Activity
From 11/02/2015 to 12/01/2015
12/01/2015
- 11:48 PM Revision 13925c70 (ceph): init-ceph.in: Allow custom cluster names during startup.
- Signed-off-by: Richard Chan <richard@treeboxsolutions.com>
- 10:38 PM Revision 708ec2b8 (ceph): tests and tools/scratchtool: Don't attempt to use NULL xattr
- Prior commit changes rados{striper}_getxattrs_next to be able to return
NULL in the 'val' param. Handle that.
Fixes... - 10:35 PM Revision 4ec0def9 (ceph): librados.cc: rados_getxattrs_next: don't try to use malloc(0)
- If an xattr is 0 length, don't try to malloc a buffer for the value;
leave it NULL. (Linux doesn't promise malloc(0)... - 10:25 PM Feature #13942: ceph-disk: support bluestore
- https://github.com/ceph/ceph/pull/6759 fixes the block device probing part
- 07:02 PM Feature #13942 (Resolved): ceph-disk: support bluestore
- bluestore (newstore) is based on a very small file system (with osd metadata, like the keyring, features, etc.) and o...
- 10:21 PM Revision db9ec690 (ceph): osd: mark osd backend type in osd_data dir
- When we create an osd, mark the type of the backend in the
osd_data dir in the 'type' file. On startup, if this file... - 10:16 PM Revision 880a59d1 (ceph): osd: make block device fsid probing generic
- Currently the option name and invocation assume that the block device
is a journal (and FileStore journal, managed by... - 09:54 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Better run http://pulpito.ceph.com/teuthology-2015-12-01_12:43:56-rgw-wip-11104-firefly-add-epoch-distro-basic-vps/
- 08:55 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Yuri Weinstein wrote:
> See failed run on wip-11104-firefly-add-epoch
The error there is:... - 08:24 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- See failed run on wip-11104-firefly-add-epoch
http://pulpito.ceph.com/teuthology-2015-12-01_12:12:27-rgw-wip-1110... - 09:19 PM devops Bug #13946: Broken ditaa package makes it difficult to build docs in Trusty
- The bug has already been reported upstream: https://bugs.launchpad.net/ubuntu/+source/ditaa/+bug/1498832
- 09:15 PM devops Bug #13946: Broken ditaa package makes it difficult to build docs in Trusty
- Obviously this is an upstream bug.
- 09:13 PM devops Bug #13946 (Fix Under Review): Broken ditaa package makes it difficult to build docs in Trusty
- The ditaa package in Trusty appears to be seriously broken:...
- 09:04 PM Bug #13944: librados assumes malloc(0) returns valid pointer
- libradosstriper's test program also needs the check.
It looks like a possibly-existing second bug is that rados.py... - 07:55 PM Bug #13944: librados assumes malloc(0) returns valid pointer
- Maybe new/delete are right.
Investigating effects of changing to return NULL for val when len == 0:
ctypes.stri... - 07:42 PM Bug #13944: librados assumes malloc(0) returns valid pointer
- we should really just use new and delete instead
- 07:38 PM Bug #13944 (Resolved): librados assumes malloc(0) returns valid pointer
- librados relies on malloc(0) returning a valid pointer; this is not portable, and even Linux's manpage says "If size ...
- 08:46 PM devops Bug #13945: ./make-deb.sh fails due to filename/path length exceeding 99 chars
- Dupe of 396702aabf67453d4151d9e5fadfd01edf7e053b, fixed already
- 08:43 PM devops Bug #13945 (Duplicate): ./make-deb.sh fails due to filename/path length exceeding 99 chars
- Ubuntu 14.04 system, up to date.
Solution: Add tar-pax to AM_INIT_AUTOMAKE
PR incoming for fix
./make-debs.sh
... - 08:14 PM Revision c5510915 (ceph): Merge pull request #664 from dachary/wip-nop
- nop: suite that does not even lock targets
- 07:56 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Looks good, definitely seems ready for a PR. I'm upgrading the docs gitbuilder - it was too old to have cython 0.20. ...
- 03:43 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Note: just amended and force pushed the last commit a couple times to fix some issues in the interaction between admi...
- 03:24 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- I got rid of rbd_install_files; it's only useful for "make uninstall" (to know what files to remove) but we don't eve...
- 07:33 PM Bug #13872: ceph-mon segmentation fault
- Joao Luis wrote:
> If this is reproducible, mind installing the ceph-dbg package (or whatever it is called in your d... - 07:19 PM Bug #13943 (Resolved): ceph-disk: prepare with partition doesn't set or validate GUIDs
- "ceph-disk prepare" can be fed a block device (e.g. /dev/sda), or a partition (e.g. /dev/sda1) as a device argument.
... - 06:40 PM Cleanup #13941 (New): Create can_discard_op_initial_decode and can_discard_op_final_decode to dis...
- Related: The MOSDOp OpRequestRef needs to have its rmw flags initialized when the final decode happens -- or when the...
- 05:27 PM Stable releases Tasks #13750: infernalis v9.2.1
- h3. fs...
- 05:15 PM Revision 999b24f7 (ceph): Implemented log message size predictor. It tracks size of log messages.
- Initial allocation size is derived from last log message from the same line of code.
Fixed bug in test.
Signed-off-b... - 05:04 PM Bug #13940 (Won't Fix): OSDs fail to start on reboot with dmcrypt/luks
- ceph version 0.94.3 (95cefea9fd9ab740263bf8bb4796fd864d9afe2b)
Linux smr-r1-r1-head2 3.19.0-25-generic #26~14.04.1-U... - 04:50 PM Bug #13939: PGs stuck in "creating" when created just after deleting another pool
- Seen this twice in a row when scheduling wip-testing-jcsp (branch of same name in ceph and ceph-qa-suite) for the "fs...
- 04:49 PM Bug #13939 (Can't reproduce): PGs stuck in "creating" when created just after deleting another pool
http://pulpito.ceph.com/jspray-2015-12-01_03:22:35-fs:recovery-wip-testing-jcsp---basic-multi/1164775
The PG sta...- 04:46 PM rbd Bug #13912 (Resolved): qemu-iotests fails due to extraneous output from journal
- 04:46 PM rbd Bug #13914 (Resolved): FAILED assert(m_image_ctx.owner_lock.is_locked())
- 04:45 PM rbd Bug #13913 (Resolved): librbd: assertion failure on copyup request during trim operation
- 12:30 AM rbd Bug #13913 (Fix Under Review): librbd: assertion failure on copyup request during trim operation
- *master PR*: https://github.com/ceph/ceph/pull/6742
- 04:45 PM rbd Bug #13922 (Fix Under Review): cls_rbd:misused metadata_name_from_key
- 03:32 AM rbd Bug #13922: cls_rbd:misused metadata_name_from_key
- Fix proposed in https://github.com/ceph/ceph/pull/6661
- 03:31 AM rbd Bug #13922 (Resolved): cls_rbd:misused metadata_name_from_key
- The string last_read is already prefixed with RBD_METADATA_KEY_PREFIX,
also it->first. So compare them directly.
... - 04:44 PM rbd Bug #13911 (Resolved): librbd: parent op_work_queue not empty on close
- 04:39 PM rbd Bug #13924 (In Progress): TestJournalPlayer.PrefetchSkippedObject test/journal/test_JournalPlayer...
- 08:54 AM rbd Bug #13924 (Resolved): TestJournalPlayer.PrefetchSkippedObject test/journal/test_JournalPlayer.cc...
- It looks like a rare make check false negative....
- 04:39 PM Linux kernel client Bug #13699 (Can't reproduce): krbd: crash under pblio benchmark
- Also couldn't duplicate with 3.10.
- 04:31 PM Revision 18c5e18f (ceph): Merge pull request #6742 from dillaman/wip-13913
- librbd: automatically flush IO after blocking write operations
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:27 PM Revision a45e0253 (ceph): Merge pull request #6691 from SUSE/wip-13858
- ceph.spec.in: limit _smp_mflags when lowmem_builder is set in SUSE's OBS
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 04:25 PM Backport #13870 (In Progress): hammer: OSD: race condition detected during send_failures
- 04:03 PM Backport #13870: hammer: OSD: race condition detected during send_failures
- Would be nice to get it in 0.94.6, looks like a clean and simple patch.
- 04:12 PM Revision ac05617b (ceph): osd: fix send_failures() locking
- It is unsafe to check failure_queue.empty() without the lock.
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry pic... - 04:12 PM Linux kernel client Bug #13712: Page allocation failure in Kernel 4.2.3.
- I looked into the "vmalloc: allocation failure: 18446744072439583573 bytes" and it turns out we have a buggy memory a...
- 03:43 PM Linux kernel client Bug #13712: Page allocation failure in Kernel 4.2.3.
- We've seen this problem repeatedly on an AMD Opteron system here, running Debian Jessie, which panics every few days....
- 04:04 PM Revision ff537634 (ceph): Merge pull request #6747 from ukernel/wip-osd-getfilter
- osd: fix ClassHandler::ClassData::get_filter()
Reviewed-by: John Spray <john.spray@redhat.com> - 04:04 PM Feature #13938 (Resolved): librbd: reuse ImageCtx::finisher and SafeTimer for lots of images case
- Each Image structure will create two new threads for finisher and SafeTimer, we may reuse these two threads in the sa...
- 04:01 PM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- How do you force faster flushing in hammer?
Also if it's not fixed in the hammer branch I think it should be docum... - 03:52 PM Bug #13894 (Rejected): RBD over cache tier over EC pool: rbd rm doesn't remove objects
- In current master, we'll actually proxy the delete operation to the base pool rather than promote, so this should wor...
- 04:01 PM Bug #13937: osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- first error on one of the two OSDs was actually this one (see logs):...
- 03:53 PM Bug #13937 (Resolved): osd/ECBackend.cc: 201: FAILED assert(res.errors.empty())
- I am getting the following error with ceph v9.2.0 on two different OSDs. The error occurs shortly after startup.
<... - 04:00 PM Bug #13213: stuck recovering apparently due to pg_query not sent by async messenger?
- thanks! let me know if reproduce
- 03:40 PM Bug #13213: stuck recovering apparently due to pg_query not sent by async messenger?
- let's schedule a run of -s rados/thrash with debug ms = 20 and ms type = async to hunt these last few bugs down!
- 03:40 PM Bug #13213: stuck recovering apparently due to pg_query not sent by async messenger?
- Haomai, you can create a branch of the suite with debug_ms = 20 to reproduce.
- 03:59 PM Bug #13497 (Resolved): fine-grained control systemd to start/stop/restart ceph services at once
- 03:59 PM Bug #13350 (Can't reproduce): "Error cancelling global ust listener thread" errors
- 03:55 PM Bug #13853 (Can't reproduce): osd/ReplicatedPG.cc: 10773: FAILED assert(r >= 0)
- 03:46 PM Bug #13057 (Resolved): python-setuptools is missing from debian/control
- 03:44 PM Bug #13370 (Won't Fix): ceph-disk: ceph-deploy suite fails with dmcrypt (hammer)
- 03:44 PM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- OSD logs have debug enabled and are large over the limit for tracker.
OSD.1087 is located here:
https://api.acces... - 03:26 PM Bug #13827: OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer 94.5
- Can you attach the osd logs?
- 03:42 PM Bug #13920: build failure due to distribution implicit compiler files: _FORTIFY_SOURCE on Gentoo
- 03:41 PM Bug #9738 (Won't Fix): rados cli: objects not present in a snapshot are listed anyway
- 03:41 PM Bug #9738 (Closed): rados cli: objects not present in a snapshot are listed anyway
- 03:41 PM Revision 9cca28a9 (ceph): pybind: convert librbd bindings to Cython
- ctypes is fundamentally incapable of providing safe callback support
(exceptions during callbacks are not handled pro... - 03:38 PM Bug #11142 (Can't reproduce): "Exception: ceph-objectstore-tool: import failure" in upgrade:firef...
- 03:37 PM Bug #13468: osd/ReplicatedPG.cc: 9128: FAILED assert(info.last_complete == info.last_update)
- 03:34 PM Bug #8592 (Can't reproduce): sgdisk no longer likes `--change-name` when creating partitions
- 03:34 PM Bug #13543 (Closed): one host down lead to all virtual machine filesystem in cluster can't be wri...
- 03:33 PM Bug #13474: Ceph daemon failed to start, because the service name was already used.
- commit:2f36909e1e08bac993e77d1781a777b386335669
- 03:30 PM Bug #13474 (Pending Backport): Ceph daemon failed to start, because the service name was already ...
- 03:32 PM Bug #13822 (Fix Under Review): Objecter: potential null pointer access in list_(n)objects.
- https://github.com/ceph/ceph/pull/6639
- 03:32 PM Backport #13936 (Resolved): hammer: Ceph daemon failed to start, because the service name was alr...
- https://github.com/ceph/ceph/pull/6832
- 03:32 PM Backport #13935 (Resolved): infernalis: Ceph daemon failed to start, because the service name was...
- https://github.com/ceph/ceph/pull/6833
- 03:29 PM Revision 0f5ce5ea (ceph): Makefile: break out local targets into variables
- To support more than one set of local-* rules, break them out into
sub-rules referenced by appending to variables. Th... - 03:29 PM Revision 8655cca1 (ceph): debian/control: make python-rbd depend on minimum librbd version
- As the Cython bindings build to a binary module, backwards compatibility with
older librbd ABIs at runtime is not pos... - 03:29 PM Revision 5113c962 (ceph): configure/packaging: introduce Cython dependency
- To prepare for the migration of rbd.py to Cython, add Cython as a package
dependency and have the configure script lo... - 03:29 PM Revision 2f36909e (ceph): init-ceph: fix systemd-run cant't start ceph daemon sometimes
- Fixes: #13474
Signed-off-by: Chuanhong Wang <wang.chuanhong@zte.com.cn> - 03:27 PM Backport #13933 (Rejected): infernalis: ceph-disk prepare fails if device is a symlink
- https://github.com/ceph/ceph/pull/7557
- 03:27 PM Bug #13563: "[ FAILED ] LibRadosAioEC.RoundTripSparseReadPP" in upgrade:hammer-x-infernalis-dis...
- Probably fixed by a fix that we can't retrieve right now and that was backported. If it happens again, reopen.
- 03:22 PM Bug #13563 (Resolved): "[ FAILED ] LibRadosAioEC.RoundTripSparseReadPP" in upgrade:hammer-x-inf...
- 03:27 PM Bug #13531: latest update osd lost, cluster still stuck on Peering
- 03:19 PM Bug #13531: latest update osd lost, cluster still stuck on Peering
- 03:25 PM Bug #13438 (Pending Backport): ceph-disk prepare fails if device is a symlink
- 03:24 PM Bug #13902: OSD:project_pg_history may not return the latest same_interval_since.
- 03:24 PM Bug #13902: OSD:project_pg_history may not return the latest same_interval_since.
- https://github.com/ceph/ceph/pull/6721
- 03:22 PM RADOS Bug #13111: replicatedPG:the assert occurs in the fuction ReplicatedPG::on_local_recover.
- 03:21 PM Backport #13342 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- 03:21 PM rbd Backport #13619 (Resolved): rbd clone issue
- 03:21 PM rbd Backport #13705 (Resolved): rbd : enable feature objectmap
- 03:21 PM rbd Backport #13754 (Resolved): Avoid re-writing old-format image header on resize
- 03:21 PM rbd Backport #13756 (Resolved): QEMU hangs after creating snapshot and stopping VM
- 03:21 PM rbd Backport #13759 (Resolved): rbd: pure virtual method called
- 03:21 PM rbd Backport #13761 (Resolved): unknown argument --quiet in udevadm settle
- 03:20 PM rgw Backport #13830 (Resolved): infernalis: init script reload doesn't work on EL7
- 03:18 PM Bug #12746 (Resolved): failed assert ctx.manager.pg_inconsistent(pool, 0) on repair_test.yaml
- 89dcc0d
- 03:16 PM CephFS Backport #13931 (In Progress): infernalis: kclient: intermittent log warnings "client.XXXX isn't ...
- 03:13 PM CephFS Backport #13931 (Resolved): infernalis: kclient: intermittent log warnings "client.XXXX isn't res...
- https://github.com/ceph/ceph/pull/6752
- 03:14 PM CephFS Backport #13932 (In Progress): hammer: kclient: intermittent log warnings "client.XXXX isn't resp...
- 03:13 PM CephFS Backport #13932 (Rejected): hammer: kclient: intermittent log warnings "client.XXXX isn't respond...
- https://github.com/ceph/ceph/pull/8848
- 03:12 PM Backport #13930 (Resolved): hammer: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- https://github.com/ceph/ceph/pull/6834
- 03:12 PM Backport #13929 (Resolved): infernalis: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- https://github.com/ceph/ceph/pull/6907
- 03:12 PM CephFS Backport #13928 (Duplicate): hammer: libcephfs-java failure on hammer
- 03:07 PM CephFS Bug #13926: lockup in multithreaded application
- The logfile has already been uploaded with ceph-post-file, id is a8eb75d5-cc13-430a-bed8-428c8a33d
- 02:10 PM CephFS Bug #13926: lockup in multithreaded application
- looks like you have debug_client=20, could you upload the client log to some place.
- 09:56 AM CephFS Bug #13926 (Closed): lockup in multithreaded application
- A multithreaded applications end up in a blocked state when multiple threads try to access the same file.
# apt-ca... - 03:03 PM Revision 9bd4f745 (ceph): Merge pull request #6749 from dachary/wip-doc-install
- doc: INSTALL redirect to online documentation
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:59 PM CephFS Backport #13927 (In Progress): hammer: cephfs-java ftruncate unit test failure
- 02:58 PM CephFS Backport #13927 (Resolved): hammer: cephfs-java ftruncate unit test failure
- https://github.com/ceph/ceph/pull/11939
- 02:58 PM CephFS Bug #11258 (Pending Backport): cephfs-java ftruncate unit test failure
- 02:57 PM Revision 2ab79d72 (ceph): tools/cephfs: fix layout handling in injection
- When the stashed-layout handling stuff was added,
the guessing part got lost from the path where
we only had a single... - 02:54 PM CephFS Bug #13782 (Resolved): Snapshotted files not properly purged
- https://github.com/ceph/ceph/pull/6603
- 02:48 PM CephFS Bug #13876: qa: openstack MPI connection failures
- 02:47 PM Revision 4eded389 (ceph): rbdmap: Move do_map and do_unmap shell functions to rbdmap script
- This patch creates rbdmap shell script that is called from init-rbdmap
init script. The patch also renames src/rbdmap... - 02:47 PM Revision 1bfb6f76 (ceph): rbdmap: systemd support
- Fixes: #13374
Signed-off-by: Boris Ranto <branto@redhat.com>
(cherry picked from commit 9224ac2ad25f7d017916f58b642c0... - 02:47 PM CephFS Bug #13800 (Resolved): deadlock when invalidating kernel page cache
- 02:44 PM CephFS Bug #13906: pjd failure on hammer
- Yes, we'll want that.
- 02:43 PM CephFS Bug #13904 (Duplicate): Failure in tasks.cephfs.test_client_limits.TestClientLimits
- 03:10 AM CephFS Bug #13904: Failure in tasks.cephfs.test_client_limits.TestClientLimits
- this should be dup of #13583. the test case use fsync(), but fsync is broken,
- 02:41 PM CephFS Bug #11517: Libcephfs: Doesn't check file's open mode when do read/write
- This is done, need to find PR and close!
- 02:40 PM CephFS Bug #13472 (Duplicate): ceph-fuse crash
- 02:38 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- Zheng thinks this is two bugs:
1) Missing "." in list results (fixed in waiting PR)
2) if MDS fragments directory, ... - 02:36 PM CephFS Bug #13907 (Pending Backport): libcephfs-java failure on hammer
- https://github.com/ceph/ceph/pull/6754
- 02:24 PM Revision b2370e41 (ceph): Merge pull request #6729 from majianpeng/librbd-journal
- librbd: only send signal when AIO completions queue empty
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:22 PM Revision 6c68971d (ceph): mds: consider client's flushing caps when choosing lock states
- Client may flush and drop caps at the same time. If client need to
send cap reconnect before the caps get flushed. Th... - 02:21 PM Revision 3fcf905d (ceph): client: cancel revoking caps when reconnecting the mds
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 9ab61b2779740d9038b169da0de616b89b07b813) - 02:19 PM Revision 7e8706ba (ceph): mds: choose EXCL state for filelock when client has Fb capability
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 655ae79dd266dfd488aff67642aceab4ab383d01) - 02:17 PM Revision c07c76b8 (ceph): Merge pull request #6751 from ceph/wip-cmake-strerror_r
- cmake: define STRERROR_R_CHAR_P for GNU-specific strerror_r
Reviewed-by: John Spray <john.spray@redhat.com> - 02:16 PM Revision 2884d8b4 (ceph): Merge pull request #5465 from yuyuyu101/wip-librbd-ap
- librbd: support eventfd for AIO completion notifications
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:07 PM Revision 184914b8 (ceph): cmake: define STRERROR_R_CHAR_P for GNU-specific strerror_r
- This is what autotools does with AC_FUNC_STRERROR_R bit. It takes us
from
$ monmaptool --print nonexistant
... - 01:59 PM Revision 57c7d558 (ceph): Merge pull request #6745 from drunkard/master
- doc: fix typo in cephfs/quota
- 01:51 PM Revision 48abbe70 (ceph): Merge remote-tracking branch 'gh/jewel'
- 01:44 PM Revision e27109ba (ceph): doc: INSTALL redirect to online documentation
- The INSTALL file has obsolete and misleading instructions to compile
from sources (-pg actually fails at link time). ... - 01:14 PM Revision 35403da1 (ceph): qa/workunits/cephtool/test.sh: no ./
- Introduced by 1ace4d03b23b80c699f4861d004f3212ca56a323
Signed-off-by: Sage Weil <sage@redhat.com> - 12:21 PM Revision 88e6694a (ceph): osd: fix ClassHandler::ClassData::get_filter()
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 12:14 PM Revision af86215e (ceph): Merge pull request #6634 from Abhishekvrshny/wip-13761-infernalis
- unknown argument --quiet in udevadm settle
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 09:38 AM Revision 5b35eb8d (ceph): PG: fix message refcounter in replica_scrub
- Signed-off-by: Jie Wang <jie.wang@kylin-cloud.com>
- 09:15 AM Revision 9fba4024 (ceph): doc: typo fix in cephfs/quota
- 09:14 AM Revision fd684ca1 (ceph): librbd/JournalReplay: Only Send signal when aio completions queue empty.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 09:02 AM CephFS Bug #13875 (Duplicate): hammer: java libcephfs test failure
- dup of #13907
- 08:50 AM Revision ac20f38f (ceph): Merge pull request #6697 from XinzeChi/wip-scrub-test
- test: fix osd-scrub-snaps.sh
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:13 AM Feature #13923 (Resolved): Set health to ERR when one or more PGs is stuck inactive
- Based on this thread: http://article.gmane.org/gmane.comp.file-systems.ceph.user/25551
I would propose two additio... - 07:03 AM Bug #13840 (Pending Backport): Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- Merged into master: https://github.com/ceph/ceph/pull/6660
- 02:29 AM Bug #13840: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- Effects my OpenStack. Lost ability to create cinder volumes today due to this issue.
- 06:24 AM Bug #13921: Error connecting to cluster: TypeError
- Can't reproduce on master (at least not easily), maybe a bug in a testing commit
- 01:21 AM Bug #13921: Error connecting to cluster: TypeError
- this is likely related to the python3 rados.py changes
- 04:56 AM Bug #13880 (Resolved): all/mon-config-keys.yaml failing
- commit:f76d5d6fe6a9f92b1ec17191f5504e2f61e0ff28
- 03:10 AM Revision ce2d3c73 (ceph): test: add pg_scrub for ceph-helpers.sh
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 03:10 AM Revision 2548ad8b (ceph): test: fix osd-scrub-snaps.sh
- when we run run-make-check.sh in hdd disk, it would spend much more
time to finish scrub.
Signed-off-by: Xinze Chi <... - 02:04 AM Revision c57ceff2 (ceph): librbd: Fix rebase with new io flow
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:04 AM Revision 5cc9ff90 (ceph): librbd: fix lttng tracing argument mismatch
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision 1da30935 (ceph): librbd: Add set_event_notify to AioImageRequestWQ
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision bddab3ef (ceph): librbd: Remove unneeded set_event_notify
- Since xlist clear method invoked below is enough to disassociate the xlist
item from the xlist, so the remove_myself(... - 02:03 AM Revision d625b89c (ceph): Makefile: Add noinst headr files
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision 97507d5c (ceph): librbd: Make rbd header file uses independent enum definition
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision c42044af (ceph): Librbd: Make AioCompletion complete doesn't unlock if callback
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision c470e0bc (ceph): Librbd: fix return code of EventSocket init and notify
- Signed-off-by: Haomai Wang <haomai@xsky.com>
- 02:03 AM Revision d19deacc (ceph): librbd: Add ictx check to avoid AIO_TYPE_NONE completion
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:03 AM Revision 39327146 (ceph): librbd: normalize notify return code
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:03 AM Revision 6d114749 (ceph): librbd: Fix incorrect api declaration
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:03 AM Revision ca32fc5a (ceph): librbd: check event_notify to avoid extra logic
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:02 AM Revision c7703db9 (ceph): EventSocket: Add new event type pipe support
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:02 AM Revision 0dc93211 (ceph): test: Add tests for getting arg of completion
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:02 AM Revision 1ab727d1 (ceph): librbd: Add interface to let user can get private data from comp
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:02 AM Revision e7a1506b (ceph): tests: Add tests for user io event notify
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 02:02 AM Revision c3a1edbd (ceph): librbd: Add event notify interfaces
- Signed-off-by: Haomai Wang <haomaiwang@gmail.com>
- 01:10 AM rbd Bug #13711 (Resolved): RBD: formatter session may not be rightfully closed.
- 12:26 AM Revision 169cd4d9 (ceph): osd: dump number of missing objects for each peer with pg query
- Signed-off-by: Guang Yang <yguang@yahoo-inc.com>
- 12:24 AM Revision 9b0e3592 (ceph): librbd: automatically flush IO after blocking write operations
- This simplifies other state machines that previously had to flush IO
after blocking write operations.
Fixes: #13913
... - 12:08 AM Tasks #13618: objectstore_bench did not support newstore
- The problem was caused by no of open file limits:
1. Please check your open file limits in the system by command :
...
11/30/2015
- 11:58 PM Revision ce944e4c (ceph): Merge pull request #6741 from SUSE/wip-tyepdef-typo-fix
- include/rados/librados.h: fix typo
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:41 PM Revision 9ced26c1 (ceph): rgw/s3website: errordoc conditional handling
- We need to override all conditional request parameters in errordoc
fallback request, and serve a complete page always... - 11:26 PM Revision 3c6e692c (ceph): include/rados/librados.h: fix typo
- This typo causes a warning when building the docs.
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 10:50 PM Revision dcce366c (ceph): Merge pull request #6740 from dillaman/wip-13911
- librbd: ensure copy-on-read requests are complete prior to closing parent image
Reviewed-by: Josh Durgin <jdurgin@re... - 10:46 PM Bug #13921 (Can't reproduce): Error connecting to cluster: TypeError
- ...
- 09:34 PM rbd Bug #13911 (Fix Under Review): librbd: parent op_work_queue not empty on close
- *master PR*: https://github.com/ceph/ceph/pull/6740
- 08:24 PM rbd Bug #13911: librbd: parent op_work_queue not empty on close
- Associated with CoR: "rbd clone copy on read = true"
- 06:38 PM rbd Bug #13911 (In Progress): librbd: parent op_work_queue not empty on close
- 04:38 PM rbd Bug #13911 (Resolved): librbd: parent op_work_queue not empty on close
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-11-27_23:00:10-rbd-master---basic-multi/1161689/teuthology.log
... - 09:32 PM Revision 6f6fd2f2 (ceph): librbd: utilize common flush helper when closing parent images
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:30 PM Revision 39c5b701 (ceph): librbd: only enqueue flush completion if a flush is pending
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:24 PM Bug #13920: build failure due to distribution implicit compiler files: _FORTIFY_SOURCE on Gentoo
- PR for fix is here: https://github.com/ceph/ceph/pull/6739
should be backported as well, but not 100% required. - 09:18 PM Bug #13920 (Resolved): build failure due to distribution implicit compiler files: _FORTIFY_SOURCE...
- Gentoo's compiler patches include -D_FORTIFY_SOURCE=2 if -O2 or higher are used.
https://sources.gentoo.org/cgi-bi... - 09:20 PM Revision ccf7c29b (ceph): Gentoo: _FORTIFY_SOURCE fix.
- GCC under Gentoo has a patch that has a built-in define for
_FORTIFY_SOURCE if -O2 or higher are used. This causes wa... - 09:16 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- https://github.com/ceph/ceph/tree/wip-11104-firefly-add-epoch bumps the Firefly packages' Epoch to "1".
- 09:13 PM Bug #13919 (Can't reproduce): build failure due to bad distribution libraries with as-needed link...
- Build failure coming up in my gitbuilder, traced to the distributions's liblttng-ust library missing some NEEDED entr...
- 08:30 PM Revision 55e743fd (ceph): Merge pull request #6737 from dillaman/wip-13912
- librbd: check for presence of journal before attempting to remove
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:30 PM Revision ee41d1da (ceph): Merge pull request #6668 from zaitcev/cleanup-dead-code-2
- rgw: Remove unused code in PutMetadataAccount:execute
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com>
Reviewed-by: Rad... - 08:02 PM CephFS Bug #11482: kclient: intermittent log warnings "client.XXXX isn't responding to mclientcaps(revoke)"
- Hi John: Backport to which major versions - hammer, infernalis?
- 05:58 PM CephFS Bug #11482 (Pending Backport): kclient: intermittent log warnings "client.XXXX isn't responding t...
- Merged to master...
- 07:43 PM Revision 48723534 (ceph): Merge pull request #6738 from ceph/wip-rbd-cli-misc
- rbd: fixes for refactored CLI and related tests
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 07:38 PM Revision 206b8e2c (ceph): common/buffer: forward declare buffer
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:38 PM Revision aa387003 (ceph): common/buffer: changed buffer from class to namespace
- Since the buffer only contained static functions it doesn't make sense
for it to be a class. Changing it to a namespa... - 07:02 PM Revision a722fa22 (ceph): Merge pull request #6715 from jcsp/wip-librbd-cmake
- cmake: update for recent librbd changes
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:36 PM rbd Bug #13913: librbd: assertion failure on copyup request during trim operation
- Lost watch during copy-up operation, resulting in the exclusive lock being released:
#2 0x00007ff49f47d6b3 in lib... - 04:48 PM rbd Bug #13913 (Resolved): librbd: assertion failure on copyup request during trim operation
- 2015-11-27T23:38:28.281 INFO:teuthology.orchestra.run.burnupi22.stderr:librbd/operation/TrimRequest.cc: In function '...
- 05:53 PM Revision 304965f1 (ceph): Merge pull request #6432 from ukernel/wip-11482
- mds: fix client capabilities during reconnect (client.XXXX isn't responding to mclientcaps(revoke))
Reviewed-by: Joh... - 05:44 PM Bug #13872: ceph-mon segmentation fault
- If this is reproducible, mind installing the ceph-dbg package (or whatever it is called in your distribution) and get...
- 05:28 PM Bug #13872: ceph-mon segmentation fault
- Hi Joao,
I'm working with Kane on this. The keyring file is named @ceph-ceph1.mon.keyring@, and the contents are:... - 05:43 PM Revision 1ada4c39 (ceph): Merge pull request #6736 from dillaman/wip-13914
- librbd: not necessary to hold owner_lock while releasing snap id
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:37 PM rbd Bug #13912 (Fix Under Review): qemu-iotests fails due to extraneous output from journal
- *master PR*: https://github.com/ceph/ceph/pull/6737
- 04:47 PM rbd Bug #13912 (Resolved): qemu-iotests fails due to extraneous output from journal
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-11-27_23:00:10-rbd-master---basic-multi/1161666/teuthology.log
- 05:36 PM Revision 083fdbf8 (ceph): librbd: check for presence of journal before attempting to remove
- Fixes: #13912
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 05:31 PM Revision ac35e84f (ceph): journal: helper method to determine if journal exists
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:27 PM Bug #13916 (Can't reproduce): erasure code profile name
- I've been experimenting with ceph erasure pools. In my naivety I created an erasure pool with a dash in the name. E...
- 05:16 PM Bug #13915 (Can't reproduce): "failed: mon_thrash" in upgrade:hammer-hammer-distro-basic-openstack
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-29_16:05:03-upgrade:hammer-hammer-distro-basic-opensta...
- 04:56 PM rbd Bug #13914 (Fix Under Review): FAILED assert(m_image_ctx.owner_lock.is_locked())
- *master PR*: https://github.com/ceph/ceph/pull/6736
- 04:51 PM rbd Bug #13914 (Resolved): FAILED assert(m_image_ctx.owner_lock.is_locked())
- 2015-11-27T23:39:48.037 INFO:tasks.workunit.client.0.burnupi29.stderr:librbd/operation/SnapshotCreateRequest.cc: 235:...
- 04:55 PM Revision 644d6000 (ceph): librbd: not necessary to hold owner_lock while releasing snap id
- Fixes: #13914
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 04:50 PM Revision 9d060414 (ceph): rbd: bail if too many arguments provided
- The code has a catch clause for that, but it was being rendered useless
by the preceding
if (command_spec.size()... - 04:43 PM Revision a86b8895 (ceph): Merge pull request #750 from dachary/wip-13910-buildpackages-images-hammer
- buildpackages: create the image if it does not exist
Reviewed-by: Abhishek Varshney <abhishek.varshney@flipkart.com> - 04:43 PM Revision 98c2f9c9 (ceph): Merge pull request #748 from dachary/wip-13910-buildpackages-images
- buildpackages: create the image if it does not exist
Reviewed-by: Abhishek Varshney <abhishek.varshney@flipkart.com> - 04:38 PM Revision dfbe316f (ceph): buildpackages: create the image if it does not exist
- Since buildpackages runs before target provisioning, it is possible that
the desired image does not yet exist on a ne... - 04:26 PM Revision 899ff616 (ceph): Merge pull request #6650 from Abhishekvrshny/wip-13830-infernalis
- init script reload doesn't work on EL7
Reviewed-by: Boris Ranto <branto@redhat.com> - 04:25 PM Revision f2b323a6 (ceph): Merge pull request #6477 from SUSE/wip-13705-infernalis
- rbd : enable feature objectmap
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:25 PM Revision 5c02e2bd (ceph): Merge pull request #6474 from SUSE/wip-13619-infernalis
- rbd clone issue
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 04:24 PM Revision ed8ac030 (ceph): Merge pull request #6633 from Abhishekvrshny/wip-13759-infernalis
- rbd: pure virtual method called
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:24 PM Revision 1551c1be (ceph): Merge pull request #6632 from Abhishekvrshny/wip-13756-infernalis
- QEMU hangs after creating snapshot and stopping VM
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:22 PM Revision d133f423 (ceph): rbd: don't append an extra newline after some errors
- Don't append an extra newline after program_options-generated errors,
like "unrecognised option" or "the argument for... - 04:20 PM Revision b8000d6f (ceph): Merge pull request #6630 from Abhishekvrshny/wip-13754-infernalis
- Avoid re-writing old-format image header on resize
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:55 PM Revision ab9a3d5a (ceph): buildpackages: create the image if it does not exist
- Since buildpackages runs before target provisioning, it is possible that
the desired image does not yet exist on a ne... - 03:45 PM Revision 1c846816 (ceph): tests: update unmap.t CLI test
- Fixup the exit code - the old CLI tried to differentiate between CLI
errors and action errors by returning EXIT_FAILU... - 03:29 PM Revision 5ce663f1 (ceph): cmake: librbd needs libjournal and libcls_journal_client
- Commit 4719696cadd1 ("cmake: updates for refactored librbd IO path")
fixed file lists but missed the link dependency ... - 03:20 PM Bug #13057: python-setuptools is missing from debian/control
- Sorry for not getting back earlier, I think my test has been on Ubuntu Trusty, but it may have been some newer Ubuntu...
- 03:12 PM Revision 56e58e55 (ceph): Merge pull request #6706 from xiexingguo/xxg-wip-13711
- rbd: output formatter may not be closed upon error
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:11 PM Revision fe3d8552 (ceph): Merge pull request #6734 from accelazh/master
- Correct typo 'restared' to 'restarted'
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:01 PM Revision 77aef0d8 (ceph): rgw: remove unused variable in RGWPutMetadataBucket::execute.
- Signed-off-by: Radoslaw Zarzynski <rzarzynski@mirantis.com>
- 02:24 PM Revision 117e6304 (ceph): Correct typo 'restared' to 'restarted'
- There is a typo in document "Monitoring OSDs and PGs" as below
An OSD was ``down``, was restared, and is now ``r... - 02:20 PM Revision 4f29d92f (ceph): suites: yaml for TestDataScan
- This was an oversight.
Signed-off-by: John Spray <john.spray@redhat.com> - 02:01 PM Revision fc6f21a1 (ceph): Merge pull request #6396 from SUSE/wip-13342-infernalis
- ceph upstart script rbdmap.conf incorrectly processes parameters
Reviewed-by: Sage Weil <sage@redhat.com> - 02:00 PM Revision 99d18047 (ceph): Merge pull request #6733 from tchaikov/wip-fixcodingstyle
- CodingStyle: fix broken URLs
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:57 PM Revision bf894405 (ceph): Merge pull request #745 from ceph/wip-ceph-whitespace-hammer
- tasks/ceph: fix up whitespace
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:23 PM CephFS Bug #13907: libcephfs-java failure on hammer
- seems like dup of #11258. the fix is included in infernalis
- 11:57 AM CephFS Bug #13907 (Duplicate): libcephfs-java failure on hammer
http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-26_18:00:01-fs-hammer---basic-openstack/20947/
(Note t...- 01:12 PM Revision 691199bd (ceph): CodingStyle: fix broken URLs
- Signed-off-by: Kefu Chai <kchai@redhat.com>
- 12:59 PM CephFS Bug #13906: pjd failure on hammer
- this should be #11783. should we backport the fix?
- 11:39 AM CephFS Bug #13906 (Closed): pjd failure on hammer
No idea what changed recently to cause this: seen once in on an openstack cluster
http://pulpito.ovh.sepia.ceph....- 12:27 PM CephFS Bug #13903: Failure in TestStrays.test_ops_throttle
- Passes when run locally :-/
- 10:28 AM CephFS Bug #13903 (Resolved): Failure in TestStrays.test_ops_throttle
Note that this is different from http://tracker.ceph.com/issues/12657
http://pulpito.ceph.com/teuthology-2015-11...- 12:27 PM CephFS Bug #13904: Failure in tasks.cephfs.test_client_limits.TestClientLimits
- Passes when run locally :-/
- 10:36 AM CephFS Bug #13904 (Duplicate): Failure in tasks.cephfs.test_client_limits.TestClientLimits
http://pulpito.ceph.com/teuthology-2015-11-27_23:04:02-fs-master---basic-multi/1161827/
Failed at ceph d704c54...- 12:16 PM Revision 54163923 (ceph): tasks/ceph: fix up whitespace
- ...because otherwise it lights up like a christmas
tree in pycharm.
Signed-off-by: John Spray <john.spray@redhat.com... - 11:47 AM CephFS Bug #13876: qa: openstack MPI connection failures
- Hmm, so the update to firewall rules was in teuthology, and is this:...
- 11:41 AM CephFS Bug #13876: qa: openstack MPI connection failures
- Here's another more recent one:
teuthology-2015-11-26_18:00:01-fs-hammer---basic-openstack/ ['20901', '20933', '2091... - 10:57 AM Revision 3ee2f6df (ceph): os/LFNIndex: check object whether exist for remove_object.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 10:55 AM Linux kernel client Bug #13905 (Closed): "BUG: held lock freed!"
Seen:
http://pulpito.ceph.com/teuthology-2015-11-27_23:10:02-knfs-master-testing-basic-multi/1161921/
http://pulp...- 07:27 AM Revision 6b402f5f (ceph): ceph::buffer, Add cached_crc and cached_crc_adjust count in perf dump
- in order to track the hit rate and efficiency of crc_cache
Signed-off-by: Ning Yao <zay11022@gmail.com> - 03:12 AM Revision bcb8f362 (ceph): mon: support min_down_reporter conuted by subtree level
- In many case OSDs in an isolated(public/cluster connection lost but osd<->mon is good) node
will report other OSD dow...
11/29/2015
- 06:14 PM Stable releases Tasks #13750: infernalis v9.2.1
- h3. upgrade...
- 05:07 PM Revision 43c1ba7c (ceph): tools: fix cephfs-data-scan scan_frags vs. nlink
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:01 PM Bug #13592 (Resolved): ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- 11:20 AM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9649/console
- 04:01 PM Revision 2af7c9f7 (ceph): Merge pull request #6724 from dachary/wip-13592-test-auto-repair
- tests: fix race condition testing auto scrub
Reviewed-by: Xinze Chi <xinze@xsky.com> - 02:28 PM Revision 06b3b47e (ceph): mon/PGMonitor: MAX AVAIL is 0 if some OSDs' weight is 0
- In get_rule_avail(), even p->second is 0, it's possible to be used
as divisor and quotient is infinity, then is conve... - 02:27 PM Revision b2eefcac (ceph): os: FileStore::_destroy_collection may hide the real mistake.
- Signed-off-by: Ruifeng Yang <yangruifeng.09209@h3c.com>
(cherry picked from commit 9e9770ca87720781264d2e283739fc9e19... - 02:25 PM Revision 04c03607 (ceph): Fix mon routed_request_tids leak
- Signed-off-by: Ning Yao <zay11022@gmail.com>
(cherry picked from commit ba3c64ca705590f833806300461f3b98de0e62f8) - 02:24 PM Revision baf9da31 (ceph): pybind: decode empty string in conf_parse_argv() correctly
- cretargs is a array of c_char_p, which means ctypes has already
converted it to python byte strings. decode_cstr() wo... - 02:24 PM Revision 903350cf (ceph): ceph_test_keyvaluedb_iterators: Fix broken test
- Introduced by #6312
Signed-off-by: Haomai Wang <haomai@xsky.com>
(cherry picked from commit ce0369444558b6308e1e0ffa4... - 11:17 AM Revision f79e2890 (ceph): tests: fix race condition testing auto scrub
- When testing auto scrub, waiting 20 seconds for the scrub to complete is
sometimes not enough and creates false negat...
11/28/2015
- 07:03 PM Revision 26752f96 (ceph): cmake: update for recent librbd changes
- Recent merge moved lots of things.
Signed-off-by: John Spray <john.spray@redhat.com> - 05:49 PM Bug #13592 (Fix Under Review): ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- https://github.com/ceph/ceph/pull/6724
- 03:29 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- # Remove the object from one shard physically
objectstore_tool $dir $(get_not_primary $poolname SOMETHING) SOMETHIN... - 03:24 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- I think we could schedule the scrub by manually (using the ceph pg scrub command)
- 03:21 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- I think the reason is that the scrub is not be scheduled by osd.
Because the sched_scrub is only 33% percent called ... - 03:48 PM Revision e9e05333 (ceph): auth: fix double PK11_DestroyContext() if PK11_DigestFinal() failed
- Signed-off-by: Dunrong Huang <riegamaths@gmail.com>
- 03:48 PM Revision a7f520ca (ceph): auth: fix a crash issue due to CryptoHandler::create() failed
- In this case(e.g. user passes wrong key), attempts to call the CryptoKey.ckh will lead to a segfault.
