
Yes, they are. The same jobs p... - 08:25 PM Bug #17997: ceph-fuse causing OS crash or hang
- Are these tests being run with "-k testing" by any chance? I saw very similar behavior in powercycle recently and Ily...
- 06:47 PM Bug #17997 (Closed): ceph-fuse causing OS crash or hang
- Yuri noticed smoke suite runs on VPSes were having SSH connection failures. I looked into it and it would appear per...
- 11:48 PM Revision 1d7c9f57 (ceph): Merge pull request #12111 from batrick/client-capsnap-emplace
- client: put CapSnap not ptr in cap_snaps map
Reviewed-by: John Spray <john.spray@redhat.com> - 11:44 PM Revision 69adf697 (ceph): Merge pull request #12098 from ukernel/wip-17606
- multimds: fix state check in Migrator::find_stale_export_freeze()
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:42 PM Revision a977c902 (ceph): src/mds: fix MDSMap upgrade decoding
- Hammer MDSMonitors did not validate the state in beacons
and would apply anything to the mds_info_t for a standby,
su... - 11:33 PM Bug #18002: kstore failed in rados run
- Also in http://qa-proxy.ceph.com/teuthology/yuriw-2016-11-22_16:38:08-rados-wip-yuri-testing2_2016_11_21-distro-basic...
- 11:32 PM Bug #18002 (Resolved): kstore failed in rados run
- Run: http://pulpito.front.sepia.ceph.com/yuriw-2016-11-22_22:33:48-rados-wip-yuri-testing2_2016_11_21-distro-basic-sm...
- 11:28 PM CephFS Bug #17858 (Pending Backport): Cannot create deep directories when caps contain "path=/somepath"
- 11:28 PM Revision 44d9f974 (ceph): Merge pull request #12063 from batrick/i17858
- mds: use projected path construction for access
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 11:14 PM Revision b1171f8c (ceph): src/doc: move exports.txt into doc/
- Signed-off-by: John Spray <john.spray@redhat.com>
- 11:14 PM Revision 907bdb59 (ceph): src/doc: fix class names in exports.txt
- Signed-off-by: John Spray <john.spray@redhat.com>
- 11:14 PM Revision 3ae9bd84 (ceph): src/doc: remove anchortable.txt
- The anchor table is long gone.
Signed-off-by: John Spray <john.spray@redhat.com> - 11:02 PM Bug #18000 (Closed): Error: error calling conf_read_file: error code 22"
- 10:50 PM Bug #18000 (Closed): Error: error calling conf_read_file: error code 22"
- 10:53 PM Bug #18001 (Rejected): "Error: error calling conf_read_file: error code 22"
- Run: http://pulpito.ceph.com/yuriw-2016-11-22_19:46:31-upgrade:client-upgrade-master-distro-basic-smithi/
Jobs: 5701... - 10:47 PM Bug #17809 (New): "symbol lookup error: ceph_test_librbd_api: undefined symbol" in upgrade:client...
- Kefu, can you take a look at this one maybe related issue?
http://qa-proxy.ceph.com/teuthology/yuriw-2016-11-22_19... - 12:28 PM Bug #17809 (Resolved): "symbol lookup error: ceph_test_librbd_api: undefined symbol" in upgrade:c...
- 10:19 PM Bug #17436 (Resolved): selinux: Allow ceph to manage tmp files
- 10:15 PM Bug #16678 (Closed): selinux polocy related errors in syslog during ceph-selinux package install
- Closing as per Comment #7 and #8.
- 09:29 PM Bug #16678: selinux polocy related errors in syslog during ceph-selinux package install
- Thanks for the update. I totally agree with you.
- 08:16 PM Bug #16678: selinux polocy related errors in syslog during ceph-selinux package install
- OK, I did a bit more research on the topic and I believe this is a bug in OEL, not ceph. We do manifest it only becau...
- 05:51 PM Bug #16678: selinux polocy related errors in syslog during ceph-selinux package install
- Tried your approach and yet got the error "Class binder not defined in policy.".
- 01:04 PM Bug #16678: selinux polocy related errors in syslog during ceph-selinux package install
- Well, you said the kernels 3.8/3.10 which are probably the RHCK ones work fine. I doubt the 4.1.2 where the warnings ...