This patch fix... - 01:31 PM Revision dc217d43 (ceph): Merge pull request #6503 from XinzeChi/wip-repop-worker
- osd: defer decoding of MOSDRepOp/MOSDRepOpReply
Reviewed-by: Haomai Wang <haomai@xsky.com>
Reviewed-by: Sage Weil <s... - 01:29 PM Revision 2a9d6cbc (ceph): Merge pull request #6597 from ceph/wip-fix-kvdb-test
- tests: ceph_test_keyvaluedb_iterators: fix broken test
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com> - 01:28 PM Revision 7b90b50a (ceph): Merge pull request #6543 from efirs/optimize-stringify-call
- common: reduce CPU usage by making stringstream in stringify function thread local
Reviewed-by: Haomai Wang <haomai@... - 01:27 PM Revision daf08784 (ceph): Merge pull request #6455 from 0003ydlom/perfctrwa
- osd: enable perfcounters on sharded work queue mutexes
Reviewed-by: Sage Weil <sage@redhat.com> - 01:26 PM Revision dc9bbbf4 (ceph): Merge pull request #6441 from aclamk/wip-faster-log-fixed
- common: optimize debug logging code
Reviewed-by: Sage Weil <sage@redhat.com> - 01:25 PM Revision a12efa20 (ceph): Merge pull request #6276 from david-z/wip-systemd-finegrain-ceph-service
- systemd: start/stop/restart ceph services by daemon type
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: ... - 01:23 PM Revision c72bb31d (ceph): Merge pull request #6198 from XinzeChi/wip-buffer-history-alloc
- common: perf counter for bufferlist history total alloc
Reviewed-by: Sage Weil <sage@redhat.com> - 07:57 AM Bug #13902 (Closed): OSD:project_pg_history may not return the latest same_interval_since.
- The project_pg_history is designed to calculate the latest same_interval_since, same_up_since and same_primary_since ...
11/27/2015
- 08:39 PM rgw Bug #13900 (Closed): "test_s3.test_non_versioned_concurrent_object_create_concurrent_remove ... E...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-27_16:05:03-upgrade:hammer-hammer-distro-basic-opensta...
- 05:58 PM Revision ca642294 (ceph): Merge pull request #679 from ceph/wip-ceph-whitespace
- tasks/ceph: fix up whitespace
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:43 PM Revision b3da9d7e (ceph): tasks/cephfs: add TestJournalRepair.test_table_tool_take_inos
- Signed-off-by: John Spray <john.spray@redhat.com>
- 05:40 PM Revision 574e3193 (ceph): Test:bencher ops counter doesn't increase
- Signed-off-by: Tao Chang <changtao@hihuron.com>
- 04:28 PM Revision 0b474c52 (ceph): mon: don't require OSD W for MRemoveSnaps
- Use ability to execute "osd pool rmsnap" command
as a signal that the client should be permitted
to send MRemoveSnaps... - 04:21 PM Revision 9ea3b26b (ceph): Merge pull request #740 from dachary/wip-13899-rbd-fio
- task/rbd_fio: allow for unsigned packages
Reviewed-by: Abhishek Varshney <abhishek.varshney@flipkart.com> - 04:01 PM Bug #12814 (In Progress): flipping the overlay from forward to seems to reorder writes
- 12:45 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
- testing infernalis *rados/singleton/{all/thrash_cache_writeback_forward_none.yaml fs/btrfs.yaml msgr/simple.yaml msgr...
- 03:34 PM Feature #13077 (Resolved): osd: new pool settings: scrub_interval, deep_scrub_interval
- 03:34 PM Revision d704c54b (ceph): Merge pull request #6081 from trociny/wip-pool_opts_t
- osd: pg_pool_t: add dictionary for pool options
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: Sage Weil <sa... - 02:35 PM rgw Backport #13536 (Resolved): rgw: bucket listing hangs on versioned buckets
- 02:35 PM Backport #13693 (Resolved): bug with cache/tiering and snapshot reads [merged, needs a test in ce...
- 02:12 PM Revision 77e75c03 (ceph): Merge pull request #742 from dachary/wip-openstack-morepggrow
- openstack: rados/.../morepggrow.yaml may need more disk
Reviewed-by: Abhishek Varshney <abhishek.varshney@flipkart.com> - 02:11 PM Revision a6de4a01 (ceph): openstack: rados/.../morepggrow.yaml may need more disk
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:47 PM Revision 6d976b7a (ceph): openstack: rados/thrash...cache-pool-snaps.yaml: need 15GB
- 8GB is not enough for cache-pool-snaps.yaml, it needs more otherwise it
will intermittently fail by crashing the targ... - 01:47 PM Feature #13837: Make snap_trimming robust to inconsistent snaphots
- Related crash that happens when trying to repair one of the affected PGs:
(Filtered to only contain the actions of... - 01:23 PM CephFS Bug #13898 (Fix Under Review): Bad layouts injected by cephfs-data-scan scan_inodes
- 12:33 PM CephFS Bug #13898 (Resolved): Bad layouts injected by cephfs-data-scan scan_inodes
TestDataScan picked this up, symptom was crashing fuse client when it aborted on an invalid layout.
Patch incoming.- 01:20 PM Revision d14f2da4 (ceph): task/rbd_fio: allow for unsigned packages
- Similar to what the teuthology install.py task does, add --force-yes to
the apt-get install so that unsigned packages... - 12:38 PM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rbd...
- 12:37 PM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rgw...
- 12:22 PM Tasks #13618: objectstore_bench did not support newstore
- James Liu wrote:
> sudo ./src/test/ceph_objectstore_bench --conf=./src/test/ceph.conf --size=2000M --block-size=16K ... - 12:15 PM Tasks #13618: objectstore_bench did not support newstore
- James Liu wrote:
> thanks for providing the configure file. I am able to run objectstore_bench for newstore too over... - 11:58 AM Revision 50e83e32 (ceph): Merge pull request #736 from dachary/wip-buildpackage-delete-wait
- buildpackages: wait for the build machine deletion
- 11:37 AM Bug #13882 (Rejected): The monitor always election
- I don't think this is a bug. The problem should be the monitors being unable to reply to leases in time. This is also...
- 07:59 AM Bug #13882: The monitor always election
- In ceph the leader will keep talk to the quorum every 3s.If all the quorum answer the lease message ,
it is ok. B... - 11:35 AM Revision e6dcf141 (ceph): osd: store per pool scrub intervals in pool options
- ceph osd pool set $POOL scrub_min_interval N
ceph osd pool set $POOL scrub_max_interval N
ceph osd pool set $POOL... - 11:05 AM Bug #13897: (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED assert(r == 0)
- @David Does that ring a bell by any chance ?
- 11:00 AM Bug #13897 (Resolved): (jewel) rados/objectstore/objectstore.yaml common/Mutex.cc: 105: FAILED as...
- ...
- 10:44 AM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9619/console
- 10:40 AM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9622/console
- 10:32 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- I'm just guessing, but it seems that when we delete a rbd image, for each rados object, the tier cache load it into t...
- 09:53 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- Then I have put the cache in forward mode:
$ sudo ceph osd tier cache-mode cache forward
$ sudo rados -p cache ca... - 09:48 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- We can see neither the data or the cache are deleted too:
$ sudo rbd -p data import --image-format 2 file file
Im... - 08:54 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- $ sudo rados df
pool name category KB objects clones degraded unfound ... - 08:36 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- I have setuped a cluster with one osd node to reproduce and got the issue easily. I have not used erasure coding, so ...
- 08:24 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- We have leftover objects showing up in rados ls, but rados get fails on them while the shard files are presents on di...
- 08:22 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- The same issue was reported one year ago, no answer on the list:
http://lists.opennebula.org/pipermail/ceph-users-... - 08:21 AM Bug #13894: RBD over cache tier over EC pool: rbd rm doesn't remove objects
- We
root@g1:~# date;time rbd rm ec4p1/volume-bd767663-ca3a-4b88-82bd-30817f20f762;echo $?;date
Wed Nov 25 16:23:25... - 08:19 AM Bug #13894 (Resolved): RBD over cache tier over EC pool: rbd rm doesn't remove objects
- When using rbd rm on an image over an EC 4+1 pool witch replicated 3 cache, the command exits successfully but no obj...
- 10:17 AM Revision 2b252d29 (ceph): tests: workunits should not have ./ (assume it in $PATH)
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 10:17 AM Revision 73077dd0 (ceph): osd: pg_pool_t: add dictionary for pool options
- It is going to be used to store per pool configuration parameters like
scrub intervals or recovery priority.
Signed-... - 09:11 AM rbd Bug #13877 (Resolved): osdc/ObjectCacher.cc: 467: FAILED assert(tid == 0 || bh_tid <= tid)
- 08:48 AM Revision 4189380f (ceph): Merge pull request #6710 from jdurgin/wip-13877
- test: use sequential journal_tid for object cacher test
Reported-by: Kefu Chai <kchai@redhat.com> - 08:47 AM Revision edde13ce (ceph): osd: fix send_failures() locking
- It is unsafe to check failure_queue.empty() without the lock.
Fixes: #13869
Signed-off-by: Sage Weil <sage@redhat.com... - 06:39 AM Revision 9a14ff7e (ceph): osd/OSD.cc: shutdown after flapping certain times
- OSD stauts may flapping due to some hardware/network issue.
Although we tried our best to self healthing but still in... - 06:14 AM Revision 9ab820f8 (ceph): Merge pull request #6711 from jdurgin/wip-13880
- pybind: decode empty string in conf_parse_argv() correctly
Reviewed-by: Kefu Chai <kchai@redhat.com> - 05:16 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Looks like the ubuntu build worked. On centos 7 it had a final error when checking the packages:...
- 02:18 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Good point about the python3 packages being required regardless of cython.
I'm fine with that docs hack. Avoiding ... - 04:30 AM Documentation #13893 (Closed): Manual Deployment Documentation Bugs (systemd)
- On the manual deployment page: http://docs.ceph.com/docs/v9.0.2/install/manual-deployment/
The page is not written... - 01:31 AM Revision 09c0d8da (ceph): librbd: fix tracepoint parameter
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
11/26/2015
- 10:31 PM Revision d0690be5 (ceph): Merge pull request #6704 from liewegas/wip-up-thru
- mon: block 'ceph osd pg-temp ...' if pg_temp update is already pending
Reviewed-by: Joao Eduardo Luis <joao@suse.de> - 10:30 PM Revision 4b80b300 (ceph): Merge pull request #6653 from branch-predictor/bp-no-zero-reverse
- common: don't reverse hobject_t hash bits when zero
Reviewed-by: Sage Weil <sage@redhat.com> - 10:29 PM Revision 2c460045 (ceph): Merge pull request #6475 from branch-predictor/bp-trim-n-reorder-bools
- osd: reduce memory consumption of some structs
Reviewed-by: Sage Weil <sage@redhat.com> - 10:29 PM Revision 6ddaf357 (ceph): Merge pull request #6456 from stiopaa1/removeConstr
- common: buffer: remove unneeded list destructor
Reviewed-by: Sage Weil <sage@redhat.com> - 10:28 PM Revision 4d52382d (ceph): Merge pull request #6263 from dx9/wip-12406-os-filestore
- osd: FileStore: remove __SWORD_TYPE dependency
Reviewed-by: Sage Weil <sage@redhat.com> - 10:28 PM Revision ca9f9d17 (ceph): Merge pull request #6262 from dx9/wip-12406-os-fs
- osd: remove __SWORD_TYPE dependency
Reviewed-by: Sage Weil <sage@redhat.com> - 10:28 PM Revision 489b2a35 (ceph): Merge pull request #6175 from XinzeChi/wip-finisher-lat
- common: add latency perf counter for finisher
Reviewed-by: Sage Weil <sage@redhat.com> - 10:27 PM Revision d8cfce25 (ceph): Merge pull request #6102 from mslovy/wip-mon-leak-fix
- mon: fix routed_request_tids leak
Reviewed-by: Sage Weil <sage@redhat.com> - 10:26 PM Revision 1d46a65c (ceph): Merge pull request #6093 from tchaikov/wip-kvstore-tool-argv
- ceph-kvstore-tool: handle bad out file on command line
Reviewed-by: Sage Weil <sage@redhat.com> - 10:26 PM Revision b7eb1678 (ceph): Merge pull request #5793 from yuyuyu101/impl-perf
- osd: add osd op queue latency perfcounter
Reviewed-by: Sage Weil <sage@redhat.com> - 10:24 PM Revision d633b645 (ceph): Merge pull request #5734 from cxwshawn/mon-fix
- auth: make keyring without mon entity type return -EACCES
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:19 PM Revision 63d3569d (ceph): Merge pull request #738 from dachary/wip-openstack-debug
- openstack: add 15GB for debugging purposes
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com> - 09:10 PM Revision a25638c5 (ceph): openstack: add 15GB for debugging purposes
- So that it can be used as follows:
teuthology-openstack ... --suite mysuite ... debug/openstack-15G.yaml
Signed-... - 08:45 PM CephFS Bug #13777: Ceph file system is not freeing space
- Can both pull requests in this ticket be back ported to the next Infernalis release?
Thanks
Eric - 06:14 PM Backport #13892 (Resolved): hammer: auth/cephx: large amounts of log are produced by osd
- https://github.com/ceph/ceph/pull/6835
- 06:13 PM Backport #13891 (Resolved): infernalis: auth/cephx: large amounts of log are produced by osd
- https://github.com/ceph/ceph/pull/6836
- 06:10 PM CephFS Backport #13890 (Rejected): infernalis: Race in TestSessionMap.test_version_splitting
- 06:09 PM CephFS Backport #13889 (Resolved): infernalis: Segmentation fault accessing file using fuse mount
- https://github.com/ceph/ceph/pull/6853
- 06:07 PM rgw Backport #13888 (Resolved): hammer: orphans finish segfaults
- https://github.com/ceph/ceph/pull/7186
- 06:07 PM rgw Backport #13887 (Resolved): infernalis: orphans finish segfaults
- https://github.com/ceph/ceph/pull/7424
- 06:04 PM Revision 014e2f0e (ceph): ceph.spec.in: use %tmpfiles_create macro
- Ensure the macro is defined, and use it to placate the relevant openSUSE
RPMLINT check.
Drop --prefix=/run/ceph (int... - 02:59 PM Revision da52b5e4 (ceph): Workunits : fs/misc/: check if cache is used in direct IO
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:12 PM Revision c4fff6f7 (ceph): Merge pull request #6714 from aiicore/test_encoding_readable
- test/encoding/readable.sh fix
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:07 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
- ...
- 01:36 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
- /a/sage-2015-11-25_07:26:30-rados-wip-sage-testing---basic-multi/1160057
- 01:04 PM rgw Bug #13885: rgw: DNSError on OpenStack
- most probably a DNS configuration error in the openstack cluster but quite difficult to figure out whithout an indica...
- 01:03 PM rgw Bug #13885 (Resolved): rgw: DNSError on OpenStack
- ...
- 12:54 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- RPM packages seem to build after the latest few commits, and debs should work too unless I broke something. Let me kn...
- 10:23 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- I figured out what was up with setup.py. It wasn't about cwd, the issue was that 'make dist' was not including setup....
- 12:42 PM rgw Documentation #13235: rgw: The command of [log show] show an incorrect usage according to both of...
- Hi,Yehuda. how about this issue?You can search #6080 on github ceph.
- 12:38 PM Revision 8a9db373 (ceph): test/encoding/readable.sh fix
- 1. Fix formatting (mixed tabs and spaces)
2. Status of skipped types was showing always last version in directory
Si... - 12:14 PM Revision 84db4963 (ceph): os/CollectionIndex: Change meaning of last parameter for lookup function.
- Origin:
virtual int lookup(
const ghobject_t &oid, ///< [in] Object to lookup
IndexedPath *path, ///< [ou... - 12:14 PM Revision 1813ef31 (ceph): os/LNFIndex: Remove the dupicated code.
- In _lookup, it already check object whether exists. So no need check
again in lookup func.
Signed-off-by: Jianpeng M... - 12:14 PM Revision a0a424e2 (ceph): os/FileStore: cleanup code for lfn_unlink.
- Signed-off-by: Jianpeng Ma <jianpeng.ma@intel.com>
- 12:13 PM Revision 8088d605 (ceph): buildpackages: wait for the build machine deletion
- When the quotas are low, it matters to block until the build machine is
actually deleted. Otherwise target provisionn... - 11:56 AM rbd Backport #13753 (Resolved): Avoid re-writing old-format image header on resize
- 11:56 AM rbd Backport #13755 (Resolved): QEMU hangs after creating snapshot and stopping VM
- 11:56 AM rbd Backport #13758 (Resolved): rbd: pure virtual method called
- 11:56 AM Backport #13770 (Resolved): Objecter: pool op callback may hang forever.
- 11:09 AM Bug #13882 (Rejected): The monitor always election
- Hello.My ceph version is 0.87.2.
The ceph info is below
[root@ceph243 ~]# rbd showmapped
id pool im... - 09:15 AM Revision 8870a4ae (ceph): Merge pull request #6705 from vanpire110/master
- doc: Fixes a spelling error
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:10 AM Revision 375c53bb (ceph): cephfs/test_client_recovery: check fsync waits for unsafe requests
- make sure fsync wait for unsafe requests that created/modified the
file.
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 05:45 AM Bug #13880 (Fix Under Review): all/mon-config-keys.yaml failing
- https://github.com/ceph/ceph/pull/6711
- 05:42 AM Revision f76d5d6f (ceph): pybind: decode empty string in conf_parse_argv() correctly
- cretargs is a array of c_char_p, which means ctypes has already
converted it to python byte strings. decode_cstr() wo... - 04:38 AM Revision 1bf02392 (ceph): Merge pull request #6699 from dachary/wip-ceph-helpers
- tests: ceph-helpers assert success getting backfills
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:29 AM rbd Bug #13877 (Fix Under Review): osdc/ObjectCacher.cc: 467: FAILED assert(tid == 0 || bh_tid <= tid)
- https://github.com/ceph/ceph/pull/6710
- 04:24 AM Revision 9331e031 (ceph): test: use sequential journal_tid for object cacher test
- This matches the real usage by librbd.
Fixes: #13877
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 03:52 AM Revision 46400a56 (ceph): Merge pull request #720 from dachary/wip-12748-hammer
- rados/singleton-nomsgr/all: add export-after-evict.yaml
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:44 AM Bug #13878 (Fix Under Review): test/librados/tier.cc doesn't completely clean up EC pools
- obsolete https://github.com/ceph/ceph/pull/6707
- 02:58 AM Revision 720ac2b8 (ceph): EventSocket: Add EventSocket structure used for event notification
- EventSocket will wrap different user event notification method like linux
eventfd, solaris port. Caller can user this... - 02:08 AM Revision f5e0cce9 (ceph): osd: don't update rollback_info for replicated pool
- rollback_info is just needed for ec-pool to rollback the patial committed chunks to previous version. Avoid recording...
- 02:05 AM Revision 788077fa (ceph): List: close formatter session on error exit.
- Fixes: #13711
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 02:02 AM Revision 2b390fc2 (ceph): osd: don't update unneccessary epoch for pg
- epoch always remains unless state of cluster changes. Therefore, avoid update epoch for every Op in order to same cpu...
- 02:00 AM Revision 75f1412b (ceph): DiskUsage: close formatter session on error exit
- Fixes: #13711
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 01:49 AM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- Greg Farnum wrote:
> http://pulpito.ceph.com/teuthology-2015-11-09_23:04:02-fs-master---basic-multi/1144848/
>
> ... - 01:44 AM Revision 573151f3 (ceph): doc: Fixes a spelling error
- Signed-off-by: Jeremy Qian <vanpire110@163.com>
- 01:15 AM CephFS Bug #13876: qa: openstack MPI connection failures
- No, no I'm not sure. I didn't see any more recent runs that succeeded in the pulpito comparison page, but I might hav...
- 12:28 AM CephFS Bug #13876: qa: openstack MPI connection failures
- Those runs are from a couple of weeks ago, are you sure they aren't from before Loic updated the firewall rules to be...
- 01:15 AM Revision 891e985f (ceph): Merge pull request #6533 from ghost/wip-fix-trivial-bug
- osd: fix trivial scrub bug
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:14 AM Revision 7f34d559 (ceph): Merge pull request #6612 from H3C/wip-yrf-destroy_collection
- osd: fix FileStore::_destroy_collection error return code
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Haom... - 01:13 AM Revision 55487eeb (ceph): Merge pull request #6660 from chengyli/master
- mon: fix ceph df pool available calculation for 0-weighted OSDs
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:08 AM Revision 30b64fd7 (ceph): rados/thrash/workloads/admin-socket: 60s -> 180s
- Provide more time for the asok workload to run.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:07 AM Revision 5c232b4e (ceph): Merge remote-tracking branch 'gh/jewel'
- 12:37 AM Revision 2f330f6c (ceph): src/*/Makefile.am: test fixup for as-needed compiling.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
11/25/2015
- 11:30 PM Revision b96c7e63 (ceph): aix shared library build
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 11:05 PM Bug #13880: all/mon-config-keys.yaml failing
- 11:05 PM Bug #13880: all/mon-config-keys.yaml failing
- this commit:0b3435f114b91c473b1ec7d73e8e6dbb4089628f
- 11:04 PM Bug #13880: all/mon-config-keys.yaml failing
- it was this merge: b7de34bc7e4237fd407dc6c0d714deec026d0594
- 09:56 PM Bug #13880 (Resolved): all/mon-config-keys.yaml failing
- http://pulpito.ceph.com/compare/?branch=wip-sage-testing2&suite=rados
Looks like it's been doing it for a while no... - 10:53 PM Tasks #13618: objectstore_bench did not support newstore
- sudo ./src/test/ceph_objectstore_bench --conf=./src/test/ceph.conf --size=2000M --block-size=16K --threads=1
Whe... - 10:46 PM Tasks #13618: objectstore_bench did not support newstore
- thanks for providing the configure file. I am able to run objectstore_bench for newstore too over here. However, the ...
- 10:46 PM Bug #13610 (Pending Backport): auth/cephx: large amounts of log are produced by osd
- 10:46 PM Revision 88fe166c (ceph): Merge pull request #6473 from H3C/wip-osd-bugfix1
- auth: fail if rotating key is missing (do not spam log)
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:44 PM Revision d9705f49 (ceph): Merge pull request #6278 from XinzeChi/wip-failinfo-mon
- osd: cancel failure reports if we fail to rebind network
Reviewed-by: Sage Weil <sage@redhat.com> - 10:43 PM Revision 058733bb (ceph): Merge pull request #6675 from rohanmars/wip-aix-librados-port
- aix gcc librados port
Reviewed-by: Sage Weil <sage@redhat.com> - 10:41 PM Bug #13516: ObjectStore_Bench failed to rerun
- Yes, I got to delete the data everytime by hand if I rerun it. I am trying to develop a solution to automatically del...
- 10:21 PM Revision 50907445 (ceph): Merge branch 'wip-13800' of git://github.com/ukernel/ceph
- client: fix deadlock related to async pagecache invalidation
Conflicts:
src/client/Client.cc
Fixed a conflict with ... - 10:13 PM Revision bb5aaac9 (ceph): Merge pull request #729 from ceph/wip-scrub-tidy
- tasks/cephfs: tidy test_scrub_checks
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:13 PM CephFS Bug #13698 (Pending Backport): Race in TestSessionMap.test_version_splitting
- https://github.com/ceph/ceph-qa-suite/commit/3ba38a4c29030964a210a87c213aaba17297159e
- 10:12 PM Revision 3ba38a4c (ceph): Merge pull request #674 from ceph/wip-13698
- tasks/cephfs: fix race in test_sessionmap
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:10 PM Revision 37dd1f00 (ceph): Merge pull request #6454 from H3C/wip-mds
- mds: repair the command option "--hot-standby"
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Greg Far... - 10:08 PM Revision e774886a (ceph): Merge pull request #663 from ceph/wip-client-mark-down
- tasks/cephfs: quick test for `tell`...
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:07 PM Revision 3fed378f (ceph): Merge pull request #6269 from jcsp/wip-client-mark-down
- client: close mds sessions in shutdown()
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:04 PM Revision 079ba9ef (ceph): Merge pull request #647 from ceph/wip-repair-dir
- tasks/cephfs: include an empty dir in journal repair
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:02 PM Revision 7d129141 (ceph): Merge pull request #6380 from ukernel/wip-client-keep-cache
- client: don't invalidate page cache when inode is no longer used
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:00 PM Revision d5934fc9 (ceph): Merge pull request #633 from ceph/wip-test-failover
- tasks/cephfs/test_failover
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:00 PM Revision e3e08464 (ceph): Merge pull request #6253 from jcsp/wip-client-availability
- client: a better check for MDS availability
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 09:40 PM Revision 3680dc32 (ceph): mon/OSDMonitor: block 'ceph osd pg-temp ...' if update is pending
- The OSD expects it's pg_temp update requests to succeed. If it
races with an ill-timed admin request, it can get stu... - 09:38 PM CephFS Bug #13879 (New): ovh: hadoop wordcount is timing out on OpenStack nodes
- We don't really have any logging, and I think this runs pretty fast on sepia. We've got some other issues with MPI no...
- 09:36 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- @boris @ken - when can we have the permanent fix?
- 09:32 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- Greg, to answer your question, Warren has his own wip branch to test firefly that fixes http://tracker.ceph.com/issue...
- 07:47 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- ...why does a branch of Warren's have anything to do with the Firefly nightlies?
- 07:00 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- I pushed a rebased wip-13622-fix-wusui branch back to master.
- 06:43 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- Ansible should be installing @build-essential@ on ubuntu, but it's not even being run in these jobs. Here's why:
T... - 04:46 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- Moved to urgent it fails lots of test on ovh
- 04:41 PM devops Bug #13874: Missing `make` on openstack-provisioned nodes
- and more in this run http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-24_23:00:01-rbd-firefly-distro-basic-o...
- 02:25 PM devops Bug #13874 (Resolved): Missing `make` on openstack-provisioned nodes
- http://teuthology.ovh.sepia.ceph.com/teuthology/teuthology-2015-11-24_23:08:02-kcephfs-firefly-testing-basic-openstac...
- 09:19 PM CephFS Bug #13364: LibCephFS locking tests are failing and/or lockdep asserting
- http://pulpito.ceph.com/teuthology-2015-11-09_23:04:02-fs-master---basic-multi/1144848/
We've been hitting lockdep... - 09:12 PM Bug #13878 (Resolved): test/librados/tier.cc doesn't completely clean up EC pools
- Creating an EC pool also creates a custom crush rule for it; tier.cc creates and destroys the pool, but leaves behind...
- 09:06 PM rbd Bug #13877 (Resolved): osdc/ObjectCacher.cc: 467: FAILED assert(tid == 0 || bh_tid <= tid)
- ...
- 08:52 PM CephFS Bug #13876: qa: openstack MPI connection failures
- Also http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_18:00:02-fs-hammer---basic-openstack/14386/, 14402
- 08:50 PM CephFS Bug #13876 (Resolved): qa: openstack MPI connection failures
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_18:00:02-fs-hammer---basic-openstack/14418/...
- 08:04 PM Revision 7a8fd0ea (ceph): tools: add cephfs-table-tool 'take_inos'
- For when your InoTable is wrong, and you want to
bluntly mark all the inos up to the highest you've
seen as in use. ... - 08:00 PM Linux kernel client Bug #13699: krbd: crash under pblio benchmark
- Are there more details available? How large were the ASUs? This benchmark ran fine on a test cluster with upstream ke...
- 07:48 PM Revision 043a7378 (ceph): crush: add CEPH_FEATURE_CRUSH_TUNABLES5
- Signed-off-by: Sangdi Xu <xu.sangdi@h3c.com>
- 07:48 PM Revision ac7c7b66 (ceph): crush: add 'jewel' tunables
- Set chooseleaf_stable = 1
Signed-off-by: Sage Weil <sage@redhat.com> - 07:47 PM Revision 07dbd932 (ceph): crush: optimal is hammer
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:47 PM Revision fdb3f664 (ceph): crush: add chooseleaf_stable tunable
- Add a tunable to fix the bug that chooseleaf may cause unnecessary pg
migrations when some device fails.
Signed-off-... - 07:47 PM Revision 983d44f4 (ceph): crush: add chooseleaf_stable tunable tooling, wrapper infrastructure
- Signed-off-by: Sangdi Xu <xu.sangdi@h3c.com>
- 07:47 PM Revision a79a72fb (ceph): crush: add step set chooseleaf stable
- Signed-off-by: Sangdi Xu <xu.sangdi@h3c.com>
- 07:47 PM Revision 6c2a4e7e (ceph): crushtool: add hammer test map (with straw2 buckets)
- Signed-off-by: Sage Weil <sage@redhat.com>
- 07:40 PM Revision 528eae92 (ceph): osd: recency should look at newest (not oldest) hitsets
- Reported-by: xinxin shu <xinxin.shu@intel.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 07:40 PM Revision 180c8743 (ceph): osd/ReplicatedPG: fix promotion recency logic
- Recency is defined as how many of the last N hitsets an object
must appear in in order to be promoted. The previous ... - 07:16 PM Revision 788477ac (ceph): rgw: user has a tenant property
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:16 PM Revision 1f19b608 (ceph): rgw: buckets within tenant namespace
- Signed-off-by: Yehuda Sadeh <yehuda@inktank.com>
- 07:16 PM Revision f7ca00a6 (ceph): rgw: make APIs to work with tenants
- Previous commits introduced the tenant infrastructure such as
rgw_user, but did not allow anyone to access it product... - 07:16 PM Revision 9bd0b11a (ceph): rgw: fix tenant/bucket parsing
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 06:41 PM CephFS Bug #13875 (Duplicate): hammer: java libcephfs test failure
- It looks to be passing in master, but in hammer it's failing reliably and I see...
- 06:25 PM Revision 6e184ad0 (ceph): Merge pull request #732 from dachary/wip-openstack-debug
- openstack: add 30GB for debugging purposes
- 06:20 PM Revision abc07e25 (ceph): openstack: add 30GB for debugging purposes
- So that it can be used as follows:
teuthology-openstack ... --suite mysuite ... debug/openstack-30G.yaml
Signed-... - 06:14 PM Revision 61bf1bda (ceph): rgw/Makefile.am: declare rgw_rest_s3website.h as well for bugfixing.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 05:44 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9565/console
- 05:38 PM rgw Bug #13096 (Resolved): rgw: The type of caps can be any value.
- Merge commit:7ce223ec0f4906a9dee688af1d3c16ecf6a52be9
- 03:10 AM rgw Bug #13096: rgw: The type of caps can be any value.
- Yehuda Sadeh wrote:
> Ah, right! Ok, added a couple of comments in the PR, but looks good otherwise.
Hi,Yehuda,I ... - 05:37 PM Revision 7ce223ec (ceph): Merge pull request #6051 from clever215/master
- rgw: add an inspection to the field of type when assigning user caps
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:01 PM rbd Bug #13810: "stderr:rbd.InvalidArgument: error writing to test_notify_clone)" in upgrade:client-u...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-24_23:20:01-upgrade:client-upgrade-infernalis-distro-b...
- 04:47 PM Revision 8c4145ec (ceph): Merge pull request #6587 from theanalyst/wip-13758-hammer
- common: pure virtual method called
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:33 PM Revision 13a12a53 (ceph): rgw: add an inspection to the field of type when assigning user caps
- Bug #13096
This modification adds the check to the field of type of a user's capality while previous versions set it... - 04:32 PM Documentation #8536: Ceph-deploy install on Centos and RHEL
- ...
- 04:24 PM Revision 12d3d644 (ceph): Merge pull request #6700 from dillaman/wip-librbd-32bit-support
- librbd: simplify IO method signatures for 32bit environments
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 03:49 PM Revision 4804eec0 (ceph): Merge pull request #6352 from theanalyst/wip-13536-hammer
- rgw: bucket listing hangs on versioned buckets
- 03:48 PM Revision 9b97e4f6 (ceph): Merge pull request #6589 from theanalyst/wip-13693-hammer
- osd: bug with cache/tiering and snapshot reads
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:22 PM Revision 5a9e0a72 (ceph): Merge pull request #6585 from theanalyst/wip-13753-hammer
- rbd: avoid re-writing old-format image header on resize
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 02:23 PM Revision 3369a835 (ceph): librbd: simplify IO method signatures for 32bit environments
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 02:13 PM Revision ba3c64ca (ceph): Fix mon routed_request_tids leak
- Signed-off-by: Ning Yao <zay11022@gmail.com>
- 02:12 PM Revision e242d84f (ceph): mds: remove MDCache::cap_import_paths
- it's no longer used.
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:42 PM Backport #13869 (In Progress): infernalis: OSD: race condition detected during send_failures
- 11:23 AM Revision 15b2aca3 (ceph): tests: ceph-helpers assert success getting backfills
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 09:31 AM Bug #13872: ceph-mon segmentation fault
- Kane Kim wrote:
> Trying to follow ceph installation instructions got this:
>
> [root@ceph1 ~]# ceph-mon --cluste... - 12:48 AM Bug #13872 (Closed): ceph-mon segmentation fault
- Trying to follow ceph installation instructions got this:
[root@ceph1 ~]# ceph-mon --cluster ceph --mkfs -i ceph1 ... - 09:18 AM devops Bug #13860: openSUSE Tumbleweed build cannot find systemd-tmpfiles
- By the way, here is the OBS script in question:
https://github.com/openSUSE/post-build-checks/blob/master/checks/0... - 09:15 AM Revision 3c875987 (ceph): MOSDOp/MOSDOpReply: Move MOSDOp and MOSDOpReply newest version
- decoding to the front of decoding function.
Signed-off-by: Jacek J. Łakis <jacek.lakis@intel.com> - 09:01 AM Revision 889158af (ceph): WBThrottle: fix incorrect throttle
- This bug is introduced in commit 573d2cc, that throttle()
incorrectly use the "start flusher" throttle value to block... - 03:01 AM Revision 97affaa2 (ceph): Merge pull request #6625 from dillaman/wip-12698
- librbd: integrate journaling for maintenance operations
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 01:45 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- Feel free to squash those commits into your branch btw
- 01:44 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- I added a couple more things on top of your branch to https://github.com/ceph/ceph/commits/wip-cython-rbd and it buil...
- 12:37 AM Revision ec7f4610 (ceph): Merge pull request #6687 from dillaman/wip-journal-replay-fixes
- journal: support replaying beyond skipped splay objects
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:37 AM Bug #13850: master fails to build when liblz4 is present (rocksdb)
- rex001 had lz4-devel installed, which caused rocksdb to configure itself to use LZ4...but nothing consumed the '-llz4...
11/24/2015
- 11:40 PM devops Bug #13860: openSUSE Tumbleweed build cannot find systemd-tmpfiles
- To check if they are idempotent.
- 04:52 PM devops Bug #13860: openSUSE Tumbleweed build cannot find systemd-tmpfiles
- Why does OBS run @%post@ scripts?
- 04:22 PM devops Bug #13860 (Fix Under Review): openSUSE Tumbleweed build cannot find systemd-tmpfiles
- *jewel PR*: https://github.com/ceph/ceph/pull/6692
- 03:22 PM devops Bug #13860 (In Progress): openSUSE Tumbleweed build cannot find systemd-tmpfiles
- 11:12 PM Revision b913cc2b (ceph): rgw/Makefile.am: declare rgw_website.h for buildfix.
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 08:54 PM CephFS Bug #13714 (Pending Backport): Segmentation fault accessing file using fuse mount
- 08:25 PM Revision 5d15b920 (ceph): Merge pull request #6685 from dachary/wip-erasure-code-benchmark
- qa: erasure-code benchmark plugin selection
Reviewed-by: Andreas Peters <andreas.joachim.peters@cern.ch> - 08:09 PM Revision 53eda867 (ceph): Merge pull request #6292 from dx9/wip-12406-res_nquery
- rgw/rgw_resolve: fallback to res_query when res_nquery not implemented
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 08:00 PM Revision 692b7407 (ceph): Merge pull request #6236 from guangyy/err-msg
- osd: use pg id (without shard) when referring the PG
Reviewed-by: Sage Weil <sage@redhat.com> - 05:49 PM Revision ff75ae9a (ceph): Merge pull request #6610 from ktdreyer/wip-build-doc-lxml
- admin/build-doc: add lxml dependencies on debian
Reviewed-by: Sage Weil <sage@redhat.com> - 05:48 PM Revision 922fea7e (ceph): client: s/close_sessions/_close_sessions/
- Signed-off-by: John Spray <john.spray@redhat.com>
- 04:59 PM Bug #13857: tests: make check timeout occasionaly
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9518/console
- 04:20 PM Revision a4924d49 (ceph): ceph.spec.in: add BuildRequires: systemd
- http://tracker.ceph.com/issues/13860 Fixes: #13860
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 04:09 PM Backport #13870 (Resolved): hammer: OSD: race condition detected during send_failures
- https://github.com/ceph/ceph/pull/6755
- 04:09 PM Backport #13869 (Resolved): infernalis: OSD: race condition detected during send_failures
- https://github.com/ceph/ceph/pull/6694
- 04:07 PM Bug #13821 (Pending Backport): OSD: race condition detected during send_failures
- master merge https://github.com/ceph/ceph/commit/b3ca828ae8ebc9068073494c46faf3e8e1443ada
- 03:43 PM CephFS Cleanup #13868 (Resolved): mds: MDCache::cap_import_paths is never used
- ...
- 03:24 PM Feature #9021 (Resolved): librbd: shared flag, object map
- 03:24 PM Feature #13521 (In Progress): AsyncMessenger: Support memory pool per worker
- 03:24 PM Feature #12801 (Resolved): Make "ceph osd metadata" command support dumping all osds info
- 03:16 PM Revision 0ab60276 (ceph): Merge pull request #6323 from dingshang/wip-cephfs-dingshang
- pybind/cephfs: add symlink and its unit test
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 03:12 PM Revision 07a74831 (ceph): client: close mds sessions in shutdown()
- Usually this happens in unmount(), but when we
have instantiated Client without mounting (to
send MDS commands), we n... - 03:08 PM Feature #13867 (Resolved): Make non-client op users of OpContext use something else
- 02:51 PM devops Bug #13858 (Fix Under Review): No way to limit parallelism on low-memory builders
- 02:50 PM devops Bug #13858: No way to limit parallelism on low-memory builders
- *jewel PR*: https://github.com/ceph/ceph/pull/6691
- 01:49 PM devops Bug #13858 (In Progress): No way to limit parallelism on low-memory builders
- There is a twist here, because if we put a hard upper limit of -j8 for all SUSE builds, this has a potential adverse ...
- 02:45 PM Revision 095c29c3 (ceph): ceph.spec.in: make --with lowmem_builder limit _smp_mflags
- The limit, -j8, may seem arbitrary but works nicely in the openSUSE Build
Service.
http://tracker.ceph.com/issues/13... - 02:24 PM Revision 56da1065 (ceph): Test:bencher wrong test margin casuses writes over object_size
- Signed-off-by: Tao Chang <changtao@hihuron.com>
- 01:41 PM Revision 1e9aeb57 (ceph): Merge tag 'v10.0.0'
- v10.0.0
- 11:08 AM Backport #13512: If blkid hangs, ceph-osd appears to start but does not come up on mon, and gdb c...
- Still happening: http://pulpito.ceph.com/teuthology-2015-11-16_23:10:01-knfs-master-testing-basic-multi/1152807/
- 11:00 AM Revision 917d85fe (ceph): osbench: Adds handling for the lack of required folders ( data & journa...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 11:00 AM Revision 2902030d (ceph): osbench: Fix race condition that may cause Sequencer::dtor assertion on...
- Signed-off-by: Igor Fedotov <ifedotov@mirantis.com>
- 10:42 AM Bug #13853: osd/ReplicatedPG.cc: 10773: FAILED assert(r >= 0)
- I deleted and re-installed the OSD and the issue is gone. You can close this as not reproducible.
- 10:39 AM Feature #13837: Make snap_trimming robust to inconsistent snaphots
- Nevermind, it just took longer until it crashed.
Issue #12665 is still present in both master and 9.2 with the "dz... - 09:09 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
- Hi Peter! Please see http://tracker.ceph.com/issues/13832#note-3
- 08:47 AM Revision daae1800 (ceph): Doubled marking from line 1151
- Signed-off-by: Jacek J. Łakis <jacek.lakis@intel.com>
- 08:26 AM Revision ada6e320 (ceph): osd: slightly reduce actual size of pg_log_entry_t
- - Move fields around so they're ordered in size descending order. This
reduces pg_log_entry_t size down to 360 (fro... - 07:49 AM rgw Bug #13096: rgw: The type of caps can be any value.
- Yehuda Sadeh wrote:
> Ah, right! Ok, added a couple of comments in the PR, but looks good otherwise.
OK!I see it ... - 04:06 AM rgw Bug #13096: rgw: The type of caps can be any value.
- Ah, right! Ok, added a couple of comments in the PR, but looks good otherwise.
- 01:45 AM rgw Bug #13096: rgw: The type of caps can be any value.
- Yehuda Sadeh wrote:
> The solution would require mapping out the different types of caps that exist, and then to res... - 02:56 AM Revision b498fdf1 (ceph): Merge pull request #6684 from jcsp/wip-fix-scrub
- mds: fix scrub_path
11/23/2015
- 11:38 PM Revision 5c8f3499 (ceph): Merge pull request #718 from ceph/wip-fast-read
- rados: add test for ec fast_read
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:37 PM Revision af95065c (ceph): Merge pull request #730 from ceph/wip-repair
- ceph_manager: do_pg_scrub: keep scrubbing until it's done
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:46 PM Revision d1c9bf63 (ceph): journal: support replay passed skipped splay objects
- It's possible for a splay object within a set to be skipped
if the set is closed due to a full object within the set.... - 10:44 PM Revision 56100efb (ceph): tests: verify that journal player can handle skipped journal objects
- It's possible for a journal object to not exist if another journal object
within the same object set filled up before... - 10:33 PM Bug #13797 (Resolved): Messenger/MessengerTest.ClientStandbyTest/0 hang
- https://github.com/ceph/ceph/pull/6605 is merged
- 10:33 PM Revision f0d17d88 (ceph): Merge pull request #6605 from yuyuyu101/wip-13797
- ceph_test_msgr: Use send_message instead of keepalive to wakeup connection
Reviewed-by: Greg Farnum <gfarnum@redhat.... - 10:31 PM Revision 16b6f7ac (ceph): Merge pull request #6495 from objoo/master
- Mailmap updates for infernalis.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:13 PM Revision d92f6111 (ceph): mailmap: Burkhard Linke affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:13 PM Revision 1509ada5 (ceph): mailmap: Jenkins affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 10:11 PM Bug #12328: Ceph KV OSD crashes sometimes with FAILED assert(0 == "hit suicide timeout") on 0.94.1
- This is unlikely to be the same issue you're hitting, Dan, unless you're also using KV-backed OSDs.
Probably you'r... - 10:05 PM Bug #13857: tests: make check timeout occasionaly
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9502/console
- 12:05 PM Bug #13857: tests: make check timeout occasionaly
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9483/console
- 12:04 PM Bug #13857 (Can't reproduce): tests: make check timeout occasionaly
- It happens every 10 run or so and that makes a lot of false negative. The bot must be modified to provide more inform...
- 09:33 PM Revision 8dc67487 (ceph): mailmap: Wei Qian affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 09:33 PM Revision 27f81d4f (ceph): mailmap: Chen Dihao affiliation
- Signed-off-by: Yann Dupont <yann@objoo.org>
- 08:25 PM Revision 39032ba9 (ceph): qa: erasure-code-benchmark technique and plugin selection
- Update the PLUGINS variable that was no longer used. Add the TECHNIQUES
variable to control which techniques are comp... - 07:59 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- My experience was with a fresh installation, not an upgrade. Would like to repeat that the problem did not occur on i...
- 04:22 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- Hi Joao,
the ceph.conf being used:... - 07:21 PM Revision a6433cc4 (ceph): qa: erasure-code has --erasure-code-dir
- It is used instead of the obsoleted --parameter directory= to specify
the location of the erasure code directory plug... - 06:57 PM Revision 3047f2bc (ceph): Merge pull request #6586 from theanalyst/wip-13755-hammer
- rbd: QEMU hangs after creating snapshot and stopping VM
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:09 PM Revision 8789eb9d (ceph): add aix compile warning
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 05:47 PM Revision 5b1f9621 (ceph): initialized backtrace variables
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 05:47 PM Revision 69560a8d (ceph): tasks/cephfs: tidy test_scrub_checks
- Use named error codes instead of numbers, and
use the helper fn for getting inode number
instead of doing it by hand.... - 05:41 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
- /a/teuthology-2015-11-21_21:00:01-rados-hammer-distro-basic-openstack/17756
- 05:39 PM Revision f86eb3f7 (ceph): mds: fix scrub_path
- This was tripping up over calling
validate_disk_state with no ScrubHeader.
Signed-off-by: John Spray <john.spray@red... - 04:54 PM Bug #13862 (Resolved): pgs stuck inconsistent after infernalis upgrade
- During my infernalis upgrade I was running unmatched OSD versions for about 48 hours while I did a rolling chown/upgr...
- 04:33 PM Revision 75bd1a51 (ceph): Merge pull request #6679 from suckowbiz/patch-1
- Fixed typos
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:32 PM Revision 407bd028 (ceph): Merge pull request #6588 from theanalyst/wip-13770-hammer
- Objecter: pool op callback may hang forever.
Reviewed-by: Sage Weil <sage@redhat.com> - 04:06 PM Documentation #12056 (New): document include/ipaddr.h
- 04:03 PM Stable releases Tasks #13750: infernalis v9.2.1
- h3. rados...
- 04:01 PM Stable releases Tasks #13750: infernalis v9.2.1
- ...
- 04:02 PM Revision 4025f754 (ceph): doc/release-notes: fix typo
- Signed-off-by: Sage Weil <sage@redhat.com>
- 04:00 PM Revision efbcd120 (ceph): doc/release-notes: final v10.0.0 notes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:52 PM Fix #12049: replace snprintf(s,...); x = strlen(s); with x = snprintf...
- Hint:...
- 03:50 PM Revision c0c5a6e7 (ceph): mon: fix osd failure info in mon
- when the network adapter of node A run into error, osd in this node
would tell mon other osd's heartbeat is timeout a... - 03:50 PM Revision 48a71a73 (ceph): mon: do not ignore a failure report cancellation form osd
- do not ignore a failure report cancellation form osd even if it is
down.
Signed-off-by: Xinze Chi <xinze@xsky.com> - 03:50 PM Revision 5972a441 (ceph): doc: fix message typos in systemd
- Signed-off-by: Tobias Suckow <tobias@suckow.biz>
- 03:35 PM Documentation #10293 (Resolved): Change "ceph-deploy mon create {ceph-node}" to "ceph-deploy mon ...
- 03:35 PM Documentation #13562 (Duplicate): Error in Adding Monitors section for firefly
- This was fixed (in infernalis and above) by https://github.com/ceph/ceph/commit/cac48bd0
Please use http://docs.ce... - 02:24 PM Backport #13637 (Resolved): FileStore: potential memory leak if getattrs fails.
- 02:19 PM Backport #13654 (Resolved): crush: crash if we see CRUSH_ITEM_NONE in early rule step
- 02:13 PM Revision c3c400f6 (ceph): Merge pull request #6430 from SUSE/wip-13654-hammer
- crush: crash if we see CRUSH_ITEM_NONE in early rule step
Reviewed-by: Sage Weil <sage@redhat.com> - 02:07 PM rgw Bug #13764: Radosgw incomplete files
- Hi Yehuda,
Is there any update on this bug report? I know that we hit a pretty unusual issue but I'm hoping we can... - 02:01 PM Revision 8631b725 (ceph): Merge pull request #6666 from dachary/wip-release-notes
- release-notes: draft v10.0.0 release notes
- 02:01 PM Revision d4694f6a (ceph): Merge branch 'master' of github.com:ceph/ceph
- 01:39 PM Revision 5135292d (ceph): Merge branch 'wip-bigbang'
- Reviewed-by: Joao Eduardo Luis <joao@suse.de>
Reviewed-by: Greg Farnum <gfarnum@redhat.com>
Reviewed-by: Kefu Chai <k... - 01:39 PM Bug #13516: ObjectStore_Bench failed to rerun
- Changed to PR #6681
- 01:38 PM Revision 9aabc8a9 (ceph): test/mon/osd-crush.sh: escape ceph tell mon.*
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision 3ad0c921 (ceph): mon/PGMonitor: only send pg create messages to up osds
- If the OSD is down it will ignore the message. If it gets marked up, we
will eventually consume that map and call ch... - 01:38 PM Revision 1f4b7141 (ceph): mon/PGMonitor: revamp how pg creates are tracked
- Previously we were calculating and managing in-core state that
wasn't committed as part of the pg_map, leading to all... - 01:38 PM Revision 9864a79a (ceph): mon/PGMonitor: avoid useless pg gets when pool is deleted
- If the .0 pg no longer exists, we know the entire pool was
deleted, and can avoid querying every other pg. (This is ... - 01:38 PM Revision ca75e37a (ceph): mon/OSDMonitor: fix oldest_map in send_incremental
- This should be the oldest map on the sender (like every other
place that generates an MOSDMap message).
Signed-off-b... - 01:38 PM Revision 57121dbe (ceph): mon/MonClient: make _sub_got behave if we "got" old stuff
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision 53f2c7f2 (ceph): osd: simplify pg creation
- We used to have a complicated pg creation process in which we
would query any previous mappings for the pg before we ... - 01:38 PM Revision 0269a0c1 (ceph): mon/OSDMonitor: simplify failure reporters vs reports logic
- Since each OSD only sends a failure report for a given peer once,
we don't need to count reports vs reporters separat... - 01:38 PM Revision d201c6d9 (ceph): mon: change mon_osd_min_down_reporters from 1 -> 2
- This makes more sense to me.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 987f68a8 (ceph): osdc/Objecter: call notify completion only once
- If we race with a reconnect we could get a second notify message
before the notify linger op is torn down. Ensure we... - 01:38 PM Revision 72edab28 (ceph): osd: make some of the pg_temp methods/fields private
- Reported-by: Kefu Chai <kchai@redhat.com>
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 6cbdd675 (ceph): mon/PGMonitor: remove map_pg_creates, send_pg_creates commands
- These shouldn't be triggered manually.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 0938bf05 (ceph): mon/PGMonitor: only map and send pg creates post paxos update
- These other call sites are no longer needed.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision c85b1523 (ceph): mon/PGMonitor: send pg creates via persistent subscriptions, not spam
- Generate and send pg create messages only for those OSDs who have
subscribed on this monitor. This is N time more ef... - 01:38 PM Revision 7fcffe3d (ceph): mon/MonClient: only send new subscriptions
- Instead of resending all subscriptions, only send the new ones. This
avoids races like
- ask for 4+
- mon sends m... - 01:38 PM Revision 160a0205 (ceph): osd: reduce mon_subscribe messages
- 1. MonClient remembers our subscriptions; only indicate we want
osd_pg_creates once, in init.
2. We don't need to re... - 01:38 PM Revision 0389763a (ceph): mon/PGMonitor: drop old creating_pgs_by_osd
- Obsoleted by creating_pgs_by_osd_epoch.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 59123824 (ceph): mon/PGMonitor: a bunch of cosmetic cleanup
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision 23d4df3e (ceph): mon/PGMonitor: only churn mapping_epoch if the primary changes
- This results is fewer resent pg create messages.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 242bf504 (ceph): mon/PGMonitor: note mapping_epoch for creating pgs
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision b3b0a95e (ceph): mon/OSDMonitor: do not prime pg_temp for creating pgs
- It will be less work for the old primary to ignore the create message
and the new one to query it and find nothing th... - 01:38 PM Revision 2754007c (ceph): mon/PGMap: assert our pg counts don't go negative
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision dd91837a (ceph): mon/PGMonitor: track creating_pgs_by_osd_epoch
- Track pg creations, grouped by the first epoch they mapped to a particular
OSD. This will be necessary to send messa... - 01:38 PM Revision d3eba9b0 (ceph): osd: subscribe to all pg creates, not just once on start
- We want to know about all future pg creations, not just those pending
when we start. (This only helps once the mon k... - 01:38 PM Revision c1f6eec9 (ceph): messages/MOSDPGCreate: make it more readable
- 1- include the epoch
2- drop the 'pg'
3- hide the timestamp
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 536c7028 (ceph): msg: make last_keepalive[_ack] lock safe
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision e5fc7903 (ceph): mon: new session_timeout mechanism that is not subscribe-based
- Simplify the session liveness detection:
- renew on any message
- renew on keepalive[2] messages (lightweight ping... - 01:38 PM Revision 6f300024 (ceph): mon: small cleanup in _ms_dispatch
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision ae9d5ee6 (ceph): mon: remove old subscribe renewal-based timeouts
- This is no longer needed/used.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:38 PM Revision 26496b90 (ceph): mon: only ack subscriptions (and renew) if client or mon is old
- Old client expect an ack so they can schedule renewal; send it for
them only.
Old mons expect renewals.
Signed-off-... - 01:38 PM Revision 6557b76f (ceph): mon: set mon_subscribe_interval to a day
- This is only needed for legacy clients to avoid confusing them--
we don't actually need the renewals at all. Make th... - 01:38 PM Revision 05aaa60e (ceph): msg/simple/Pipe: show keepalives at level 2
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision 39e06ef8 (ceph): mon: let peon mons send the osdmap replies
- Currently the leader mon often replies to OSDs by sending a set of
incremental OSDmaps (e.g., in response to an osd b... - 01:38 PM Revision 39c14954 (ceph): osd: protect mon reporting with mon_report_lock
- We need an exclusive lock over paths that update state related to
mon reports, lest they step on fields like up_thru_... - 01:38 PM Revision 7489ec48 (ceph): osd: cap adjusted max mon report interval at 2/3 of timeout
- This ensures that we don't throttle back mon reports so much that
the mon times out out due to no pg stat reports. S... - 01:38 PM Revision a12dd1b6 (ceph): mon: disabled rocksdb compression when used as the backend
- This significantly reduced CPU utilization on the bigbang scale
testing cluster at CERN. Note that it is already dis... - 01:38 PM Revision 73bdf0fc (ceph): mon/MonClient: don't send log if we're reconnecting
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision d781f484 (ceph): common: mirror leveldb default tuning w/ rocksdb
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision fb9dfada (ceph): msg: track stamp of last keepalive[2] received
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:38 PM Revision e31b6951 (ceph): osd: fix reconnect behavior from booting state
- We don't need to restart the boot process unless we are in preboot;
if we are in booting state we just need to resend... - 01:36 PM Revision 605e1880 (ceph): osd: make [_]maybe_boot lockless variant
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:36 PM Revision 2af422a5 (ceph): osd: skip osdmap version query if we can
- If we get OSDmaps from the mon we *also* learn the oldest/newest
map epochs; no need to query again.
Signed-off-by: ... - 01:36 PM Revision d4f813b3 (ceph): osd: introduce explicit preboot stage
- We want to separate the stage where we do a bunch of work
prior to booting (but intend to eventually boot), like when... - 01:36 PM Revision 21ca0b59 (ceph): osd: don't send dup subscribes so much
- The subscribe MonClient service is stateful--we don't need to
force a new subscribe send unless sub_want() says we ne... - 01:36 PM Revision 7bc4763e (ceph): osd: _got_mon_epochs - refactor the lock scope to avoid a race (which f...
- Reviewed-by: Guang Yang <yguang@yahoo-inc.com>
- 01:36 PM Revision 8b5b6c85 (ceph): osd: move the monitor report to OSD::tick_without_osd_lock
- Fixes: #12722
Reviewed-by: Guang Yang <yguang@yahoo-inc.com> - 01:36 PM Revision d5a2f9a6 (ceph): osd: fix pg stat reporting
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:36 PM Revision 19b714f5 (ceph): osd: just send alive when it is queue
- No need to futz with last_mon_report or resend it again later.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 12c7e54f (ceph): osd: no need for regular send_pg_temps
- This is done by process_peering_events.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 5e10de4c (ceph): osd: backoff the max reporting interval, too
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:36 PM Revision b3ca828a (ceph): osd: fix send_failures() locking
- It is unsafe to check failure_queue.empty() without the lock.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 865ddcac (ceph): osd: resend pending failure reports with a new mon session
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:36 PM Revision c9534dfb (ceph): osd: do not send dup failure reports
- If a failure report is already pending, we do not need to resend
it.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:36 PM Revision 894eb2af (ceph): osd: do not resend pg_temp requests
- Send each pg_temp request once (per mon session); no need to
resend everything that is pending every time.
Signed-of... - 01:36 PM Revision 21e95c2d (ceph): osd: only send boot if booting on getversion completion
- Signed-off-by: Sage Weil <sage@redhat.com>
- 01:32 PM devops Bug #12164 (Duplicate): ceph.spec.in: 50-rbd.rules conditional is wrong
- 01:29 PM Bug #13861 (Can't reproduce): osd/ReplicatedBackend.cc: 1150: FAILED assert(!parent->get_log().ge...
- ...
- 01:29 PM devops Bug #12173 (Resolved): logrotate.conf needs systemd-ization
- 01:26 PM devops Bug #12931 (Resolved): Unpackaged directories causes SUSE build failure
- 01:12 PM devops Bug #13860 (Resolved): openSUSE Tumbleweed build cannot find systemd-tmpfiles
- When building infernalis and jewel in the OBS, the openSUSE_Tumbleweed build target fails with:...
- 12:59 PM devops Backport #13859 (In Progress): hammer: ceph.spec.in License line does not reflect COPYING
- 12:52 PM devops Backport #13859 (Resolved): hammer: ceph.spec.in License line does not reflect COPYING
- https://github.com/ceph/ceph/pull/6680
- 12:58 PM Revision 3f1292e1 (ceph): ceph.spec.in: fix License line
- This is closer to my reading of
https://github.com/ceph/ceph/blob/master/COPYING than the previous version.
http://t... - 12:43 PM devops Bug #12935 (Pending Backport): ceph.spec.in License line does not reflect COPYING
- 12:41 PM Bug #13424 (Resolved): wrong conditional for boolean function KeyServer::get_auth()
- 12:40 PM devops Fix #13445: ceph.spec.in: drop support for RHEL<7 and SUSE<1210 in jewel and above
- Changed status to "Feedback" to reflect that we are waiting for feedback from the community.
- 12:38 PM devops Fix #13445: ceph.spec.in: drop support for RHEL<7 and SUSE<1210 in jewel and above
- Agreed with Sage that, while this cleanup is desirable and necessary, it may make life difficult for folks who might ...
- 12:36 PM devops Bug #12360 (Resolved): rbd-replay-prep not getting packaged for SUSE
- 12:22 PM devops Bug #13858 (Resolved): No way to limit parallelism on low-memory builders
- In the openSUSE Build Service, _smp_mflags often gets set to a high number, like -j16 yet the amount of memory availa...
- 12:16 PM Revision 0151fecc (ceph): tools: refactor DataScan injection
- To take an InodeStore instead of size/mtime/layout
args in injection fns. This is to enable use for
injecting direct... - 12:16 PM Revision ea41e483 (ceph): tools/cephfs: add scan_frags to DataScan
- This command is for injecting linkage for orphaned
directory fragments.
Currently does not support fragmented direct... - 10:09 AM Bug #13743: objecter: last_tid changed without protection of rwlock
- https://github.com/ceph/ceph/pull/6521
- 10:09 AM Bug #13743 (Won't Fix): objecter: last_tid changed without protection of rwlock
- 09:30 AM Revision 083c2e42 (ceph): Merge pull request #6565 from chenji-kael/patch-1
- Update .organizationmap
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 08:28 AM Revision d1169594 (ceph): Merge pull request #6420 from SUSE/wip-13637-hammer
- FileStore: potential memory leak if getattrs fails.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:36 AM Revision 0f504397 (ceph): osd: move misdirected op check from OSD thread to PG thread
- The op message isn't fully decoded until after the start of the PG
op handling. Therefore, checking for misdirected ... - 05:09 AM Revision b7faf678 (ceph): tools:support printing the crushmap in readable fashion.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
- 05:03 AM Revision a3a0e1cb (ceph): aix gcc librados port
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:16 AM Bug #13828: OSD: wrong broken osd state due to disconnection of node backend network
- David Zafman wrote:
> Where are the monitor(s) running? How many do you have configured? If there was a single ce... - 01:11 AM Revision ba5f45a7 (ceph): Merge pull request #6673 from dzafman/wip-rand-scrub-fix
- Reviewed-by: Loic Dachary <ldachary@redhat.com>
11/22/2015
- 06:15 PM Revision f74e3105 (ceph): osd: Only add random deep scrubs when NOT user initiated scrub
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 06:13 PM Revision 4c19abd0 (ceph): Revert "test: osd-scrub-snaps.sh: Randomized deep-scrubs can now happen...
- This reverts commit 0fe26c25c5fefd12628fcdba67be047f640b4afc.
- 05:44 PM Revision 3adbc154 (ceph): Merge pull request #724 from dachary/wip-openstack-rbd-hammer
- openstack: rbd/thrash: allocate three disks, always
- 05:43 PM Revision b9fac37c (ceph): openstack: rbd/{thrash,qemu}: allocate three disks, always
- The thrasher and qemu need disk attached to run against xfs or btrfs,
otherwise it will use the local file system whi... - 05:39 PM Revision a1cf4d25 (ceph): Merge pull request #725 from dachary/wip-openstack-rbd
- openstack: rbd/thrash and rbd/qemu resources
- 01:34 PM Bug #13350: "Error cancelling global ust listener thread" errors
- Yuri, are these still happening?
- 01:03 PM devops Backport #12925 (Resolved): ceph.spec.in: rgw placeholder dirs are not packaged
- 01:03 PM devops Backport #12932 (Resolved): Unpackaged directories causes SUSE build failure
- 01:03 PM devops Backport #13172 (Resolved): rbd-replay* should ship in ceph-common
- 01:03 PM Backport #13340 (Resolved): small probability sigabrt when setting rados_osd_op_timeout
- 01:03 PM devops Backport #13599 (Resolved): rbd-replay-prep not getting packaged for SUSE
- 01:03 PM CephFS Backport #13621 (Resolved): CephFS restriction on removing cache tiers is overly strict
- 01:02 PM Backport #13692 (Resolved): osd: do not cache unused memory in attrs
- 01:02 PM rbd Backport #13695 (Resolved): init-rbdmap uses distro-specific functions
- 01:02 PM Backport #13786 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 01:01 PM Backport #12848 (New): ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
- 01:01 PM Backport #13288 (New): hammer: stuck recovering, unfound hit set due to removing it while !active
- 12:42 PM Revision 90a37c72 (ceph): Merge pull request #6219 from joejulian/master_fix_13438_parted_must_co...
- Compare parted output with the dereferenced path
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:41 AM Revision 09cd89ed (ceph): Merge pull request #6671 from dzafman/wip-jenkins-fix
- Fix Jenkins make check errors due to deep-scrub randomization
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:23 AM Revision 29973822 (ceph): openstack: rbd/{thrash,qemu}: allocate three disks, always
- The thrasher and qemu need disk attached to run against xfs or btrfs,
otherwise it will use the local file system whi...
11/21/2015
- 06:57 PM Revision 0fe26c25 (ceph): test: osd-scrub-snaps.sh: Randomized deep-scrubs can now happen during ...
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:18 PM Revision 240542da (ceph): Merge pull request #6659 from cholcombe973/master
- Doc: Typo in the apt-get command
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 03:26 PM Revision 37f1e84e (ceph): add rbd-nbd tool
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
Signed-off-by: Li Wang <li.wang@kylin-cloud.com> - 03:26 PM Revision 5ac1cbf9 (ceph): add rbd-nbd doc
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:26 PM Revision 7bbd54a1 (ceph): add rbd-nbd package
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:26 PM Revision 46a06eb5 (ceph): modify stuff follow rbd-fuse
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
Reviewed-by: Li Wang <li.wang@kylin-cloud.com> - 03:26 PM Revision fda3f7e0 (ceph): add rbd-nbd test case
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:26 PM Revision 40b5bcbb (ceph): SubProcess: allow CLOSE/PIPE/KEEP parent std fd
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 03:26 PM Revision 000306e2 (ceph): SubProcess: include iostream
- The class SubProcess will use std::cerr,
but not include the header.
Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin... - 03:26 PM Revision 328c6631 (ceph): SubProcess: update to use new constructor
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 02:03 PM Bug #13497 (Fix Under Review): fine-grained control systemd to start/stop/restart ceph services a...
- 10:33 AM Revision 8db84e5a (ceph): Merge pull request #722 from dachary/wip-13581-openstack-hints-hammer
- openstack: convert to array hints
- 10:33 AM Revision dfdcb764 (ceph): Merge pull request #721 from dachary/wip-13581-openstack-hints
- openstack: convert to array hints
- 10:14 AM Revision b5614b97 (ceph): openstack: convert to array hints (hammer specific)
- So that it is more flexible.
http://tracker.ceph.com/issues/13581 Fixes: #13581
Signed-off-by: Loic Dachary <loic@d... - 10:12 AM Revision 078dcdd1 (ceph): openstack: convert to array hints
- So that it is more flexible.
http://tracker.ceph.com/issues/13581 Fixes: #13581
Signed-off-by: Loic Dachary <loic@d... - 10:08 AM Revision 8f2af594 (ceph): openstack: convert to array hints
- So that it is more flexible.
http://tracker.ceph.com/issues/13581 Fixes: #13581
Signed-off-by: Loic Dachary <loic@d... - 09:37 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rbd...
- 08:23 AM Revision aa7737c2 (ceph): rados/singleton-nomsgr/all: add export-after-evict.yaml
- add a test for http://tracker.ceph.com/issues/12748
Fixes: #12748
Signed-off-by: Kefu Chai <kchai@redhat.com>
(cherr... - 08:10 AM Revision 12be099a (ceph): Merge pull request #6528 from theanalyst/wip-13695-hammer
- init-rbdmap uses distro-specific functions
Reviewed-by: Boris Ranto <branto@redhat.com> - 08:07 AM Revision 39c70d43 (ceph): Merge pull request #6499 from SUSE/wip-13692-hammer
- osd: do not cache unused memory in attrs
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:59 AM Revision 65aeba0b (ceph): Merge pull request #6143 from dachary/wip-13340-hammer
- small probability sigabrt when setting rados_osd_op_timeout
Reviewed-by: Sage Weil <sage@redhat.com> - 07:58 AM Revision 24d66981 (ceph): Merge pull request #5773 from tchaikov/wip-12835-hammer
- mon: map_cache can become inaccurate if osd does not receive the osdmaps
Reviewed-by: Loic Dachary <ldachary@redhat.... - 03:37 AM Bug #13219: get_device_by_uuid->blkid_find_dev_with_tag() may hang for 3 min
- Part of the following pull request..
https://github.com/ceph/ceph/pull/6670 - 12:47 AM Bug #13840: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- Here is patch to fix this bug.
https://github.com/ceph/ceph/pull/6660
11/20/2015
- 11:08 PM Revision 806c09ec (ceph): Merge pull request #717 from dachary/wip-dumpling-parallel-hammer
- buildpackages: do not -jX on dumpling
- 11:05 PM Revision 1eeb2298 (ceph): buildpackages: do not -jX on dumpling
- http://tracker.ceph.com/issues/13845 Refs: #13845
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from... - 11:04 PM Revision 3598da44 (ceph): Merge pull request #719 from dachary/wip-dumpling-parallel
- buildpackages: do not -jX on dumpling
- 10:54 PM Revision 8e2831b3 (ceph): rgw: Remove unused code in PutMetadataAccount:execute
- Apparently this belonged to Object branch and escaped during
refactoring in commit 84d746b36.
Signed-off-by: Pete Za... - 08:02 PM Bug #13853 (Can't reproduce): osd/ReplicatedPG.cc: 10773: FAILED assert(r >= 0)
- Hi,
we had some issues with snapshots which were originally triggered by a PG split in an older version and we got... - 07:41 PM Feature #13837: Make snap_trimming robust to inconsistent snaphots
- Applying https://github.com/ceph/ceph/compare/v9.2.0...dzafman:wip-snap-scrub on the v9.2.0 tag (with a small and obv...
- 03:07 PM Feature #13837: Make snap_trimming robust to inconsistent snaphots
- I also tried to set osd pg max concurrent snap trims = 0 as a work-around to prevent trimming. However, it then crash...
- 02:33 PM Feature #13837: Make snap_trimming robust to inconsistent snaphots
- Looks like debug 10/10 works. I've uploaded a full log here, it contains several crashes: https://www.dropbox.com/s/y...
- 07:13 PM Bug #13850: master fails to build when liblz4 is present (rocksdb)
- --with-librocksdb-static is true; src/rocksdb/librocksdb.a does indeed still have unbound references to LZ4*
- 06:54 PM Bug #13850: master fails to build when liblz4 is present (rocksdb)
- g++ -I/usr/include/nss3 -I/usr/include/nspr4 -Wall -Wtype-limits -Wignored-qualifiers -Winit-self -Wpointer-arith -fn...
- 06:48 PM Bug #13850: master fails to build when liblz4 is present (rocksdb)
- all these symbols are in the installed /usr/lib64/liblz4.so.1.6.0
- 06:40 PM Bug #13850 (Resolved): master fails to build when liblz4 is present (rocksdb)
- on rex001:
rocksdb/librocksdb.a(format.o): In function `LZ4_Uncompress':
/home/dmick/ceph/src/rocksdb/./util/comp... - 06:51 PM Bug #13849 (Can't reproduce): s3tests fail in smoke-master-distro-basic-multi
- Closing for now as those failures did not happen in the rerun of smoke
- 05:03 PM Bug #13849 (Can't reproduce): s3tests fail in smoke-master-distro-basic-multi
- Run: http://pulpito.ceph.com/teuthology-2015-11-19_05:00:09-smoke-master-distro-basic-multi/
Jobs: ['1155188', '1155... - 05:46 PM Bug #13748 (Need More Info): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- Logan and Tom, I've been trying to reproduce this without success.
The store Tom provided appears to work just fin... - 05:41 PM Tasks #13618: objectstore_bench did not support newstore
- I am able to use newstore in objectstore_bench using following config file ( provided with -c command option):
; gen... - 05:40 PM Bug #13783 (Duplicate): monitors crashing constantly with 0.94.5
- From the trace I can tell this is indeed a duplicate of #13748. Will follow up there.
- 05:39 PM Bug #13516: ObjectStore_Bench failed to rerun
- PR #6667 adds some error reporting for this case instead of assertion.
- 05:12 PM Revision a81bcf72 (ceph): ceph_context: remove unsafe cast for singletons
- It was previously assumed that a CephContext singleton would
inherit from CephContext::AssociatedSingletonObject, but... - 04:54 PM Revision d50d7b2f (ceph): osd: conditionally initialize the tracepoint provider
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 0009f343a5daf28358a669836d95660c0d9068d8) - 04:54 PM Revision bf34b365 (ceph): librados: conditionally initialize the tracepoint provider
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 6368c281b53d6175a564725b85516de4b6ae54de) - 04:53 PM Revision afc4f176 (ceph): librbd: conditionally initialize the tracepoint provider
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 1a6eea95bd1ccef53f01cf53e493e652faa203... - 04:53 PM Revision c82f9391 (ceph): common: new tracing config options
- Config options to enable LTTng-UST tracepoint providers for
the OSD, OSD objectstore, librados, and librbd.
Signed-o... - 04:52 PM Revision 2168c151 (ceph): tracing: merge tracepoint provider makefiles into main makefile
- This results in the tracepoint provider shared libraries being
placed in the library path for unittests.
Signed-off-... - 04:51 PM Revision d02beff1 (ceph): tracing: dynamic tracepoint provider helper
- The TracepointProvider class is a configuration observer. When
tracing is enabled, it will dynamically load the asso... - 04:50 PM Revision e53d66e4 (ceph): packaging: add new tracepoint probe shared libraries
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit a7ed8e161b27c7852bf0f3a23a977ebd39137943) - 04:50 PM Revision bb7c0f50 (ceph): ceph.spec.in: add new tracepoint probe shared libraries
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit f4feee2f9dcd7b94476701b66d1f0bdf6fb6e0... - 04:48 PM Revision e1da2713 (ceph): lttng: move tracepoint probes to dynamic libraries
- LTTng-UST initializes itself at program load, which means it is
currently always enabled. This can lead to issues wi... - 04:45 PM Bug #13828: OSD: wrong broken osd state due to disconnection of node backend network
- Where are the monitor(s) running? How many do you have configured? If there was a single ceph-mon running on ceph2...
- 04:00 PM Revision 07f68b5b (ceph): Typo in the apt-get command.
- Signed-off-by: Chris Holcombe <xfactor973@gmail.com>
- 03:44 PM Revision f3e88ace (ceph): Merge remote-tracking branch 'gh/jewel'
- 03:20 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. upgrade...
- 03:02 PM Feature #13505: scrub/repair: persist scrub results.
- > 2. A missing SnapSet in a head object requires rebuilding the SnapSet or removing all clones. Are the clones in err...
- 02:25 PM Revision d9b12df6 (ceph): Merge pull request #6553 from ukernel/wip-13777
- mds: properly set STATE_STRAY/STATE_ORPHAN for stray dentry/inode
Reviewed-by: John Spray <john.spray@redhat.com> - 02:20 PM Revision 3193ee1c (ceph): scripts: ceph-release-notes for development versions
- Relax the requirements for titles and issues when --strict is not set.
Collect and display the merge messages when th... - 02:19 PM Revision c44ab625 (ceph): release-notes: draft v10.0.0 release notes
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:59 PM Revision 0b21492e (ceph): Merge pull request #6603 from ukernel/wip-13782
- client: avoid creating orphan object in Client::check_pool_perm()
Reviewed-by: John Spray <john.spray@redhat.com> - 01:44 PM Revision 93598473 (ceph): librbd: commit journal op events immediately
- Op events are split into a start and finish record, so they can
be immediately marked as committed within the journal... - 01:33 PM Bug #13848: Removed objects may stay in cache forever
- Simple ( but probably not the best) solution to trigger cache flush can be found at:
https://github.com/ceph/ceph/pu... - 01:14 PM Bug #13848: Removed objects may stay in cache forever
- Behavior described at
http://tracker.ceph.com/issues/12177
was probably caused by the same root cause. - 12:58 PM Bug #13848 (Resolved): Removed objects may stay in cache forever
- It seems that Ceph caching doesn't take removed ( whitened out) objects
into accounts when checks for the need to fl... - 01:01 PM Bug #13797: Messenger/MessengerTest.ClientStandbyTest/0 hang
- Do you tested this patch https://github.com/ceph/ceph/pull/6605/files?
- 11:53 AM Bug #13797: Messenger/MessengerTest.ClientStandbyTest/0 hang
- /a/sage-2015-11-19_06:18:51-rados-wip-sage-testing---basic-multi/1155245
currently running on plana20 if you want ... - 12:46 PM Revision f398b71e (ceph): buildpackages: do not -jX on dumpling
- http://tracker.ceph.com/issues/13845 Refs: #13845
Signed-off-by: Loic Dachary <loic@dachary.org> - 12:37 PM Bug #13845 (Won't Fix): dumpling v0.67.10 does not compile with -j16
- It looks like the Makefile should be modified to not try to link against libglobal.la before it is compiled....
- 12:01 PM Revision 28c0f8fe (ceph): Merge branch 'osd-op-create' of git://github.com/majianpeng/ceph
- Conflicts:
src/osd/ReplicatedPG.cc
Reviewed-by: Sage Weil <sage@redhat.com> - 11:57 AM Bug #13715 (Resolved): RadosClient: result code overflowed!
- 11:57 AM Revision b584388c (ceph): Merge pull request #6489 from xiexingguo/xxg-wip-13715
- librados: fix pool alignment API overflow issue
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewed-by: David Zafman ... - 11:56 AM Revision 8771aa19 (ceph): Merge pull request #6492 from cxwshawn/wip-perf-fix
- osd: change mutex to spinlock to optimize thread context switch.
Reviewed-by: Sage Weil <sage@redhat.com> - 11:56 AM Revision bc7d6771 (ceph): Merge pull request #6550 from cernceph/wip-deepscrub
- osd: randomize deep scrubbing
Reviewed-by: Sage Weil <sage@redhat.com> - 11:55 AM Revision e0dfa0d2 (ceph): Merge pull request #6568 from ghost/wip-scrub-error
- scrub: do not assign value if read error
Reviewed-by: David Zafman <dzafman@redhat.com> - 11:55 AM Revision dcd1834c (ceph): Merge pull request #6609 from liewegas/wip-newstore
- newstore: misc updates (including kv and os/fs stuff)
- 11:54 AM rgw Bug #13796 (Resolved): ERROR: testContainerListing, list index out of range
- 11:54 AM Revision dddf7d1a (ceph): Merge pull request #6622 from liewegas/wip-13796
- osd: partial revert of "ReplicatedPG: result code not correctly set in some cases."
Reviewed-by: Yehuda Sadeh <yehud... - 10:25 AM Bug #13844 (Rejected): ceph df MAX AVAIL is incorrect for simple replicated pool
- Since we upgraded from firefly to hammer the MAX AVAIL column is quite wrong for most of our pools....
- 09:31 AM Bug #13843: ceph osd pool stats broken in hammer
- Correction, this only happens when there is ongoing backfilling. When the cluster is degraded but there's no backfill...
- 08:30 AM Bug #13843 (Resolved): ceph osd pool stats broken in hammer
- Since we updated from firefly to hammer the ceph osd pool stats is wrong when the cluster is degraded:...
- 09:26 AM Revision 18713e60 (ceph): mon/PGMonitor: MAX AVAIL is 0 if some OSDs' weight is 0
- In get_rule_avail(), even p->second is 0, it's possible to be used
as divisor and quotient is infinity, then is conve... - 08:19 AM rgw Bug #13223 (Fix Under Review): Can’t reach quota limit when use multipart upload objects
- *master PR*: https://github.com/ceph/ceph/pull/6460
- 08:19 AM rgw Bug #13223: Can’t reach quota limit when use multipart upload objects
- Hi! Do you think this is reproducible on latest master?
- 08:15 AM Revision a2c6a212 (ceph): init-rbdmap: fix CMDPARAMS
- Fixes: #13214
Reported-by: Wyllys Ingersoll <wyllys.ingersoll@keepertech.com>
Signed-off-by: Sage Weil <sage@redhat.c... - 08:03 AM Bug #13842 (Closed): rados/thrash: msgr-failures/osd-delay.yaml workloads/radosbench.yaml may nee...
- http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-19_21:00:02-rados-hammer-distro-basic-openstack/17411/
f... - 07:42 AM Revision b2393dce (ceph): client: add InodeRef.h to make dist
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 07:20 AM Bug #13840: Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- This bug is related to http://tracker.ceph.com/issues/10257. And as pointed it out in https://bugzilla.redhat.com/sh...
- 04:59 AM Bug #13840 (Resolved): Ceph Pools' MAX AVAIL is 0 if some OSDs' weight is 0
- After adding a new OSD and set its weight to 0, the pools' MAX AVAIL becomes 0 in "ceph df".
# ceph df
GLOBAL:
... - 05:59 AM Revision 5e6fcd46 (ceph): rgw: compile fixup for JSONFormatter move
- Signed-off-by: Robin H. Johnson <robin.johnson@dreamhost.com>
- 12:25 AM Bug #13219: get_device_by_uuid->blkid_find_dev_with_tag() may hang for 3 min
- Sage,
Here is snippet of my last mail to the community regarding this.
Xiaoxi,
Thanks for giving me some pointer...
11/19/2015
- 11:10 PM Revision 4bc39bcd (ceph): Merge pull request #6658 from dachary/wip-releases
- doc: add v0.80.11 to the release timeline
Reviewed-by: Nathan Cutler <ncutler@suse.cz> - 11:07 PM Revision 89dcc0da (ceph): ceph_manager: do_pg_scrub: keep scrubbing until it's done
- The ceph pg scrub ... command isn't really guarranteed to
start a scrub, keep reissuing it until the scrub actually
h... - 11:07 PM Revision 97bf0bcf (ceph): Merge pull request #6057 from rahul1aggarwal/master
- Bug #13207: Rados Gateway: Anonymous user is able to read bucket with authenticated read ACL
- 10:47 PM Revision 1420a1f1 (ceph): doc: add v0.80.11 to the release timeline
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 10:44 PM Revision 5f90c35f (ceph): rados: add test for ec fast_read
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 10:35 PM Stable releases Tasks #13645 (Resolved): infernalis v9.1.1
- 10:34 PM Stable releases Tasks #13838 (In Progress): firefly v0.80.12
- 10:33 PM Stable releases Tasks #13838 (Rejected): firefly v0.80.12
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 10:20 PM Stable releases Tasks #11644 (Resolved): firefly v0.80.11
- 10:05 PM Revision 9e9b03ea (ceph): doc/releases: add v0.80.11 to release table
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:04 PM Revision 4b5afe5f (ceph): doc/release-notes: final v0.80.11 notes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 10:03 PM Revision 842deb88 (ceph): Merge pull request #6374 from dachary/wip-release-notes-firefly
- release-notes: draft v0.80.11 release notes
- 09:45 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 06:37 PM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 09:14 PM Revision 6316ff83 (ceph): 10.0.0
- 07:46 PM devops Feature #11978 (Closed): Tool that updates git-notes for backports
- 07:45 PM devops Feature #11978: Tool that updates git-notes for backports
- Moved to http://ceph-workbench.dachary.org/root/ceph-workbench/issues/5
- 07:22 PM Revision 99ba6610 (ceph): 13207: Rados Gateway: Anonymous user is able to read bucket with authen...
- Signed-off-by: root <rahul.1aggarwal@gmail.com>
- 07:06 PM Revision 2c7b04c3 (ceph): Merge pull request #6654 from tchaikov/wip-unsigned-missing-scrub
- osd: note down the number of missing clones
Reviewed-by: David Zafman <dzafman@redhat.com> - 06:45 PM Revision 5d204db8 (ceph): Merge pull request #6580 from dachary/wip-13786-hammer
- rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:45 PM Revision 1dbd4c66 (ceph): Merge pull request #6286 from dillaman/wip-13460-hammer
- rbd-replay-prep and rbd-replay improvements
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:41 PM Revision 24a5dc0a (ceph): Merge pull request #5790 from SUSE/wip-12932-hammer
- Miscellaneous spec file fixes
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:13 PM Revision 2fab020a (ceph): Merge pull request #707 from ceph/wip-13774-jewel
- Added infernalis-client-x
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 05:59 PM Revision 1536cb02 (ceph): osd: note down the number of missing clones
- Caused by 2e0bb0ae9498fd9a0c49f1b81bf0c86f7a7cac42
Signed-off-by: Kefu Chai <kchai@redhat.com> - 05:44 PM Bug #13713 (Rejected): Ceph CRC32 algorithm appears broken
- 05:36 PM Revision f8fcb67e (ceph): Added infernalis-client-x - fixes #13774
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 05:36 PM Feature #13837 (Resolved): Make snap_trimming robust to inconsistent snaphots
- Hi,
we upgraded to 9.2 and we still encountering a crash that looks a lot like issue #12665
So it looks like the ... - 04:28 PM Bug #12328: Ceph KV OSD crashes sometimes with FAILED assert(0 == "hit suicide timeout") on 0.94.1
- Did you guys find a fix for this?
We upgraded from firefly to hammer 0.94.5 two days ago and since then we've had ... - 03:04 PM Support #12177: removing cached objects doesn't quickly remove tiered ec objects
- A couple days ago I did investigation on the same issue. Indeed whiteout cache entry removal happens on cache flushin...
- 02:11 PM Bug #13835 (Can't reproduce): on_flushed: object 1/f9b8d3f7/burnupi0951139-337/head obc still alive
- ...
- 01:55 PM rgw Feature #13834: rgw: add bucket request payment feature usage statistics integration
- Added bpr-ul-example-0001.txt
This file shows the new usage log structure indexing by user (requester) instead of ... - 01:39 PM rgw Feature #13834 (Fix Under Review): rgw: add bucket request payment feature usage statistics integ...
- 01:39 PM rgw Feature #13834: rgw: add bucket request payment feature usage statistics integration
- PR available at:
https://github.com/ceph/ceph/pull/6656 - 12:52 PM rgw Feature #13834 (Resolved): rgw: add bucket request payment feature usage statistics integration
- Add usage statistics support for the bucket request payment feature.
- 01:41 PM rgw Bug #13020 (Resolved): rgw: include RequestId as part of the Error response
- Merged.
- 01:40 PM rgw Feature #13427 (Resolved): rgw: bucket request payment support
- Merged.
- 12:00 PM rgw Backport #13830 (In Progress): infernalis: init script reload doesn't work on EL7
- 06:40 AM rgw Backport #13830 (Resolved): infernalis: init script reload doesn't work on EL7
- https://github.com/ceph/ceph/pull/6650
- 11:48 AM Bug #13812: pgs stuck creating in upgrade test hammer->hammer.?->jewel
- One of these four commits is responsible for the regression:
* https://github.com/ceph/ceph/pull/6336 "PASS":http:... - 11:20 AM Bug #13812 (Resolved): pgs stuck creating in upgrade test hammer->hammer.?->jewel
- 11:13 AM Revision d27da2ee (ceph): Merge pull request #6644 from dachary/wip-13812-upgrade
- revert: osd: use GMT time for hitsets
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:47 AM rgw Bug #13824: orphans finish segfaults
- Here is PR:
https://github.com/ceph/ceph/pull/6652 - 10:06 AM Revision b2f2e6c8 (ceph): Merge pull request #6637 from Vicente-Cheng/update-ceph-disk-manual-page
- doc: Update ceph-disk manual page with new feature deactivate/destroy.
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:57 AM Revision 9109f14e (ceph): common/hobject.h: don't reverse bits in zero
- Zero is passed in around 30% of all calls to _reverse_bits (and most of
them during daemon startup). Optimize this by... - 08:14 AM Revision 65ea6bbc (ceph): rgw:swift use Civetweb ssl cannot get right url
- Fixes: #13628
Signed-off-by: Weijun Duan <duanweijun@h3c.com>
(cherry picked from commit e0fd540bf441e2f8276cbd96c60... - 08:12 AM Revision b4961ba5 (ceph): Merge pull request #713 from dachary/wip-buildpackages-refactor-hammer
- buildpackages: implement get_pkg_type & avoid duplicate packages-repository
- 08:11 AM Revision 762af158 (ceph): Merge pull request #712 from dachary/wip-buildpackages-refactor
- buildpackages: implement get_pkg_type & avoid duplicate packages-repository
- 08:09 AM Revision abafb539 (ceph): buildpackages: avoid duplicate packages-repository
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 87e50d394a26682614ab3ec8f566bda9f30e8416) - 08:08 AM Revision 87e50d39 (ceph): buildpackages: avoid duplicate packages-repository
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 08:06 AM Linux kernel client Bug #13712: Page allocation failure in Kernel 4.2.3.
- Hmm, "vmalloc: allocation failure: 18446744072439583573 bytes" stands out in the second trace. I'll try to investigate.
- 07:58 AM Bug #13829: config set with negative value results in "error setting 'filestore_merge_threshold' ...
- brad, i attached a POC to explain my idea to this change.