- 02:04 AM Bug #16678: selinux polocy related errors in syslog during ceph-selinux package install
- I am using Oracle linux 7.2 which is based on RHEL 7.2. And has the same RHCK kernel.
- 09:56 PM rgw Bug #17788: rgw: failing to authenticate aws4 with boto and with port specified
- Can I reproduce this w/boto? Could someone paste a quick reproducer?
Thanks! - 09:30 PM Bug #17983 (Resolved): osd: setattr on old object name in ec transaction
- 07:34 PM Bug #17983: osd: setattr on old object name in ec transaction
- https://github.com/ceph/ceph/pull/12141
- 07:34 PM Bug #17983 (Fix Under Review): osd: setattr on old object name in ec transaction
- 09:30 PM Revision d126abf8 (ceph): Merge pull request #12141 from athanatos/wip-17983
- osd/ECTransaction: only write out the hinfo if not delete
Reviewed-by: Sage Weil <sage@redhat.com> - 09:29 PM Revision 5aa8121d (ceph): Merge pull request #12143 from rook/wip-boost-ext
- cmake: fix boost build on ubuntu 16.10 yakkety
- 09:03 PM Revision ac4a407c (ceph): Merge pull request #12078 from yangdongsheng/rbd_cleanup
- librbd: minor cleanup
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:27 PM Bug #17984 (Resolved): powercycle: fuse mount fails (0.94.10 integration testing)
- Fixed by specifying ...
- 06:00 AM Bug #17984: powercycle: fuse mount fails (0.94.10 integration testing)
- However, the same run with ...
- 08:26 PM Revision 64e00a53 (ceph): ExtentCache: fix bug in get_remaining_extents_for_rmw
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 07:53 PM Revision 3eef10b9 (ceph): cmake: fix boost build on ubuntu yakkety
- If the host system has boost version 1.61 or higher (as in the case
for ubuntu 16.10 yakkety) the ceph build is curre... - 07:34 PM Bug #17966: test-erasure-eio.sh can crash osd
- https://github.com/ceph/ceph/pull/12142
- 07:34 PM Bug #17966 (Fix Under Review): test-erasure-eio.sh can crash osd
- 07:32 PM Revision 9d2fd4bd (ceph): Merge pull request #12110 from batrick/client-failure-msg
- client: improve failure messages/debugging
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 07:28 PM Bug #17999 (Resolved): ec scrub mismatch during teuthology run
- {description: 'rados/thrash-erasure-code/{leveldb.yaml rados.yaml clusters/{fixed-2.yaml
openstack.yaml} fast/fa... - 07:26 PM Bug #17998 (Closed): ceph-osd oom killed during rados bench teuthology run
- Notably, this was btrfs. Looks like 2 osd processes were running 2-3 gb and another was 4-5. That's not necessarily...
- 06:28 PM rgw Bug #17996 (Resolved): rgw: ECANCELED in rgw_get_system_obj() leads to infinite loop
- 06:24 PM CephFS Bug #17837: ceph-mon crashed after upgrade from hammer 0.94.7 to jewel 10.2.3
- 05:42 PM Revision 9a6b3e5a (ceph): Merge pull request #1272 from ceph/wip-rgw-sync-agent-retry-jewel
- jewel: rgw: fix some races with radosgw and radosgw-agent startup
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:16 PM Revision 1a63cb68 (ceph): tasks.rgw: 'time' imported but unused
- flake8 was failing.
Signed-off-by: Owen Synge <osynge@suse.com>
(cherry picked from commit ef1d2a6aabe91282e28dbb620... - 05:01 PM Revision dd50c146 (ceph): rgw: fix zone did't update realm_id when added to zonegroup
- Fixes: http://tracker.ceph.com/issues/17995
Signed-off-by: Tianshan Qu <tianshan@xsky.com> - 04:52 PM rgw Bug #17995 (Resolved): rgw: zonegroup add cmd didn't update zone's realm_id
- before zone add to a zonegroup, it's realm_id may be empty or an old realm_id, so when it join another zonegroup, it ...