- 06:39 AM Bug #13829 (Resolved): config set with negative value results in "error setting 'filestore_merge_...
- In the filestore-config-ref we say...
> filestore merge threshold
> Description: Min number of files in a subdir ... - 06:44 AM Revision fdb5dbd7 (ceph): rgw: fix reload on non Debian systems.
- When using reload in non-debian systems, /bin/sh's kill is used to send the HUP signal to the radosgw process.
This k... - 06:41 AM rgw Backport #13831 (Resolved): hammer: init script reload doesn't work on EL7
- https://github.com/ceph/ceph/pull/7187
- 06:33 AM rbd Backport #13733 (In Progress): misdirected op in rbd balance-reads test
- 06:33 AM rbd Backport #13754 (In Progress): Avoid re-writing old-format image header on resize
- 06:32 AM rbd Backport #13756 (In Progress): QEMU hangs after creating snapshot and stopping VM
- 06:31 AM rbd Backport #13759 (In Progress): rbd: pure virtual method called
- 06:30 AM rbd Backport #13761 (In Progress): unknown argument --quiet in udevadm settle
- 06:30 AM rgw Backport #13735 (In Progress): rgw: swift API returns more than real object count and bytes used ...
- 06:29 AM rgw Backport #13798 (In Progress): infernalis: rgw: default quota params
- 04:48 AM Revision 3b146f59 (ceph): RadosClient: reimplement the pool alignment methods using the new ones
- so we don't less duplicated code and the logic reveals the problem of the old methods in a more visible way.
Fixes: #... - 01:34 AM Revision 1633d3e1 (ceph): doc: Update ceph-disk manual page to remove some option description.
- - remove `--mark-init` and `--activate-key` from options because
they are not options that are common to all subc... - 01:34 AM Revision cd3d056c (ceph): librbd: journal op requests
- Any op request that has the potential to impact the layout or data
within an image needs to be journaled for RBD mirr... - 01:34 AM Revision 63f9ae3d (ceph): tests: updated librbd::Journal API
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 3d6cde01 (ceph): librbd: possible unit test race condition
- It's possible during unit tests for the requests to complete
prior to marking the Context as complete. In this case,... - 01:34 AM Revision 2d340da5 (ceph): librbd: possible recursive reader lock during resize
- With multiple resizes concurrently queued, it's possible for
the owner lock to be locked multiple times.
Signed-off-... - 01:34 AM Revision da473a7e (ceph): tests: add missing test cases for rbd exclusive-lock RPC
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 6f94bde4 (ceph): librbd: ImageWatcher shouldn't block the notification thread
- Now that all RPC operations are asynchronous, blocking the notification
thread will also result in librados async cal... - 01:34 AM Revision aa02a07e (ceph): librbd: owner_lock should be held while opening parent image
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision ac84faac (ceph): librbd: improve debug output for object map state machines
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision cea6a23e (ceph): tests: new tests for watch/notify snap protect/unprotect ops
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 5e20ffe9 (ceph): cls_rbd: dir_rename_image is now async
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 8c8a9170 (ceph): tests: update cls_rbd test for async dir_rename_image method
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision dceb6cfa (ceph): librados_test_stub: added ObjectWriteOperation::tmap_update
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 8351ed09 (ceph): librbd: added async image rename op
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 59a7615a (ceph): tests: new watch/notify rename image tests
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision c1bca63f (ceph): tests: added snap protect/unprotect and rename to client update test
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision c4247f5f (ceph): librbd: new journal types for maintenance commands
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 01abb20f (ceph): librbd: new watch/notify types for snap protect/unprotect and rename
- When journaling is enabled, these actions will need to be executed via the
lock owner to ensure that they are journal... - 01:34 AM Revision 8a15fa64 (ceph): tests: new ImageWatcher tests for snap protect/unprotect and rename
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 83115045 (ceph): librbd: async ops should return status via the Context
- Avoid handling a return value which could indicate an error and
instead return initialization errors via the Context ... - 01:34 AM Revision 983d12b5 (ceph): librbd: snap protect/unprotect now connected to watch/notify
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 9df7e39d (ceph): librbd: drain op work queue after shutting down journal
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision daf36f03 (ceph): librbd: do not send duplicate lock event
- No need to alert clients that the lock has been released since it
is already handled by ImageWatcher::release_lock
S... - 01:34 AM Revision f02e4464 (ceph): librbd: rename librbd::WatchNotify namespace to librbd::watch_notify
- The new namespace follows the expected naming conventions.
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:34 AM Revision d1541d6e (ceph): librbd: migrate object map snapshot ops to async state machines
- Since all snapshot handling was migrated to async state machines, the
object map snapshot handling also needs to be c... - 01:34 AM Revision 7b1170a8 (ceph): librbd: move object map async ops to standalone classes
- In preparation for creating new async snapshot-related object map
operations, move the existing object map async ops ... - 01:34 AM Revision 36032f8d (ceph): librbd: consolidate object map invalidation to new state machine
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:34 AM Revision 6326d075 (ceph): cls_rbd: add async version of object_map_load
- Most librbd object map interactions are moving to async state machines.
The sync version must remain until the librbd... - 01:34 AM Revision 4944f20c (ceph): librbd: initial conversion of snapshot ops to async versions
- Object map updates are not currently integrated until those methods
are converted to async state machines.
Signed-of... - 01:33 AM Revision d3d139b4 (ceph): doc: Update ceph-disk manual page with new feature deactivate/destroy.
- - Update the ceph-disk manual page
Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.com> - 01:28 AM Bug #13828 (Can't reproduce): OSD: wrong broken osd state due to disconnection of node backend ne...
- Our cluster is made up of 4 nodes, which consist of 10 osds each. The
topology of the cluster is illustrated as bel... - 01:16 AM Bug #13826: segfault from PrebufferedStreambuf::overflow
- But not that. As a newbie I tried tofigure out how to use ceph-deploy to add a new mon to a running cluster. It seems...
- 12:07 AM Revision 8358fb89 (ceph): revert: osd: use GMT time for hitsets
- "Merge pull request #5825 from tchaikov/wip-12848-hammer"
This reverts commit 39544718dc2f09bcfdc632ac72fd2a3cda8768...
11/18/2015
- 11:44 PM Backport #13288 (In Progress): hammer: stuck recovering, unfound hit set due to removing it while...
- https://github.com/ceph/ceph/pull/5825 was reverted by https://github.com/ceph/ceph/pull/6644 because of a regression...
- 11:43 PM Backport #12848 (In Progress): ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED asse...
- https://github.com/ceph/ceph/pull/5825 was reverted because of a regression http://tracker.ceph.com/issues/13812
- 11:37 PM Revision 356ca81e (ceph): buildpackages: implement get_pkg_type
- It can be deprectated when it is implemented in teuthology.
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry p... - 11:36 PM Revision 13fb23ed (ceph): buildpackages: implement get_pkg_type
- It can be deprectated when it is implemented in teuthology.
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:23 PM Bug #13812 (Fix Under Review): pgs stuck creating in upgrade test hammer->hammer.?->jewel
- https://github.com/ceph/ceph/pull/6644
- 10:30 PM Bug #13801: Deep-scrub will crash osd if osd backend is newstore
- #13668 looks related, or possibly a duplicate.
#13827 describes a scrub-related OSD crash in Hammer. - 10:10 PM Bug #13827 (Resolved): OSD takes suicide timeout during deep_scrub on pg after upgrade to Hammer ...
- Dreamhost has upgraded to Ceph Hammer 94.5 and has been incurring occasional OSD crashes due to suicide timeouts duri...
- 10:03 PM Revision fc29c1e8 (ceph): Merge pull request #711 from dachary/wip-buildpackages-refactor-hammer
- buildpackages: refactor to not require remote
- 10:02 PM Revision 570a5a0e (ceph): buildpackages: refactor to not require remote
- Most of the flavor, sha1, tag etc. selection logic as implemented in the
packaging module of teuthology relies on rem... - 10:01 PM Revision a5133dec (ceph): Merge pull request #710 from dachary/wip-buildpackages-refactor
- buildpackages: refactor to not require remote
- 09:49 PM Revision 69e9b22e (ceph): buildpackages: refactor to not require remote
- Most of the flavor, sha1, tag etc. selection logic as implemented in the
packaging module of teuthology relies on rem... - 09:14 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
- I believe I have found the culprit.
I tried to add 2 new monitors. One was fine - same environment as the sole init... - 08:14 PM Bug #13826: segfault from PrebufferedStreambuf::overflow
- ceph version 9.2.0 (bb2ecea240f3a1d525bcb35670cb07bd1f0ca299)
- 08:11 PM Bug #13826 (Duplicate): segfault from PrebufferedStreambuf::overflow
- Granted, I may have something done to mons on my test cluster (tried to add new mons to the cluster and visibly faile...
- 08:41 PM Revision b75d1074 (ceph): Merge pull request #6545 from dzafman/wip-dry-fixes
- Fix --dry-run for many ceph-objectstore-tool operations
Includes adding missing tests for xattr and omap
Add testing... - 08:20 PM Bug #13238: duplicate start of ceph-osd daemon
- 2nd confirmation that this still occurs with Hammer and RHEL 7. pid file missing, resulting in orphaned procs from sy...
- 08:14 PM Revision 9cbe1320 (ceph): pep8 changes
- Signed-off-by: Joe Julian <jjulian@io.com>
- 08:13 PM Revision cb18a103 (ceph): Add test cases to validate symlinks pointing to devs
- Signed-off-by: Joe Julian <jjulian@io.com>
- 08:08 PM Revision b3c7cb09 (ceph): Compare parted output with the dereferenced path
- Compare parted output with the dereferenced path of the device as parted
prints that instead of the symlink we called... - 05:09 PM Bug #13713: Ceph CRC32 algorithm appears broken
- Thanks! This was exactly the answer I was hoping for. I thought I might be missing something but I couldn't quite f...
- 10:37 AM Bug #13713: Ceph CRC32 algorithm appears broken
- (Sorry for the formatting on the last message -- I think it's readable anyway).
I read some more and found that cr... - 09:34 AM Bug #13713: Ceph CRC32 algorithm appears broken
- I checked the partial crc after each iteration in google's python implementation and found that the crc of the last i...
- 03:53 PM Revision 133b0dee (ceph): Merge pull request #6640 from david-z/wip-async-msg-crash-cephfs
- Cephfs will crash if enabling async msg because of an assertion
Reviewed-by: Haomai Wang <haomai@xsky.com> - 03:06 PM rgw Bug #13709 (Pending Backport): init script reload doesn't work on EL7
- Merged upstream (master). We should probably back-port this to infernalis as well.
- 03:03 PM Revision 16ef1da5 (ceph): Merge pull request #6482 from herver/wip-13709
- rgw: fix reload on non Debian systems.
Reviewed-by: Nathan Cutler <ncutler@suse.com>
Reviewed-by: Ken Dreyer <kdreye... - 02:23 PM Feature #13163: Add flag to delete a pool and its cache tier.
- Just tried to delete cache pool with some data ( pretty small though ) in it using following command sequence:
./cep... - 02:00 PM rgw Bug #13824 (Resolved): orphans finish segfaults
- The orphans finish command segfaults due to dereferencing the null pointer *info*, passed as NULL:...
- 12:00 PM Revision 5a2d24ba (ceph): Merge pull request #5662 from ceph/wip-scrub-basic
- ScrubStack and "tag path" command
Reviewed-by: John Spray <john.spray@redhat.com>
Reviewed-by: Yan, Zheng <zyan@redh... - 11:33 AM rgw Bug #13680: New keystone expire dates cannot be parsed
- Yes, seems this commit:
https://github.com/ceph/ceph/commit/136242b5612b8bbf260910b1678389361e86d22a
fixed this bug.
- 10:29 AM Bug #13783: monitors crashing constantly with 0.94.5
- Quick note: we've upgraded to infernalis and it runs as expected, as also confirmed by Logan V in the other ticket. M...
- 10:28 AM Revision 7d6002b7 (ceph): Cephfs will crash if enabling async msg because of an assertion
- Signed-off-by: Zhi Zhang <zhangz.david@outlook.com>
- 09:50 AM Bug #13822 (Resolved): Objecter: potential null pointer access in list_(n)objects.
- In list_objects and list_nobjects, we are possibly access a null returned pointer from the osdmap->get_pg_pool() call
- 09:17 AM Bug #13821 (Resolved): OSD: race condition detected during send_failures
- In OSD::send_failures(), we are risking changing failure_queue possibly without protection of heartbeat_lock, and thu...
- 08:28 AM Backport #13792 (In Progress): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 08:28 AM Backport #13771 (In Progress): Objecter: pool op callback may hang forever.
- 08:27 AM Backport #13655 (In Progress): crush: crash if we see CRUSH_ITEM_NONE in early rule step
- 08:24 AM Revision 8e6130d0 (ceph): rgw: Add default quota config
- Add a default quota config that is applied when no specific quota is
enabled. There are both per-bucket and per-user... - 08:20 AM Revision 1e82bbda (ceph): rgw: fix swift API returning incorrect account metadata
- Fixes: #13140
Fix the bug that swift account stat command returns doubled object count and bytes used
Signed-off-by... - 08:16 AM Revision d0536f9d (ceph): run_cmd: close parent process console file descriptors
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit f46f7dc94139c0bafe10361622416d7dc343d31f) - 08:16 AM Revision 497c1f06 (ceph): krbd: remove deprecated --quiet param from udevadm
- This parameter has been removed since systemd 213, so this
effects Fedora 21+, Debian Jessie, and potentially future
... - 08:13 AM Revision ad84753a (ceph): WorkQueue: new PointerWQ base class for ContextWQ
- The existing work queues do not properly function if added to a running
thread pool. librbd uses a singleton thread ... - 08:06 AM Revision 0b21b3f0 (ceph): tests: new test case to catch deadlock on RBD image refresh
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit a9729d9553e7fb925509cad8d388cf52a9fede9c) - 08:06 AM Revision 83c38802 (ceph): librbd: fixed deadlock while attempting to flush AIO requests
- In-flight AIO requests might force a flush if a snapshot was created
out-of-band. The flush completion was previousl... - 07:58 AM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- I just rebased the changes and updated the bindings based on the latest rbd.py from master, and I'm trying deb and rp...
- 07:42 AM Revision 74cb593a (ceph): librbd: resize should only update image size within header
- Previously, the whole RBD image format 1 header struct was
re-written to disk on a resize operation.
Fixes: #13674
B... - 07:33 AM Revision 6750cab2 (ceph): osd: ensure op rwm flags are checked before they are initialized
- These flags are now lazy-initialized within the PG thread at the
start of op processing instead of once the message i... - 07:26 AM Revision 58b43e65 (ceph): build/ops: rbd-replay moved from ceph-test-dbg to ceph-common-dbg
- http://tracker.ceph.com/issues/13785 Fixes: #13785
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro... - 07:20 AM Revision 2647c20c (ceph): Objecter: pool_op callback may hang forever.
- pool_op callback may hang forever due to osdmap update during reply handling.
Fixes: #13642
Signed-off-by: xie xinggu... - 07:11 AM Revision ecb6aa23 (ceph): crush/mapper: ensure bucket id is valid before indexing buckets array
- We were indexing the buckets array without verifying the index was within
the [0,max_buckets) range. This could happ... - 07:11 AM Revision 4d2a135c (ceph): crush/mapper: ensure take bucket value is valid
- Ensure that the take argument is a valid bucket ID before indexing the
buckets array.
Signed-off-by: Sage Weil <sage... - 06:35 AM Bug #13741: There is an error format in Pgmap printing information
- @Sage Weil
I have to repair, to see if feasible
https://github.com/ceph/ceph/pull/6515 - 02:03 AM Revision d0756286 (ceph): tests: update cls_rbd tests for async snapshot methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
11/17/2015
- 09:58 PM rgw Bug #13764: Radosgw incomplete files
- It shows normal to me (and the reported size too):
root@controller1:~# radosgw-admin object stat --bucket=oicr.icg... - 07:25 PM rgw Bug #13764: Radosgw incomplete files
- For 534acdce-ffda-5aef-ad77-3fabfb9317d5, what does the manifest (radosgw-admin object stats) show?
- 06:07 PM rgw Bug #13764: Radosgw incomplete files
- Hi,
I can provide more info about this issue if it helps troubleshooting.
We have rgw_obj_stripe_size = 6710886... - 08:45 PM rgw Bug #13796 (Fix Under Review): ERROR: testContainerListing, list index out of range
- https://github.com/ceph/ceph/pull/6622
- 08:40 PM Revision 04e3810c (ceph): osd: partial revert of "ReplicatedPG: result code not correctly set in ...
- This reverts the parts of commit 3b5d54bec0f0556b7dd6e7ea7e6df02ec71f97d9
that change omap return values (i.e., do no... - 08:18 PM Revision 22a0824e (ceph): cls_rbd: convert snapshot methods to async versions
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 08:14 PM Revision 6a12b95d (ceph): librbd: new intermediate request class for handling journal ops
- All operations that should be recorded to the journal will inherit
from the new librbd::operation::Request class.
Si... - 08:10 PM Revision ff924278 (ceph): librbd: move all image operation state machines to new namespace
- Prior to creating multiple new state machines for image operations,
move all existing op requests to a new namespace ... - 08:05 PM Revision 2e17bdc8 (ceph): librbd: simplify state machine lock assumptions
- Use asynchronous callbacks to ensure that no locks are held when
re-entering a state machine. This helps to avoid od... - 08:05 PM Revision a701d5e8 (ceph): librbd: remove AsyncRequest::safely_cancel
- Long-running operations controlled via the AsyncObjectThrottle will
automatically cancel with an -ERESTART return cod... - 08:02 PM rgw Bug #13817: RGW does not send HTTP header
- Yes, I'm hitting rgw directly:...
- 07:30 PM rgw Bug #13817: RGW does not send HTTP header
- Are you sure that you actually reach rgw? Does the rgw log show anything? (add 'debug rgw = 20', 'debug civetweb = 10...
- 11:03 AM rgw Bug #13817 (In Progress): RGW does not send HTTP header
- ...
- 07:56 PM Revision c62a07a9 (ceph): librbd: removed Async* prefix from request state machines
- In preparation for adding more snapshot handling request state machines,
simplify the naming of the existing classes ... - 07:56 PM Revision daa75945 (ceph): librbd: async version of AioImageRequestWQ::block_writes
- Snapshot create will uses the async version to block write ops
prior to creating the new snapshot context.
Signed-of... - 07:53 PM rgw Backport #13819 (In Progress): infernalis: Setting ACL on Object removes ETag
- 07:49 PM rgw Backport #13819 (Rejected): infernalis: Setting ACL on Object removes ETag
- https://github.com/ceph/ceph/pull/6621
- 07:51 PM rgw Backport #13820 (In Progress): hammer: Setting ACL on Object removes ETag
- 07:50 PM rgw Backport #13820 (Resolved): hammer: Setting ACL on Object removes ETag
- https://github.com/ceph/ceph/pull/6620
- 07:51 PM Revision 4420929e (ceph): rgw: fix modification to index attrs when setting acls
- Fixes: #12955
- add ACL change after initial population
- populate bufferlist with object attributes
Signed-off-b... - 07:39 PM Revision 46249fe5 (ceph): Merge pull request #6541 from dillaman/wip-11287
- librbd: integrate journaling support for IO operations
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:38 PM rgw Bug #13680: New keystone expire dates cannot be parsed
- (believed to be resolved in keystone v3 change)
- 07:16 PM rgw Bug #12955 (Pending Backport): Setting ACL on Object removes ETag
- Merged commit:7496741ebbd75b74d5ffeca5341cccb2318176e6
- 07:09 PM rgw Bug #13613 (Rejected): radosgw problems concurrent downloads
- 07:09 PM Bug #13426: rebuilding stable releases from source require editing .gitmodules
- I looked at this, but can't make any sense of it. The firefly .gitmodules is here: https://github.com/ceph/ceph/blob/...
- 07:08 PM rgw Bug #13529 (Fix Under Review): rgw: leak from RGWWatcher::handle_error
- 07:07 PM rgw Bug #13529: rgw: leak from RGWWatcher::handle_error
- *master PR*: https://github.com/ceph/ceph/pull/6507
- 07:00 PM Bug #13781: Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- Loic, see description - this is Hammer (no systemd).
- 03:28 PM Bug #13781: Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- Is the corresponding systemd service enabled ? I kind of remember a similar problem where all was good, only the serv...
- 06:57 PM Revision 8424145d (ceph): 0.80.11
- 06:14 PM rbd Tasks #13818 (Resolved): Update RBD notification workunit test to include new infernalis RPC mess...
- 04:50 PM Bug #13713: Ceph CRC32 algorithm appears broken
- Here's a code snippet of python using google's crc32c python library https://code.google.com/p/googleappengine/source...
- 04:20 PM Bug #13713: Ceph CRC32 algorithm appears broken
- I'm almost sure at this point that the ceph crc calculation is incorrect.
I wrote a short C program utilizing th... - 04:48 PM rbd Bug #13115: librbd python bindings eat exceptions in callbacks
- If you have a prototype of the build changes we can pull them into a branch to try building on several platforms via ...
- 04:45 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- We have a ceph-qa-suite for the fast read - https://github.com/ceph/ceph-qa-suite/pull/503, is that enough?
- 04:01 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Samuel Just wrote:
> Apparently fast-read does not have tests in ceph-qa-suite. That is very bad, I've got a wip-fa... - 03:51 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Apparently fast-read does not have tests in ceph-qa-suite. That is very bad, I've got a wip-fast-read branch now tha...
- 03:21 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Part of the discussion needs to be how well it's currently tested in master (and therefore in hammer after the backpo...
- 04:45 PM rbd Bug #12383: "Segmentation fault rbd()"
- Packaging should make this unhittable
- 04:44 PM rbd Bug #13457 (Resolved): Test and document "--cluster" option for RBD
- 04:43 PM rbd Bug #13804 (Can't reproduce): rbd/copy.sh: hangs with features/layering.yaml msgr-failures/many.y...
- Can reopen if it recurs. Seems to be just failure injection getting unlucky.
- 04:43 PM rbd Bug #13806 (Resolved): rbd: new CLI doesn't support 'snap list' command alias
- 04:41 PM rbd Bug #13784 (Resolved): rbd: new cli arg parsing doesn't handle negative boolean common options
- 04:40 PM rbd Bug #13636 (Pending Backport): rbd: pure virtual method called
- 04:30 PM Bug #13812: pgs stuck creating in upgrade test hammer->hammer.?->jewel
- Can be the same in hammer stable, in run:
http://pulpito.ceph.com/teuthology-2015-11-16_16:05:08-upgrade:hammer-hamm... - 03:05 PM Bug #13812: pgs stuck creating in upgrade test hammer->hammer.?->jewel
- More details at http://tracker.ceph.com/issues/13356#note-27
- 03:01 PM Bug #13812 (In Progress): pgs stuck creating in upgrade test hammer->hammer.?->jewel
- 04:05 PM Bug #13802: osd/osd_types.cc: 459: FAILED assert(m_seed < old_pg_num)
- okay.... And i double checked that everything was up to date and the instances where restarted after the change date....
- 03:24 PM Bug #13802 (Rejected): osd/osd_types.cc: 459: FAILED assert(m_seed < old_pg_num)
- fixed in 0.94.4 by commit:bee86660377cfaa74f7ed668dd02492f25553ff9 ... you need to upgrade the client!
- 03:24 PM Bug #13802: osd/osd_types.cc: 459: FAILED assert(m_seed < old_pg_num)
- Well, both of those backtraces are 94.3.
- 04:03 PM Documentation #13814: document the *_full* config options
- Lots of details from Sage here:
http://permalink.gmane.org/gmane.comp.file-systems.ceph.devel/23391 - 08:26 AM Documentation #13814 (Resolved): document the *_full* config options
- For instance:...
- 03:59 PM Bug #13741 (Won't Fix): There is an error format in Pgmap printing information
- 03:57 PM Bug #13013 (Duplicate): Cache tier thrashing causes out of order write
- #12814
- 03:51 PM Bug #13592 (Need More Info): ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- 03:50 PM Bug #13778 (Won't Fix): OSD crash (giant)
- Could you please upgrade to hammer ? If the problem still happens, please re-open this issue. The giant release (0.87...
- 03:48 PM Bug #12892 (Rejected): Image'snapshot too much cause the "Deep Scrub" function running too long, ...
- We need a way to limit the number of snapshots both at the osd level and at the client level (rbd). The trick is tha...
- 03:47 PM Bug #12580 (Can't reproduce): Enclosure power failure pausing client IO
- 03:46 PM Bug #13787 (Need More Info): test-erasure-code.sh: Error EINVAL: The option value '2147483647' se...
- It probably is environmental but better wait a few weeks to be sure.
- 03:44 PM Bug #13219 (Can't reproduce): get_device_by_uuid->blkid_find_dev_with_tag() may hang for 3 min
- 03:43 PM Bug #10097 (Resolved): failed: mon_thrash
- 03:42 PM Bug #13435: "failed: mon_thrash" in upgrade:hammer-x-infernalis-distro-basic-multi run
- fixed by commit:fb50ff6250d10c300bfa135739d4fda4ac55d7c1
- 03:42 PM Bug #7995: osd shutdown: ./common/shared_cache.hpp: 93: FAILED assert(weak_refs.empty())
- 03:40 PM Bug #13380 (Resolved): Proxied write of lock.lock class method results in incorrect locker
- 03:38 PM Bug #12722 (Resolved): osd: OSD::do_mon_report stuck at acquiring osd_lock (more than 10mins) and...
- commit:2074be2db7eebd420faaf15fa9d65ff1f6a7bf4d
- 03:37 PM Bug #12722: osd: OSD::do_mon_report stuck at acquiring osd_lock (more than 10mins) and cause OSD ...
- Which PR is it ?
- 03:37 PM Bug #13530 (Won't Fix): HashIndex: shall cancel merge if it is going to trigger another split on ...
- 03:36 PM Bug #13530: HashIndex: shall cancel merge if it is going to trigger another split on it's direct ...
- see discussion at https://github.com/ceph/ceph/pull/6457
- 03:36 PM Bug #13530 (Rejected): HashIndex: shall cancel merge if it is going to trigger another split on i...
- 03:30 PM Bug #13577 (Rejected): The osd should handle only the kill signal and pass other signal.
- ceph zte wrote:
> Because there are some other software,like cgroup or openstack guard thread,when use cgroup with c... - 03:28 PM Bug #13543: one host down lead to all virtual machine filesystem in cluster can't be written,
- zcc icy wrote:
> Samuel Just wrote:
> > I don't quite follow what happened, but it looks like your cluster is full ... - 03:23 PM Bug #13801 (Fix Under Review): Deep-scrub will crash osd if osd backend is newstore
- 03:22 PM Revision f92f7417 (ceph): librbd: copy operation needs to use AIO work queue for writes
- This ensures that the exclusive lock is properly acquired prior to
writing to the new image.
Signed-off-by: Jason Di... - 03:22 PM Revision ee7c6f73 (ceph): librbd: simplify IO flush handling
- Add a new convenience method to ImageCtx for handling flush
requests and cleanup flush handling with dealing with the... - 03:16 PM Bug #13386 (Can't reproduce): heartbeat check failed due to hang processing copy_from (hammer)
- 03:16 PM Bug #13531: latest update osd lost, cluster still stuck on Peering
- will try to ping shawn for adding a test.
- 03:15 PM Bug #13531: latest update osd lost, cluster still stuck on Peering
- This needs a test before merge, shouldn't be hard.
- 03:16 PM Bug #13130 (Can't reproduce): qa:failed pool create in mkpool_layout_vxattrs.sh
- 03:15 PM Bug #13453 (In Progress): backfill pushes do not appear to increment the recovery rate counters
- 03:13 PM Bug #13484: pg notify sent but not recieved -- 4 pgs hung in peering as a result
- No, this is a messenger bug.
- 03:13 PM Bug #13517 (Resolved): common: fix reset max in Throttle using perf reset command
- 03:10 PM Bug #13805: segfault in Objecter::handle_watch_notify
- 03:01 PM Bug #13815 (Duplicate): OSDs failed after upgrade from 0.80.10 to 0.94.5
- 12:31 PM Bug #13815: OSDs failed after upgrade from 0.80.10 to 0.94.5
- It turns out, it is the same issue as this one: http://tracker.ceph.com/issues/12428
The workaround fixed it. - 08:43 AM Bug #13815 (Duplicate): OSDs failed after upgrade from 0.80.10 to 0.94.5
- Hello,
Few hours аfter upgrading from Firefly 0.80.10 to 0.94.5, 2 OSDs died simultaneously. The upgrade was done wi... - 02:59 PM Bug #13785 (Pending Backport): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 02:40 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Does these modifications only need to be applied on a ceph client?
- 02:28 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Dennis Kramer wrote:
> Does the ceph samba_vfs also needs to be fixed? Upgrading to Infernalis doesn't resolve my is... - 01:59 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Does the ceph samba_vfs also needs to be fixed? Upgrading to Infernalis doesn't resolve my issue. ACL's (acl_xattr in...
- 02:20 AM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Nathan Cutler wrote:
> Also, that PR claims to be fixing http://tracker.ceph.com/issues/12617 - what is the relation... - 02:17 AM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Nathan Cutler wrote:
> https://github.com/ceph/ceph/pull/6604 is a backport, to hammer, of https://github.com/ceph/c... - 02:01 PM Revision cb634dfa (ceph): librbd: possible deadlock attempting to drain parent image WQs
- Ensure all AIO to the parent image is properly flushed and assert
that all work queues are empty before closing the p... - 01:52 PM Revision b118d7df (ceph): WorkQueue: PointerWQ drain no longer waits for other queues
- If another (independent) queue was processing, drain could
block waiting. Instead, allow drain to exit quickly if
no... - 12:38 PM CephFS Bug #13816 (Resolved): Crash in cephfs-journal-tool
- 12:22 PM CephFS Bug #13816 (Fix Under Review): Crash in cephfs-journal-tool
- https://github.com/ceph/ceph/pull/6617
- 10:57 AM CephFS Bug #13816 (Resolved): Crash in cephfs-journal-tool
- ...
- 12:34 PM Revision acb8fdec (ceph): Merge pull request #6617 from jcsp/wip-13816
- tools/cephfs: fix overflow writing header to fixed size buffer (#13816)
- 12:20 PM Revision 5c2815e9 (ceph): tools/cephfs: enlarge dump header
- This was never big enough for largest possible
numbers in the %llu formats.
Not being backwards compatible for this ... - 12:20 PM Revision 58753453 (ceph): tools/cephfs: use snprintf in Dumper
- Signed-off-by: John Spray <john.spray@redhat.com>
- 10:45 AM devops Feature #7454 (Resolved): ceph-disk: support osd removal / ceph-disk remove
- 10:43 AM Revision 257a3c38 (ceph): Merge pull request #5867 from Vicente-Cheng/ceph-disk-destroy-implement...
- ceph-disk: Add destroy and deactivate option
ceph-disk now understands deactivate to shutdown an OSD and umount the ... - 09:32 AM Revision 5bfe05ae (ceph): Speed optimizations. Merged 3 writes into 1.
- Got rid of std::string construction.
More unification on syslog,stderr,fd.
Signed-off-by: Adam Kupczyk <akupczyk@mir... - 09:24 AM Revision 7d21127f (ceph): Merge pull request #6402 from SUSE/wip-13621-hammer
- CephFS restriction on removing cache tiers is overly strict
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 08:18 AM RADOS Feature #8695: OSD: make osd_backfill_full_ratio respond to injectargs/whatever
- We had backfill_toofull on one of our 0.94.5 OSD and we did
ceph tell osd.* injectargs '--osd-backfill-full-ratio... - 04:29 AM CephFS Backport #13813 (In Progress): hammer: Daily segfault ll_forget reader couldn't read tag
- Original PR was merged by John Spray.
- 04:28 AM CephFS Backport #13813 (Resolved): hammer: Daily segfault ll_forget reader couldn't read tag
- https://github.com/ceph/ceph/pull/6551
- 03:32 AM Revision 9ab61b27 (ceph): client: cancel revoking caps when reconnecting the mds
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 03:32 AM Revision 655ae79d (ceph): mds: choose EXCL state for filelock when client has Fb capability
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 03:32 AM Revision ce9a596d (ceph): mds: consider client's flushing caps when choosing lock states
- Client may flush and drop caps at the same time. If client need to
send cap reconnect before the caps get flushed. Th... - 03:18 AM Revision 9e9770ca (ceph): os: FileStore::_destroy_collection may hide the real mistake.
- Signed-off-by: Ruifeng Yang <yangruifeng.09209@h3c.com>
- 02:47 AM CephFS Bug #13729 (Pending Backport): Daily segfault ll_forget reader couldn't read tag
- https://github.com/ceph/ceph/pull/6551
the original RP is https://github.com/ceph/ceph/pull/4753 - 01:24 AM Revision f0646221 (ceph): ceph-disk: add destroy feature
- Implement destroy option on ceph-disk.
- remove OSD from CRUSH map
- remove OSD cephx key
- deallocate OSD ID
... - 01:24 AM Revision be471a29 (ceph): ceph-disk: use `ceph osd dump` to check osd status
- - Before deactivated osd, we need to know the status
including IN/OUT, UP/DOWN on this osd.
Signed-off-by: Vicen... - 01:24 AM Revision 7ca8d1da (ceph): ceph-disk: add `--mark-out` option on deactivate feature.
- - Using `--mark-out` option to mark osd out when
deactivate this osd instead of always mark osd out.
Signed-off-... - 01:24 AM Revision 7b5151a4 (ceph): ceph-disk: add --reactivate option, modify parameter about deactivate a...
- - add `--reactivate` option (activate do no-op without reactivate with deactive flag)
- for consistency, make both ... - 01:24 AM Revision 79220410 (ceph): ceph-disk: Implement unittest for ceph-disk deactivate/destroy feature
- - The unit tests cover all the implemention about deactivate/destroy.
Signed-off-by: Vicente Cheng <freeze.bilsted@g... - 01:24 AM Revision 06aeec9e (ceph): tests: ceph-disk: modified the destroy_osd test function.
- - use the new implementation (ceph-disk deactivate/destroy) instead of step by step remove
Signed-off-by: Vicente Ch... - 01:24 AM Revision d490fe99 (ceph): tests: ceph-disk: Make unit test coverage all ceph-disk destroy/deactiv...
- - Add some unit test to coverage all destroy/deactivate feature.
- Do some minor modifications on the ceph-diskw
S... - 01:24 AM Revision 56b3bbcd (ceph): ceph-disk: modify the destroy/deactivate behavior to handle dmcrypt/mpa...
- - modify the behavior to handle dmcrypt/mpath osd
- add some functions to get the information of dmcrypt osd
- fi... - 01:24 AM Revision f51dd57b (ceph): tests: ceph-disk: add some unittest functions to coverage destroy/deact...
- - Add new unittest functions to coverage the part of dmcrypt/mpath handling.
Signed-off-by: Vicente Cheng <freeze.bi... - 01:24 AM Revision 7e88cf00 (ceph): tests: ceph-disk: add deactivate/reactivate/destroy test cases.
- - using the deactivate/destroy feature to destroy osd
- test reactivate option when the osd goes deactive
- add c... - 01:24 AM Revision 3823c31f (ceph): ceph-disk: improve the device query stage on deactivate/destroy feature.
- - Make code path much easier to get device info. (get little bit overhead)
- Let some error rasie the correct execp... - 01:24 AM Revision c110a633 (ceph): tests: ceph-disk: improve the unit test to coverage all deactivate/dest...
- - rework the unit test to coverage all deactivate/destroy function
- make test item simple and easier to read
Sign... - 01:24 AM Revision 0f892e65 (ceph): tests: ceph-disk: modify the ceph-disk qa test cases
- - minor correct for the latest ceph-disk qa test cases
Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.com> - 01:24 AM Revision b954c519 (ceph): tests: ceph-disk: add wait_for_osd_down() in ceph-disk-test.py of qa
- - add wait_for_osd_down() to avoid the side effect of deactivate
Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.... - 01:24 AM Revision 2a3040b8 (ceph): ceph-disk: remove the redundant try except and minor nits
- - remove the redundant try except
Signed-off-by: Vicente Cheng <freeze.bilsted@gmail.com> - 01:24 AM Revision 3fcdf411 (ceph): ceph-disk: add deactivate feature
- Implement deactivate option on ceph-disk.
- stop ceph-osd service if needed (If osd still in osd map, make it out ...
11/16/2015
- 11:59 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- The EPEL update at https://bodhi.fedoraproject.org/updates/FEDORA-EPEL-2015-e71600c1f0 will solve half of the problem...
- 11:44 PM Bug #13812: pgs stuck creating in upgrade test hammer->hammer.?->jewel
- Version grep (never got to jewel):
2015-11-13 12:54:17.204648 7fa815761900 0 ceph version 0.94 (e61c4f093f88e4496... - 11:27 PM Bug #13812 (Resolved): pgs stuck creating in upgrade test hammer->hammer.?->jewel
- http://pulpito.ceph.com/teuthology-2015-11-09_17:02:01-upgrade:hammer-x-jewel-distro-basic-multi/1143830/
- 11:28 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- @smithfarm, I meant to backport just https://github.com/ceph/ceph/pull/5309. Let me know if you think entire 5173 ne...
- 11:15 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Partial backport of https://github.com/ceph/ceph/pull/5173
- 11:05 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- -https://github.com/ceph/ceph/pull/6611-
- 11:09 PM rbd Bug #13727 (Resolved): TestClsRbd.snapshot failure
- cherry-picked to jewel
- 09:37 PM rbd Bug #13727: TestClsRbd.snapshot failure
- Still in run http://pulpito.ceph.com/teuthology-2015-11-09_17:02:01-upgrade:hammer-x-jewel-distro-basic-multi/
- 10:40 PM rbd Backport #13387 (Resolved): librbd: reads larger than cache size hang
- 10:38 PM Bug #13811: "osd/ReplicatedPG.cc: 10525: FAILED assert(obc)" in upgrade:firefly-hammer-x-jewel-di...
- maybe http://tracker.ceph.com/issues/13185 investigating
- 09:51 PM Bug #13811 (Can't reproduce): "osd/ReplicatedPG.cc: 10525: FAILED assert(obc)" in upgrade:firefly...
- Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_21:36:48-upgrade:firefly-hammer-x-jewel-distro-basi...
- 10:34 PM Revision 1a626675 (ceph): admin/build-doc: add lxml dependencies on debian
- Some parts of the docs require libxml2 in order to build. We were
already checking for these lxml dependencies on Fed... - 10:33 PM Revision 00a9ce74 (ceph): tests: fix typo in TestClsRbd.snapshots test case
- Fixes: #13727
Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit 3b39226709b2fd7122b75fda... - 09:41 PM Revision 2622993c (ceph): 10.0.0
- 09:26 PM rbd Bug #13810 (Resolved): "stderr:rbd.InvalidArgument: error writing to test_notify_clone)" in upgra...
- Run: http://pulpito.ceph.com/teuthology-2015-11-12_23:20:02-upgrade:client-upgrade-jewel-distro-basic-multi/
Job: 11... - 09:06 PM Revision 69306010 (ceph): Merge pull request #6354 from theanalyst/wip-13387-hammer
- librbd: reads larger than cache size hang
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 07:21 PM Revision 6bf5c875 (ceph): Merge pull request #6607 from dillaman/wip-13784
- rbd: support negative boolean command-line optionals
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:20 PM Revision b66af10f (ceph): Merge pull request #6606 from dillaman/wip-13806
- rbd: add missing command aliases to refactored CLI
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:07 PM CephFS Backport #13809 (In Progress): hammer: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS ...
- 07:05 PM CephFS Backport #13809 (Resolved): hammer: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- https://github.com/ceph/ceph/pull/6604
- 07:00 PM rbd Bug #13804: rbd/copy.sh: hangs with features/layering.yaml msgr-failures/many.yaml (hammer)
- Looks to me like the ms failure injection just got unlucky and failed auth enough to make the client back off and eve...
- 06:12 PM rbd Bug #13804: rbd/copy.sh: hangs with features/layering.yaml msgr-failures/many.yaml (hammer)
- Wait a few weeks before declaring this "Can't reproduce"
- 06:12 PM rbd Bug #13804: rbd/copy.sh: hangs with features/layering.yaml msgr-failures/many.yaml (hammer)
Re-run failed job...- 03:33 PM rbd Bug #13804 (Can't reproduce): rbd/copy.sh: hangs with features/layering.yaml msgr-failures/many.y...
- http://pulpito.ceph.com/loic-2015-11-12_15:36:25-rbd-hammer-backports---basic-multi/1147551/...
- 06:48 PM Revision c2daf09f (ceph): Merge pull request #6289 from dillaman/wip-13461-hammer
- librbd: invalidate object map on error even w/o holding lock
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 06:33 PM rbd Bug #13784 (Fix Under Review): rbd: new cli arg parsing doesn't handle negative boolean common op...
- *master PR*: https://github.com/ceph/ceph/pull/6607
- 04:50 PM rbd Bug #13784 (In Progress): rbd: new cli arg parsing doesn't handle negative boolean common options
- 06:31 PM Revision 5aa840af (ceph): rbd: support negative boolean command-line optionals
- Fixes: #13784
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 06:27 PM Revision d8854890 (ceph): common: mirror leveldb default tuning w/ rocksdb
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:27 PM Revision 6df48f8e (ceph): os/newstore: disable rocksdb compression
- This has been shown to be problematic for performance on the
monitor. Note that this takes us from ~170/bytes per on... - 06:27 PM Revision ae516d7d (ceph): mon: disabled rocksdb compression when used as the backend
- This significantly reduced CPU utilization on the bigbang scale
testing cluster at CERN. Note that it is already dis... - 06:23 PM Revision ba60bf05 (ceph): os/fs/FS: fix zero()'s PUNCH_HOLE incancation
- We get EOPNOTSUPP unconditionally without KEEP_SIZE.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:23 PM Revision 7f07e1ee (ceph): os/newstore: set rocksdb default options
- max_write_buffer_number=16
min_write_buffer_number_to_merge=6
This cuts the amount of short-lived WAL data that get... - 06:23 PM Revision 9c0ae4b8 (ceph): os/newstore: newstore_backend_options -> newstore_rocksdb_options
- This way we can have default settings per-backend. Also note that
this is what we currently do with leveldb on the m... - 06:23 PM Revision 22c9310b (ceph): os/newstore: remove newstore_db_path option
- It is simpler to have fixed locations and symlinks.
Signed-off-by: Sage Weil <sage@redhat.com> - 06:23 PM Revision 0dac747c (ceph): os/newstore: distinguish between db open and create
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:23 PM Revision eddb00bd (ceph): os/RocksDBStore: set up $path.wal -> $path symlink
- If $path.wal doesn't exist, create it and symlink it to $path.
Set wal_dir to that. This makes it easy to move the w... - 06:23 PM Revision 2d921138 (ceph): os/fs/FS: fix zero() return value on fallback
- Signed-off-by: Sage Weil <sage@redhat.com>
- 06:21 PM rbd Bug #13806 (Fix Under Review): rbd: new CLI doesn't support 'snap list' command alias
- *master PR*: https://github.com/ceph/ceph/pull/6606
- 05:19 PM rbd Bug #13806: rbd: new CLI doesn't support 'snap list' command alias
- Also missing the following:
lock ls
snap add
snap revert - 04:48 PM rbd Bug #13806 (Resolved): rbd: new CLI doesn't support 'snap list' command alias
- http://qa-proxy.ceph.com/teuthology/teuthology-2015-11-13_23:00:08-rbd-master---basic-multi/1148826/teuthology.log
- 06:09 PM Backport #13808 (Rejected): infernalis: segfault in Objecter::handle_watch_notify
- https://github.com/ceph/ceph/pull/7993
- 06:09 PM Backport #13807 (Resolved): hammer: segfault in Objecter::handle_watch_notify
- https://github.com/ceph/ceph/pull/7992
- 06:09 PM Bug #11580: pg a copy_from->pg b peered (blocked on backfill blocked on local reservation)->pg a ...
- ubuntu@teuthology:/a/samuelj-2015-11-13_13:43:58-rados-wip-sam-working-distro-basic-multi/1148427/remote
Edit: thi... - 06:03 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Also, that PR claims to be fixing http://tracker.ceph.com/issues/12617 - what is the relationship between that issue ...
- 06:02 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- https://github.com/ceph/ceph/pull/6604 is a backport, to hammer, of https://github.com/ceph/ceph/commit/f04c8da543217...
- 02:15 PM CephFS Bug #13268 (Pending Backport): Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- https://github.com/ceph/ceph/pull/6604/files
- 05:57 PM Revision f58ffdc0 (ceph): tests: new rbd CLI command aliases
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 05:55 PM Revision 1ff68890 (ceph): rbd: add missing command aliases to refactored CLI
- Fixes: #13806
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 05:26 PM Revision 37642a77 (ceph): osd: scrub if load below daily avg and decreasing
- Store a daily loadavg and use as an upper limit on when to allow
scrubs. Also track the 15 minute loadavg and only sc... - 05:18 PM Revision cf408a31 (ceph): ceph_test_msgr: Use send_message instead of keepalive to wakeup connection
- If connection is standby state and call send keepalive, we should reconnect
this connection.
Fix #13797
Signed-off-b... - 05:16 PM Revision b7df772d (ceph): osd: randomize deep scrubbing
- osd_scrub_interval_randomize_ratio works to randomize the shallow scrubs
but doesn't prevent a thundering herd of dee... - 05:12 PM Backport #13205 (Resolved): ReplicatedBackend: populate recovery_info.size for clone (bug symptom...
- 05:12 PM Backport #13336 (Resolved): osd: we do not ignore notify from down osds
- 05:12 PM Backport #13488 (Resolved): object_info_t::decode() has wrong version
- 05:12 PM Backport #13620 (Resolved): osd: pg stuck in replay
- 05:06 PM Revision 1ca72fbe (ceph): Merge pull request #6153 from dachary/wip-13205-hammer
- ReplicatedBackend: populate recovery_info.size for clone (bug symptom is size mismatch on replicated backend on a clo...
- 05:06 PM Revision ca573fe7 (ceph): Merge pull request #6158 from dachary/wip-13336-hammer
- osd: we do not ignore notify from down osds
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:06 PM Revision fdb34461 (ceph): Merge pull request #6335 from Abhishekvrshny/wip-13488-hammer
- object_info_t::decode() has wrong version
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:05 PM Revision f0175668 (ceph): Merge pull request #6401 from SUSE/wip-13620-hammer
- osd: pg stuck in replay
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:52 PM Revision 4bac5c6a (ceph): Merge branch 'jewel' of https://github.com/ceph/ceph-qa-suite into jewel
- 04:35 PM Bug #13805: segfault in Objecter::handle_watch_notify
- ...
- 04:35 PM Bug #13805 (Resolved): segfault in Objecter::handle_watch_notify
- ...
- 04:18 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- Works flawlessly with fuse_multithreaded=false in fstab. No crash after 6 days of operation.
Thanks again! - 04:17 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 02:26 PM devops Bug #13803 (Rejected): ceph-deploy and ceph packages installation issue
- Both packages try to manage the man pages for ceph-deploy and cause ceph to fail installing on any system with ceph-d...
- 02:20 PM Revision 8378aaf3 (ceph): build/ops: rbd-replay moved from ceph-test-dbg to ceph-common-dbg
- http://tracker.ceph.com/issues/13785 Fixes: #13785
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro... - 02:14 PM Bug #13802 (Rejected): osd/osd_types.cc: 459: FAILED assert(m_seed < old_pg_num)
- Increasing the number of placement groups results in crashing Openstack instances. This bug should be fixed in versio...
- 02:07 PM Revision 8f9841d6 (ceph): Merge pull request #6590 from ceph/wip-rbd-user-option
- rbd: accept --user, refuse -i command-line optionals
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:05 PM Revision 9fd0df50 (ceph): Merge pull request #6593 from trociny/fixup-rbd-refactor
- rbd: stripe unit/count set incorrectly from config
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:17 PM Revision 511435f5 (ceph): client: avoid creating orphan object in Client::check_pool_perm()
- Fixes: #13782
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:11 PM Revision 64b104cb (ceph): client: fix deadlock related to async pagecache invalidation
- When mds reovkes Fc capability, client code first invalidates kernel
pagecache, then calls check_caps() to release Fc... - 01:03 PM CephFS Bug #13782: Snapshotted files not properly purged
- the head object is created by Client::check_pool_perm().(we should skip the check for reading snapshot). the reason o...
- 12:10 PM CephFS Bug #13782: Snapshotted files not properly purged
- I've pushed an updated test branch which removes the mid-test assertions to avoid confusion.
Not only are the snap... - 11:43 AM CephFS Bug #13777: Ceph file system is not freeing space
Patch here for the capabilities issue:
https://github.com/ceph/ceph/pull/6601- 10:56 AM Bug #13801: Deep-scrub will crash osd if osd backend is newstore
- https://github.com/ceph/ceph/pull/6599
- 10:54 AM Bug #13801 (Resolved): Deep-scrub will crash osd if osd backend is newstore
- Because of this change (https://github.com/ceph/ceph/pull/6076), the hobject_t will contain pool id, hence the ghobje...
- 09:56 AM CephFS Bug #13800 (Fix Under Review): deadlock when invalidating kernel page cache
- https://github.com/ceph/ceph/pull/6598
- 09:54 AM CephFS Bug #13800 (Resolved): deadlock when invalidating kernel page cache
- ...
- 06:33 AM Revision 28f884e3 (ceph): Merge pull request #6594 from chenji-kael/patch-2
- Update .mailmap
- 04:41 AM Revision ce036944 (ceph): ceph_test_keyvaluedb_iterators: Fix broken test
- Introduced by #6312
Signed-off-by: Haomai Wang <haomai@xsky.com> - 04:17 AM Revision f02a51ff (ceph): scrub: do not assign value if read error for ECBackend
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 04:17 AM Revision 8bb61d3e (ceph): scrub: do not assign value if read error for ReplicatedBackend
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 02:56 AM Revision a8b74641 (ceph): osdservice: state changed to atomic_t to decrease thread context switch.
- service.is_stopping is in the key IO path, hot call, better use spinlock.
Signed-off-by: Xiaowei Chen <chen.xiaowei@... - 02:40 AM Revision b3a12904 (ceph): osd: change mutex to spinlock to optimize thread context switch.
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:25 AM Revision 7fc87e34 (ceph): Update .mailmap
11/15/2015
- 10:10 PM rgw Backport #13799 (Resolved): hammer: rgw: default quota params
- https://github.com/ceph/ceph/pull/7188
- 10:10 PM rgw Backport #13798 (Resolved): infernalis: rgw: default quota params
- https://github.com/ceph/ceph/pull/6636
- 07:37 PM Revision 08fd09a8 (ceph): rbd: stripe unit/count set incorrectly from config
- (after rbd-refactor fixup)
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 06:58 PM Bug #10758 (Resolved): write_full interface of libradosstriper fails on new files
- 06:45 PM Revision 6ad1013a (ceph): Merge pull request #6549 from kylinstorage/global_flags
- fix: use right init_flags to finish CephContext
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 08:14 AM Linux kernel client Bug #12697 (Resolved): [RBD] rbd_dev_id_put causes system crash
- rbd: don't free rbd_dev outside of the release callback, merged into 4.4-rc1.
- 08:10 AM Linux kernel client Bug #12538 (Resolved): An image with a long clone chain blows up kernel stack
- 02:45 AM Revision d5bf38e6 (ceph): Merge pull request #6575 from ceph/update-infernalis-releasenotes
- doc: update infernalis release notes
- 02:44 AM Revision 16f23abb (ceph): Merge pull request #6484 from XinzeChi/wip-journal-optimization
- os: write file journal optimization
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: David Zafman <dzafman@redh... - 02:42 AM Revision 6becf839 (ceph): Merge pull request #6371 from liewegas/wip-osd-less-crush
- osd: avoid calculating crush mapping for most ops
Reviewed-by: Samuel Just <sjust@redhat.com> - 02:41 AM Revision 3a5e0a3d (ceph): Merge pull request #6416 from rohanmars/wip-solaris-port
- librados: Solaris port
Reviewed-by: Sage Weil <sage@redhat.com> - 02:40 AM Revision b9251b4b (ceph): Merge pull request #6439 from XinzeChi/wip-merge-tnx
- osd: merge local_t and op_t txn to single one
Reviewed-by: Sage Weil <sage@redhat.com> - 02:39 AM Revision 8dd801d8 (ceph): Merge pull request #6547 from xiaoxichen/fix1
- osd: check do_shutdown before do_restart
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:38 AM Revision ef2fec78 (ceph): Merge pull request #6566 from kylinstorage/wip-fix-wrong-use-parenthesis
- osd: fix wrong use of right parenthesis in localized read logic
Reviewed-by: Sage Weil <sage@redhat.com> - 02:37 AM Bug #13797 (Resolved): Messenger/MessengerTest.ClientStandbyTest/0 hang
- /a/sage-2015-11-14_04:50:22-rados-wip-sage-testing---basic-multi/1149191...
11/14/2015
- 09:35 PM Revision 481bb2ce (ceph): rbd: accept --user, refuse -i
- --user is the equivalent of --id (mentioned in docs and ceph -h) and
used by at least a couple of qa scripts and teut... - 07:08 PM Backport #13693 (In Progress): bug with cache/tiering and snapshot reads [merged, needs a test in...
- 07:07 PM Backport #13693: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- Since the upstream PR needed an additional test case in the qa suite, for the backport PR, it may be necessary to add...
- 07:02 PM Revision 03784457 (ceph): osd: fix the snapshot reads of evicted tiering pool
- reset ssc->exsits in finish_ctx() if the ctx->cache_evict is true, and
the head is removed.
Fixes: #12748
Signed-off... - 06:59 PM Backport #13770 (In Progress): Objecter: pool op callback may hang forever.
- 06:57 PM rbd Backport #13758 (In Progress): rbd: pure virtual method called
- 06:53 PM Revision bddbda12 (ceph): Objecter: pool_op callback may hang forever.
- pool_op callback may hang forever due to osdmap update during reply handling.
Fixes: #13642
Signed-off-by: xie xinggu... - 06:49 PM Revision 112c686f (ceph): WorkQueue: new PointerWQ base class for ContextWQ
- The existing work queues do not properly function if added to a running
thread pool. librbd uses a singleton thread ... - 06:47 PM rbd Backport #13755 (In Progress): QEMU hangs after creating snapshot and stopping VM
- 06:45 PM rbd Backport #13753 (In Progress): Avoid re-writing old-format image header on resize
- 06:41 PM Revision b3b7877f (ceph): tests: new test case to catch deadlock on RBD image refresh
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit a9729d9553e7fb925509cad8d388cf52a9fede9c) - 06:41 PM Revision 9c33dcca (ceph): librbd: fixed deadlock while attempting to flush AIO requests
- In-flight AIO requests might force a flush if a snapshot was created
out-of-band. The flush completion was previousl... - 06:39 PM Revision a3223173 (ceph): librbd: resize should only update image size within header
- Previously, the whole RBD image format 1 header struct was
re-written to disk on a resize operation.
Fixes: #13674
B... - 06:15 PM rgw Bug #13796 (Resolved): ERROR: testContainerListing, list index out of range
- /a/sage-2015-11-14_04:50:22-rados-wip-sage-testing---basic-multi/1149135...
- 06:12 PM Bug #12814: flipping the overlay from forward to seems to reorder writes
- /a/sage-2015-11-14_04:50:22-rados-wip-sage-testing---basic-multi/1149284
- 05:50 PM Revision 02acff39 (ceph): Merge pull request #6584 from dachary/wip-test
- tests: ignore test-suite.log
Reviewed-by: Sage Weil <sage@redhat.com> - 05:27 PM Revision 118fc222 (ceph): Merge pull request #6583 from ceph/wip-krbd-map-args
- rbd: unbreak rbd map + cephx_sign_messages option
Reviewed-by: Sage Weil <sage@redhat.com> - 04:57 PM Revision 8629b61b (ceph): tests: ignore test-suite.log
- Now that the tests at the top level directory are run via TESTS and not
check-local:, the test-suite.log file is crea... - 03:39 PM Revision f2432e01 (ceph): rbd: recognize cephx_sign_messages option
- Signed-off-by: Ilya Dryomov <idryomov@redhat.com>
- 03:38 PM Revision 34b2b8f4 (ceph): rbd: unbreak rbd map CLI
- Previously, if snapname wasn't specified we would pass NULL to
krbd_map(), which was a cue for it to use "-" as a sna... - 09:45 AM Revision c6a2ec27 (ceph): tests: fix test case using new api
- Signed-off-by: Xinze Chi <xinze@xsky.com>
- 09:29 AM Revision f40bd4a1 (ceph): Merge pull request #705 from dachary/wip-buildpackages-packaging-hammer
- buildpackages: protect packages-repository
- 09:28 AM Revision 63d8181a (ceph): buildpackages: protect packages-repository
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 4825f64a7c22320b034b020093489bf86a953fca) - 09:27 AM Revision 1877b818 (ceph): Merge pull request #704 from dachary/wip-buildpackages-packaging
- buildpackages: protect packages-repository
- 08:31 AM Revision 4825f64a (ceph): buildpackages: protect packages-repository
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 03:47 AM CephFS Bug #13777: Ceph file system is not freeing space
- ...
- 03:42 AM Revision ae1cae02 (ceph): osd: keep count of outstanding pg stat updates to mon
- Count how many stat updates we have in flight.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:42 AM Revision e2756f9a (ceph): osd: scale mon report interval with timeout backoff
- If we have had to scale the backoff by 3x because the mon is
loaded, scale the min report interval accordingly.
Sign... - 03:42 AM Revision 093478af (ceph): osd: fix pg_stats_queue lock protection
- We are indirectly relying on osd_lock, but that may no longer
work for us in the future. Use the stats lock instead.... - 03:42 AM Revision c131c815 (ceph): osd: limit nubmer of pg stat updates in flight
- There is no reason to heavily pipeline this. If the mon is slow
committing them we should go slow too.
Signed-off-b... - 03:42 AM Revision 2d2e6b2e (ceph): osd: inline do_mon_report
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:42 AM Revision facd36fc (ceph): osd: exponential backoff on pg stats ack timeout
- If we don't get a timely response to our pg stats update we fail
the mon connection and reconnect to a new mon. If t... - 03:42 AM Revision 17d24292 (ceph): osd: remove old stats backoff mechanism
- This would only backoff 2x the configured rate, and is less
robust than the new backoff + decay approach.
Signed-off... - 03:42 AM Revision 75e28c42 (ceph): osd: no stats outstanding when we reset the session
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:35 AM Revision 56dbf7a6 (ceph): osd/OSDMap: cache values for in, up osds
- We already do this for num_osd; do the same for the up and in
counts.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:35 AM Revision 25888bb7 (ceph): message/MLog: include seq in print
- ...so we can disambiguate which log message(s) we have.
Signed-off-by: Sage Weil <sage@redhat.com> - 03:34 AM Revision 28138c65 (ceph): mon/PGMonitor: avoid iterating over all pgs to find stale
- Instead of iterating over all pgs when an osd goes down, make a
set of all osds that might have gone down, and only c... - 02:14 AM Revision 492720e8 (ceph): Merge pull request #6574 from yuyuyu101/fix-broken-kinects
- kv/KineticStore: fix broken split_key
Reviewed-by: Sage Weil <sage@redhat.com> - 12:27 AM Revision 6015bfb2 (ceph): Merge pull request #6571 from dachary/wip-test-run-cli
- tests: restore run-cli-tests
11/13/2015
- 09:22 PM Backport #13792 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- https://github.com/ceph/ceph/pull/6628
- 09:09 PM Backport #13786 (In Progress): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- 06:14 PM Backport #13786 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- https://github.com/ceph/ceph/pull/6580
- 09:06 PM Backport #13791: Objecter: potential null pointer access when do pool_snap_list.
- Sage merged the master PR.
- 09:06 PM Backport #13791 (Resolved): Objecter: potential null pointer access when do pool_snap_list.
- https://github.com/ceph/ceph/pull/6840
- 09:05 PM Backport #13789: Objecter: potential null pointer access when do pool_snap_list.
- Sage merged the master PR.
- 09:05 PM Backport #13789 (Resolved): Objecter: potential null pointer access when do pool_snap_list.
- https://github.com/ceph/ceph/pull/6839
- 09:05 PM Bug #13639: Objecter: potential null pointer access when do pool_snap_list.
- *master PR*: https://github.com/ceph/ceph/pull/6422
- 08:22 PM Bug #13639 (Pending Backport): Objecter: potential null pointer access when do pool_snap_list.
- 09:04 PM Revision 7d926ce7 (ceph): Merge pull request #6578 from dachary/wip-13785-debian-rbd-replay
- build/ops: rbd-replay moved from ceph-test-dbg to ceph-common-dbg
Reviewed-by: Ken Dreyer <kdreyer@redhat.com> - 08:50 PM devops Bug #13788 (Rejected): 403 on http://gitbuilder.ceph.com/ceph-rpm-centos7-x86_64-basic/ref/v0.80....
- Run: http://pulpito.ceph.com/teuthology-2015-11-12_17:21:52-upgrade:firefly-x-hammer-distro-basic-vps/
Job: 1147918
... - 08:39 PM Revision 8d3082df (ceph): Merge pull request #4737 from kylinstorage/wip-temp-based-object-eviction
- osd: improve temperature calculation for cache tier agent
Reviewed-by: Sage Weil - 08:22 PM Revision a8f2e237 (ceph): Merge pull request #6422 from xiexingguo/xxg-wip13639
- librados: fix potential null pointer access when do pool_snap_list
Reviewed-by: Kefu Chai <kchai@redhat.com>
Reviewe... - 08:20 PM Revision bc450675 (ceph): Merge pull request #6486 from XinzeChi/wip-multiple-finisher
- osd: FileStore: support multiple ondisk finish and apply finishers
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed... - 08:20 PM Revision 954ddc83 (ceph): Merge pull request #6518 from kylinstorage/wip-trivial-optimization
- osd: optimize scrub subset_last_update calculation
Reviewed-by: Sage Weil <sage@redhat.com> - 07:59 PM Bug #13787: test-erasure-code.sh: Error EINVAL: The option value '2147483647' seems to be invalid
- Attaching build log for comparison purposes.
- 07:57 PM Bug #13787: test-erasure-code.sh: Error EINVAL: The option value '2147483647' seems to be invalid
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9266/console
- 07:56 PM Bug #13787 (Can't reproduce): test-erasure-code.sh: Error EINVAL: The option value '2147483647' s...
- ...
- 06:40 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9278/console
- 06:13 PM Bug #13785 (Fix Under Review): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- https://github.com/ceph/ceph/pull/6578
- 06:07 PM Bug #13785 (Resolved): rbd-replay-* moved from ceph-test-dbg to ceph-common-dbg as well
- If -dbg packages are upgraded, they will complain with something like:...
- 06:11 PM Revision a0204dc4 (ceph): build/ops: rbd-replay moved from ceph-test-dbg to ceph-common-dbg
- http://tracker.ceph.com/issues/13785 Fixes: #13785
Signed-off-by: Loic Dachary <loic@dachary.org> - 05:47 PM Revision fe012a22 (ceph): tests: avoid bashism
- The shell used by the cli tests is not always bash. Not using the
here-word is also more readable in this specific ca... - 05:33 PM Revision 5281bdde (ceph): rbd: hardcode application name into help
- Avoid dynamically detecting the application name and instead hardcode
the rbd CLI name into the help output.
Signed-... - 05:22 PM Revision cbaed6a8 (ceph): test: Add test cases for xattr and omap ceph-objectstore-tool operations
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:22 PM Revision 92d00f22 (ceph): test: Fix verify() used after import to also check xattr and omap
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:22 PM Revision 9a29c598 (ceph): test: Verify replicated PG beyond just data after vstart
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:22 PM Revision e6f1bdcd (ceph): test: Remove redundant test output
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:22 PM Revision 4666d5ff (ceph): ceph-objectstore-tool: Remove unused function (cleanup)
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 05:22 PM Revision e89f0e1c (ceph): ceph-objectstore-tool: Add dry-run checking to ops missing it
- Update test to check most operations
Signed-off-by: David Zafman <dzafman@redhat.com> - 05:04 PM Revision c549a8cc (ceph): kv/KineticStore: Fix broken split_key
- Introduced by PR #6312
Signed-off-by: Haomai Wang <haomai@xsky.com> - 05:02 PM Revision 2b8c30d4 (ceph): Update infernalis release notes
- Update infernalis release notes
Signed-off-by: Vasu Kulkarni vasu@redhat.com - 04:44 PM Revision d0e9c401 (ceph): tests: restore run-cli-tests
- e4ca468 moved src/test/run-cli-tests from check-local to check_SCRIPTS
but did not add it to the TESTS variable.
Sig... - 04:18 PM Revision 131deb39 (ceph): SIGPIPE suppression for platforms without SO_NOSIGPIPE or MSG_NOSIGNAL
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 03:34 PM rbd Bug #12383 (In Progress): "Segmentation fault rbd()"
- 03:06 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- If this is a bugfix and you want it backported to hammer, please:
# update this ticket with the commit hash(es) an... - 03:01 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Okay, very nice! What was the issue? I would've thought the issue would be in the samba ceph vfs module...
- 02:49 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- the code is included in infernalis
- 02:03 PM CephFS Bug #13268: Secondary groups are not read /w SAMBA 4.2.2 & CEPHFS VFS module
- Any news when the code hits the stable tree?
- 03:06 PM Revision c73e96a3 (ceph): radosgw-admin: fix cli tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 03:05 PM Revision 4ff0368d (ceph): osdmaptool: fix cli tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:53 PM Revision a5b04650 (ceph): crushtool: fix cli tests
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:29 PM CephFS Feature #11903 (Resolved): libcephfs: implement read/write interface support "struct iovec"
- 02:27 PM Revision b7bb2167 (ceph): crushtool: fix cli test help
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:27 PM Bug #13666 (Resolved): "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with as...
- 02:18 PM Revision 2829e9dc (ceph): doc: flesh out MDS auth docs
- ...including updating for 'rwp'.
Signed-off-by: John Spray <john.spray@redhat.com> - 02:16 PM Revision 95538f2c (ceph): tasks/cephfs: test for auth caps pool-setting restriction
- Signed-off-by: John Spray <john.spray@redhat.com>
- 02:15 PM Revision eee4b8f9 (ceph): mds: add MAY_SET_POOL in MDSAuthCaps
- For controlling whether a client is allowed
to modify the pool field in file/dir layouts.
Signed-off-by: John Spray ... - 02:15 PM Revision a536d114 (ceph): mds: apply MAY_SET_POOL in request handling
- Signed-off-by: John Spray <john.spray@redhat.com>
- 02:14 PM Revision 1d03924a (ceph): Merge pull request #6532 from dachary/wip-mailmap
- mailmap: Ubuntu Kylin name changed to Kylin Cloud
Reviewed-by: Li Wang <li.wang@kylin-cloud.com> - 02:04 PM Revision f622301f (ceph): Merge pull request #5848 from storage-zuiwanyuan/wip-nonblock-connect
- msg/async: support of non-block connect in async messenger
Reviewed-by: Haomai Wang <haomai@xsky.com> - 02:03 PM Revision 0fa88ea9 (ceph): Merge pull request #6478 from yuyuyu101/wip-13666
- msg/async: let receiver ack message ASAP
Reviewed-by: Sage Weil <sage@redhat.com> - 01:58 PM Revision 0533cf9d (ceph): osd: fix wrong use of right parenthesis
- Signed-off-by: Jie Wang <jie.wang@kylin-cloud.com>
Reviewed-by: Li Wang <li.wang@kylin-cloud.com> - 01:08 PM Bug #13742 (Fix Under Review): MonitorDBStore::get semantic change triggers regressions
- 12:09 PM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- Pushed https://github.com/ceph/ceph/pull/6564 which fixes this, and other issues.
- 01:05 PM devops Bug #11104 (Fix Under Review): dependency problem with Ceph "Firefly" upstream and EPEL
- 01:37 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- This works for Centos 7.0 (tested on sepia vpms) and on RHEL 7.1 (tested on magna), for rgw, rbd, and rados.
Cento... - 12:37 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- This is fixed by the changes in:
https://github.com/ceph/teuthology/pull/704 - 12:58 PM Revision e508a444 (ceph): ceph.spec.in: fix lttng/babeltrace conditionals
- lttng and babeltrace are build dependencies for rbd-replay-prep. Make
sure the right package names are used. Enable f... - 12:58 PM Revision 6a40e4f1 (ceph): ceph.spec.in: lttng in SLES12 only
- Over in the SUSE sector, we are trying to enable the SLE_12 and openSUSE_13.2
build targets. The lttng/babeltrace stu... - 12:56 PM Revision 19c9546b (ceph): packaging: move rbd-replay* to ceph-common
- The rbd-replay* utilities are useful for Ceph users with RBD clients.
Currently the rbd-replay* utilities ship in the... - 12:46 PM Revision ef011da1 (ceph): Update .organizationmap
- 10:41 AM devops Bug #13776: curl and libcurl packages for debian 8
- Ken Dreyer wrote:
> The reason ceph.com shipped its own libcurl Debian package back in the day is because libcurl ve... - 08:59 AM CephFS Bug #13782: Snapshotted files not properly purged
- John Spray wrote:
> It seems like there is a premature purge happening when the head revision is unlinked, the stray... - 07:57 AM CephFS Bug #13777: Ceph file system is not freeing space
- ...
- 04:21 AM CephFS Bug #13777: Ceph file system is not freeing space
- The output of "rados -p cephfs_data ls" returns no objects. I also ran a rados df: ...
- 04:01 AM CephFS Bug #13777: Ceph file system is not freeing space
- It seems MDS has deleted all object? what is the output of "rados -p cephfs_data ls". If there are leftover objects. ...
- 07:36 AM Revision 0fd8de3f (ceph): msg/async: support of non-block connect in async messenger
- Fixes: #12802
Signed-off-by: Jianhui Yuan <zuiwanyuan@gmail.com> - 07:28 AM Revision 14df4b04 (ceph): Merge pull request #6534 from kylinstorage/wip-trivial-scrub-cleanup
- osd: clarify the scrub result report
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:19 AM Revision f7f55e3d (ceph): scrub: compare omap_digest with each other
- For the authoritative object, auth.digest was compared with
auth_oi.omap_digest. It should compare omap_digest with e... - 07:03 AM Revision 785e58eb (ceph): scrub: clarify the result report
- It may happen that the authoritative object
such that auth.size != be_get_ondisk_size(auth_oi.size),
in that case, cl... - 07:00 AM Revision a3aa565b (ceph): journal: avoid holding lock while marking ops are complete
- There is a possibility of a race if the JournalTrimmer destructor is
waiting for an async op to complete but the op i... - 04:27 AM Revision b5153141 (ceph): librbd: only erase IO events after they are marked safe
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision 10deea8d (ceph): librbd: flush journal entries prior to releasing lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision 4719696c (ceph): cmake: updates for refactored librbd IO path
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision 5cf282a6 (ceph): tests: librbd updates for C++11
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision 25072e4a (ceph): tests: verify librbd journal entries are written to disk
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision b2eb5ab7 (ceph): librbd: addressed possible race conditions / deadlocks from unit testing
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision a1affd87 (ceph): tests: updated librbd ImageWatcher listener signature
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision c67a85e2 (ceph): tests: verify proper handling of librbd replay of IO journal events
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision 107bca75 (ceph): librbd: treat flush op as a write op
- This will ensure that the journal is properly opened to handle
appending events.
Signed-off-by: Jason Dillaman <dill... - 04:27 AM Revision b10398b0 (ceph): osdc: track journal commit tid within ObjectCacher for writes
- Writebacks from the journal will provide the associated journal commit
tid so that writebacks can be delayed until af... - 04:27 AM Revision 00390414 (ceph): librbd: integrate cache with journal
- Cache writeback should be delayed until after journal event has been
commmitted to disk.
Signed-off-by: Jason Dillam... - 04:27 AM Revision fc8b8d62 (ceph): librbd: inform the journal when pending IO safely commits
- When caching is disabled, the AioCompletion notifies the journal that
the update is safe. When caching is enabled, w... - 04:27 AM Revision 9259476d (ceph): librbd: fix integration with journal library
- Valgrind-related updates to the journal library required tweaks to
current implementation of librbd journaling.
Sign... - 04:27 AM Revision e34cd800 (ceph): librbd: add replay support for IO events
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:27 AM Revision d480ad76 (ceph): librbd: add support for removing the journal from disk
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:26 AM Revision a39fcf9e (ceph): tests: add journal support to RBD test cases
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 04:26 AM Revision 03636c93 (ceph): librdb: initial interface with journal library
- Rough draft of journal library integration within librbd. Non-cached
IO paths are now recorded to the journal. Incom... - 04:16 AM Revision 5220d8fa (ceph): Merge branch 'wip-py3'
- pybind: a few more python 3 fixes for rbd and rados
Reviewed-by: David Coles <dcoles@gaikai.com> - 04:01 AM rbd Bug #13784 (Resolved): rbd: new cli arg parsing doesn't handle negative boolean common options
- Generic ceph bool options can be prefixed with no- to turn them off, e.g.:...
- 03:35 AM rgw Bug #13764: Radosgw incomplete files
- Thank you for looking at this Yehuda.
I uploaded the last 500 log lines, but I can reproduce the error and provide... - 03:35 AM Revision ddb1ee9a (ceph): pybind/rbd: decode stat() and list_children() results for py3
- For stat(), only block_name_prefix is filled in - parent and
parent_pool are always blank.
Signed-off-by: Josh Durgi... - 03:35 AM Revision d5bec875 (ceph): pybind/rbd: encode snap_rename args for py3
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 03:35 AM Revision 763ca2a9 (ceph): pybind/test_rbd: convert a few more str to bytes for py3
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 03:35 AM Revision 3515e22e (ceph): pybind/rados: return pool_reverse_lookup() result as a string
- This makes it symmetric with create_pool() in python 3.
Signed-off-by: Josh Durgin <jdurgin@redhat.com> - 03:35 AM Revision ea2a6541 (ceph): pybind/test_rbd: use // for division for py3
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 03:35 AM Revision 1af26747 (ceph): pybind/test_rbd: fix map() usage for py3 compat
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 03:35 AM Revision 3c839b44 (ceph): pybind/rbd: decode parent_info() to str types for py3
- Signed-off-by: Josh Durgin <jdurgin@redhat.com>
- 03:32 AM Revision b7de34bc (ceph): Merge branch 'pybind3' of https://github.com/dcoles/ceph into wip-pybind3
- pybind: Add Python 3 support for rados and rbd modules
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
sr... - 01:30 AM Revision 2a1b9f9a (ceph): updated common library linked objects
- 01:30 AM Revision b7cc9d4f (ceph): Solaris compilation/build changes
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:30 AM Revision 6a3aedd2 (ceph): error code translation logic
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:30 AM Revision f83f10a5 (ceph): solaris big endian fixes
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:30 AM Revision ecab8e1e (ceph): cross platform pthreads
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:30 AM Revision 41eff6b8 (ceph): fix sem_open() call to be compliant
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:30 AM Revision 4512ed58 (ceph): import missing free function definition
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:29 AM Revision 671ab30a (ceph): stdin/stdout/stderr clash with standard definition, renamed to getter/s...
- Signed-off-by: Rohan Mars <code@rohanmars.com>
- 01:26 AM Revision 615f8f45 (ceph): ceph: Make stdout/stderr always output Unicode (UTF-8)
- If a stream is not interactive, then under Python 2, then the encoding for
stdout/stderr may be None. This means that... - 01:26 AM Revision 0b3435f1 (ceph): pybind: Add decode_cstr helper function
- This function attempts to decode a C-style string into a Python Unicode string.
It accepts an optional "size" paramet... - 01:26 AM Revision 801ea73a (ceph): pybind: Add test for creating pool by raw UTF-8
- Some clients try providing non-ASCII pool names by sending raw encoded bytes.
This check ensures that we still suppor... - 01:26 AM Revision 63f5462c (ceph): pybind: Import cstr from the rados module
- Since rados is required for rbd, we can avoid duplication of code across these
two modules.
Signed-off-by: David Col... - 01:26 AM Revision 47d9ca7d (ceph): pybind: Don't encode str on Python 2
- If you attempt to call encode on a non-ASCII string, then a UnicodeDecodeError
will be raised.
Since str on Python 2... - 01:20 AM rbd Bug #13727: TestClsRbd.snapshot failure
- Fix is on master branch (looks like jewel branch was reset to master shortly between the bug introduction and its fix...
- 01:17 AM Revision be9d26f5 (ceph): librbd: prevent concurrent image refreshes
- With multiple concurrent AIO requests, it's possible for multiple
image refreshes to be scheduled.
Signed-off-by: Ja... - 01:17 AM Revision eea016db (ceph): librbd: cleanup ictx_check's handling of owner_lock
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 6be6c3d8 (ceph): librbd: simplify AioImageRequestWQ function signatures
- The ImageCtx is known so there is no need to pass it with each
function call.
Signed-off-by: Jason Dillaman <dillama... - 01:17 AM Revision ca83e4b9 (ceph): librbd: consistent owner_lock handling for AIO paths
- Required moving non-AIO read/write/discard methods to
AioImageRequestWQ to avoid deadlock on lock request.
Signed-of... - 01:17 AM Revision 75240f12 (ceph): tests: updates for AIO locking changes
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 75e26b23 (ceph): librbd: ImageWatcher no longer maintains pending AIO op list
- Previously the ImageWatcher stored delayed ops that were waiting
on the image exclusive lock. This management has be... - 01:17 AM Revision cc0ed06e (ceph): tests: update librbd tests to support new AIO / lock handling
- ImageWatcher is no longer responsible for queueing write ops while
waiting for the exclusive lock.
Signed-off-by: Ja... - 01:17 AM Revision 6f18f045 (ceph): librbd: initial journal entry structures
- New journal entries to cover AIO write/discard/flush operations.
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:17 AM Revision 7d5d1aed (ceph): librbd: simplify watch/notify type encoding
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision eb8d37a1 (ceph): test: encoding: add new librbd journal event type
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 49664166 (ceph): osdc: improved discard_set signature const correctness
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 44a49aa8 (ceph): librbd: re-use common logic between aio_write/discard
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 50e2a6c4 (ceph): librbd: removed ImageWatcher header namespace indentation
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision dcd3a652 (ceph): librbd: added journal::EventEntry::get_event_type() helper
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 750771c6 (ceph): librbd: add new RBD_FEATURE_JOURNALING feature code
- When enabled, all mutable operations against an RBD image
will be recorded to a journal prior to changing the underly... - 01:17 AM Revision 3a9b8698 (ceph): pybind/rbd.py: add new journaling feature code
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 7d5323b9 (ceph): librbd: add support for dynamically enabling/disabling journaling
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 3710c437 (ceph): librbd: removed unused method declarations and definitions
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:17 AM Revision 4c33afbe (ceph): librbd: rename C_AioWrite to C_AioRequest
- This context is used for more than just write requests. It is always
tied to an AioCompletion, so moved request refer... - 01:17 AM Revision b85a5fef (ceph): librbd: rename AioRequest classes to AioObjectRequest
- This better reflects the fact that these represent requests against
an object extent and helps differentiate it from ... - 01:17 AM Revision 8aae868a (ceph): librbd: AIO submissions processed by new AioImageRequestWQ
- New work queue has the ability to suspend write operations, which
should occur when exclusive locking is enabled and ... - 01:17 AM Revision 91177781 (ceph): librbd: refactor AIO request handling
- Move aio_read/write/discard/flush to new AioImageRequest classes
in support of a unified aio queue / journaling.
Sig... - 01:17 AM Revision e0c9b881 (ceph): tests: aio_write/aio_discard have been refactored
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
11/12/2015
- 10:47 PM Linux kernel client Bug #13643: task kworker/u128:1:11460 blocked for more than 120 seconds. with rbd device and dd ...
- hi,
ok so its a known bug.
ceph daemon osd.0 dump_ops_in_flight
{
"ops": [],
"num_ops": 0
}
o... - 10:14 PM rbd Bug #13727 (New): TestClsRbd.snapshot failure
- Still on jewel
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_17:24:14-upgrade:hammer-x-jewel-dis... - 10:11 PM rbd Bug #12383: "Segmentation fault rbd()"
- In run http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_17:24:14-upgrade:hammer-x-jewel-distro-basic-open...
- 10:08 PM Revision 773713b0 (ceph): Merge branch 'wip-13504' of https://github.com/trociny/ceph
- rbd: API: options on image create
Reviewed-by: Josh Durgin <jdurgin@redhat.com>
Conflicts:
src/test/librbd/test_li... - 10:08 PM Bug #13381: osd/SnapMapper.cc: 282: FAILED assert(check(oid)) on hammer->jewel upgrade
- See in jewel
Run: http://pulpito.ovh.sepia.ceph.com:8081/teuthology-2015-11-12_17:24:14-upgrade:hammer-x-jewel-distr... - 09:54 PM Revision eb020b6a (ceph): os: write file journal optimezation
- Currently, there is single write thread for file journal, so it would be bottleneck.
It is important to keep logic of... - 09:19 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- I can send it to you but the mons are no longer running 0.94.5 anymore. They are now on infernalis. The mons kept cra...
- 06:18 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- I've found similar behavior and opened bug #13783. Hoping this is the same bug but not sure.
- 12:20 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- Can you upload the mon's store.db somewhere or send it via email to joao@suse.de ?
This is failing applying an upd... - 09:14 PM Revision 73183845 (ceph): stringify: Enable optimization for GCC only
- Signed-off-by: Evgeniy Firsov <evgeniy.firsov@sandisk.com>
- 07:43 PM Revision c3be44ed (ceph): librbd: API: options on image create
- Pass options as key/value configuration pairs on image create instead
of expanding rbd_create/rbd_clone/rbd_copy for ... - 07:43 PM Revision 102539e1 (ceph): librbd: API: options on image create: update tests
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 07:20 PM Revision aa2d64e8 (ceph): Merge pull request #702 from dachary/wip-buildpackages-giant-hammer
- buildpackages: do not fails for unpackaged files
- 07:19 PM Revision 9bc05de0 (ceph): buildpackages: do not fails for unpackaged files
- Older versions of Ceph have that problem failing would break all upgrade suites.
Signed-off-by: Loic Dachary <loic@d... - 07:18 PM Revision 58eabaae (ceph): Merge pull request #701 from dachary/wip-buildpackages-giant
- buildpackages: do not fails for unpackaged files
- 07:17 PM Revision 8d798c4e (ceph): buildpackages: do not fails for unpackaged files
- Older versions of Ceph have that problem failing would break all upgrade suites.
Signed-off-by: Loic Dachary <loic@d... - 07:01 PM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9235/console
- 06:34 PM Bug #13783: monitors crashing constantly with 0.94.5
- got it. thanks!
- 06:29 PM Bug #13783: monitors crashing constantly with 0.94.5
- Done! They were slightly large so I sent them to you by e-mail.
- 06:19 PM Bug #13783: monitors crashing constantly with 0.94.5
- Yep, looks like a duplicate. Let me make the same request I made on the other ticket: can you share your monitor's st...
- 06:17 PM Bug #13783: monitors crashing constantly with 0.94.5
- Logs now small enough to be attached :)
- 06:07 PM Bug #13783: monitors crashing constantly with 0.94.5
- Logs
- 06:05 PM Bug #13783: monitors crashing constantly with 0.94.5
- Logs
- 06:04 PM Bug #13783 (Duplicate): monitors crashing constantly with 0.94.5
- Deployed a new ceph hammer cluster on hardware using puppet. Last time we tested was with 0.94.3 which went fine, but...
- 06:32 PM Revision 035ea29d (ceph): Merge pull request #6557 from ceph/wip-rbd-cmake-fixes
- cmake: librbd and libjournal build fixes
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:12 PM Revision 6755ada9 (ceph): Merge pull request #700 from ceph/yuriw-patch-1
- Update schedule_rados.sh
- 06:12 PM Revision cebabdf3 (ceph): Update schedule_rados.sh
- Fixed the args order
- 06:07 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- 04:35 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- Since no user level workaround were effective we rebuilt the ubuntu trusty 3.19 kernel with the following patch:
h... - 04:19 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- @laurent @mehdi : could you please summarize what you did to work around the problem ?
- 05:55 PM Revision 49f5a9e8 (ceph): Merge pull request #699 from ceph/wip_rados_subset
- Require -e arg for email address
- 05:53 PM Revision 4a78df07 (ceph): Require -e arg for email address
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 05:34 PM Revision 3ccc3aff (ceph): Merge pull request #6556 from athanatos/wip-cmake-nss
- cmake: add nss as a suffix for pk11pub.h
- 05:12 PM Revision 40522828 (ceph): cmake: add nss as a suffix for pk11pub.h
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 04:59 PM Revision 6c5d601b (ceph): cmake: fix librbd and add src/journal
- librbd was missing a recently added file, src/journal was missing
entirely - this brings the build back.
Signed-off-... - 04:59 PM Revision 0e5a794e (ceph): librbd: provide an out-of-class definition for MAX_DESCRIPTION_OFFSET
- std::min() takes its parameters by reference, so provide a definition
for OptionPrinter::MAX_DESCRIPTION_OFFSET const... - 04:44 PM devops Fix #5900: Create a Python package for ceph Python bindings
- Hey, I've manually created a pypi package for the ceph python bindings, I'll happily remove it once the official pack...
- 04:13 PM Bug #13742 (In Progress): MonitorDBStore::get semantic change triggers regressions
- 04:09 PM Bug #13742 (Resolved): MonitorDBStore::get semantic change triggers regressions
- 04:07 PM Revision cbdabae7 (ceph): Merge pull request #698 from ceph/wip_wip_fix_f-h-x-offline-jewel
- Added %
- 04:05 PM Revision 12ba21d0 (ceph): Added %
- Fixed intall.upgrade syntax
Whitelisted 'reached quota'
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> - 04:02 PM Bug #13522 (Can't reproduce): Apparent deadlock between tcmalloc getting a stacktrace and dlopen ...
- 03:56 PM Revision bdf49e0f (ceph): Added %
- Fixed intall.upgrade syntax
Whitelisted 'reached quota'
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry ... - 03:49 PM Feature #13691 (Resolved): tests: merge src/test/test_rados_tool.sh with qa/workunits/rados/test_...
- 03:42 PM devops Bug #13776: curl and libcurl packages for debian 8
- The reason ceph.com shipped its own libcurl Debian package back in the day is because libcurl version 7.28.0 (and abo...
- 02:42 AM devops Bug #13776 (Rejected): curl and libcurl packages for debian 8
- i use debian 8 with rados gateway multi zone(ceph version 0.94.5 (9764da52395923e0b32908d83a9f7304401fee43)),when i s...
- 03:39 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
- confirmed with sage that it's not the case that we are returning a reference to the caller. reassign myself from this...
- 03:32 PM Bug #12181 (Can't reproduce): test: indep mapping fails because an osd is down
- Did not show up in months (according to the make check failure logs).
- 03:30 PM Bug #12457 (Can't reproduce): tests: run_osd sometime fails
- This did not happen in a long time (according to the fail logs of the make check bot).