- 04:40 PM CephFS Bug #17990: newly created directory may get fragmented before it gets journaled
- I guess this was getting highlighted because of the timing change in https://github.com/ceph/ceph/pull/12022 (which w...
- 09:49 AM CephFS Bug #17990 (Fix Under Review): newly created directory may get fragmented before it gets journaled
- https://github.com/ceph/ceph/pull/12125
- 09:45 AM CephFS Bug #17990 (Resolved): newly created directory may get fragmented before it gets journaled
- http://pulpito.ceph.com/jspray-2016-11-18_13:57:54-fs-wip-jcsp-testing-20161118-distro-basic-smithi/559675
- 04:38 PM CephFS Backport #17974: jewel: ceph/Client segfaults in handle_mds_map when switching mds
- h3. Original description
Our manila-share daemon is segfaulting when our active mds goes away and we switch to the... - 04:38 PM CephFS Backport #17974 (In Progress): jewel: ceph/Client segfaults in handle_mds_map when switching mds
- 03:51 PM CephFS Backport #17974 (Fix Under Review): jewel: ceph/Client segfaults in handle_mds_map when switching...
- In jewel there is no call to erase a command from the table after it receives a reply, so if a command has ever been ...
- 04:31 PM rbd Bug #17993 (Resolved): rbd-mirror: potential race mirroring cloned image
- With pool-level replication enabled, when a clone is created, it first creates an empty standalone image and adds it ...
- 04:12 PM rgw Bug #17976: multisite upgrade from hammer->jewel still doesn't handle different rgw_region_root_pool
- simple workaround:
add rgw_zonegroup_root_pool, rgw_realm_root_pool and rgw_period_root_pool entries in the config w... - 03:49 PM Revision ea9665b8 (ceph): client: fix stale entries in command table
- This patch is Jewel-specific because in Kraken
this code was already refactored for CommandTable
and got fixed in the... - 03:39 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- One oddity in the check_caps code is that we always try to retain CEPH_CAP_PIN, even when unmounting. I'm going to te...
- 03:07 PM CephFS Bug #17982: fuse client failing to trim disconnected inode on unmount
- I'll grab this for now since I was in this codepath recently. Looking at it though, I suspect that this is unrelated ...
- 03:29 PM rbd Bug #16176: objectmap does not show object existence correctly
- @Xinxin: Thanks for the debug logs. I will try to take a look at this today or tomorrow.
- 08:29 AM rbd Bug #16176: objectmap does not show object existence correctly
- hi jason, i reproduce this bug, detail logs are attached, pls check the log, "./bin/rbd -c ceph.conf -p rbd bench-wri...
- 02:43 PM Bug #17889 (Fix Under Review): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- https://github.com/ceph/ceph/pull/12136
- 06:30 AM Bug #17889 (In Progress): ceph-disk: ceph-disk@.service races with ceph-osd@.service
- 02:37 PM Revision 6f8be395 (ceph): osd/PG.h: remove unneeded forward declaration
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 02:29 PM Revision c8a37772 (ceph): test_cors.cc: fix the mem leak
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 02:29 PM Revision d932c8f2 (ceph): global/signal_handler: reset injected segv after test
- ~CephContext() => ~TypedSingletonWrapper() => ~MempoolObs =>
unregister_command() => ldout() << "unregister_command" ... - 02:29 PM Revision e01b89ed (ceph): crushtool: s/exit(EXIT_FAILURE)/return EXIT_FAILURE/
- so the destructor(s) can be called.
Signed-off-by: Kefu Chai <kchai@redhat.com> - 02:29 PM Revision 72f0b2aa (ceph): ceph-disk: trigger must ensure device ownership
- The udev rules that set the owner/group of the OSD devices are racing
with 50-udev-default.rules and depending on whi... - 02:23 PM Revision d954de55 (ceph): ceph-disk: systemd unit must run after local-fs.target
- A ceph udev action may be triggered before the local file systems are
mounted because there is no ordering in udev. T... - 02:11 PM CephFS Bug #16924 (Fix Under Review): Crash replaying EExport
- https://github.com/ceph/ceph/pull/12133
- 01:50 PM Bug #17813 (Fix Under Review): ceph-disk: udev permission race with dm
- https://github.com/ceph/ceph/pull/12136
- 01:08 PM Revision 23dc8532 (ceph): common/Throttle: fix typo for BackoffThrottle
- Fix formula so that pepople can understand it smoothly.