- 03:29 PM Feature #13710 (Resolved): test deo support
- Unless I misunderstood something, it looks like Deo is going to be transparent to Ceph.
- 03:23 PM CephFS Bug #13777: Ceph file system is not freeing space
- I ran the command *@ceph daemon mds.ede-c2-mds03 flush journal@* and restarted the MDS. It did not seem to free up an...
- 02:00 PM CephFS Bug #13777 (Fix Under Review): Ceph file system is not freeing space
- https://github.com/ceph/ceph/pull/6553
- 01:33 PM CephFS Bug #13777: Ceph file system is not freeing space
- seems like we forget to set CDentry::STATE_STRAY/CInode::STATE_ORPHAN for stray dentry/inode.
Eric Eastman, could... - 12:51 PM CephFS Bug #13777: Ceph file system is not freeing space
- So it looks like some portion of the strays are getting purged during this log, but you mentioned that there were man...
- 02:59 AM CephFS Bug #13777: Ceph file system is not freeing space
- I noticed the MDS log file did not get attached. It is about 7MB, so maybe too big to upload? You can grab it at:
... - 02:50 AM CephFS Bug #13777 (Resolved): Ceph file system is not freeing space
- I have a Ceph file system that is not freeing space. Using Ceph 9.1.0 I created a file system with snapshots enabled,...
- 03:12 PM Revision 87c3e7a9 (ceph): Merge pull request #697 from dachary/wip-buildpackages-giant
- buildpackages: giant has some unpackaged files
- 03:11 PM Revision 92874938 (ceph): buildpackages: giant has some unpackaged files
- And there really is nothing we can do about it expect ignore them.
Signed-off-by: Loic Dachary <loic@dachary.org> - 03:00 PM Feature #13505 (In Progress): scrub/repair: persist scrub results.
- 02:39 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. fs...
- 02:37 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rbd...
- 02:30 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. rgw...
- 02:29 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. ceph-deploy...
- 02:27 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. powercycle...
- 02:12 PM Revision b5144ed5 (ceph): Merge pull request #696 from dachary/wip-buildpackages-flavor-hammer
- buildpackages: 10GB is too small most of the time
- 02:11 PM Revision 93ce9ad1 (ceph): buildpackages: 10GB is too small most of the time
- Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked from commit 129c5db6c9bc41faa5c52df340776f00ab2db2b6) - 02:11 PM Revision 118e919d (ceph): Merge pull request #695 from dachary/wip-buildpackages-flavor
- buildpackages: 10GB is too small most of the time
- 02:09 PM Revision 129c5db6 (ceph): buildpackages: 10GB is too small most of the time
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 02:07 PM Revision db772b99 (ceph): Merge pull request #685 from dachary/wip-12973-hammer
- failed to encode map e428 with expected crc
- 02:06 PM Revision 3e191585 (ceph): Merge pull request #684 from dachary/wip-12973
- rados: 'failed to encode ...' warnings are normal on upgrades
- 01:57 PM Revision 460c74a0 (ceph): mds: properly set STATE_STRAY/STATE_ORPHAN for stray dentry/inode
- Fixes: #13777
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:54 PM Revision 1ce364b1 (ceph): mailmap: Ubuntu Kylin name changed to Kylin Cloud
- Reviewed-by: Li Wang <li.wang@kylin-cloud.com>
Signed-off-by: Loic Dachary <loic@dachary.org> - 01:53 PM Revision 0d684ad8 (ceph): mailmap: sort files
- Signed-off-by: Loic Dachary <loic@dachary.org>
- 01:40 PM Revision 0ee9fdce (ceph): Merge pull request #6517 from kylinstorage/wip-trivial-bug
- osd: fix bug in last_* PG state timestamps
Reviewed-by: Sage Weil <sage@redhat.com>
Reviewed-by: Kefu Chai <kchai@re... - 01:21 PM Revision 085d8bed (ceph): Merge pull request #6552 from trociny/wip-journal
- journal: incremental improvements and fixes
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 12:52 PM CephFS Bug #13782: Snapshotted files not properly purged
- NB the difference between this and #13777 is that in the other bug, we are seeing strays getting stuck (never getting...
- 12:48 PM CephFS Bug #13782 (Resolved): Snapshotted files not properly purged
Bad behaviour shown up by test TestStrays.test_snapshot_remove on this branch:
https://github.com/ceph/ceph-qa-sui...- 11:53 AM Bug #13781 (Resolved): Random Ceph-osd processes doesn't start upon system restart (rhel 7.1)
- Random ceph-osd processes doesn't get started up when the OSD node restarts. This can happen in any of the OSD nodes,...
- 11:35 AM Revision 0ce234b8 (ceph): Merge pull request #6462 from javacruft/wip/ec-modules
- Build internal plugins and classes as modules
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:33 AM Revision d911641c (ceph): journal: update allocated tid when skipping committed entry in player
- Otherwise, if on image open, there are no any uncommitted entries in
journal, allocated tid is not updated to the lat... - 11:32 AM Revision 926f99bb (ceph): buildpackages: giant has some unpackaged files
- And there really is nothing we can do about it expect ignore them.
Signed-off-by: Loic Dachary <loic@dachary.org> - 10:16 AM CephFS Bug #13729 (Fix Under Review): Daily segfault ll_forget reader couldn't read tag
- Change to "Pending backport" after filling out the "Backport" field (e.g. "infernalis", or "hammer,infernalis") and a...
- 09:03 AM CephFS Bug #13729 (Pending Backport): Daily segfault ll_forget reader couldn't read tag
- https://github.com/ceph/ceph/pull/6551
- 09:04 AM CephFS Bug #13472: ceph-fuse crash
- seems like dup of #13729
- 08:11 AM Revision 0669cba4 (ceph): use new api and fix some wrong flag caller
- Signed-off-by: Yunchuan Wen <yunchuan.wen@kylin-cloud.com>
- 08:10 AM Revision 628f69f1 (ceph): save init flags to CephContext
- The constructor of RadosClient will use CephContext,
and RadosClient.connect func will *always* use 0 as
init_flags t... - 07:41 AM Revision fa79bd97 (ceph): client: use smart pointer to track 'cwd' and 'root_parents'
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 8c45ae1239c934b6727071398a1cfccb6277069e) - 07:35 AM Revision fcafc65e (ceph): client: convert Inode::snapdir_parent to smart pointer
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 89648e7ed56a1299a096b16080e4a52724893bdd) - 07:35 AM Revision 78cca4e3 (ceph): client: use smart pointer to track temporary inode reference
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 217837b89f6adabcf686377a9b3d33d5008b1097) - 07:34 AM Revision bad6f335 (ceph): client: convert CapSnap::in to smart pointer
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 07:34 AM Revision 4bb48ee4 (ceph): client: convert Fh::inode to smart pointer
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit dac11e6b4b1e8766ee5165366cf021d9ee91d3ae) - 07:34 AM Revision 5bebb3ac (ceph): client: use smart pointers in MetaRequest
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit fd02f0f245ccdc1d33c6d24f57267c8fb102618b) - 07:34 AM Revision e18f1aec (ceph): client: convert Dentry::inode to smart pointer
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
(cherry picked from commit 07f580977319110cbdd60c78fff892c85711ef3e) - 07:34 AM Revision a7f6d2ff (ceph): client: hold reference for returned inode
- CLient::make_request() returns pointer of target inode, but it does not
increase reference count of the returned inod... - 05:48 AM Revision 925596a5 (ceph): osd: check do_shutdown before do_restart
- This will save extart boot message when do_shutdown && do_restart == true,
which is the case when rebind failed.
Als... - 03:53 AM Revision b6f223b5 (ceph): Merge pull request #6539 from yehudasa/wip-cmake-fix
- cmake: fix files list
Reviewed-by: Kefu Chai <kchai@redhat.com> - 03:13 AM Bug #13778 (Won't Fix): OSD crash (giant)
- -1> 2015-11-12 11:05:10.798295 7fe9364fc880 5 osd.0 pg_epoch: 657 pg[2.aa(unlocked)] enter Initial
0> 2015... - 12:24 AM Revision 8fc42b8c (ceph): Merge pull request #694 from ceph/wip_fix_f-h-x-offline
- Fixing /hammer-x/f-h-x-offline suite
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 12:19 AM Revision 978d83d9 (ceph): Added %
- Fixed intall.upgrade syntax
Whitelisted 'reached quota'
Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
11/11/2015
- 11:45 PM Bug #13773 (Duplicate): pid files on some OSD's are not created correctly (empty)
- We are running into the issue where some pid files are not created correctly when an OSD starts.
There are 40 OSD'... - 11:24 PM rbd Feature #13772: Add Pool information to 'rbd ls -l' for integration facilitation and efficiency.
- The aforementioned integration can also be for stand-alone monitoring system that needs to understand the RBD-pool st...
- 11:19 PM rbd Feature #13772 (Rejected): Add Pool information to 'rbd ls -l' for integration facilitation and e...
- For purposes of integration, it would greatly benefit systems like OpenStack to have full RBD image hierarchical info...
- 11:24 PM Revision f425c929 (ceph): Merge pull request #693 from ceph/wip_fix_f-h-x-offline
- Fixed install.upgrade syntax
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:54 PM Revision ec1dbd23 (ceph): Added %
- Fixed intall.upgrade syntax
Signed-off-by: Yuri Weinstein <yweinste@redhat.com> - 08:57 PM rbd Feature #13494 (Resolved): Improve rbd CLI bash completion
- 08:08 PM devops Bug #13765 (Resolved): Missing debian jessie ceph-common package in repo
- 06:36 PM devops Bug #13765: Missing debian jessie ceph-common package in repo
- it was in
deb http://ceph.com/debian-infernalis/ jessie main
but apparently it was fixed yesterday :
[ ] ce... - 08:39 AM devops Bug #13765: Missing debian jessie ceph-common package in repo
- Which repo?
- 08:02 PM Revision 44b14883 (ceph): stringify: Reduce CPU usage by reusing stringstream in stringify function
- About 10% CPU reduction and 10% TPS bump in CPU bound workload.
Signed-off-by: Evgeniy Firsov <evgeniy.firsov@sandis... - 07:54 PM Revision 5385883e (ceph): Merge pull request #6316 from dillaman/wip-13494
- rbd: dynamically generated bash completion
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:54 PM Revision 016ed34c (ceph): rados: Minor output changes for consistency across operations
- Signed-off-by: David Zafman <dzafman@redhat.com>
- 07:51 PM Revision 0ce0bc15 (ceph): Merge remote-tracking branch 'origin/jewel'
- 07:20 PM Backport #13771 (Resolved): Objecter: pool op callback may hang forever.
- https://github.com/ceph/ceph/pull/6627
- 07:20 PM Backport #13770 (Resolved): Objecter: pool op callback may hang forever.
- https://github.com/ceph/ceph/pull/6588
- 07:15 PM rbd Bug #13767 (Duplicate): ceph_test_cls_rbd: [ FAILED ] TestClsRbd.snapshots
- Yeah, this is a dup of #13727
- 11:30 AM rbd Bug #13767: ceph_test_cls_rbd: [ FAILED ] TestClsRbd.snapshots
- is this bug duplicated with http://tracker.ceph.com/issues/13727 ?
- 06:11 AM rbd Bug #13767: ceph_test_cls_rbd: [ FAILED ] TestClsRbd.snapshots
- http://qa-proxy.ceph.com/teuthology/haomai-2015-11-10_11:24:27-rados-wip-haomai-testing-distro-basic-multi/1145178/te...
- 06:06 AM rbd Bug #13767 (Duplicate): ceph_test_cls_rbd: [ FAILED ] TestClsRbd.snapshots
- test/cls_rbd/test_cls_rbd.cc:789: Failure
2015-11-10T08:49:17.349 INFO:tasks.workunit.client.0.plana41.stdout:Value ... - 07:01 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- -https://github.com/ceph/ceph/pull/6542-
- 05:33 PM Backport #13769: EC async "fast read" patchset for hammer (EC read latency improvements)
- Backport EC "fast read" patches from master:
Correct commit IDs:... - 05:29 PM Backport #13769 (Rejected): EC async "fast read" patchset for hammer (EC read latency improvements)
- Backport EC "fast read" patches from master:...
- 06:17 PM Revision b861c174 (ceph): Merge pull request #692 from ceph/wip_fix_f-h-x-offline
- Added %
- 05:47 PM Revision 5c09af29 (ceph): Added %
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 05:43 PM Revision 7a8224a3 (ceph): Merge pull request #691 from ceph/yuriw-patch-2
- Update schedule_rados.sh
- 05:43 PM Revision ef9e43b7 (ceph): Update schedule_rados.sh
- 05:37 PM Revision eb755034 (ceph): Merge pull request #689 from ceph/wip_rados_subset
- Merge pull request #686 from ceph/wip_rados_subset
Reviewed-by: Samuel Just <sjust@redhat.com> - 05:36 PM Revision 9e80ca2e (ceph): Merge pull request #686 from ceph/wip_rados_subset
- Reducing the ammount of resulting jobs scheduled
Fixed the math added comments
Signed-off-by: Yuri Weinstein <yweins... - 05:30 PM Revision f2939aa4 (ceph): Merge pull request #688 from ceph/jewel
- Reducing the ammount of resulting jobs scheduled
- 05:04 PM Revision 6c1a8a91 (ceph): Reducing the ammount of resulting jobs scheduled
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit 92980c3063487b477c1bff71ebb2c403bcdfa7... - 04:55 PM Revision e82cba04 (ceph): Merge pull request #686 from ceph/wip_rados_subset
- Reducing the ammount of resulting jobs scheduled
- 04:38 PM Revision 3ea903e7 (ceph): cmake: fix files list
- Signed-off-by: Yehuda Sadeh <yehuda@redhat.com>
- 04:27 PM Revision 5ed8cdc1 (ceph): tools:print the map infomation in human readable format.
- Signed-off-by: Bo Cai <cai.bo@h3c.com>
- 04:26 PM RADOS Cleanup #13768 (New): Remove tmap support
There isn't any need to keep this code around anymore as far as I know. Maybe we need to e-mail ceph mailing list ...- 04:12 PM Revision 92980c30 (ceph): Reducing the ammount of resulting jobs scheduled
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 03:59 PM rbd Bug #13719 (Resolved): perf dump for librbd socket generates invalid xml due to slash in attribut...
- 03:36 PM rgw Bug #13764: Radosgw incomplete files
- Looking at this log snippet, I can't really tell what's happening. It seems that we try sending back data to the clie...
- 03:04 PM Revision a1b690d9 (ceph): cls::journal: fixup: constify dump functions
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 03:04 PM Revision 0b261e2f (ceph): journal: call metadata shutdown on journal remove
- This fixes error observed when disabling journal:
JournalMetadata: journal watch error: (107) Transport endpoint i... - 03:03 PM Revision 0dd6e0fd (ceph): journal: don't use object_number when comparing positions
- Only tid does matter.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 03:00 PM Revision b9c6ae87 (ceph): journal: make commit and flush params configurable
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 02:44 PM Revision 13bc7beb (ceph): journal: allow alternate pool for journal objects
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 02:43 PM Revision d4a14e0b (ceph): journal: output operators for journal types
- They are going to be used for diagnostic.
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 02:23 PM Revision 384d10db (ceph): Merge pull request #6471 from mslovy/wip-check-reply-guard-again
- osd: avoid double-check for replaying and can_checkpoint() in FileStore::_check_replay_guard
Reviewed-by: Josh Durgi... - 02:17 PM Bug #13642 (Pending Backport): Objecter: pool op callback may hang forever.
- 02:16 PM Revision 33c15895 (ceph): Merge pull request #6426 from xiexingguo/xxg-wip-13642
- librados: fix rare race where pool op callback may hang forever
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:16 PM Bug #13627 (Resolved): mon: last seen election epoch not honored in win_standalone_election()
- 02:15 PM Revision 17c002a0 (ceph): Merge pull request #6407 from renhwztetecs/renhw-wip-13627
- mon: initialize recorded election epoch properly even when standalone
Reviewed-by: Joao Eduardo Luis <joao@suse.de>
... - 02:14 PM Bug #13586 (Resolved): osd: OSD::mkfs does not decode an existing superblock
- 02:14 PM Revision 88fe7810 (ceph): Merge pull request #6385 from Vicente-Cheng/mkfs-does-not-decode-an-exi...
- osd: fix reactivate (check OSDSuperblock in mkfs() when we already have the superblock)
Reviewed-by: Loic Dachary <l... - 02:13 PM devops Cleanup #3015 (Resolved): order of arguments should not matter for init-ceph
- 02:12 PM Revision 7dc16691 (ceph): Merge pull request #6373 from liewegas/wip-promoteon2ndread-ec
- librados: fix PromoteOn2ndRead test for EC
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:11 PM Bug #13566 (Resolved): ReplicatedPG: result code not correctly set in some cases.
- 02:10 PM Revision bddb1259 (ceph): Merge pull request #6520 from trociny/fix-rbd-apply_changes
- rbd: make config changes actually apply
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 02:07 PM Revision c8e47d11 (ceph): Merge pull request #6347 from xiexingguo/xxg-wip-13566
- osd: fixes for several cases where op result code was not checked or set
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:02 PM Revision dde76ae9 (ceph): Merge pull request #5168 from majianpeng/dynamic-control-optracker
- common: allow enable/disable of optracker at runtime
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:00 PM Revision 9c1a4ed6 (ceph): Merge pull request #6089 from SUSE/wip-init-ceph-getopt
- init-ceph: use getopt to make option processing more flexible
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:16 PM rgw Feature #12997: rgw: default quota params
- Yehuda, can you confirm that this feature should be backported? (Ordinarily, features are not eligible for backporting.)
- 12:22 PM rgw Feature #12997 (Pending Backport): rgw: default quota params
- 01:10 PM Revision d4c09697 (ceph): src/init-ceph.in: improve usage message
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 01:10 PM Revision a6d354c6 (ceph): src/init-ceph.in: remove unused variables
- Signed-off-by: Nathan Cutler <ncutler@suse.com>
- 01:10 PM Revision c994c0a9 (ceph): src/init-ceph.in: process command-line options using getopt
- http://tracker.ceph.com/issues/3015 Fixes: #3015
Signed-off-by: Nathan Cutler <ncutler@suse.com> - 12:21 PM rgw Feature #12919 (Duplicate): RGW : setting bucket_quota and user_quota for via ceph.conf
- 11:05 AM Backport #13425 (Resolved): wrong conditional for boolean function KeyServer::get_auth()
- 10:59 AM Revision a79acd41 (ceph): Merge pull request #6213 from SUSE/wip-13425-hammer
- wrong conditional for boolean function KeyServer::get_auth()
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:52 AM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/9175/console
- 09:12 AM RADOS Bug #13766: FileStore always failed to dump open fds when got EMFILE error
- See http://pulpito.ceph.com/haomai-2015-11-10_11:24:27-rados-wip-haomai-testing-distro-basic-multi/1145207/ for a fai...
- 05:49 AM RADOS Bug #13766 (New): FileStore always failed to dump open fds when got EMFILE error
- Because process has hit the hard limit, we couldn't open fd directory to do dump.
- 08:45 AM Revision ff8b06fe (ceph): rbd: RBD::clone2: fix tracepoint
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 08:19 AM Backport #13288 (Resolved): hammer: stuck recovering, unfound hit set due to removing it while !a...
- 08:19 AM Backport #13409 (Resolved): randomize scrub times
- 08:19 AM Backport #13535 (Resolved): LibRadosWatchNotify.WatchNotify2Timeout
- 08:19 AM Backport #13588 (Resolved): OSD::build_past_intervals_parallel() shall reset primary and up_prima...
- 08:19 AM Backport #13590 (Resolved): mon: should not set isvalid = true when cephx_verify_authorizer retur...
- 07:55 AM Revision f661a559 (ceph): Merge pull request #6516 from trociny/wip-13719
- librbd: perf section name: use hyphen to separate components
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:38 AM Revision 3f749b7a (ceph): rbd: make config changes actually apply
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 07:22 AM Revision 738d64c7 (ceph): Doc: add temperature related stuff in documents and test scripts
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 07:22 AM Revision e5789260 (ceph): Mon: add temperature support for existing cache related commands
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 07:22 AM Revision ed7d8796 (ceph): Osd: add a temperature based object eviction policy for cache tiering
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 07:19 AM Revision fbe5526d (ceph): librbd: perf section name: use hyphen to separate components
- "/" and "@" characters make invalid xml format output.
Fixes: #13719
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 07:19 AM Revision 595c1e56 (ceph): tests: rbd/admin_socket: use xmlstarlet when parsing perf dump
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 07:17 AM Revision 9d5bb61e (ceph): Mon: expose commands for temperature related setting
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 06:52 AM Revision e6290946 (ceph): Osd: add two fields to pg_pool_t
- Signed-off-by: MingXin Liu <mingxinliu@ubuntukylin.com>
Reviewed-by: Li Wang <liwang@ubuntukylin.com> - 06:43 AM Revision 1f855456 (ceph): RadosClient: result code overflowed
- pool_requires_alignment and pool_required_alignment may produce overflowed results and need to refactered.
Fixes: #13... - 06:05 AM Revision b30d1b8d (ceph): doc: Adding --cluster option to rbd man page.
- Fixes #13457
Signed-off-by: Vikhyat Umrao <vumrao@redhat.com>
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:05 AM Revision 50504c90 (ceph): Merge pull request #6519 from kylinstorage/wip-revise-organization
- revise organization
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 05:59 AM Revision 3d614933 (ceph): Merge pull request #6336 from Abhishekvrshny/wip-13535-hammer
- LibRadosWatchNotify.WatchNotify2Timeout
Reviewed-by: Sage Weil <sage@redhat.com> - 05:59 AM Revision 147f4372 (ceph): Merge pull request #6391 from SUSE/wip-13590-hammer
- mon: should not set isvalid = true when cephx_verify_authorizer return false
Reviewed-by: Sage Weil <sage@redhat.com> - 05:58 AM Revision 1970e618 (ceph): Merge pull request #6398 from SUSE/wip-13588-hammer
- OSD::build_past_intervals_parallel() shall reset primary and up_primary when begin a new past_interval.
Reviewed-by:... - 05:43 AM Revision 3ab1668c (ceph): Merge pull request #6525 from dillaman/wip-13636-jewel
- WorkQueue: new PointerWQ base class for ContextWQ
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:34 AM rbd Feature #11286 (Resolved): add general journal
- 05:19 AM Revision 42645047 (ceph): Merge branch 'wip-11286' of https://github.com/dillaman/ceph
- Reviewed-by: Josh Durgin <jdurgin@redhat.com>
- 05:18 AM Revision d46d4a98 (ceph): Merge pull request #5987 from dillaman/wip-rbd-refactor
- rbd: refactor cli command handling
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 02:05 AM Revision 01c720b1 (ceph): rbd: hidden 'bash-completion' command dumps all available commands
- It also extracts all available options for a given command for use
which can be used by an improved bash completion s... - 02:05 AM Revision 9ebea48c (ceph): rbd: dynamically generated bash completion
- The rbd CLI bash completion is now dynamically generated by extracting
the available commands and command options fro... - 01:00 AM CephFS Bug #13714: Segmentation fault accessing file using fuse mount
- Sorry for the delay. It took me a bit of time to create a build environment.
The patch fixed my problem. Thanks!
... - 12:05 AM devops Bug #13738: Infernalis CentOS 7 packages depend on Jenkins' venv/bin/python
- Alfredo rebuilt CentOS 7 infernalis packages, re-signed them, and re-uploaded them to the same location on download.c...
- 12:05 AM devops Bug #13746: update wth yum to 9.2.0 from 0.94.5 fails because of faulty(?) rpm dependency
- Alfredo rebuilt CentOS 7 infernalis packages, re-signed them, and re-uploaded them to the same location on download.c...
11/10/2015
- 11:19 PM devops Bug #13738 (Resolved): Infernalis CentOS 7 packages depend on Jenkins' venv/bin/python
- 09:10 PM devops Bug #13738 (In Progress): Infernalis CentOS 7 packages depend on Jenkins' venv/bin/python
- 09:09 PM devops Bug #13738: Infernalis CentOS 7 packages depend on Jenkins' venv/bin/python
- The fix meant to remove several places where a virtualenv was activated. The binaries have since been built and
I a... - 11:19 PM devops Bug #13746 (Resolved): update wth yum to 9.2.0 from 0.94.5 fails because of faulty(?) rpm dependency
- 04:10 PM devops Bug #13746: update wth yum to 9.2.0 from 0.94.5 fails because of faulty(?) rpm dependency
- I'm sorry, looks like I added a duplicate of #13738
- 04:00 PM devops Bug #13746 (Resolved): update wth yum to 9.2.0 from 0.94.5 fails because of faulty(?) rpm dependency
- ...
- 09:58 PM devops Bug #13765 (Resolved): Missing debian jessie ceph-common package in repo
- Hello,
Apparently the package ceph-common for debian jessie is missing in the repo,
thanks for your help
BR
CP - 09:04 PM rbd Backport #13760: unknown argument --quiet in udevadm settle
- Assigning backport to Josh for convenience only, to track the fact that he merged the original PR.
- 09:03 PM rbd Backport #13760 (In Progress): unknown argument --quiet in udevadm settle
- 06:11 PM rbd Backport #13760 (Resolved): unknown argument --quiet in udevadm settle
- https://github.com/ceph/ceph/pull/6530
- 09:02 PM Revision 3d3595f8 (ceph): krbd: remove deprecated --quiet param from udevadm
- This parameter has been removed since systemd 213, so this
effects Fedora 21+, Debian Jessie, and potentially future
... - 09:02 PM Revision 4d81cd19 (ceph): run_cmd: close parent process console file descriptors
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
(cherry picked from commit f46f7dc94139c0bafe10361622416d7dc343d31f) - 08:49 PM rgw Bug #13764 (Closed): Radosgw incomplete files
- Hi,
We have a Ceph cluster running on Ubuntu 14.04 with Hammer 0.94.5-1trusty that is used primarily to storage la... - 08:49 PM Revision 1f21cae1 (ceph): Merge pull request #681 from ceph/wip-fio-ver
- Update fio version from 2.2.9 to 2.2.11
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:47 PM Revision 769512cf (ceph): rados: 'failed to encode ...' warnings are normal on upgrades (part 2)
- http://tracker.ceph.com/issues/12973 Fixes: #12973
Signed-off-by: Loic Dachary <loic@dachary.org>
(cherry picked fro... - 08:28 PM Revision 4cbf1770 (ceph): rados: 'failed to encode ...' warnings are normal on upgrades
- http://tracker.ceph.com/issues/12973 Fixes: #12973
Signed-off-by: Loic Dachary <loic@dachary.org> - 08:23 PM Feature #13702: 'ceph osd pool create' should not require pg_num
- I can have a look at this
- 08:17 PM Revision b748c358 (ceph): rados: 'failed to encode ...' warnings are normal on upgrades
- Fixes: #12973
Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit 3084453b047ca8b6bd0ce56e4e5a7ecce... - 07:48 PM Revision 5ba70c8e (ceph): Update fio version from 2.2.9 to 2.2.11
- Also removes fio-version option from yaml since its redundant and if required can be specified in
overrides
Signed-o... - 07:28 PM rbd Bug #13719 (Fix Under Review): perf dump for librbd socket generates invalid xml due to slash in ...
- 06:55 AM rbd Bug #13719: perf dump for librbd socket generates invalid xml due to slash in attribute name
- https://github.com/ceph/ceph/pull/6516
- 12:18 AM rbd Bug #13719: perf dump for librbd socket generates invalid xml due to slash in attribute name
- It won't support the "@" character for a snapshot name, either. I am fine w/ just using a hyphen to separate the com...
- 07:26 PM rbd Bug #13304 (Resolved): "TestLibRBD.Metadata , TestLibRBD.UpdateFeatures" tests failed in upgrade:...
- 07:25 PM rbd Bug #13432 (Resolved): "Mutex.cc: 105: FAILED assert(r == 0)" in rbd run
- Fixed included in fio v2.2.11 release
- 07:24 PM Revision fb83704d (ceph): Merge pull request #6199 from liewegas/wip-randomize-scrub-hammer
- osd: randomize scrub times
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 07:24 PM rbd Bug #13559 (Resolved): FAILED assert(m_ictx->owner_lock.is_locked())
- 07:23 PM Revision 39544718 (ceph): Merge pull request #5825 from tchaikov/wip-12848-hammer
- ReplicatedPG::hit_set_trim osd/ReplicatedPG.cc: 11006: FAILED assert(obc)
Reviewed-by: Loic Dachary <ldachary@redhat... - 07:22 PM rbd Bug #13560 (Pending Backport): unknown argument --quiet in udevadm settle
- 07:20 PM rbd Bug #13745 (Resolved): fio teuthology test using deprecated / removed CLI option
- 01:55 PM rbd Bug #13745 (Fix Under Review): fio teuthology test using deprecated / removed CLI option
- *PR*: https://github.com/ceph/ceph-qa-suite/pull/682
- 01:01 PM rbd Bug #13745 (Resolved): fio teuthology test using deprecated / removed CLI option
- The '--image-features' CLI option was deprecated in infernalis and removed from jewel. The '--image-feature' option ...
- 07:13 PM Bug #13563: "[ FAILED ] LibRadosAioEC.RoundTripSparseReadPP" in upgrade:hammer-x-infernalis-dis...
- ...
- 06:55 PM Revision 6daa1ebc (ceph): tests: updated rbd CLI --image-feature optional
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:42 PM Revision c12f7d23 (ceph): ceph_test_rados_api_tier: fix PromoteOn2ndRead for EC case
- The ec and non-ec cases are copy&pasted code. Yuck. This duplicates the
non-ec fix from 347ac0f8.
Signed-off-by: S... - 06:39 PM Revision c4823d59 (ceph): Merge pull request #683 from dachary/wip-13451-hammer
- rados/objectstore/alloc-hint: need three attached disks
- 06:37 PM devops Bug #13762 (Rejected): infernalis osd fails to start on ubuntu trusty
- Traceback (most recent call last):
File "/usr/bin/ceph-detect-init", line 5, in <module>
from pkg_resources i... - 06:26 PM Linux kernel client Feature #24 (New): mdsc: preallocate reply msgs
- 03:09 PM Linux kernel client Feature #24 (Need More Info): mdsc: preallocate reply msgs
- 06:21 PM Revision 1be02b1d (ceph): rbd: corrected handling of '--image-feature' optional
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 06:14 PM rbd Backport #13761 (Resolved): unknown argument --quiet in udevadm settle
- https://github.com/ceph/ceph/pull/6634
- 06:09 PM rbd Backport #13759 (Resolved): rbd: pure virtual method called
- https://github.com/ceph/ceph/pull/6633
- 06:09 PM rbd Backport #13758 (Resolved): rbd: pure virtual method called
- https://github.com/ceph/ceph/pull/6587
- 06:09 PM rbd Backport #13757 (Rejected): rbd: pure virtual method called
- 06:08 PM rbd Backport #13756 (Resolved): QEMU hangs after creating snapshot and stopping VM
- https://github.com/ceph/ceph/pull/6632
- 06:07 PM rbd Backport #13755 (Resolved): QEMU hangs after creating snapshot and stopping VM
- https://github.com/ceph/ceph/pull/6586
- 06:07 PM rbd Bug #13726 (Pending Backport): QEMU hangs after creating snapshot and stopping VM
- 05:04 PM rbd Bug #13726: QEMU hangs after creating snapshot and stopping VM
- I confirm this is fixed with this PR.
(tested on infernalis) - 06:06 PM rbd Bug #13674 (Pending Backport): Avoid re-writing old-format image header on resize
- 06:04 PM rbd Backport #13754 (Resolved): Avoid re-writing old-format image header on resize
- https://github.com/ceph/ceph/pull/6630
- 06:04 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- Just got done upgrading all of the osds to 0.94.5. The mons were crashing every 2-3 minutes the whole time. After upg...
- 05:11 PM Bug #13748: ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- Apparently the file filed to attach
Failed to load resource: the server responded with a status of 413 (Request En... - 05:05 PM Bug #13748 (Resolved): ceph-mons crashing constantly after 0.94.3->0.94.5 upgrade
- This was posted about on ceph-users but I now have a debug log and didn't want to send a 6mb file to the list.
I a... - 06:04 PM rbd Backport #13753 (Resolved): Avoid re-writing old-format image header on resize
- https://github.com/ceph/ceph/pull/6585
- 06:01 PM rbd Backport #13752 (Rejected): Avoid re-writing old-format image header on resize
- 05:51 PM Bug #13749: possible osd messenger deadlock "hit suicide timeout" in rados-infernalis-distro-basi...
- Here are all of the backtraces
- 05:49 PM Bug #13749: possible osd messenger deadlock "hit suicide timeout" in rados-infernalis-distro-basi...
- Looks deadlocky:
Thread 104 (Thread 0x7fe91ce79700 (LWP 7571)):
#0 __lll_lock_wait () at ../nptl/sysdeps/unix/sy... - 05:42 PM Bug #13749 (Can't reproduce): possible osd messenger deadlock "hit suicide timeout" in rados-infe...
- Run: http://pulpito.ceph.com/teuthology-2015-11-04_21:00:09-rados-infernalis-distro-basic-multi/
Job: 1138922
Logs:... - 05:48 PM Stable releases Tasks #13750 (Resolved): infernalis v9.2.1
- h3. Workflow
* "Preparing the release":http://ceph.com/docs/master/dev/development-workflow/#preparing-a-new-relea... - 05:41 PM rbd Backport #13695 (In Progress): init-rbdmap uses distro-specific functions
- 05:36 PM Revision 20521879 (ceph): init-rbdmap: Rewrite to use logger + clean-up
- This patch rewrites the init-rbdmap init script so that it uses logger
instead of the log_* functions. The patch also... - 05:31 PM Revision f972f384 (ceph): ceph.spec.in: We no longer need redhat-lsb-core
- Drop the redhat-lsb-core dependency as it is no longer necessary on
fedora/rhel.
The other two init scripts do not u... - 05:29 PM rbd Bug #13727: TestClsRbd.snapshot failure
- Seen in run:
http://pulpito.ceph.com/teuthology-2015-11-09_13:42:51-upgrade:hammer-x-jewel-distro-basic-vps/
Jobs: ... - 05:24 PM rbd Bug #13740 (Resolved): librbd: crash on open of image with missing header
- 01:21 PM rbd Bug #13740 (Fix Under Review): librbd: crash on open of image with missing header
- *master PR*: https://github.com/ceph/ceph/pull/6523
- 01:02 PM rbd Bug #13740 (In Progress): librbd: crash on open of image with missing header
- 04:52 AM rbd Bug #13740: librbd: crash on open of image with missing header
- Partial fix, still failing the copy.sh workunit, now in a different way:...
- 04:50 AM rbd Bug #13740 (Resolved): librbd: crash on open of image with missing header
- This happens because perfcounters are no longer initialized before errors can occur, and they're used in the cleanup ...
- 05:10 PM Revision fe00de2c (ceph): rados/objectstore/alloc-hint: need three attached disks
- So they can be mkfs xfs.
http://tracker.ceph.com/issues/13451 Fixes: #13451
Signed-off-by: Loic Dachary <loic@dacha... - 05:01 PM Bug #13013: Cache tier thrashing causes out of order write
- On hammer http://149.202.184.126:8081/ubuntu-2015-11-02_11:32:06-rados-hammer-backports---basic-openstack/75...
- 04:56 PM Revision 7481f43e (ceph): Merge pull request #6488 from xiexingguo/xxg-wip-rados-cleanup
- librados: do cleanup
Reviewed-by: Sebastien Ponce <sebastien.ponce@cern.ch>
Reviewed-by: Kefu Chai <kchai@redhat.com> - 04:55 PM rbd Feature #5003 (Rejected): cinder/nova: don't require ceph.conf on a compute host / support multip...
- obsolete
- 04:54 PM rgw Backport #12856 (In Progress): rgw: missing handling of encoding-type=url when listing keys in bu...
- 04:48 PM Revision 609f256a (ceph): rgw: implement s3 encoding-type for get bucket
- This change introduces handling for the encoding-type request
parameter on the get bucket operation. An object key ma... - 04:44 PM Revision cf6ddc8d (ceph): Merge pull request #682 from ceph/wip-13745-jewel
- rbd_fio: removed deprecated command-line option to rbd CLI
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:42 PM Stable releases Tasks #13356: hammer v0.94.6
- h3. upgrade...
- 01:52 PM Stable releases Tasks #13356: hammer v0.94.6
- This branch has all of the above except "Pull request 6390":https://github.com/ceph/ceph/pull/6390. It has a few more...
- 04:32 PM Revision b54719b0 (ceph): Merge pull request #6523 from dillaman/wip-13740
- librbd: perf counters might not be initialized on error
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 04:31 PM Revision 3e78b18b (ceph): WorkQueue: new PointerWQ base class for ContextWQ
- The existing work queues do not properly function if added to a running
thread pool. librbd uses a singleton thread ... - 04:19 PM rbd Bug #13636 (Fix Under Review): rbd: pure virtual method called
- *jewel PR*: https://github.com/ceph/ceph/pull/6525
- 03:08 PM Bug #13666 (Fix Under Review): "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")"...
- https://github.com/ceph/ceph/pull/6478
- 02:47 PM Linux kernel client Bug #13712: Page allocation failure in Kernel 4.2.3.
- hit this this backtrace also. Also debian backport kernel 4.2.3 .
Ubuntu Wiley is using 4.2.x . Might be often enco... - 02:31 PM Revision 394fbfcc (ceph): Objecter: maybe access wild pointer(op) in _op_submit_with_budget.
- look at "after giving up session lock it can be freed at any time by response handler" in _op_submit,
so the _op_subm... - 02:30 PM Revision 84068f8c (ceph): Objecter: repeated free op->ontimeout.
- repeated free op->ontimeout in SafeTimer::timer_thread::callback->complete
Fixes: #13208
Signed-off-by: Ruifeng Yang... - 02:21 PM Revision b65345e3 (ceph): mds: remove dir dentry from scrubstack after finishing scrube dirfrags
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:21 PM Revision 6e370bbf (ceph): mds: call CDentry::scrub_finished() when skipping special dentry
- Also set the on finish context when starting scrub a dentry, this
avoids deleting context for skipped dentry.
Signed... - 02:21 PM Revision afef58bb (ceph): mds: avoid potenial double get CDentry::PIN_SCRUBQUEUE
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:21 PM Revision 48186fc4 (ceph): mds: re-use C_KickOffScrubs context
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:21 PM Revision b65ace24 (ceph): mds: properly update scrubs_in_progress
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 02:21 PM Revision 50c088b0 (ceph): mds: properly call CDir::scrub_finished()
- call CDir::scrub_finished() after finishing scrub a dirfrag
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 02:03 PM RADOS Bug #13385: cephx: verify_authorizer could not decrypt ticket info: error: NSS AES final round fa...
- > Well, the rotating keyring used for authenticating is protected by a Mutex, but it hands out a reference, so it's p...
- 01:50 PM Revision accb2873 (ceph): rbd_fio: removed deprecated command-line option to rbd CLI
- Fixes: #13745
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:20 PM Revision dd5a263b (ceph): librbd: perf counters might not be initialized on error
- Fixes: #13740
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 12:59 PM Revision 08b4c294 (ceph): PendingReleaseNotes: document updated rbd CLI options
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 12:46 PM Revision 3e657304 (ceph): ReplicatedBackend::prepare_pull: set recover_info.size for clones
- Fixes: #12828
Signed-off-by: Samuel Just <sjust@redhat.com>
(cherry picked from commit 1d3e46bedb9a8c0d2200e39f62f4e2... - 11:58 AM Revision f4f1f57e (ceph): mds: skip scrubbing remote linkage
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 11:54 AM Revision cd71c1a4 (ceph): Merge pull request #6522 from branch-predictor/bp-temporary-mon-fix
- mon: revert MonitorDBStore's WholeStoreIteratorImpl::get
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 11:53 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- Pushed https://github.com/ceph/ceph/pull/6522 with temporary fix.
- 08:55 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- Loic Dachary wrote:
> https://github.com/ceph/ceph/commit/66b7b920cf5a0a9c71212573ef47fb2c7ea9b5ff changed the behav... - 08:34 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- https://github.com/ceph/ceph/commit/66b7b920cf5a0a9c71212573ef47fb2c7ea9b5ff changed the behavior of the function. It...
- 08:11 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- Reverting https://github.com/ceph/ceph/commit/66b7b920cf5a0a9c71212573ef47fb2c7ea9b5ff, the test passes
- 07:59 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- ...
- 07:44 AM Bug #13742: MonitorDBStore::get semantic change triggers regressions
- https://github.com/ceph/ceph/pull/6312 may have introduced a regression
- 07:27 AM Bug #13742 (Resolved): MonitorDBStore::get semantic change triggers regressions
- On master make check...
- 11:50 AM Revision d548b5fb (ceph): mon: revert MonitorDBStore's WholeStoreIteratorImpl::get
- Revert MonitorDBStore's WholeStoreIteratorImpl::get method to state
before commit 66b7b920cf5a0a9c71212573ef47fb2c7ea... - 11:22 AM Documentation #13744 (Resolved): ceph-disk: document osd_mkfs_options_{fstype}
- https://github.com/ceph/ceph/blob/infernalis/src/ceph-disk#L1731
- 11:15 AM Bug #13234 (Resolved): dumpling incrementals do not work properly on hammer and newer
- 11:15 AM Bug #13209 (Resolved): filestore: fix peek_queue for OpSequencer
- 11:15 AM Bug #13199 (Resolved): segfault in agent_work
- 11:15 AM Bug #13089 (Resolved): mon: check for store writeablility before participating in election
- 11:15 AM Bug #13071 (Resolved): objecter: cancellation bugs
- 11:15 AM Bug #12809 (Resolved): hit set clear repops fired in same epoch as map change -- segfault since t...
- 11:15 AM Bug #12570 (Resolved): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- 11:15 AM Bug #12540 (Resolved): osd: avoid multi set osd_op.outdata in tier pool
- 11:15 AM Bug #12515 (Resolved): requeue_scrub when kick_object_context_blocked
- 11:15 AM Bug #12512 (Resolved): FileStore calls syncfs(2) even it is not supported
- 11:14 AM Bug #11786 (Resolved): mon: MonitorDBStore iterator's get_next_key() returns wrong keys
- 11:14 AM CephFS Bug #11758 (Resolved): kernel_untar_build fails on EL7
- 11:14 AM Bug #11330 (Resolved): logrotate reload error on Ubuntu 14.04
- 10:30 AM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- @Zeng I switched to fuse_multithreaded=false in fstab and will report back in a couple of days. I'm on debian wheezy ...
- 03:23 AM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- It's likely been fixed by pull request https://github.com/ceph/ceph/pull/4753 (it's large change, we haven't back-por...
- 10:13 AM Bug #13743 (Won't Fix): objecter: last_tid changed without protection of rwlock
- See Objecter::get_pool_stats().
Shall grab rwlock before increase last_tid, otherwise order of ops' tid may not be c... - 09:50 AM Backport #12948 (Resolved): Heavy memory shuffling in rados bench
- 09:50 AM Backport #13035 (Resolved): requeue_scrub when kick_object_context_blocked
- 09:50 AM Backport #13037 (Resolved): hit set clear repops fired in same epoch as map change -- segfault si...
- 09:50 AM Backport #13040 (Resolved): common/Thread:pthread_attr_destroy(thread_attr) when done with it
- 09:50 AM Backport #13171 (Resolved): objecter: cancellation bugs
- 09:50 AM Backport #13233 (Resolved): mon: include min_last_epoch_clean as part of PGMap::print_summary and...
- 09:49 AM Backport #13337 (Resolved): segfault in agent_work
- 09:49 AM Backport #13338 (Resolved): filestore: fix peek_queue for OpSequencer
- 09:49 AM Backport #13339 (Resolved): mon: check for store writeablility before participating in election
- 09:34 AM Revision 4ad97162 (ceph): Merge pull request #6157 from dachary/wip-13040-hammer
- common/Thread:pthread_attr_destroy(thread_attr) when done with it
Reviewed-by: Sage Weil <sage@redhat.com> - 09:33 AM Revision 92b21532 (ceph): Merge pull request #6155 from dachary/wip-13171-hammer
- objecter: cancellation bugs
Reviewed-by: Sage Weil <sage@redhat.com> - 09:33 AM Revision 1f02886d (ceph): Merge pull request #6152 from dachary/wip-13233-hammer
- mon: include min_last_epoch_clean as part of PGMap::print_summary and PGMap::dump
Reviewed-by: Sage Weil <sage@redha... - 09:33 AM Revision 77df385e (ceph): Merge pull request #6146 from dachary/wip-13337-hammer
- segfault in agent_work
Reviewed-by: Sage Weil <sage@redhat.com> - 09:32 AM Revision 469398f1 (ceph): Merge pull request #6145 from dachary/wip-13338-hammer
- filestore: fix peek_queue for OpSequencer
Reviewed-by: Sage Weil <sage@redhat.com> - 09:32 AM Revision d87d1364 (ceph): Merge pull request #6144 from dachary/wip-13339-hammer
- mon: check for store writeablility before participating in election
Reviewed-by: Sage Weil <sage@redhat.com> - 09:30 AM Revision 717eff9a (ceph): Merge pull request #5891 from Abhishekvrshny/wip-13035-hammer
- requeue_scrub when kick_object_context_blocked
Reviewed-by: Sage Weil <sage@redhat.com> - 09:30 AM Revision e133ddc6 (ceph): Merge pull request #5890 from Abhishekvrshny/wip-13037-hammer
- hit set clear repops fired in same epoch as map change -- segfault since they fall into the new interval even though ...
- 09:24 AM Revision f0189280 (ceph): revise organization
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 09:21 AM Backport #13210 (Resolved): tests : Fixed broken Makefiles after integration of lttng into rados
- 09:21 AM Revision c72306a1 (ceph): Merge pull request #6322 from sponce/WIP-13210-hammer
- tests : BACKPORT #13210 Fixed broken Makefiles after integration of ttng into rados
Reviewed-by: Kefu Chai <kchai@re... - 09:09 AM rgw Bug #12993: RGW/Swift sends an extra byte on error
- I'm looking at a similar problem with sts. If this is the same problem, then you are pretty-printing either json or ...
- 09:07 AM Revision d290b276 (ceph): osd: trivial optimization
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
- 08:32 AM Revision d28698ba (ceph): osd: fix trivial bug
- Signed-off-by: Li Wang <li.wang@kylin-cloud.com>
Reported-by: Jie Wang <jie.wang@kylin-cloud.com> - 07:54 AM Revision 1ace4d03 (ceph): auth: keyring without mon entity type should return -EACCES
- test:
see test.sh:test_mon_caps
before modify:
... - 07:30 AM Revision 15f8ea00 (ceph): Merge pull request #6394 from dillaman/wip-13560
- krbd: remove deprecated --quiet param from udevadm
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:28 AM Revision de95d204 (ceph): Merge pull request #6508 from dillaman/wip-13726
- librbd: deadlock while attempting to flush AIO requests
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 07:27 AM Revision 220ed185 (ceph): Merge pull request #6447 from dillaman/wip-13674
- librbd: resize should only update image size within header
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:23 AM Bug #13741 (Won't Fix): There is an error format in Pgmap printing information
- PGMap::print_summary function to print the following information:
*out << " pgmap v" << version << ": "
<< p... - 06:12 AM Revision ae79f1d1 (ceph): osd: update recovery stats when the recovery completes
- Neither ReplicatedBackend nor ECBackend increments the num_recovered
counter and friends when not doing a local recov... - 03:30 AM CephFS Bug #13714 (Resolved): Segmentation fault accessing file using fuse mount
- 12:19 AM rbd Bug #13711 (Fix Under Review): RBD: formatter session may not be rightfully closed.
- *master PR*: https://github.com/ceph/ceph/pull/6485
- 12:16 AM rbd Bug #13731 (Resolved): TestClsRbd.add_remove_child failure
11/09/2015
- 11:43 PM rgw Feature #13718: rgw:CivetWeb http and https be support in the same time.
- I like the idea of not starting up multiple copies of civetweb. This seems a bit too specialized though. What if I ...
- 08:38 PM rgw Feature #13718: rgw:CivetWeb http and https be support in the same time.
- I took a look at your pull request, overall it looks ok. My question is though whether isn't specifying multiple fron...
- 11:29 PM Revision f7f5a080 (ceph): internal: remove unused local variables
- Remove unused variables bl and bl2 in snap_list and ictx_refresh.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 11:27 PM Revision c8fe5ae3 (ceph): librados: cast oid to object explicitly before call ioctx methods
- Cast oid to object explicitly before call ioctx methods.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 11:26 PM Revision 866d0a08 (ceph): Merge pull request #6513 from ceph/revert-6419-wip-openssl
- Revert 0374bb4a2f5054d606e4aba2d97b5e6765e781b0
- 11:26 PM Revision e986ade8 (ceph): IoCtxImpl: remove unused variable sName
- remove unused local variable sName in rollback.
Signed-off-by: xie xingguo <xie.xingguo@zte.com.cn> - 11:24 PM Revision a5651b86 (ceph): Revert 0374bb4a2f5054d606e4aba2d97b5e6765e781b0
- 09:58 PM devops Bug #13738 (Resolved): Infernalis CentOS 7 packages depend on Jenkins' venv/bin/python
- Installing ceph.x86_64 1:9.2.0-0.el7 and its dependencies failed on centos 7.
File /home/jenkins-build/build/work... - 09:56 PM Revision 0374bb4a (ceph): Merge pull request #6419 from ceph/wip-openssl
- rgw: link against system openssl (instead of dlopen at runtime)
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:36 PM Revision d93a7951 (ceph): Merge pull request #6453 from trociny/wip-2468
- librbd: flush and invalidate cache via admin socket
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 09:27 PM rbd Bug #13727 (Resolved): TestClsRbd.snapshot failure
- 09:26 PM rbd Bug #13727: TestClsRbd.snapshot failure
- Second issue covered by #13731
- 06:38 PM rbd Bug #13727: TestClsRbd.snapshot failure
- For 'TestClsRbd.add_remove_child', OSD log shows that a child was added to the image -- yet the get child call failed...
- 02:07 PM rbd Bug #13727 (Fix Under Review): TestClsRbd.snapshot failure
- *master PR*: https://github.com/ceph/ceph/pull/6504
- 02:06 PM rbd Bug #13727 (In Progress): TestClsRbd.snapshot failure
- 01:59 PM rbd Bug #13727: TestClsRbd.snapshot failure
- ...
- 01:58 PM rbd Bug #13727 (Resolved): TestClsRbd.snapshot failure
- ...
- 08:51 PM rgw Backport #13734: rgw: swift API returns more than real object count and bytes used when retrievin...
- Assigning to Yehuda because he merged the original PR, not because any action is needed.
- 08:50 PM rgw Backport #13734 (In Progress): rgw: swift API returns more than real object count and bytes used ...
- 08:44 PM rgw Backport #13734 (Resolved): rgw: swift API returns more than real object count and bytes used whe...
- https://github.com/ceph/ceph/pull/6512
- 08:50 PM Revision 3d5bfdce (ceph): Merge remote-tracking branch 'gh/infernalis'
- 08:49 PM Revision b62cac6c (ceph): rgw: fix swift API returning incorrect account metadata
- Fixes: #13140
Fix the bug that swift account stat command returns doubled object count and bytes used
Signed-off-by... - 08:48 PM rgw Bug #13140: rgw: swift API returns more than real object count and bytes used when retrieving acc...
- *jewel PR*: https://github.com/ceph/ceph/pull/6047
- 06:40 PM rgw Bug #13140 (Pending Backport): rgw: swift API returns more than real object count and bytes used ...
- Fix merged, commit:754e37a9525e9ce4c82dfa5bb66aa493fb052cfe
- 08:45 PM rgw Backport #13735 (Resolved): rgw: swift API returns more than real object count and bytes used whe...
- https://github.com/ceph/ceph/pull/6635
- 07:30 PM Revision 62f122d4 (ceph): Merge pull request #6511 from liewegas/wip-fix-kv
- kv: fix bug in kv key optimization
Reviewed-by: Samuel Just <sjust@redhat.com>
Reviewed-by: Piotr Dałek <piotr.dalek... - 07:07 PM rbd Bug #13731 (Fix Under Review): TestClsRbd.add_remove_child failure
- https://github.com/ceph/ceph/pull/6511
- 04:44 PM rbd Bug #13731 (Resolved): TestClsRbd.add_remove_child failure
- ...
- 07:03 PM Revision f5ac4a0c (ceph): Merge branch 'wip-12955'
- 07:03 PM Revision 7496741e (ceph): rgw: fix modification to index attrs when setting acls
- Fixes: #12955
- add ACL change after initial population
- populate bufferlist with object attributes
Signed-off-b... - 06:40 PM Revision 9689fe0a (ceph): kv: fix string ctor usage
- When constructing a string from a char* there is only a single
length argument, no offset. The 3 argument variant we... - 06:38 PM Revision 754e37a9 (ceph): Merge pull request #6047 from Sandy4999/wip-13140
- rgw: fix swift API returning incorrect account metadata
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 06:19 PM Revision c26ec99c (ceph): Merge pull request #6504 from dillaman/wip-13727
- tests: fix typo in TestClsRbd.snapshots test case
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:58 PM rbd Backport #13733 (Resolved): misdirected op in rbd balance-reads test
- https://github.com/ceph/ceph/pull/6629
- 05:28 PM CephFS Bug #13730 (Rejected): Impossible to change a file with cephfs in Infernalis
- 05:26 PM CephFS Bug #13730: Impossible to change a file with cephfs in Infernalis
- Oh, Greg and John, I'm so sorry to have disturbed you for this dummy ticket. It's totally my fault:...
- 04:59 PM CephFS Bug #13730: Impossible to change a file with cephfs in Infernalis
- Hmm. Usually this is a symptom of bad OSD capabilities on the client.
You've got "allow class-read object_prefix ... - 04:36 PM CephFS Bug #13730: Impossible to change a file with cephfs in Infernalis
- Another information, here is the curious behaviour is I try the same commands when I mount cephfs via the kernel modu...
- 04:29 PM CephFS Bug #13730 (Rejected): Impossible to change a file with cephfs in Infernalis
- Hi,
I have mounted a cephfs via fuse and I can remove, add files *but I can't change a file*.
In the attached fil... - 04:26 PM rbd Bug #13726 (Fix Under Review): QEMU hangs after creating snapshot and stopping VM
- *jewel PR*: https://github.com/ceph/ceph/pull/6508
- 03:01 PM rbd Bug #13726 (In Progress): QEMU hangs after creating snapshot and stopping VM
- 02:59 PM rbd Bug #13726: QEMU hangs after creating snapshot and stopping VM
- In-flight AIO read request forces an image refresh due to out-of-band snapshot creation. Detecting the newly created...
- 02:02 PM rbd Bug #13726: QEMU hangs after creating snapshot and stopping VM
- I have attached the client log,
the snapshot create command was :
rbd -p pooltest --image vm-162-disk-1 snap cr... - 01:42 PM rbd Bug #13726 (Resolved): QEMU hangs after creating snapshot and stopping VM
- When RBD cache is disabled, taking a snapshot and stopping the VM results in a hung QEMU process. Setting "rbd_non_b...
- 04:22 PM Revision bfeb90e5 (ceph): librbd: fixed deadlock while attempting to flush AIO requests
- In-flight AIO requests might force a flush if a snapshot was created
out-of-band. The flush completion was previousl... - 03:48 PM Revision a9729d95 (ceph): tests: new test case to catch deadlock on RBD image refresh
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 03:45 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- It's 1.3MB. Dropbox link ok? https://www.dropbox.com/s/k38ff7zb7z0czst/log.txt.zip?dl=1
- 03:43 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- The tracker's limited to some pretty small files (1.5MB?). If it's larger than that you can use ceph-post-file and co...
- 03:42 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- retry fileupload with firefox...
- 03:35 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- Sure. Each crash creates 10k lines of recent events. I attached the last 100k lines with more or less the same stack ...
- 03:20 PM CephFS Bug #13729: Daily segfault ll_forget reader couldn't read tag
- The debug output about "reader couldn't read tag" actually has nothing to do with the crash here. There should be a w...
- 02:18 PM CephFS Bug #13729 (Resolved): Daily segfault ll_forget reader couldn't read tag
- Hi,
since upgrading to Giant (v0.94.2) I frequently have been seeing the following segmentation fault daily. Same on... - 02:21 PM Revision 22d27327 (ceph): MOSDRepOpReply: Simple Messenger optimization
- the origin idea is from https://github.com/ceph/ceph/pull/5211.
Signed-off-by: Xinze Chi <xinze@xsky.com> - 02:14 PM Revision 39503f58 (ceph): librbd: perf counter for cache invalidates
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 02:14 PM Revision 0996f9df (ceph): librbd: flush and invalidate cache via admin socket
- Fixes: #2468
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 02:14 PM Revision d33842d2 (ceph): tests: librbd: admin socket commands to flush and invalidate cache
- Signed-off-by: Mykola Golub <mgolub@mirantis.com>
- 02:11 PM Revision c6ee5fa2 (ceph): MOSDRepOp: Simple Messenger optimization
- the origin idea is from https://github.com/ceph/ceph/pull/5211.
Signed-off-by: Xinze Chi <xinze@xsky.com> - 02:10 PM Revision 6ab35330 (ceph): Merge pull request #6312 from liewegas/wip-kv
- kv: optimize and clean up internal key/value interface
Reviewed-by: Piotr Dałek <piotr.dalek@ts.fujitsu.com> - 02:06 PM Revision 3b392267 (ceph): tests: fix typo in TestClsRbd.snapshots test case
- Fixes: #13727
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 02:04 PM Revision b5332742 (ceph): Merge pull request #6300 from XinzeChi/wip-throttle-max
- common: fix reset max in Throttle using perf reset command
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 02:03 PM rbd Bug #13491 (Pending Backport): misdirected op in rbd balance-reads test
- 02:03 PM Revision d74de14f (ceph): Merge pull request #6364 from dillaman/wip-13491
- osd: fix broken balance / localized read handling
Reviewed-by: Kefu Chai <kchai@redhat.com> - 02:03 PM Revision 057d39a1 (ceph): os/osd: disable extra iterator validation
- In a number of loops using ObjectMapIterator, the iterator is validated
twice, first as an loop break condition, then... - 02:03 PM Revision 8ad594fb (ceph): tracing: fix librados signed/unsigned warnings
- Signed-off-by: Sage Weil <sage@redhat.com>
- 02:03 PM Revision 1e3c2fa2 (ceph): kv/LevelDBStore: do not Delete before Put
- A put implicitly overwrites the previous value.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:03 PM Revision 48ceaaf0 (ceph): kv/RocksDBStore: do not Delete before Put
- A put implicitly overwrites the previous value.
Signed-off-by: Sage Weil <sage@redhat.com> - 02:03 PM Revision e184ca23 (ceph): os/LevelDBStore: faster LevelDBTransactionImpl::set
- This patch builds on Sage's idea to reduce bufferlist copying on
::set() calls. Initial patch reduced LevelDB's Slice... - 02:03 PM Revision 76eb04ae (ceph): kv/LevelDBStore: simpler code for single-key fetches
- Often there's a need to fetch value for a specified, single key. Publish
a new method in LevelDB that takes key and p... - 02:03 PM Revision a3f88918 (ceph): os/DBObjectMap: use single-key LevelDB::get method
- Make FileStore use single-key ::get() method for some performance
increase in k/v-heavy workloads.
Signed-off-by: Pi... - 02:03 PM Revision 66b7b920 (ceph): mon/MonitorDBStore: use single-key LevelDB::get() method
- Make MonitorDBStore use single-key ::get() method for some performance
increase in heavy K/V workloads.
Signed-off-b... - 02:03 PM Revision 117f40c6 (ceph): os/KeyValueDB: don't call self.valid() from next() and prev()
- In most loops using ObjectMapIteratorImpl, there is a call to valid()
followed by a call to next(), which calls valid... - 02:03 PM Revision 338b4ed4 (ceph): osd/ReplicatedPG: use bl-based setkeys/rmkeys
- FIXME: what about the tracepoint?
Signed-off-by: Sage Weil <sage@redhat.com> - 01:53 PM Revision 2d8bd53a (ceph): Merge pull request #6502 from dachary/wip-13691-rados-test
- tests: fix test_rados_tools.sh rados lookup
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:40 PM rbd Feature #13500 (Resolved): Optimize clone write path if object-map is enabled
- 01:40 PM rbd Bug #13720 (Resolved): librbd: perf counter section name hase empty id
- 01:39 PM Feature #13691: tests: merge src/test/test_rados_tool.sh with qa/workunits/rados/test_rados_tool.sh
- https://github.com/ceph/ceph/pull/6502
- 01:33 PM Revision d167489a (ceph): Merge pull request #6403 from xinxinsh/wip-13500
- optimize clone write path if object-map is enabled
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:20 PM Revision f05d9776 (ceph): tasks/ceph: fix up whitespace
- ...because otherwise it lights up like a christmas
tree in pycharm.
Signed-off-by: John Spray <john.spray@redhat.com> - 01:20 PM Revision 12790535 (ceph): Merge pull request #6494 from trociny/wip-13720
- librbd: start perf counters after id is initialized
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 01:15 PM Bug #13634 (Can't reproduce): ceph-mon: crash when running ceph-mon --mkfs
- assuming htis is a bad build?
- 11:57 AM Revision 402d181e (ceph): tests: fix test_rados_tools.sh rados lookup
- http://tracker.ceph.com/issues/13691 Fixes: #13691
Signed-off-by: Loic Dachary <loic@dachary.org> - 11:31 AM Revision cbe25efe (ceph): Merge pull request #6464 from dachary/wip-13691-rados-test
- tests: concatenate test_rados_test_tool from src and qa
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:27 AM Revision e43ce71c (ceph): suites/fs: enable all snapshost test scripts
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
- 11:14 AM rgw Bug #13724 (Resolved): rgw:bucket check remove _multipart_ prefix
- root@compiler:/home/dwj/git/ceph/src# ./radosgw-admin bucket check --bucket=key-bkt
[
"_multipart_TODO",
"... - 10:47 AM Backport #13678: systemd: no rbdmap systemd unit file
- Original PR merged by Sage. No action required at this time.
- 10:46 AM Backport #13678 (In Progress): systemd: no rbdmap systemd unit file
- 10:46 AM Revision e55c9c85 (ceph): rgw:bucket check remove _multipart_ prefix
- Fixes: 13724
Signed-off-by: Weijun Duan <duanweijun@h3c.com> - 10:36 AM Bug #13374 (Pending Backport): systemd: no rbdmap systemd unit file
- 10:35 AM Bug #13374: systemd: no rbdmap systemd unit file
- *master PR*: https://github.com/ceph/ceph/pull/6479
- 10:34 AM Revision 8965a494 (ceph): Merge pull request #6497 from ukernel/wip-13714
- client: use null snapc to check pool permission
Reviewed-by: John Spray <john.spray@redhat.com> - 09:50 AM Backport #13692: osd: do not cache unused memory in attrs
- Sage merged the original PR. No action required at this time.
- 09:48 AM Backport #13692 (In Progress): osd: do not cache unused memory in attrs
- 09:47 AM Revision 9643ee65 (ceph): bug fix: osd: do not cache unused buffer in attrs
- attrs only reference the origin bufferlist (decode from MOSDPGPush or
ECSubReadReply message) whose size is much grea... - 07:38 AM Revision 5e8c9d96 (ceph): Merge pull request #5810 from Abhishekvrshny/wip-12948-hammer
- Heavy memory shuffling in rados bench
Reviewed-by: Kefu Chai <kchai@redhat.com> - 06:54 AM CephFS Bug #13714 (Fix Under Review): Segmentation fault accessing file using fuse mount
- https://github.com/ceph/ceph/pull/6497
- 02:40 AM CephFS Bug #13714: Segmentation fault accessing file using fuse mount
- please try the attached patch
- 02:30 AM CephFS Bug #13714: Segmentation fault accessing file using fuse mount
- ...
- 03:51 AM Revision fad3772f (ceph): client: use null snapc to check pool permission
- snap inodes' ->snaprealm can be NULL, so dereferencing it in
check_pool_perm() can cause segment fault. The pool perm... - 03:09 AM Revision 4580cf5d (ceph): qa/workunits/snaps: move snap tests into fs sub-directory
- Signed-off-by: Yan, Zheng <zyan@redhat.com>
11/08/2015
- 08:45 PM Bug #13366 (Duplicate): ceph-deploy: "unable to get 'HEALTH_OK' after waiting 15 minutes" in ceph...
- 08:44 PM Bug #13721 (Duplicate): ceph-deploy: "unable to get 'HEALTH_OK' after waiting 15 minutes" in ceph...
- 06:06 PM Bug #13721: ceph-deploy: "unable to get 'HEALTH_OK' after waiting 15 minutes" in ceph-deploy-hamm...
- Similar to #13366 but on trusty
- 06:05 PM Bug #13721 (Duplicate): ceph-deploy: "unable to get 'HEALTH_OK' after waiting 15 minutes" in ceph...
- Run: http://pulpito.ceph.com/teuthology-2015-11-08_01:10:08-ceph-deploy-hammer-distro-basic-vps/
Job: 1141922
Logs:... - 04:01 PM CephFS Bug #13714: Segmentation fault accessing file using fuse mount
- The file system is very simple with two pools. One data, one metatdata. Created with the command:
ceph fs new ce... - 03:40 PM CephFS Bug #13714: Segmentation fault accessing file using fuse mount
- Was the snapshotted file's layout pointing to a different data pool than other files accessed by that client? Not cl...
- 03:31 PM Bug #13713: Ceph CRC32 algorithm appears broken
- Chris Holcombe wrote:
> I found a mailing list showing a known good crc for castagnoli: http://www.pdl.cmu.edu/maili...
11/07/2015
- 09:27 PM rbd Bug #13720 (Fix Under Review): librbd: perf counter section name hase empty id
- 08:00 PM rbd Bug #13720: librbd: perf counter section name hase empty id
- https://github.com/ceph/ceph/pull/6494/
- 07:48 PM rbd Bug #13720 (Resolved): librbd: perf counter section name hase empty id
- The expected format for librbd perf counter section name is: librbd-%{id}-%{pool}/name[@%{snap}]. But in generated na...
- 08:24 PM Bug #13713: Ceph CRC32 algorithm appears broken
- I found a mailing list showing a known good crc for castagnoli: http://www.pdl.cmu.edu/mailinglists/ips/mail/msg04970...
- 07:57 PM Revision f33dd766 (ceph): librbd: start perf counters after id is initialized
- So the perf counters section name has non-empty id.
Fixes: #13720
Signed-off-by: Mykola Golub <mgolub@mirantis.com> - 07:22 PM rbd Bug #13719: perf dump for librbd socket generates invalid xml due to slash in attribute name
- The easiest fix (workaround) could be not to use "/" as a separator between pool and image name.
- 07:19 PM rbd Bug #13719 (Resolved): perf dump for librbd socket generates invalid xml due to slash in attribut...
- % ceph --format xml --admin-daemon out/client.admin.19285.asok perf dump > /tmp/perf.xml
% xmllint /tmp/perf.xml
/t... - 12:25 PM rgw Documentation #13670: rgw frontends not mentioned in radosgw config-ref
http://tracker.ceph.com/issues/13718
now it civetweb conf ssl like this:
rgw frontends = "civetweb port=443s ...- 12:14 PM rgw Feature #13718: rgw:CivetWeb http and https be support in the same time.
- https://github.com/ceph/ceph/pull/6493
- 12:04 PM rgw Feature #13718 (Resolved): rgw:CivetWeb http and https be support in the same time.
- radosgw/CivetWeb can not support listen http port and https port in the same time
CivetWeb support it by configure... - 10:22 AM rgw Backport #13716 (In Progress): rgw:swift use Civetweb ssl can not get right url
- 09:12 AM rgw Backport #13716 (Resolved): rgw:swift use Civetweb ssl can not get right url
- https://github.com/ceph/ceph/pull/6491
- 10:22 AM Revision 1b06f03b (ceph): rgw:swift use Civetweb ssl can not get right url
- Fixes: #13628
Signed-off-by: Weijun Duan <duanweijun@h3c.com>
(cherry picked from commit e0fd540bf441e2f8276cbd96c60... - 10:20 AM rgw Backport #13717: rgw:swift use Civetweb ssl can not get right url
- Assigned to Yehuda only because he merged the original PR, not because any action is required of him.
- 10:20 AM rgw Backport #13717 (In Progress): rgw:swift use Civetweb ssl can not get right url
- 09:14 AM rgw Backport #13717 (Resolved): rgw:swift use Civetweb ssl can not get right url
- https://github.com/ceph/ceph/pull/6490
- 09:14 AM rgw Bug #13628: rgw:swift use Civetweb ssl can not get right url
- Yehuda, that commit is in master only, so I'm adding infernalis.
- 07:23 AM Bug #13715: RadosClient: result code overflowed!
- BTW, RGWRados::get_required_alignment() shall test ioctx.pool_requires_alignment() first,
otherwise the answer is u... - 07:06 AM Bug #13715 (Resolved): RadosClient: result code overflowed!
- bool librados::RadosClient::pool_requires_alignment(int64_t pool_id)
{
int r = wait_for_osdmap();
if (r < 0) {... - 06:39 AM Bug #13278: ceph-disk fails with bcache as data disk
- I also encountered this issue. My workaround was to format and mount the bcache devices manually, then give ceph-disk...
- 03:18 AM Bug #13697 (Resolved): cls_rbd: object_map_update should return 0 on success, differentiate error...
11/06/2015
- 11:31 PM CephFS Bug #13714 (Resolved): Segmentation fault accessing file using fuse mount
- On a test Ceph cluster running Ceph v9.1.0 with the 4.3.0 Kernel on Trusty, running the Ceph File System with snapsho...
- 11:25 PM Bug #13713 (Rejected): Ceph CRC32 algorithm appears broken
- I was looking at wireshark packets and I wanted to see if I could verify the crc checksums that Ceph is generating an...
- 11:13 PM Revision db85bddf (ceph): FileStore: support multiple ondisk finish and apply finisher
- ondisk finisher and apply finisher wouble be bottleneck in fast
ssd. Because apply finisher should free memory which ... - 10:18 PM Revision a5265d51 (ceph): Merge pull request #6228 from zhouyuan/fix_rgw_delete_exipre
- rgw: fix response of delete expired objects
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 10:16 PM Revision 899d7754 (ceph): Merge pull request #6214 from jmunhoz/wip-bucket-request-payment
- rgw: bucket request payment support
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:58 PM Revision 0507cff4 (ceph): Merge pull request #5969 from rzarzynski/wip-conf-md-add
- rgw: extend rgw_extended_http_attrs to affect Swift accounts and containers as well
Reviewed-by: Yehuda Sadeh <yehud... - 09:48 PM Revision a030e564 (ceph): Merge pull request #5938 from zhuangzeqiang/rgw-cerr
- rgw: clarify the error message when trying to create an existed user
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 09:24 PM Revision 24380c8e (ceph): Merge pull request #6479 from ceph/wip-systemd-rbdmap
- rbdmap: systemd support
Reviewed-by: Kefu Chai <kchai@redhat.com> - 07:39 PM Revision b55a41b5 (ceph): Merge pull request #6467 from fullerdj/wip-13697
- cls_rbd: change object_map_update to return 0 on success, add logging
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 07:33 PM Revision bbd5584b (ceph): Merge pull request #6059 from dwj192/dwj-master-tip
- rgw:mdlog trim add usage prompt
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:03 PM rgw Bug #13628 (Pending Backport): rgw:swift use Civetweb ssl can not get right url
- Merged, commit:c601a807e0161aca9b1dc48e25cfc52c79e03eed
- 07:00 PM Revision c601a807 (ceph): Merge pull request #6408 from dwj192/swift-civetweb-ssl
- rgw:swift use Civetweb ssl can not get right url
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 05:56 PM Revision bda2897c (ceph): client-upgrade: hammer-based test should be used on new client
- Avoid attempting to test new release features that are not available
on older hammer OSDs.
Fixes: #13304
Signed-off-... - 05:37 PM Revision 79ba87aa (ceph): Merge pull request #669 from ceph/wip-13304
- client-upgrade: hammer-based test should be used on new client
http://pulpito.ceph.com/teuthology-2015-11-06_08:55:24... - 04:54 PM Revision d918ff02 (ceph): client-upgrade: hammer-based test should be used on new client
- Avoid attempting to test new release features that are not available
on older hammer OSDs.
Fixes: #13304
Signed-off-... - 04:37 PM Revision 26befe15 (ceph): cls_rbd: change object_map_update to return 0 on success, add logging
- The rbd_object_map_update class method returns the size of the data read
from the object map when no update is necess... - 03:29 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- I created issue #13712 since this report is closed.
- 03:18 PM rbd Bug #8000: SLAB: Unable to allocate memory on node 0
- I seem to have the exact same problem on kernel 4.2.3 so I backtracked to a working kernel which was 3.16.
This bu... - 03:28 PM Linux kernel client Bug #13712 (Resolved): Page allocation failure in Kernel 4.2.3.
- Maybe related to issue #8000, we updated Debian from Wheezy to Jessie, we were using the backport Kernel version 3.16...
- 02:55 PM Bug #13703 (Resolved): librados: wrong passed in argument 'oid' for stat in IoCtx::stat
- 02:41 PM rbd Bug #13711 (Resolved): RBD: formatter session may not be rightfully closed.
- RBD: in do_list and do_disk_usage, formatter sessions may not be rightfully closed on error exit.
- 01:22 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- The issue seems due to a concurrency issue in the ext4 mbcache/xattr code in kernel.
In that case, does 'filestore... - 01:12 PM Bug #13634 (Need More Info): ceph-mon: crash when running ceph-mon --mkfs
- 01:11 PM Bug #13634: ceph-mon: crash when running ceph-mon --mkfs
- Yehuda,
do you still see this crash in master? as we use "ceph-mon mkfs" in vstart.sh and the later is practically... - 12:54 PM Revision 01b6f662 (ceph): Merge pull request #6483 from ceph/wip-fix-doc-build
- doc/releases-notes: fix build error
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 12:52 PM Revision f33282eb (ceph): doc/releases-notes: fix build error
- also change the release year of infernalis from 2014 to 2015
Signed-off-by: Kefu Chai <kchai@redhat.com> - 10:18 AM Feature #13710 (Resolved): test deo support
- Add a teuthology job to the ceph-disk suite to verify Ceph works as expected when the underlying device is managed by...
- 09:48 AM Stable releases Tasks #13571 (Resolved): hammer v0.94.5
- 09:26 AM Revision 9224ac2a (ceph): rbdmap: systemd support
- Fixes: #13374
Signed-off-by: Boris Ranto <branto@redhat.com> - 09:23 AM rgw Bug #13709 (Fix Under Review): init script reload doesn't work on EL7
- 09:01 AM rgw Bug #13709: init script reload doesn't work on EL7
- Pull Request: https://github.com/ceph/ceph/pull/6482
- 08:43 AM rgw Bug #13709 (Resolved): init script reload doesn't work on EL7
- Checked on ceph-radosgw-0.94.5-0.el7.centos.x86_64: ...
- 08:52 AM Revision 1b000aba (ceph): rgw: fix reload on non Debian systems.
- When using reload in non-debian systems, /bin/sh's kill is used to send the HUP signal to the radosgw process.
This k... - 08:35 AM Revision 051a52e5 (ceph): Merge pull request #6476 from xiexingguo/xxg-wip-13703
- librados: wrongly passed in argument for stat command
Reviewed-by: Kefu Chai <kchai@redhat.com> - 08:02 AM Revision 7e11ef77 (ceph): mds:the ceph-mds command option "--hot-standby" is useless.
- Signed-off-by: Wei Feng <feng.wei@h3c.com>
- 07:17 AM rgw Fix #13708: init script doesn't start daemon - errors silently (part 2)
- Ken wrote about http://tracker.ceph.com/issues/10927:
> Given the discussion in the PR on GitHub, some of the issu... - 07:12 AM rgw Fix #13708 (New): init script doesn't start daemon - errors silently (part 2)
- Trying to start the daemon in a RHEL box:...
- 07:15 AM rgw Fix #10927 (Resolved): init script doesn't start daemon - errors silently
- Opening http://tracker.ceph.com/issues/13708 instead of re-opening this ticket, for the purpose of tracking the assoc...
- 04:05 AM CephFS Bug #13689: ceph-mds not build with libjemalloc
- I found that if we move the -ljemalloc option before the -Wl,--as-needed option, libjemalloc will be linked into ceph...
- 01:43 AM Revision 78dbd138 (ceph): ceph.spec.in: add new cls_journal RADOS class
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 3f3be145 (ceph): journal: updates to support C++11
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision ea275cc2 (ceph): tests: journal updates to support C++11
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision ea4971ce (ceph): journal: FutureImpl shouldn't hold lock while invoking callbacks
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision a51d9d85 (ceph): journal: complete flush context w/o holding locks
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision b97bc2b0 (ceph): journal: signal playback complete via finisher thread
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 651e4f7e (ceph): journal: add method to remove journal from disk
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 6c284674 (ceph): journal: JournalPlayer::process_state should support positive result
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision d85ea50c (ceph): tests: update journal tests based on API changes
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 4d3969d6 (ceph): journal: fix issues discovered via valgrind
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 5c2e9ea5 (ceph): tests: fix journal test issues discovered via valgrind
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision bd9880a1 (ceph): cls_journal: EntryPositions is now represented as a list
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 352194d9 (ceph): journal: simplified commit position tracking
- Now the journal player and recorder will allocate a tid to represent
the associated journal entry. The order of thes... - 01:42 AM Revision 1faf96b1 (ceph): tests: updated journal tests to support new commit API
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 2d7f4d04 (ceph): librados_test_stub: assert that no AIO ops are outstanding on destruction
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision a68bf817 (ceph): journal: fix race condition with unwatch on shutdown
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 1acc688a (ceph): librados: don't provide an invalid watch handle on error
- If the linger op was canceled due to an error, don't provide
the caller with the pointer to the invalidated linger op... - 01:42 AM Revision 87e3e05b (ceph): journal: cleanup shutdown handling
- Avoid the case where an intrusive_ptr could be created/destroyed
during shutdown due to resetting the journal header ... - 01:42 AM Revision 2097b4de (ceph): tests: journal test no longer explicitly shuts down crypto
- This is now automatically handled by CephContext.
Signed-off-by: Jason Dillaman <dillaman@redhat.com> - 01:42 AM Revision debe1722 (ceph): journal: new generic journal implementation
- The initial use-case for this journal is for librbd and its mirroring
feature. This journal is different from the cur... - 01:42 AM Revision adfc3c71 (ceph): test/encoding/types.h: add journal::Entry to types
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 7233b8b2 (ceph): tests: initial unit tests for new generic journal library
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 6bd8c0a6 (ceph): journal: move rados_ctx_callback to utils namespace
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 65f86fe5 (ceph): journal: add support for trimming committed journal objects
- As clients periodically mark payloads as committed, the trimmer will
determine the new minimum object set and delete ... - 01:42 AM Revision d2a98753 (ceph): cls_journal: new convenience functions for ObjectSetPosition
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 00c123cb (ceph): tests: updated tests for journal trimmer modifications
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision e7d4f7b3 (ceph): cls_journal: permit empty client id string
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 5f2ab508 (ceph): cls_journal_client: get_immutable_metadata is now asynchronous
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 8fcc38c3 (ceph): tests: cls_journal: get_immutable_metadata is now async
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision d8f7e96e (ceph): journal: added additional callbacks for async ops
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 0b20876a (ceph): journal: add default constructor to Future
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision cd3c378d (ceph): journal: playback should notify when complete
- When not performing a live-playback, the client should be
notified when there are no more records to read.
Signed-of... - 01:42 AM Revision c1dd24ed (ceph): journal: new async flush method for whole journal
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 09beb8ec (ceph): journal: add default constructor to Payload
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 0e1accde (ceph): journal: avoid reentrant callbacks on Future
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 4740a666 (ceph): journal: Journaler::stop_append should be async
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision dc19d57c (ceph): cls_journal: initial implementation of journal class methods
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 0f8d7220 (ceph): cls_journal_client: initial implementation of the cls journal client li...
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 050763f7 (ceph): tests: new cls_journal_client test cases
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 8cee9a27 (ceph): test/encoding/types.h: add cls::journal types
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision c9b873ac (ceph): librados: new AIO version of notify API
- Allow watch/notify notifications to be sent asynchronously so
that they can be safely sent from a librados op callbac... - 01:42 AM Revision 312d4e25 (ceph): tests: new test for librados AIO notify API
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision 8270170f (ceph): librados_test_stub: add support for new aio_notify API
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Revision c11d71c7 (ceph): librados_test_stub: added support for append op
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 01:42 AM Bug #13576: The osd was killed by unkown thread or software.
- I can try do it,let osd konw who kill it.
- 01:02 AM Revision 33aabf27 (ceph): skip copyup if write is write_full
- Signed-off-by: xinxin shu <xinxin.shu@intel.com>
- 01:02 AM Revision 40dcfe2f (ceph): optimize clone write path if object-map is enabled
- Fixes : #13500
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
11/05/2015
- 11:37 PM Revision 2d827d8b (ceph): Merge pull request #668 from ceph/wip-firefly-workunit
- tasks/workunit: Apply several fixes from master
Reviewed-by: Dan Mick <dmick@redhat.com> - 11:32 PM devops Bug #13679 (Resolved): ceph-cm-ansible: correct 'cloud.front' hostnames
- https://github.com/ceph/ceph-cm-ansible/commit/a49991c8d7a9f6718199dd3d548a4a734345bfc8
- 10:55 PM rgw Fix #10927 (New): init script doesn't start daemon - errors silently
- Given the discussion in the PR on GitHub, some of the issues Alfredo described in the initial ticket still remain wit...
- 09:54 PM Revision 84515221 (ceph): tests: additional updates to cli/rbd cram test for updated CLI help
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:49 PM Revision a3b8e2d6 (ceph): rbd: additional common Ceph command-line arguments
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:49 PM Revision 610ddc16 (ceph): rbd: add support for new 'snap rename' command
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:49 PM Revision b2f8363d (ceph): rbd: don't print command help on error
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:12 PM Revision f955ee5c (ceph): tests: fixed deprecated option in run-rbd-tests
- The --format support for specifying either the image format
or display format has been removed. The test now uses th... - 09:12 PM Revision b838ed11 (ceph): qa/workunits/rbd: fixed incorrect stripe settings
- The rbd merge-diff tool does not support fancy striped
image exports. Corrected the test to reflect this fact.
Sign... - 09:12 PM Revision 7ef01dcd (ceph): tests: update cli/rbd cram tests for refactored rbd
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:12 PM Revision 1b9661e2 (ceph): rbd: switched rbd CLI over to refactored codebase
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:12 PM Revision 038ed523 (ceph): common: added getter for retrieving all configuration keys
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:12 PM Revision 9652721a (ceph): rbd: strictly enforce all command-line options
- All config keys are now supported via the CLI, so boost can
enforce all provided options.
Signed-off-by: Jason Dilla... - 09:11 PM Revision ba39d331 (ceph): rbd: move rbd to tools/rbd subdirectory
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:11 PM Revision 77937ed4 (ceph): rbd: support libraries for switching CLI processing to boost
- Added new classes for registering CLI commands and associated
arguments and dynamically generating help messages.
Si... - 09:11 PM Revision c4b219ab (ceph): configure: check for boost regex library support
- Signed-off-by: Jason Dillaman <dillaman@redhat.com>
- 09:11 PM Revision fa4e00f8 (ceph): rbd: stub versions of all existing CLI commands
- All existing CLI command processing has been stubbed out using the
new self-registering command implementation.
Sign... - 09:11 PM Revision c7f71d14 (ceph): rbd: migrated existing command logic to new namespaces
- No logic changes were introduced during the migration, only
syntax changes were necessary.
Signed-off-by: Jason Dill... - 09:10 PM rbd Feature #12678 (Resolved): Support the ability to rename snapshots
- 09:09 PM Revision 2c968db0 (ceph): Merge pull request #5645 from xinxinsh/wip-snap-rename
- implement snapshot rename
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 08:04 PM Revision c0980af3 (ceph): rbdmap: Move do_map and do_unmap shell functions to rbdmap script
- This patch creates rbdmap shell script that is called from init-rbdmap
init script. The patch also renames src/rbdmap... - 06:24 PM Revision 88e0b2c3 (ceph): AsyncConnection: Let receiver ack message ASAP
- Currently dispatchers may exists logic requires ack message ASAP in order to
avoid sender resend messages when socket... - 05:25 PM Revision c17a75a7 (ceph): Merge pull request #5856 from runsisi/wip-misc-remove-dup-test
- librbd: remove duplicate read_only test in librbd::async_flatten
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 05:00 PM rbd Feature #13706 (Resolved): Online sparsify RBD images from the CLI
- With the future introduction of the CMPEXT (compare extent) OSD op, it will become possible to safely detect zeroed-b...
- 03:59 PM rbd Backport #13705 (In Progress): rbd : enable feature objectmap
- 03:58 PM rbd Backport #13705 (Resolved): rbd : enable feature objectmap
- https://github.com/ceph/ceph/pull/6477
- 03:58 PM Revision effaf26a (ceph): librbd : fix enable objectmap feature issue
- Fixes: #13558
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
(cherry picked from commit b0536ebab4e1f34e1ed87fe5ef... - 03:35 PM rbd Bug #13558 (Pending Backport): rbd : enable feature objectmap
- 03:34 PM Revision 72a9fb42 (ceph): Merge pull request #6339 from xinxinsh/wip-13558
- librbd : fix enable objectmap feature issue
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 03:24 PM Bug #13703 (Fix Under Review): librados: wrong passed in argument 'oid' for stat in IoCtx::stat
- https://github.com/ceph/ceph/pull/6476
- 02:52 PM Bug #13703 (Resolved): librados: wrong passed in argument 'oid' for stat in IoCtx::stat
- See
int librados::IoCtx::stat(const std::string& oid, uint64_t *psize, time_t *pmtime)
{
object_t obj(oid);
... - 03:02 PM Bug #13704 (Closed): Inconsistent vs Down PG behavior is counterintuitive
- Had a discussion about this with João at SUSEcon. I pointed out some Ceph behavior that I merely found odd, but João ...
- 02:59 PM Revision 508bd877 (ceph): librados: wrongly passed in argument for stat command
- The first argument of io_ctx_impl->stat() requires an obj(of type object_t), but an oid(of type string) is directly p...
- 01:55 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- I have opened the issue on kernel side: https://bugzilla.kernel.org/show_bug.cgi?id=107301
And got a complete back... - 01:41 PM Revision 01e0a758 (ceph): Merge pull request #6445 from ceph/wip-init-rbdmap
- Init rbdmap patchset.
Reviewed-by: Kefu Chai <kchai@redhat.com> - 01:37 PM rbd Backport #13619: rbd clone issue
- Assigning to Jason because he merged the master PR, not because any action is expected of him.