Signed-off-by: Wei Jin <wjin.cn@gmail.com> - 12:10 PM Revision 3975b28b (ceph): doc/mds: fixup "mds bal mode" Description
- mds_load code is:
switch(g_conf->mds_bal_mode) {
case 0:
return
.8 * auth.meta_load() +
.2 * all.me... - 12:03 PM RADOS Bug #15653: crush: low weight devices get too many objects for num_rep > 1
- Does this issue explain our uneven distribution? We have four racks, with 7, 8, 8, 4 hosts in each, respectively. The...
- 12:01 PM Bug #6671: FAILED assert(ret) in OSDMapRef OSDService::get_map(epoch_t)
- we happen to see the same problem in 10.2.0. When startup OSD with 'ceph' user, it show this error. But it's ok with ...
- 11:49 AM CephFS Bug #17921: CephFS snapshot removal fails with "Stale file handle" error
- Ah, I didn't notice that.
Rama: modify your .yaml configuration to only list one MDS daemon, or make sure that all... - 11:37 AM CephFS Bug #17921 (Rejected): CephFS snapshot removal fails with "Stale file handle" error
- you were testing snaphost on multimds setup. It's known broken. For now, please test snapshot only on single active m...
- 11:20 AM Revision f0b7d36a (ceph): Merge pull request #12124 from branch-predictor/bp-fast-markdown-doc
- doc/rados/configuration/osd-config-ref.rst: document the fast mark down
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:04 AM Revision 99063bcf (ceph): Merge pull request #12123 from branch-predictor/bp-fast-markdown-is-def...
- test/osd-fast-mark-down.sh: wrong assumption on first subtest
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:35 AM Revision 0d538a14 (ceph): rbd: add datapool config YAML to rbd suite
- - cli
- librbd
- qemu
Signed-off-by: Venky Shankar <vshankar@redhat.com> - 10:19 AM Bug #17958: Simultaneous start of ceph-osd processes causes cluster stucks in error state
- Samuel Just wrote:
> It looks to me as though your cluster is just slow. You might want to post to ceph-users about... - 09:42 AM Revision 9c5d253a (ceph): doc/rados/configuration/osd-config-ref.rst: document the fast mark down
- Document the "osd fast fail on connection refused" option.
Signed-off-by: Piotr Dałek <git@predictor.org.pl> - 09:14 AM Revision 79f59e4f (ceph): test/osd-fast-mark-down.sh: wrong assumption on first subtest
- First subtest checks for proper behavior when "osd fast fail on
connection refused" is disabled, yet it doesn't disab... - 09:01 AM Bug #17989 (Closed): bluestore CEPH osd disk overloaded by reads periodically by rocksdb tables g...
During several minutes we have observed disk sday overloaded by read operations ( see this statistics in 10 secon...- 08:34 AM Revision 84cc0ddf (ceph): FreeBSD: do_freebsd.sh
- - rearrange and and more checks before building
- introduce CEPH_DEV to add test/code/debugging when DEVeloping
Sig... - 06:31 AM Revision 69c29960 (ceph): Merge pull request #8948 from cooboos/perf-reset
- test: add perf-reset test in test/perf_counters.cc
Reviewed-by: Haomai Wang <haomai@xsky.com> - 06:16 AM Bug #17948 (Rejected): erasure-code: isa-l corrupted fragment on decode
- Already dealt with : the range of k, m is restricted accordingly
- 06:14 AM Bug #16014 (Pending Backport): test fails due to "The UNIX domain socket path"
- 06:08 AM Bug #17988 (Resolved): tests: osd-scrub-repair.sh fails when stty reports 0 columns
- When running the test from within an emacs buffer, ...
- 04:37 AM Revision 61fca96c (ceph): assert(0) -> ceph_abort()
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:53 AM Revision 10472f05 (ceph): PendingReleaseNotes: document the feature to rebuild monstore
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 03:47 AM Revision e7d9c158 (ceph): mon/AuthMonitor: make AuthMonitor::IncType public
- so ceph-objectstore-tool is able to use it when rebuilding monitor
db.