- 01:36 PM rbd Backport #13619 (In Progress): rbd clone issue
- 01:35 PM Revision c2e7fe98 (ceph): rbd: fix clone issue when we specify image feature
- Fixes: #13553
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
(cherry picked from commit da48dbb8f8c9417343d2ca7819... - 12:31 PM Revision 102f0b19 (ceph): auth/cephx: large amounts of log are produced by osd
- if the auth of osd is deleted when the osd is running, the osd will produce large amounts of log.
Fixes:#13610
Signe... - 12:12 PM Backport #12587 (Resolved): FileStore calls syncfs(2) even it is not supported
- 12:12 PM Revision db0366dd (ceph): Merge pull request #5530 from SUSE/wip-12587-hammer
- FileStore calls syncfs(2) even it is not supported
Reviewed-by: Kefu Chai <kchai@redhat.com> - 10:35 AM Feature #13702 (Closed): 'ceph osd pool create' should not require pg_num
- Given we can set a default for pg_num, I think pg_num should be an optional argument when creating a new pool (like p...
- 10:07 AM devops Fix #5900: Create a Python package for ceph Python bindings
- Ken Dreyer wrote:
> To summarize progress here: that "wip-5900" branch in GitHub will need to be rebased onto the cu... - 09:49 AM Revision 619d8048 (ceph): FileStore::_check_replay_guard avoids double check on replaying and can...
- Already checked in _check_replay_guard, avoid double check in the inner function _check_global_replay_guard
Signed-o... - 06:35 AM Revision 920fc85e (ceph): Merge pull request #6468 from cxwshawn/wip-mail-fix
- modify member info in mailmap
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 01:54 AM Revision c228bd2d (ceph): [mailmap] add member info.
- Signed-off-by: Xiaowei Chen <chen.xiaowei@h3c.com>
- 01:27 AM Linux kernel client Bug #13699 (Can't reproduce): krbd: crash under pblio benchmark
- Kernel version: unknown, running in aws, with provisioned iops volumes beneath the osds
Running pblio (https://git... - 01:16 AM CephFS Bug #13698 (Fix Under Review): Race in TestSessionMap.test_version_splitting
- https://github.com/ceph/ceph-qa-suite/pull/674
+ will need backport for infernalis - 01:11 AM CephFS Bug #13698 (Resolved): Race in TestSessionMap.test_version_splitting
Test is checking OMAP results in destination MDS as soon as source mds finishes "export dir" asok, but completion o...- 01:15 AM Revision c713423b (ceph): tasks/cephfs: fix race in test_sessionmap
- Fixes: #13698
Signed-off-by: John Spray <john.spray@redhat.com> - 12:59 AM Bug #13697 (Resolved): cls_rbd: object_map_update should return 0 on success, differentiate error...
- The rbd_object_map_update class method returns the size of the data read from the object map when no update is necess...
- 12:40 AM Revision 3eccde9d (ceph): Merge tag 'v9.2.0'
- v9.2.0
- 12:38 AM Revision b0536eba (ceph): librbd : fix enable objectmap feature issue
- Fixes: #13558
Signed-off-by: xinxin shu <xinxin.shu@intel.com>
11/04/2015
- 11:36 PM Backport #13341 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- 11:33 PM Backport #13341 (In Progress): ceph upstart script rbdmap.conf incorrectly processes parameters
- 11:26 PM Backport #13341 (Resolved): ceph upstart script rbdmap.conf incorrectly processes parameters
- 11:28 PM CephFS Backport #12097 (Resolved): kernel_untar_build fails on EL7
- 11:28 PM Backport #12483 (Resolved): mon: MonitorDBStore iterator's get_next_key() returns wrong keys
- 11:28 PM CephFS Backport #12590 (Resolved): "ceph mds add_data_pool" check for EC pool is wrong
- 11:28 PM Backport #12923 (Resolved): logrotate reload error on Ubuntu 14.04
- 11:27 PM Backport #13036 (Resolved): osd: avoid multi set osd_op.outdata in tier pool
- 11:27 PM Backport #13195 (Resolved): should recalc the min_last_epoch_clean when decode PGMap
- 11:27 PM Backport #13307 (Resolved): dumpling incrementals do not work properly on hammer and newer
- 09:37 PM Revision 6e87d233 (ceph): doc/release-notes: final infernalis notes
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:37 PM Revision 2ac35be4 (ceph): doc/release-notes: edits from Nathan Cutler
- Signed-off-by: Sage Weil <sage@redhat.com>
- 09:25 PM devops Tasks #13669: remove "rhev" packages from apt-mirror's "lab-extras"
- After looking at the logs, the problem was that yum considered Ceph's qemu-kvm-rhev to obsolete the qemu-kvm that we ...
- 09:09 PM devops Tasks #13669: remove "rhev" packages from apt-mirror's "lab-extras"
- This is causing post-reimage provisioning to fail:...
- 08:53 PM Feature #13641 (In Progress): osd assert is too crudely, maybe notify mon before quit is better.
- 02:53 AM Feature #13641: osd assert is too crudely, maybe notify mon before quit is better.
- ref https://github.com/ceph/ceph/pull/6423, partial implemented, need modify more.
- 08:22 PM rbd Backport #13695 (Resolved): init-rbdmap uses distro-specific functions
- https://github.com/ceph/ceph/pull/6528
- 08:22 PM rbd Backport #13694 (Rejected): init-rbdmap uses distro-specific functions
- 08:20 PM Backport #13693 (Resolved): bug with cache/tiering and snapshot reads [merged, needs a test in ce...
- https://github.com/ceph/ceph/pull/6589
- 08:20 PM Backport #13692 (Resolved): osd: do not cache unused memory in attrs
- https://github.com/ceph/ceph/pull/6499
- 07:40 PM rbd Bug #13553 (Pending Backport): rbd clone issue
- 07:39 PM Revision 0d299c95 (ceph): Merge pull request #6334 from xinxinsh/wip-13533
- rbd : fix clone isssue
Reviewed-by: Jason Dillaman <dillaman@redhat.com> - 06:41 PM rgw Bug #13596 (Resolved): radosgw-admin fails user listing when the user pool's empty
- Merged, commit:c08344fb48aa79662d213a751591c8503f3178df
- 06:40 PM Revision c08344fb (ceph): Merge pull request #6465 from oritwas/wip-13596
- radosgw-admin: metadata list user should return an empty list when user pool is empty
Reviewed-by: Yehuda Sadeh <yeh... - 06:39 PM Bug #12662 (Resolved): ThreadPool add/remove work queue methods not thread safe
- 06:39 PM Backport #13042 (Resolved): ThreadPool add/remove work queue methods not thread safe
- 06:38 PM Revision 22dce751 (ceph): Merge pull request #5889 from Abhishekvrshny/wip-13042-hammer
- ThreadPool add/remove work queue methods not thread safe
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 06:15 PM Bug #13032 (Resolved): client nonce collision due to unshared pid namespaces
- 06:14 PM Backport #13245 (Resolved): client nonce collision due to unshared pid namespaces
- 06:14 PM Revision ed153c13 (ceph): Merge pull request #6151 from dachary/wip-13245-hammer
- client nonce collision due to unshared pid namespaces
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 05:57 PM Revision 78c5b9a2 (ceph): radosgw-admin: metadata list user should return an empty list when pool...
- Fixes: #13596
Signed-off-by: Orit Wasserman <owasserm@redhat.com> - 05:53 PM Bug #13666: "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with async msgr
- Run: http://pulpito.ceph.com/teuthology-2015-10-31_21:00:10-rados-infernalis-distro-basic-multi/
Jobs: ['1133613', '... - 02:58 PM Bug #13666: "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with async msgr
- Oh, so this is just a log trimming/op replay race that the async messenger is making a lot larger than usual. Got it....
- 03:07 AM Bug #13666: "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with async msgr
- For example, osd.0 send three messages to osd.1 successfully, and because of batch ack osd.1 doesn't reply ack to osd...
- 05:51 PM Bug #13594: osd/PG.cc: 2856: FAILED assert(values.size() == 1)
- Still see in http://pulpito.ceph.com/teuthology-2015-10-31_21:00:10-rados-infernalis-distro-basic-multi/
Job - ['113... - 05:31 PM Feature #13691 (Fix Under Review): tests: merge src/test/test_rados_tool.sh with qa/workunits/rad...
- https://github.com/ceph/ceph/pull/6464
- 04:28 PM Feature #13691 (Resolved): tests: merge src/test/test_rados_tool.sh with qa/workunits/rados/test_...
- It would be good for src/test/test_rados_tool.sh to be run by rados/singleton/all/radostool.yaml because it contains ...
- 05:28 PM Revision e8fe4bc5 (ceph): tests: concatenate test_rados_test_tool from src and qa
- It is good for src/test/test_rados_tool.sh to be run by
rados/singleton/all/radostool.yaml because it contains a lot ... - 05:22 PM Revision e2a5ebb1 (ceph): Merge pull request #6340 from joaquimrocha/rados_write_benchmark_new_op...
- Rados write benchmark new options
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 04:04 PM Bug #13690 (Closed): why does osd.11 take a long time to start
- 2015-11-04 11:47:49.104261 7f387c2da800 -1 journal FileJournal::_open: disabling aio for non-block journal. Use jour...
- 03:59 PM CephFS Bug #13689 (Won't Fix): ceph-mds not build with libjemalloc
- Looking against high RAM usage of mds, I found ceph-mds do not linked to libjemalloc. Other daemons - are.
# lddtr... - 02:53 PM CephFS Feature #13688 (Resolved): mds: performance: journal inodes with capabilities to limit rejoin tim...
- It can take a long time to load up inodes. We can use the EOpen event (or similar) to stuff clean inodes into the jo...
- 02:44 PM CephFS Feature #13569 (Fix Under Review): ceph-fuse: support direct IO
- 02:44 PM CephFS Feature #13569: ceph-fuse: support direct IO
- https://github.com/ceph/ceph/pull/6463/files
- 02:39 PM Revision 8f7ca9e3 (ceph): client: bypass objectcacher for direct IO
- Fixes: #13569
Signed-off-by: Yan, Zheng <zyan@redhat.com> - 01:14 PM Documentation #13687 (Closed): Object map vs xattr not really explained
- I could not find in the ceph documentation what is the difference between xattr and object map
(and also what is oma... - 01:01 PM rgw Bug #13613: radosgw problems concurrent downloads
- Very grateful, we found some apache physical problem, the problem has been found
- 12:57 PM Revision 7524e16f (ceph): tools/rados/rados.cc: Write to different destinations
- The write benchmark only writes the objects' contents, not the omap
nor the extended attributes, which is something a... - 12:57 PM Revision 9259e6e0 (ceph): tools/rados/rados.cc: Add options to choose the benchmark's write desti...
- Signed-off-by: Joaquim Rocha <joaquim.rocha@cern.ch>
- 12:57 PM Revision da6825d4 (ceph): test/test_rados_tool.sh: Add tests for the new bench's write options
- Those are the combinations of --write-omap, --write-xattr and --write-object.
Signed-off-by: Joaquim Rocha <joaquim.... - 12:28 PM Revision 3cc265c3 (ceph): Merge pull request #673 from dachary/wip-buildpackage-ipv6-hammer
- buildpackages: silently ignore IPv6 addresses
- 12:26 PM Revision 45478e74 (ceph): buildpackages: silently ignore IPv6 addresses
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
(cherry picked from commit 7b8f205952d5e49609efbd77a1becae3aff4e531) - 12:25 PM Revision 906159f4 (ceph): Merge pull request #672 from dachary/wip-buildpackages-ipv6
- buildpackages: silently ignore IPv6 addresses
- 12:11 PM Bug #13533: PG: shall finish scrub ahead of time if no more objects is available in NEW_CHUNK state.
- Samuel Just wrote:
> While the primary doesn't have any more objects, the replicas might still have stray objects wh... - 12:02 PM Revision 00c6fa9e (ceph): Objecter: pool_op callback may hang forever.
- pool_op callback may hang forever due to osdmap update during reply handling.
Fixes: #13642
Signed-off-by: xie xinggu... - 11:08 AM Revision 400b0f40 (ceph): Build internal plugins and classes as modules
- Erasure coding plugins and Ceph classes are never exposed outside of the Ceph codebase, so versioning the built libra...
- 10:52 AM Revision 7b8f2059 (ceph): buildpackages: silently ignore IPv6 addresses
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 10:36 AM Revision ca8802fb (ceph): Merge pull request #6159 from dachary/wip-13341-hammer
- ceph upstart script rbdmap.conf incorrectly processes parameters
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:34 AM Revision 19450b90 (ceph): Merge pull request #6154 from dachary/wip-13195-hammer
- should recalc the min_last_epoch_clean when decode PGMap
Reviewed-by: Sage Weil <sage@redhat.com> - 10:28 AM Revision 18882c81 (ceph): Merge pull request #6132 from SUSE/wip-13307-hammer
- dumpling incrementals do not work properly on hammer and newer
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:27 AM Revision 94261b5e (ceph): Merge pull request #671 from ceph/wip-13234-hammer
- rados: add test for 13234.yaml
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:23 AM Revision de4f37bb (ceph): Merge pull request #6097 from dillaman/wip-13045-hammer
- librbd: diff_iterate needs to handle holes in parent images
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:22 AM Revision 1c632a7e (ceph): Merge pull request #6060 from XinzeChi/wip-hammer-outdata-set
- bug fix: osd: avoid multi set osd_op.outdata in tier pool
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:20 AM Revision bedb3344 (ceph): Merge pull request #5897 from tchaikov/wip-12940-hammer
- IO error on kvm/rbd with an erasure coded pool tier
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:11 AM Revision 0d3d8195 (ceph): Merge pull request #5787 from SUSE/wip-12923-hammer
- logrotate reload error on Ubuntu 14.04
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 10:10 AM Revision 381cfccf (ceph): Merge pull request #5766 from dachary/wip-12590-hammer
- ceph mds add_data_pool check for EC pool is wrong
Reviewed-by: Greg Farnum <gfarnum@redhat.com> - 10:06 AM Revision cad1cfb0 (ceph): Merge pull request #5361 from ceph/wip-11786.hammer
- mon: MonitorDBStore: get_next_key() only if prefix matches
Reviewed-by: Loic Dachary <ldachary@redhat.com> - 09:17 AM Revision be04a900 (ceph): mds: initial ScrubStack implementation
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 09:17 AM Revision 069cd093 (ceph): CMake: update for ScrubStack
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision 5a3f3d0d (ceph): mds: implement enqueue scrub in MDCache
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision 3eceaf8b (ceph): mds: add "tag path" command in MDSRank
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision 3aeda582 (ceph): mds: implement ScrubHeader
- A place for scrubbed dentries to learn about the params
that started the scrub off, such as the tag.
Signed-off-by: ... - 09:17 AM Revision ee822438 (ceph): mds: Hook ScrubStack into CInode::validate_disk_state
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision 19300836 (ceph): mds: write scrub tag during validation
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision 6ba5befc (ceph): mds: tidy up cdir scrub_initialize in scrubstack
- ...now that I grok how long the dir is meant to be complete
Signed-off-by: John Spray <john.spray@redhat.com> - 09:17 AM Revision d457fc24 (ceph): mds: apply validate_disk_state to dirs too
- Signed-off-by: John Spray <john.spray@redhat.com>
- 09:17 AM Revision e09e548b (ceph): mds: CDir: rearrange constructor
- Use colon initialization for all the members we can, instead of assignment
in the function body. The split is confusi... - 09:17 AM Revision b789edd6 (ceph): mdstypes: dentry_key_t: add an is_valid() function
- Wrap up checks for whether the dentry has actually been initialized
to contain any data.
Signed-off-by: Greg Farnum ... - 09:17 AM Revision 1627b451 (ceph): MDSContinuation: remove expectation that it's using an MDR
- The ValidationContinuation is wrapping an MDR, but other MDSContinuations
might not. Remove that bit of the interface... - 09:17 AM Revision f8b2fb90 (ceph): mds: inode_t: add scrub stamp and version for latest complete scrub
- Signed-off-by: Greg Farnum <greg@inktank.com>
- 09:17 AM Revision 2cbf07b9 (ceph): mds: frag_t: add scrub stamp and version for recursive and local scrubs
- The local scrub bits are just for the data stored in the dirfrag, like
checking rstats match the actual directory con... - 09:17 AM Revision 23c38c89 (ceph): mds: CDir: create scrub_info_t and surrounding scrub infrastructure
- This is set up so that the coming-shortly scrub system can initialize scrubbing
on a directory and perform the actual... - 09:17 AM Revision fc6bd337 (ceph): mds: CDir: Implement scrub_dentries_scrubbing()
- Signed-off-by: Greg Farnum <gfarnum@redhat.com>
- 09:17 AM Revision a2e3657e (ceph): mds: CDir: implement scrub_local() and call it in CInode::validate_disk...
- Add another set of scrub stamps for the local scrub, which map onto the fnode
local scrub members. Use it in CInode:... - 09:17 AM Revision c5934c1b (ceph): mds: CDentry: create scrub_info_t and surrounding infrastructure
- The CDentry is going to be the point of entry for scrubbing code, and
is how we maintain our cache size. Therefore, i... - 09:17 AM Revision 4a6e799c (ceph): mds: CInode: create scrub_info_t and surrounding infrastructure
- Like the CDir stuff, this has data structures and helpers to track its
own internal scrub state, and -- in the case o... - 07:27 AM Bug #12748: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- Nathan,
sorry for the confusion, just added hammer to the backport field. - 07:23 AM Bug #12565 (Pending Backport): osd: do not cache unused memory in attrs
- 06:50 AM Bug #13543: one host down lead to all virtual machine filesystem in cluster can't be written,
- Samuel Just wrote:
> I don't quite follow what happened, but it looks like your cluster is full and is not accepting... - 04:42 AM Revision 3084406a (ceph): Merge pull request #6400 from ceph/wip-12997
- rgw: Add default quota config
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 03:54 AM Linux kernel client Bug #13643: task kworker/u128:1:11460 blocked for more than 120 seconds. with rbd device and dd ...
- Is this running on the same host as osds? If so, there's a known deadlock potential under memory pressure (due to a k...
- 03:37 AM devops Fix #12994: rbd-replay* should ship in ceph-common
- For these tests we really only want to update the libraries, and run the old tests, to verify that we haven't broken ...
- 12:59 AM Bug #13577: The osd should handle only the kill signal and pass other signal.
- Because there are some other software,like cgroup or openstack guard thread,when use cgroup with ceph or
install c... - 12:28 AM Feature #13142 (Fix Under Review): osd: warning if pg has not been scrubbed for a long time
11/03/2015
- 10:12 PM Revision 9b1ff636 (ceph): Merge pull request #653 from ceph/wip-13567-hammer
- suites/rbd/qemu: excercise CoW support during QEMU testing
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:12 PM Revision fec80cd5 (ceph): Merge pull request #652 from ceph/wip-13559
- suites/rbd/qemu: excercise CoW support during QEMU testing
Reviewed-by: Josh Durgin <jdurgin@redhat.com> - 10:02 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Per Tamil's request ran single rgw job on ubuntu, rhel 7.0 and centos, here are results:...
- 04:06 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Note: One way to speed up the deployment of the fix is to test and vote for the update, here:
https://bodhi.fedora... - 03:54 PM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- I was asked on IRC, " epel is fixed, this would work , right?"
Yes, however the fix that's currently in the epel-t... - 12:25 AM devops Bug #11104: dependency problem with Ceph "Firefly" upstream and EPEL
- Boris and Ken, where are we with this? you say that the change is made in epel.
am confused about the bug status "in... - 09:58 PM devops Bug #13463 (Duplicate): "Failure: ceph-deploy was not able to gatherkeys" on centos 7.0
- 05:20 PM devops Bug #13463: "Failure: ceph-deploy was not able to gatherkeys" on centos 7.0
- This looks like duplicate of #13679
- 05:02 PM devops Bug #13463: "Failure: ceph-deploy was not able to gatherkeys" on centos 7.0
- From IRC with Alfredo:...
- 04:47 PM devops Bug #13463: "Failure: ceph-deploy was not able to gatherkeys" on centos 7.0
- Run: http://pulpito.ceph.com/teuthology-2015-11-03_08:10:29-ceph-deploy-infernalis-distro-basic-vps/
- 09:36 PM Feature #13142: osd: warning if pg has not been scrubbed for a long time
- https://github.com/ceph/ceph/pull/6440
- 09:22 PM devops Bug #13679: ceph-cm-ansible: correct 'cloud.front' hostnames
- A bit of background:
When I investigated what was happening in #13365, I initially wasn't reproducing the problem.... - 09:18 PM devops Bug #13679 (Fix Under Review): ceph-cm-ansible: correct 'cloud.front' hostnames
- https://github.com/ceph/ceph-cm-ansible/pull/163
- 05:17 PM devops Bug #13679 (Resolved): ceph-cm-ansible: correct 'cloud.front' hostnames
- See #13365
Instead of the "Correct hostname if it is 'localhost'" step in the testnodes role, we should set the ho... - 09:09 PM Bug #13422 (Fix Under Review): pid file that was deleted after ceph restart leads to osd process ...
- 09:08 PM Bug #13422: pid file that was deleted after ceph restart leads to osd process lose control
- *master PR*: https://github.com/ceph/ceph/pull/6763
- 08:52 PM rgw Bug #13207 (Fix Under Review): CVE-2016-7031 rgw: Anonymous user is able to read bucket with auth...
- 06:58 PM rgw Bug #13207: CVE-2016-7031 rgw: Anonymous user is able to read bucket with authenticated read ACL
- PR 6057
- 08:38 PM Bug #12748: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- Sam, you changed status to Pending Backport, but the backport field is empty.
- 08:36 PM Bug #12748: bug with cache/tiering and snapshot reads [merged, needs a test in ceph-qa-suite]
- *infernalis PR*: https://github.com/ceph/ceph/pull/6261
- 03:20 PM Bug #12748 (Pending Backport): bug with cache/tiering and snapshot reads [merged, needs a test in...
- 08:32 PM Revision c4f68b0c (ceph): common/buffer.h: removed unneeded list destructor
- Signed-off-by: Michal Jarzabek <stiopa@gmail.com>
- 07:34 PM rgw Bug #11241 (Resolved): Incorrect ETAG calculated for POST uploads
- Merged in commit:4b07f9333537f3a77a9f4218a3c829197dd48230
- 07:33 PM rgw Bug #13096: rgw: The type of caps can be any value.
- The solution would require mapping out the different types of caps that exist, and then to restrict that to those exi...
- 07:27 PM rgw Bug #12963 (Resolved): rgw:objects can not be displayed which object name does not contain '.' wh...
- Merged at commit:8fed45843fc2d9c6c9b287530445acb008e62f93
- 07:27 PM Revision 8fed4584 (ceph): Merge pull request #5738 from dwj192/dwj192_bkt_index
- rgw: fix objects can not be displayed which object name does not cont…
Reviewed-by: Yehuda Sadeh <yehuda@redhat.com> - 07:13 PM rgw Bug #13564: [radosgw_agent.worker][WARNIN] encountered an error during sync: Http error code 400 ...
- I think we have trouble with '<domain>' as being the domain name.. can this be fixed?
- 07:07 PM Bug #13666: "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with async msgr
- I'm not understanding. How does batching up acks lead to this assert?
- 03:37 AM Bug #13666: "osd/ReplicatedPG.cc: 2818: FAILED assert(0 == "out of order op")" with async msgr
- Oh, I found why simple messenger won't happen with this. Async messenger reply ack together(https://github.com/ceph/c...
- 06:59 PM rgw Bug #13605 (Duplicate): rgw: object deletion might get bucket index state reset
- 06:52 PM rgw Bug #12951 (Closed): FAIL: s3tests.functional.test_s3.test_multipart_upload_incorrect_etag
- This was an osd issue
- 06:46 PM rgw Bug #13598: radosgw-admin: inconsistency in uid/email handling
- Two different issues here:
- when email is used, there's no check to see whether the uid matches
- email should b... - 06:40 PM rgw Bug #13680 (Resolved): New keystone expire dates cannot be parsed
- Keystone in newer OpenStack releases (I saw it in Liberty) returns the token expiration date with microseconds, e.g. ...
- 04:59 PM Linux kernel client Bug #13587: IO hang when writing to a cached erasure pool
- Does the i/o eventually complete? What does 'ceph -s' say? This could be caused by promotion/demotion thrashing in th...
- 04:59 PM Linux kernel client Bug #13643: task kworker/u128:1:11460 blocked for more than 120 seconds. with rbd device and dd ...
- Josh Durgin wrote:
> What does 'ceph -s' show for your cluster?
All is fine:
cluster <id>
health HEA... - 04:55 PM Linux kernel client Bug #13643: task kworker/u128:1:11460 blocked for more than 120 seconds. with rbd device and dd ...
- What does 'ceph -s' show for your cluster?
- 04:58 PM Revision bb2ecea2 (ceph): 9.2.0
- 04:16 PM rgw Bug #13613: radosgw problems concurrent downloads
- client timed out and disconnected. Can happen due to variety of issues, including configuration, hardware, client iss...
- 04:01 PM Bug #13556 (Won't Fix): ceph-disk failed to activate osd and killed by udev
- Giant (0.87.*) is no longer supported, upgrading to Hammer (0.94) should fix this problem.
- 03:59 PM Bug #13611: slow request > 30000 seconds on unloaded disk?
- Restarting the osd reporting it will clean it up.
- 03:57 PM Bug #13134 (Closed): old leveldb is slow (firefly->hammer upgrade leads to slow requests)
- 03:57 PM Bug #13359 (Resolved): giant stale requests
- Giant EOL
- 03:56 PM Bug #13474 (Fix Under Review): Ceph daemon failed to start, because the service name was already ...
- 03:54 PM Bug #13543: one host down lead to all virtual machine filesystem in cluster can't be written,
- I don't quite follow what happened, but it looks like your cluster is full and is not accepting writes.
- 03:51 PM Bug #13533 (Rejected): PG: shall finish scrub ahead of time if no more objects is available in NE...
- While the primary doesn't have any more objects, the replicas might still have stray objects which would constitute s...
- 03:47 PM Bug #13577: The osd should handle only the kill signal and pass other signal.
- Why do you want to pass them on?
- 03:45 PM Bug #13532 (Fix Under Review): osd flapping
- closed pr : https://github.com/ceph/ceph/pull/6318
- 03:42 PM Bug #13576 (Won't Fix): The osd was killed by unkown thread or software.
- Doesn't seem like the osd can do much about this.
- 03:40 PM Bug #13300 (Won't Fix): LibRadosTwoPoolsPP tests failing in firefly-backports
- 03:39 PM Bug #13626 (Resolved): FileJournal::_fdump wrongly returns if journal is unreadable.
- 03:38 PM Bug #13610 (Fix Under Review): auth/cephx: large amounts of log are produced by osd
- https://github.com/ceph/ceph/pull/6473
- 03:37 PM Bug #13610 (New): auth/cephx: large amounts of log are produced by osd
- I don't think that PR is related to this bug.
- 03:31 PM Bug #13473 (Resolved): ceph-fuse --localize_reads is not work
- 03:30 PM Bug #13517 (Fix Under Review): common: fix reset max in Throttle using perf reset command
- 03:30 PM Bug #13517: common: fix reset max in Throttle using perf reset command
- https://github.com/ceph/ceph/pull/6300
- 03:28 PM RADOS Bug #11357: crush: straw2: divide by 0 when weight is 0
- For the record, the first Hammer release to ship this patch (commit:b5921d5) was v0.94.1.
- 03:22 PM Bug #13662 (Need More Info): ext4 xattr linux 3.16 / 4.2.3 panic
- It would be useful to have a way to reproduce the problem. Or maybe a list of the xattr of all objects on the faulty ...
- 03:16 PM Bug #13662: ext4 xattr linux 3.16 / 4.2.3 panic
- We need to send a description of this to the ext4 list asap.
- 03:21 PM Bug #13574 (Resolved): "Caught signal (Segmentation fault)" in upgrade:firefly-hammer-x-infernali...
- 03:19 PM Revision f9e22c5e (ceph): Merge pull request #639 from ceph/wip-12748-infernalis
- rados/singleton-nomsgr/all: add export-after-evict.yaml
Reviewed-by: Samuel Just <sjust@redhat.com> - 03:13 PM devops Fix #12994: rbd-replay* should ship in ceph-common
- > We should make Infernalis' ceph-common package require ceph-test > 9.1.0.
Thinking more about this, we really do... - 05:27 AM devops Fix #12994: rbd-replay* should ship in ceph-common
- Thanks Josh, this could be fixed in the packaging.
The problem is that we've loosened the version dependencies bet... - 04:33 AM devops Fix #12994: rbd-replay* should ship in ceph-common
- A client-only upgrade test from hammer to infernalis on centos 7 failed due to rbd-replay-related binaries moving bet...
- 03:12 PM Bug #13660 (Closed): crash in Pipe::read_message
- I'm chalking this up to low memory on the vps.
- 03:10 PM Bug #13664 (Pending Backport): tests: testprofile must be removed before it is re-created
- 03:09 PM rgw Bug #13240 (Resolved): AssertionError: 31457280 != 30932992: s3tests.functional.test_s3.test_mult...
- 03:09 PM Bug #13399 (Closed): 2015-10-06 09:55:10.883565 mon.0 10.214.131.14:6789/0 61 : cluster [WRN] ...
- 12:56 PM Revision a77bfd09 (ceph): mds: refactor availability check
- ...to give a clean three-way state instead of
relying on caller to check stuck availability
first and then whether an... - 12:34 PM Revision 21f5af0a (ceph): client: a better check for MDS availability
- Requiring active daemons was pretty annoying in practice,
because:
* a client starting up in the middle of a failove... - 12:34 PM Revision 8f0d7967 (ceph): mds: don't use g_conf from MDSMap
- Signed-off-by: John Spray <john.spray@redhat.com>
- 12:13 PM Revision 0ea24d61 (ceph): Merge pull request #667 from ceph/wip-autorepair
- tasks/cephfs: simplify test_backtrace_repair
- 12:00 PM Revision 7db7eff0 (ceph): OSD / ShardData: Pass ctx to mutex constructors in sdata and sdata_orde...
- Signed-off-by: Jacek J. Łakis <jacek.lakis@intel.com>
- 11:56 AM Revision 54e53a00 (ceph): tasks/cephfs: simplify test_backtrace_repair
- This was previously using a bunch of files and a small
MDCache limit to force things out of cache. It is much
simple... - 11:43 AM rbd Feature #2468 (Fix Under Review): librbd: provide a way for a user to flush and invalidate the cache
- 09:20 AM rbd Feature #2468: librbd: provide a way for a user to flush and invalidate the cache
- https://github.com/ceph/ceph/pull/6453
- 11:31 AM Bug #13592: ceph-helpers: TEST_auto_repair_erasure_coded intermittent failures
- http://jenkins.ceph.dachary.org/job/ceph/LABELS=centos-7&&x86_64/8815/console
- 09:56 AM Stable releases Tasks #13356: hammer v0.94.6
- h3. rados...
- 09:46 AM Stable releases Tasks #13356: hammer v0.94.6
- ...
- 09:40 AM RADOS Bug #13111 (Fix Under Review): replicatedPG:the assert occurs in the fuction ReplicatedPG::on_loc...
- 07:41 AM Revision 5105d50d (ceph): tests: test/librados/test.cc must create profile
- Now that the create_one_ec_pool function removes the testprofile each
time it is called, it must create the testprofi... - 07:22 AM Revision 76de0c39 (ceph): Merge pull request #6452 from dachary/wip-13664-test-ec
- tests: test/librados/test.cc must create profile
Reviewed-by: Samuel Just <sjust@redhat.com> - 07:09 AM Backport #13678: systemd: no rbdmap systemd unit file
- master PR -is not yet- merged.
- 07:08 AM Backport #13678 (Resolved): systemd: no rbdmap systemd unit file
- https://github.com/ceph/ceph/pull/6500
- 07:05 AM Revision cab3d3f2 (ceph): Merge pull request #6410 from Vicente-Cheng/ceph-disk-list-plain-single...
- ceph-disk: get Nonetype when ceph-disk list with --format plain on single device.
Reviewed-by: Loic Dachary <ldachar... - 06:00 AM Revision da48dbb8 (ceph): rbd: fix clone issue when we specify image feature
- Fixes: #13553
Signed-off-by: xinxin shu <xinxin.shu@intel.com> - 03:22 AM CephFS Bug #13675 (Fix Under Review): Failure in LibCephFS.DirLs
- 02:18 AM CephFS Bug #13675: Failure in LibCephFS.DirLs
- https://github.com/ceph/ceph/pull/6260
11/02/2015
- 11:46 PM Bug #13664: tests: testprofile must be removed before it is re-created
- https://github.com/ceph/ceph/pull/6452 is missing...
- 07:28 PM Bug #13664 (Fix Under Review): tests: testprofile must be removed before it is re-created
- https://github.com/ceph/ceph/pull/6446 (applies cleanly to firefly)
- 06:35 PM Bug #13664 (In Progress): tests: testprofile must be removed before it is re-created
- 06:19 PM Bug #13664: tests: testprofile must be removed before it is re-created
- 2015-10-31 00:11:48.733348 7fd5f9027700 2 mon.a@0(leader) e1 send_reply 0x7fd604837960 0x7fd6046a5200 mon_command_ac...
- 11:42 PM devops Bug #13632 (Closed): unable to find ceph v0.80.4 in centos gitbuilder
- the reason the job couldnt find v0.80.4 in centos 7 gitbuilder is that this version of ceph was not supported on cent...
- 11:21 PM Revision a6034294 (ceph): tests: test/librados/test.cc must create profile
- Now that the create_one_ec_pool function removes the testprofile each
time it is called, it must create the testprofi... - 10:34 PM Revision 2a14d167 (ceph): Merge pull request #6451 from jcsp/wip-firefly-urls
- qa: http://ceph.com/qa -> http://download.ceph.com/qa
- 10:22 PM Revision a06179ac (ceph): qa: http://ceph.com/qa -> http://download.ceph.com/qa
- Signed-off-by: Sage Weil <sage@redhat.com>
(cherry picked from commit d4d65fbd6ad15320339751c604613ac63511e645) - 10:20 PM Backport #13672 (In Progress): tests: testprofile must be removed before it is re-created
- 08:33 PM Backport #13672 (Resolved): tests: testprofile must be removed before it is re-created
- https://github.com/ceph/ceph/pull/6450
- 10:20 PM Revision 3a7423db (ceph): tests: add destroy_ec_profile{,_pp} helpers
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
(cherry picked from commit ab46d79bc09fc711fa35302f49eecac81a98519b) - 10:20 PM Revision 30237506 (ceph): tests: destroy testprofile before creating one
- The testprofile erasure code profile is destroyed before creating a new
one so that it does not fail when another tes... - 10:19 PM Backport #13671 (In Progress): tests: testprofile must be removed before it is re-created
- 08:33 PM Backport #13671 (Resolved): tests: testprofile must be removed before it is re-created
- https://github.com/ceph/ceph/pull/6449
- 10:18 PM CephFS Bug #13675 (Resolved): Failure in LibCephFS.DirLs
http://pulpito.ceph.com/teuthology-2015-10-14_09:45:17-hadoop-hammer---basic-multi/1133086 (& 1133125, 1133134)
...- 10:16 PM Backport #13673 (In Progress): tests: testprofile must be removed before it is re-created
- 08:34 PM Backport #13673 (Rejected): tests: testprofile must be removed before it is re-created
- https://github.com/ceph/ceph/pull/6448
- 10:12 PM Revision 7f8bf7a2 (ceph): Merge pull request #6446 from dachary/wip-13664-test-ec
- tests: destroy testprofile before creating one
Reviewed-by: Samuel Just <sjust@redhat.com> - 09:55 PM rbd Bug #13674 (Fix Under Review): Avoid re-writing old-format image header on resize
- *master PR*: https://github.com/ceph/ceph/pull/6447
- 09:35 PM rbd Bug #13674 (Resolved): Avoid re-writing old-format image header on resize
- Race conditions are possible between snapshot creation and resize operations (especially if there are issues with wat...
- 09:51 PM Revision d5be20b6 (ceph): librbd: resize should only update image size within header
- Previously, the whole RBD image format 1 header struct was
re-written to disk on a resize operation.
Fixes: #13674
B... - 09:27 PM Revision 4fb1f6de (ceph): Merge pull request #670 from ceph/wip-no-async
- basic/msgr: remove async and random for now
- 09:25 PM Revision 0324772e (ceph): basic/msgr: remove async and random for now
- Signed-off-by: Samuel Just <sjust@redhat.com>
- 09:23 PM Bug #13594 (Resolved): osd/PG.cc: 2856: FAILED assert(values.size() == 1)
- https://github.com/ceph/ceph/pull/6444
- 08:13 PM rgw Documentation #13670 (Duplicate): rgw frontends not mentioned in radosgw config-ref
- The Ceph Object Gateway Config Reference[1] does not mention ...
- 07:43 PM rbd Bug #13304 (Fix Under Review): "TestLibRBD.Metadata , TestLibRBD.UpdateFeatures" tests failed in ...
- *PR*" https://github.com/ceph/ceph-qa-suite/pull/669
- 07:32 PM Revision 47abab9a (ceph): tests: destroy testprofile before creating one
- The testprofile erasure code profile is destroyed before creating a new
one so that it does not fail when another tes... - 07:32 PM Revision ab46d79b (ceph): tests: add destroy_ec_profile{,_pp} helpers
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 07:03 PM rbd Bug #13432: "Mutex.cc: 105: FAILED assert(r == 0)" in rbd run
- the fix is pending upstream for fio.
not a blocker for ceph. once fio bug is fixed, the teuthology test has to be m... - 06:26 PM Revision 4ebfc70a (ceph): Fixes #10869, added {role} to the dir name.
- Signed-off-by: Yuri Weinstein <yuri.weinstein@inktank.com>
Fixed typo
Signed-off-by: Yuri Weinstein <yuri.weinstein... - 06:24 PM Revision c0066ae1 (ceph): tasks/workunit: fix log message
- Signed-off-by: John Spray <john.spray@redhat.com>
(cherry picked from commit 1e7bfb842aae395a6601d6ec387dc3bd88107046) - 06:23 PM Revision 5a336d73 (ceph): task/workunit: add sudo to dir delete
- This failure to delete used to be hidden in
a catch-all exception handler that was
removed in 396dc073.
This was cau... - 06:23 PM Revision 1722475f (ceph): task/workunit: general tidy
- * PEP8-ize whitespace
* specialize a catch-all except:
* don't alias 'misc' to 'teuthology'
Signed-off-by: John Spra... - 06:20 PM Revision 2cabeb4a (ceph): Whitespace tweaks for the linter
- Signed-off-by: Zack Cerza <zack@redhat.com>
- 06:13 PM Revision 879078fc (ceph): task/workunit: clean up dir deletion
- This was always trying to remove the mountpoint,
and then swallowing the exception and printing
it to the log.
Inste... - 04:52 PM devops Feature #9411: remove qemu symlink for librbd on rhel7.1 (and later)
- As it turns out, qemu-kvm in RHEL 7.1 Base does build-time link against librbd1. So in theory the symlink is only nee...
- 04:37 PM devops Tasks #13669 (In Progress): remove "rhev" packages from apt-mirror's "lab-extras"
- There are a couple of "rhev" packages that were placed into the "lab-extras" repository on apt-mirror.
We've got t... - 04:31 PM devops Tasks #13669 (In Progress): remove "rhev" packages from apt-mirror's "lab-extras"
- 04:17 PM Revision f66e576e (ceph): Merge pull request #6444 from liewegas/wip-pg-key
- osd/PG: tolerate missing epoch key
Reviewed-by: Samuel Just <sjust@redhat.com> - 04:14 PM Revision efe165e3 (ceph): Merge pull request #6406 from xiexingguo/xxg-wip-13626
- FileJournal:_fdump wrongly returns if journal is currently unreadable.
Reviewed-by: Loic Dachary <ldachary@redhat.co... - 04:12 PM Revision e6b9b8fd (ceph): Added $4 for filter out "random.yaml\,async.yaml" tests for now
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
(cherry picked from commit ef04eaccfa2e11286d68fb84e9dc66a0ff2a430b) - 04:10 PM Revision d9ca11af (ceph): Merge pull request #666 from ceph/wip-openstack-fixes
- Added $4 for filter out "random.yaml\,async.yaml" tests for now
- 04:04 PM Revision e382c677 (ceph): init-rbdmap: Rewrite to use logger + clean-up
- This patch rewrites the init-rbdmap init script so that it uses logger
instead of the log_* functions. The patch also... - 04:04 PM Revision 629c41f9 (ceph): ceph.spec.in: We no longer need redhat-lsb-core
- Drop the redhat-lsb-core dependency as it is no longer necessary on
fedora/rhel.
The other two init scripts do not u... - 04:01 PM Revision ef04eacc (ceph): Added $4 for filter out "random.yaml\,async.yaml" tests for now
- Signed-off-by: Yuri Weinstein <yweinste@redhat.com>
- 03:59 PM Bug #13374 (Fix Under Review): systemd: no rbdmap systemd unit file
- -https://github.com/ceph/ceph/pull/6443-
- 03:34 PM Bug #13642 (Fix Under Review): Objecter: pool op callback may hang forever.
- https://github.com/ceph/ceph/pull/6426
- 02:01 PM Revision 5a6117e6 (ceph): Objecter: remove redundant result-check of _calc_target in _map_session.
- Result-code check is currently redundant since _calc_target never returns a negative value.
Signed-off-by: xie xinggu... - 02:01 PM Revision 86554160 (ceph): Objecter: potential null pointer access when do pool_snap_list.
- Objecter: potential null pointer access when do pool_snap_list. Shall check pool existence first.
Fixes: #13639
Signe... - 01:32 PM Revision 5def4b70 (ceph): osd: reoder fields in ObjectContext and ObjectContext::RWState structs
- Reorganize ObjectContext and ObjectContext::RWState structs by moving fields
around, making State enum consume 4 bits... - 01:32 PM Revision 476a6853 (ceph): osd: reoder fields in object_copy_cursor_t struct
- Reoder fields in object_copy_cursor_t, reducing its size from 40
to 24 bytes.
Signed-off-by: Piotr Dałek <piotr.dale... - 01:32 PM Revision 7401124b (ceph): osd: reoder fields in ScrubMap::object struct
- Reoder fields in ScrubMap::object struct and change booleans to
bitfields, reducing its size from 136 to 120 bytes.
... - 01:32 PM Revision 48d424c3 (ceph): osd: reoder fields in pg_stat_t struct
- Reoder fields in ObjectRecoveryProgress struct and change booleans to
bitfields, reducing its size from 592 to 576 by... - 01:32 PM Revision b9ac90d0 (ceph): osd/PG: tolerate missing epoch key
- An orphan PG may have an info attr but no epoch key.
Signed-off-by: Sage Weil <sage@redhat.com> - 01:24 PM Revision ee029ebf (ceph): Merge pull request #5133 from stiopaa1/ThreadMoveCopyConstr
- Thread.h: disable copy constructor and assignment op
Reviewed-by: Kefu Chai <kchai@redhat.com> - 11:43 AM Revision a016f29e (ceph): dummy: only use the user playbook
- Signed-off-by: Loic Dachary <ldachary@redhat.com>
- 05:26 AM Bug #13668 (Rejected): OSD always crashes while doing scrub with new store as the backend
- Hi, guys
I have built a simple test cluster with three osds which are using newstore as the backend. But when it i... - 03:48 AM devops Tasks #13667 (Won't Fix): radosgw-agent for debian8
- i use debian 8,i found that not radosgw-agent package for debian-hammber,please
add it for the next version!
htt... - 12:07 AM rgw Bug #11570 (Resolved): rgw (?) problem in upgrade:hammer-hammer-distro-basic-typica run
Also available in: Atom