Fixes: http://tracker.ceph.com/issues/17179
S... - 03:47 AM Revision 6695d179 (ceph): tools/ceph-objectstore-tool: add "update-mon-db" command
- Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit 24... - 03:47 AM Revision 3ef5dcd2 (ceph): tools/ceph_monstore_tool: add "rebuild" command
- Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picked from commit d9... - 03:47 AM Revision 828a4d7a (ceph): doc: add rados/operations/disaster-recovery.rst
- document the process to recover from leveldb corruption.
Fixes: http://tracker.ceph.com/issues/17179
Signed-off-by: ... - 03:47 AM Revision eaeb5205 (ceph): tools/rebuild_mondb: avoid unnecessary result code cast
- In general we return negative codes for error cases, so there is
no need perform the cast here.
Signed-off-by: xie x... - 03:47 AM Revision 94390a32 (ceph): tools/rebuild_mondb: return error if ondisk version of pg_info is incom...
- In this case "r" will be >= 0 and caller will be able to catch
this kind of error.
Signed-off-by: xie xingguo <xie.x... - 03:47 AM Revision ca67e8e8 (ceph): tools/rebuild_mondb: kill compiling warning
- As follow:
[ 72%] Building CXX object src/tools/CMakeFiles/ceph-objectstore-tool.dir/RadosDump.cc.o
/home/jenkins-bu... - 03:47 AM Revision 48696e9d (ceph): tools/ceph_monstore_tool: update pgmap_meta also when rebuilding store.db
- we should rebuild pgmap_meta table from the collected osdmaps
Fixes: http://tracker.ceph.com/issues/17400
Signed-off... - 03:47 AM Revision 9c00ba17 (ceph): tools/ceph_monstore_tool: bail out if no caps found for a key
- we take it as an error if no caps is granted to an entity in the
specified keyring file when rebuilding the monitor d... - 03:47 AM Revision 9473135a (ceph): doc: fill keyring with caps before passing it to ceph-monstore-tool
- to make sure the recovered monitor store is ready for use.
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherry picke... - 03:42 AM RADOS Bug #17830 (Resolved): osd-scrub-repair.sh is failing (intermittently?) on Jenkins
- 03:17 AM Revision 013d4b20 (ceph): Merge pull request #12072 from dzafman/wip-test-17830
- tests: fix osd-scrub-repair.sh
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:13 AM Revision 4fdf4016 (ceph): os/filestore: fix filestore journal logger
- Using u64 intsead of u64_counter for journal_ops/bytes.
These two items are used to metric active journal entry/size... - 02:59 AM rgw Bug #17987 (New): incorrect entry is removed when a part is upload more than once during multipar...
- Here is the discussion
2016-11-19 2:25 GMT+08:00 Yehuda Sadeh-Weinraub <ysadehwe@redhat.com>:
I understand. Yeah,... - 02:45 AM Revision 5fdaba7f (ceph): osd/OSD: cleanup on PeeringWQ::_dequeue(), remove unnecessary variable
- Signed-off-by: Jie Wang <jie.wang@kylin-cloud.com>
- 02:35 AM Revision 107e9c35 (ceph): thrasher: Add dump_ops_enable options
- Add dump_ops_enable which continuously dumps ops using 3 commands
Signed-off-by: David Zafman <dzafman@redhat.com>
(... - 02:33 AM Revision b7c87ae7 (ceph): ceph_manager: Add timeout to admin_socket/osd_admin_socket
- Signed-off-by: David Zafman <dzafman@redhat.com>
(cherry picked from commit 4ad3b866041a3a5391f46cd3d96297834b95956b) - 02:33 AM Revision f79027a2 (ceph): Thrasher: log backtrace of thrown exception
- * add a wrapper to log uncaught exception to self.logger, greenlet also
prints the backtrace and exception to stder... - 01:00 AM Revision 001c759e (ceph): ECTransaction::get_write_plan: fix bug with substripe write with aligne...
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 12:41 AM Revision 9a9b0288 (ceph): librbd: cleanup: use a more proper variable name
- Signed-off-by: Dongsheng Yang <dongsheng.yang@easystack.cn>
Also available in: Atom